Add files using upload-large-folder tool

README.md

@@ -1,3 +1,202 @@
----
-license: mit
----
+---
+base_model: naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "<EMAIL>": 110521,
+  "<KEY>": 110522,
+  "<NAME>": 110520,
+  "<PASSWORD>": 110523,
+  "<code_to_intermediate>": 110502,
+  "<empty_output>": 110501,
+  "<file_sep>": 110492,
+  "<intermediate_to_code>": 110503,
+  "<issue_closed>": 110495,
+  "<issue_comment>": 110494,
+  "<issue_start>": 110493,
+  "<jupyter_code>": 110498,
+  "<jupyter_output>": 110499,
+  "<jupyter_script>": 110500,
+  "<jupyter_start>": 110496,
+  "<jupyter_text>": 110497,
+  "<pr>": 110504,
+  "<pr_base>": 110507,
+  "<pr_base_code>": 110509,
+  "<pr_comment>": 110512,
+  "<pr_diff>": 110510,
+  "<pr_diff_hunk>": 110511,
+  "<pr_diff_hunk_comment_line>": 110519,
+  "<pr_event_id>": 110513,
+  "<pr_file>": 110508,
+  "<pr_in_reply_to_comment_id>": 110518,
+  "<pr_in_reply_to_review_id>": 110517,
+  "<pr_is_merged>": 110506,
+  "<pr_review>": 110514,
+  "<pr_review_comment>": 110516,
+  "<pr_review_state>": 110515,
+  "<pr_status>": 110505,
+  "<repo_name>": 110491
+}

chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-3000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-3000/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-3000/added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "<EMAIL>": 110521,
+  "<KEY>": 110522,
+  "<NAME>": 110520,
+  "<PASSWORD>": 110523,
+  "<code_to_intermediate>": 110502,
+  "<empty_output>": 110501,
+  "<file_sep>": 110492,
+  "<intermediate_to_code>": 110503,
+  "<issue_closed>": 110495,
+  "<issue_comment>": 110494,
+  "<issue_start>": 110493,
+  "<jupyter_code>": 110498,
+  "<jupyter_output>": 110499,
+  "<jupyter_script>": 110500,
+  "<jupyter_start>": 110496,
+  "<jupyter_text>": 110497,
+  "<pr>": 110504,
+  "<pr_base>": 110507,
+  "<pr_base_code>": 110509,
+  "<pr_comment>": 110512,
+  "<pr_diff>": 110510,
+  "<pr_diff_hunk>": 110511,
+  "<pr_diff_hunk_comment_line>": 110519,
+  "<pr_event_id>": 110513,
+  "<pr_file>": 110508,
+  "<pr_in_reply_to_comment_id>": 110518,
+  "<pr_in_reply_to_review_id>": 110517,
+  "<pr_is_merged>": 110506,
+  "<pr_review>": 110514,
+  "<pr_review_comment>": 110516,
+  "<pr_review_state>": 110515,
+  "<pr_status>": 110505,
+  "<repo_name>": 110491
+}

checkpoint-3000/chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-3000/special_tokens_map.json

@@ -0,0 +1,86 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endofturn|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-3000/tokenizer_config.json

@@ -0,0 +1,501 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|_unuse_missing_100256|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<|_unuse_missing_100261|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<|_unuse_missing_100262|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<|_unuse_missing_100263|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|_unuse_missing_100264|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|_unuse_missing_100265|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|_unuse_missing_100266|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|_unuse_missing_100267|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|_unuse_missing_100268|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|_unuse_missing_100269|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<|_unuse_missing_100270|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<|_unuse_missing_100271|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<|stop|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<|endofturn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110491": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110492": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110493": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110494": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110495": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110496": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110497": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110498": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110499": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110500": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110501": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110502": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110503": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110504": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110505": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110506": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110507": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110508": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110509": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110510": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110511": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110512": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110513": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110514": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110515": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110516": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110517": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110518": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110519": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110520": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110521": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110522": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110523": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endofturn|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-3000/trainer_state.json

@@ -0,0 +1,2884 @@
+{
+  "best_global_step": 2200,
+  "best_metric": 1.8803235292434692,
+  "best_model_checkpoint": "/content/drive/MyDrive/hyperclova-deobfuscation-lora/checkpoint-2200",
+  "epoch": 2.6666666666666665,
+  "eval_steps": 200,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008888888888888889,
+      "grad_norm": 3.629798412322998,
+      "learning_rate": 1.8e-05,
+      "loss": 4.1483,
+      "mean_token_accuracy": 0.34797456339001653,
+      "num_tokens": 11242.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 2.6125221252441406,
+      "learning_rate": 3.8e-05,
+      "loss": 3.7515,
+      "mean_token_accuracy": 0.4058148756623268,
+      "num_tokens": 22106.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 2.9313137531280518,
+      "learning_rate": 5.8e-05,
+      "loss": 3.3279,
+      "mean_token_accuracy": 0.4703808955848217,
+      "num_tokens": 33774.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 2.0496416091918945,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 2.9114,
+      "mean_token_accuracy": 0.5239812344312668,
+      "num_tokens": 44943.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 2.282668352127075,
+      "learning_rate": 9.8e-05,
+      "loss": 2.8468,
+      "mean_token_accuracy": 0.534189497679472,
+      "num_tokens": 56341.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 2.168651819229126,
+      "learning_rate": 0.000118,
+      "loss": 2.7785,
+      "mean_token_accuracy": 0.5407359585165977,
+      "num_tokens": 67397.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.06222222222222222,
+      "grad_norm": 2.289881467819214,
+      "learning_rate": 0.000138,
+      "loss": 2.736,
+      "mean_token_accuracy": 0.5326176360249519,
+      "num_tokens": 78482.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 2.1038105487823486,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 2.5855,
+      "mean_token_accuracy": 0.5618595249950886,
+      "num_tokens": 89803.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.24312686920166,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 2.5365,
+      "mean_token_accuracy": 0.5661972932517528,
+      "num_tokens": 101015.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.9482938051223755,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 2.5634,
+      "mean_token_accuracy": 0.5538406319916248,
+      "num_tokens": 112364.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.09777777777777778,
+      "grad_norm": 1.86210298538208,
+      "learning_rate": 0.00019945038167938932,
+      "loss": 2.4629,
+      "mean_token_accuracy": 0.5780388668179512,
+      "num_tokens": 122882.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 1.8806918859481812,
+      "learning_rate": 0.00019883969465648855,
+      "loss": 2.5022,
+      "mean_token_accuracy": 0.563551553338766,
+      "num_tokens": 134028.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.11555555555555555,
+      "grad_norm": 2.3264434337615967,
+      "learning_rate": 0.00019829007633587786,
+      "loss": 2.4065,
+      "mean_token_accuracy": 0.5807355619966984,
+      "num_tokens": 145192.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 1.8537976741790771,
+      "learning_rate": 0.00019767938931297712,
+      "loss": 2.4838,
+      "mean_token_accuracy": 0.566282794624567,
+      "num_tokens": 156703.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 2.0960652828216553,
+      "learning_rate": 0.00019706870229007636,
+      "loss": 2.4119,
+      "mean_token_accuracy": 0.5830203481018543,
+      "num_tokens": 168041.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 2.2244813442230225,
+      "learning_rate": 0.00019645801526717557,
+      "loss": 2.3726,
+      "mean_token_accuracy": 0.5844443172216416,
+      "num_tokens": 178986.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.1511111111111111,
+      "grad_norm": 1.8238722085952759,
+      "learning_rate": 0.0001958473282442748,
+      "loss": 2.4419,
+      "mean_token_accuracy": 0.5708602093160152,
+      "num_tokens": 190391.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.7154136896133423,
+      "learning_rate": 0.00019523664122137407,
+      "loss": 2.4293,
+      "mean_token_accuracy": 0.5748118035495281,
+      "num_tokens": 201989.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.1688888888888889,
+      "grad_norm": 1.7582788467407227,
+      "learning_rate": 0.0001946259541984733,
+      "loss": 2.3577,
+      "mean_token_accuracy": 0.5877166777849198,
+      "num_tokens": 212914.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.8613263368606567,
+      "learning_rate": 0.0001940152671755725,
+      "loss": 2.3486,
+      "mean_token_accuracy": 0.5889834299683571,
+      "num_tokens": 223936.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_loss": 2.3320820331573486,
+      "eval_mean_token_accuracy": 0.5868698905706405,
+      "eval_num_tokens": 223936.0,
+      "eval_runtime": 49.2429,
+      "eval_samples_per_second": 20.307,
+      "eval_steps_per_second": 10.154,
+      "step": 200
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 1.8486477136611938,
+      "learning_rate": 0.00019340458015267175,
+      "loss": 2.3666,
+      "mean_token_accuracy": 0.5847611322999,
+      "num_tokens": 235036.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 2.018049478530884,
+      "learning_rate": 0.000192793893129771,
+      "loss": 2.2689,
+      "mean_token_accuracy": 0.59971177354455,
+      "num_tokens": 246101.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.20444444444444446,
+      "grad_norm": 1.7244890928268433,
+      "learning_rate": 0.00019218320610687024,
+      "loss": 2.3262,
+      "mean_token_accuracy": 0.5855986528098583,
+      "num_tokens": 257953.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.8928934335708618,
+      "learning_rate": 0.00019157251908396948,
+      "loss": 2.3318,
+      "mean_token_accuracy": 0.5885626815259457,
+      "num_tokens": 269187.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.7358920574188232,
+      "learning_rate": 0.0001909618320610687,
+      "loss": 2.2145,
+      "mean_token_accuracy": 0.6092555984854698,
+      "num_tokens": 279762.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 1.6779032945632935,
+      "learning_rate": 0.00019035114503816795,
+      "loss": 2.3152,
+      "mean_token_accuracy": 0.584602715075016,
+      "num_tokens": 291454.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.6310207843780518,
+      "learning_rate": 0.0001897404580152672,
+      "loss": 2.2669,
+      "mean_token_accuracy": 0.5965895019471645,
+      "num_tokens": 302969.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 1.6765615940093994,
+      "learning_rate": 0.00018912977099236642,
+      "loss": 2.269,
+      "mean_token_accuracy": 0.5934441670775413,
+      "num_tokens": 314204.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.2577777777777778,
+      "grad_norm": 1.793959617614746,
+      "learning_rate": 0.00018851908396946566,
+      "loss": 2.2554,
+      "mean_token_accuracy": 0.600947193801403,
+      "num_tokens": 325649.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.7492129802703857,
+      "learning_rate": 0.0001879083969465649,
+      "loss": 2.2157,
+      "mean_token_accuracy": 0.6022505328059197,
+      "num_tokens": 337167.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.27555555555555555,
+      "grad_norm": 1.803576946258545,
+      "learning_rate": 0.00018729770992366413,
+      "loss": 2.2854,
+      "mean_token_accuracy": 0.5923042424023152,
+      "num_tokens": 348621.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 1.9662351608276367,
+      "learning_rate": 0.00018668702290076337,
+      "loss": 2.2639,
+      "mean_token_accuracy": 0.588193366676569,
+      "num_tokens": 360272.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 1.6725891828536987,
+      "learning_rate": 0.0001860763358778626,
+      "loss": 2.2249,
+      "mean_token_accuracy": 0.6054098337888718,
+      "num_tokens": 371346.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 1.68416166305542,
+      "learning_rate": 0.00018546564885496184,
+      "loss": 2.1678,
+      "mean_token_accuracy": 0.6146526508033275,
+      "num_tokens": 382779.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 1.7218507528305054,
+      "learning_rate": 0.00018485496183206108,
+      "loss": 2.2011,
+      "mean_token_accuracy": 0.6104303196072578,
+      "num_tokens": 393823.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.6817256212234497,
+      "learning_rate": 0.0001842442748091603,
+      "loss": 2.2264,
+      "mean_token_accuracy": 0.5987282857298851,
+      "num_tokens": 405438.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.3288888888888889,
+      "grad_norm": 1.7454718351364136,
+      "learning_rate": 0.00018363358778625955,
+      "loss": 2.2712,
+      "mean_token_accuracy": 0.5939777493476868,
+      "num_tokens": 417299.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 2.011315107345581,
+      "learning_rate": 0.00018302290076335878,
+      "loss": 2.2247,
+      "mean_token_accuracy": 0.6061037018895149,
+      "num_tokens": 428660.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 1.6242053508758545,
+      "learning_rate": 0.00018241221374045802,
+      "loss": 2.232,
+      "mean_token_accuracy": 0.6062197655439376,
+      "num_tokens": 439768.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 1.9328559637069702,
+      "learning_rate": 0.00018180152671755725,
+      "loss": 2.1291,
+      "mean_token_accuracy": 0.6168317429721355,
+      "num_tokens": 450808.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_loss": 2.1662538051605225,
+      "eval_mean_token_accuracy": 0.6099509916305542,
+      "eval_num_tokens": 450808.0,
+      "eval_runtime": 49.4213,
+      "eval_samples_per_second": 20.234,
+      "eval_steps_per_second": 10.117,
+      "step": 400
+    },
+    {
+      "epoch": 0.36444444444444446,
+      "grad_norm": 1.8797143697738647,
+      "learning_rate": 0.0001811908396946565,
+      "loss": 2.2086,
+      "mean_token_accuracy": 0.6012695133686066,
+      "num_tokens": 461592.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.7558225393295288,
+      "learning_rate": 0.00018058015267175575,
+      "loss": 2.1771,
+      "mean_token_accuracy": 0.6060668036341668,
+      "num_tokens": 473434.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.38222222222222224,
+      "grad_norm": 1.845051884651184,
+      "learning_rate": 0.00017996946564885496,
+      "loss": 2.2576,
+      "mean_token_accuracy": 0.5929104581475257,
+      "num_tokens": 485130.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 1.6992298364639282,
+      "learning_rate": 0.0001793587786259542,
+      "loss": 2.1815,
+      "mean_token_accuracy": 0.6100690707564353,
+      "num_tokens": 496482.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.7239253520965576,
+      "learning_rate": 0.00017874809160305343,
+      "loss": 2.2082,
+      "mean_token_accuracy": 0.6001435503363609,
+      "num_tokens": 508218.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 1.7856336832046509,
+      "learning_rate": 0.0001781374045801527,
+      "loss": 2.1593,
+      "mean_token_accuracy": 0.6118309393525123,
+      "num_tokens": 519379.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.4177777777777778,
+      "grad_norm": 1.611831545829773,
+      "learning_rate": 0.00017752671755725193,
+      "loss": 2.1797,
+      "mean_token_accuracy": 0.6033190444111824,
+      "num_tokens": 530561.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.7420586347579956,
+      "learning_rate": 0.00017691603053435114,
+      "loss": 2.2027,
+      "mean_token_accuracy": 0.6067790001630783,
+      "num_tokens": 542631.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.43555555555555553,
+      "grad_norm": 1.948723316192627,
+      "learning_rate": 0.00017630534351145038,
+      "loss": 2.1753,
+      "mean_token_accuracy": 0.6109650492668152,
+      "num_tokens": 553477.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.7983819246292114,
+      "learning_rate": 0.00017569465648854964,
+      "loss": 2.158,
+      "mean_token_accuracy": 0.5996212616562844,
+      "num_tokens": 565400.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 1.842372179031372,
+      "learning_rate": 0.00017508396946564888,
+      "loss": 2.0825,
+      "mean_token_accuracy": 0.6168116196990013,
+      "num_tokens": 576953.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 1.91799795627594,
+      "learning_rate": 0.00017447328244274809,
+      "loss": 2.1022,
+      "mean_token_accuracy": 0.6168905258178711,
+      "num_tokens": 588003.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.4711111111111111,
+      "grad_norm": 1.7727124691009521,
+      "learning_rate": 0.00017386259541984732,
+      "loss": 2.1695,
+      "mean_token_accuracy": 0.5997609972953797,
+      "num_tokens": 600043.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.8602296113967896,
+      "learning_rate": 0.00017325190839694658,
+      "loss": 2.0849,
+      "mean_token_accuracy": 0.6266478568315506,
+      "num_tokens": 610974.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 1.545620083808899,
+      "learning_rate": 0.00017264122137404582,
+      "loss": 2.1824,
+      "mean_token_accuracy": 0.6072694823145867,
+      "num_tokens": 622632.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 1.7485988140106201,
+      "learning_rate": 0.00017203053435114506,
+      "loss": 2.1374,
+      "mean_token_accuracy": 0.6164417043328285,
+      "num_tokens": 634093.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 1.8591196537017822,
+      "learning_rate": 0.00017141984732824426,
+      "loss": 2.0928,
+      "mean_token_accuracy": 0.6241554819047451,
+      "num_tokens": 645226.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 1.8163517713546753,
+      "learning_rate": 0.00017080916030534353,
+      "loss": 2.0476,
+      "mean_token_accuracy": 0.6285594403743744,
+      "num_tokens": 656188.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.5244444444444445,
+      "grad_norm": 1.7729696035385132,
+      "learning_rate": 0.00017019847328244276,
+      "loss": 2.1036,
+      "mean_token_accuracy": 0.6208315283060074,
+      "num_tokens": 667642.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.7804032564163208,
+      "learning_rate": 0.000169587786259542,
+      "loss": 2.1174,
+      "mean_token_accuracy": 0.6148250237107277,
+      "num_tokens": 678769.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 2.0850696563720703,
+      "eval_mean_token_accuracy": 0.6197466601729393,
+      "eval_num_tokens": 678769.0,
+      "eval_runtime": 49.7611,
+      "eval_samples_per_second": 20.096,
+      "eval_steps_per_second": 10.048,
+      "step": 600
+    },
+    {
+      "epoch": 0.5422222222222223,
+      "grad_norm": 1.8643274307250977,
+      "learning_rate": 0.00016897709923664124,
+      "loss": 2.0485,
+      "mean_token_accuracy": 0.6331146821379662,
+      "num_tokens": 690014.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 1.8060939311981201,
+      "learning_rate": 0.00016836641221374047,
+      "loss": 2.1117,
+      "mean_token_accuracy": 0.612041813135147,
+      "num_tokens": 701734.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.7059085369110107,
+      "learning_rate": 0.0001677557251908397,
+      "loss": 2.0747,
+      "mean_token_accuracy": 0.6174572542309761,
+      "num_tokens": 713570.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 1.6600592136383057,
+      "learning_rate": 0.00016714503816793894,
+      "loss": 2.0685,
+      "mean_token_accuracy": 0.6293445661664009,
+      "num_tokens": 724815.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 1.6598913669586182,
+      "learning_rate": 0.00016653435114503818,
+      "loss": 2.0255,
+      "mean_token_accuracy": 0.6309839904308319,
+      "num_tokens": 735777.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 1.8306963443756104,
+      "learning_rate": 0.00016592366412213741,
+      "loss": 2.1249,
+      "mean_token_accuracy": 0.6147443532943726,
+      "num_tokens": 746903.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.5955555555555555,
+      "grad_norm": 1.626795768737793,
+      "learning_rate": 0.00016531297709923665,
+      "loss": 2.0694,
+      "mean_token_accuracy": 0.6254988595843315,
+      "num_tokens": 757881.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 1.710806131362915,
+      "learning_rate": 0.00016470229007633589,
+      "loss": 2.0397,
+      "mean_token_accuracy": 0.6233279958367348,
+      "num_tokens": 768982.0,
+      "step": 680
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 1.7051280736923218,
+      "learning_rate": 0.00016409160305343512,
+      "loss": 2.116,
+      "mean_token_accuracy": 0.6183760315179825,
+      "num_tokens": 780072.0,
+      "step": 690
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 1.607917070388794,
+      "learning_rate": 0.00016348091603053436,
+      "loss": 2.0478,
+      "mean_token_accuracy": 0.6331974640488625,
+      "num_tokens": 791061.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.6311111111111111,
+      "grad_norm": 1.7803592681884766,
+      "learning_rate": 0.0001628702290076336,
+      "loss": 2.0595,
+      "mean_token_accuracy": 0.6249041527509689,
+      "num_tokens": 801867.0,
+      "step": 710
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.6132373809814453,
+      "learning_rate": 0.00016225954198473283,
+      "loss": 2.0789,
+      "mean_token_accuracy": 0.6235784366726875,
+      "num_tokens": 813112.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.6488888888888888,
+      "grad_norm": 1.790528655052185,
+      "learning_rate": 0.00016164885496183207,
+      "loss": 2.0632,
+      "mean_token_accuracy": 0.6268924325704575,
+      "num_tokens": 824133.0,
+      "step": 730
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 2.0007362365722656,
+      "learning_rate": 0.0001610381679389313,
+      "loss": 2.0701,
+      "mean_token_accuracy": 0.6189413338899612,
+      "num_tokens": 835469.0,
+      "step": 740
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.227158546447754,
+      "learning_rate": 0.00016042748091603054,
+      "loss": 2.0339,
+      "mean_token_accuracy": 0.621903920173645,
+      "num_tokens": 846572.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 1.80472731590271,
+      "learning_rate": 0.00015981679389312977,
+      "loss": 2.1285,
+      "mean_token_accuracy": 0.604806374013424,
+      "num_tokens": 857795.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.6844444444444444,
+      "grad_norm": 1.7893937826156616,
+      "learning_rate": 0.000159206106870229,
+      "loss": 2.0347,
+      "mean_token_accuracy": 0.6292635962367058,
+      "num_tokens": 868429.0,
+      "step": 770
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 1.6761573553085327,
+      "learning_rate": 0.00015859541984732824,
+      "loss": 2.0591,
+      "mean_token_accuracy": 0.6254431992769242,
+      "num_tokens": 879659.0,
+      "step": 780
+    },
+    {
+      "epoch": 0.7022222222222222,
+      "grad_norm": 1.803045630455017,
+      "learning_rate": 0.0001579847328244275,
+      "loss": 2.0293,
+      "mean_token_accuracy": 0.6273573949933052,
+      "num_tokens": 890911.0,
+      "step": 790
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 1.7385220527648926,
+      "learning_rate": 0.00015737404580152672,
+      "loss": 2.0197,
+      "mean_token_accuracy": 0.63025072067976,
+      "num_tokens": 902240.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 2.0297935009002686,
+      "eval_mean_token_accuracy": 0.628437293112278,
+      "eval_num_tokens": 902240.0,
+      "eval_runtime": 49.3011,
+      "eval_samples_per_second": 20.284,
+      "eval_steps_per_second": 10.142,
+      "step": 800
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.8906656503677368,
+      "learning_rate": 0.00015676335877862595,
+      "loss": 2.0806,
+      "mean_token_accuracy": 0.619849094748497,
+      "num_tokens": 914009.0,
+      "step": 810
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 1.714268684387207,
+      "learning_rate": 0.0001561526717557252,
+      "loss": 2.0343,
+      "mean_token_accuracy": 0.632188580930233,
+      "num_tokens": 925091.0,
+      "step": 820
+    },
+    {
+      "epoch": 0.7377777777777778,
+      "grad_norm": 1.833918809890747,
+      "learning_rate": 0.00015554198473282445,
+      "loss": 2.0747,
+      "mean_token_accuracy": 0.6280180156230927,
+      "num_tokens": 936675.0,
+      "step": 830
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.9817575216293335,
+      "learning_rate": 0.00015493129770992366,
+      "loss": 2.0859,
+      "mean_token_accuracy": 0.6128378361463547,
+      "num_tokens": 948151.0,
+      "step": 840
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 1.5982656478881836,
+      "learning_rate": 0.0001543206106870229,
+      "loss": 2.0455,
+      "mean_token_accuracy": 0.6276382938027382,
+      "num_tokens": 959266.0,
+      "step": 850
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 1.7298970222473145,
+      "learning_rate": 0.00015370992366412213,
+      "loss": 1.9604,
+      "mean_token_accuracy": 0.6377590849995614,
+      "num_tokens": 970339.0,
+      "step": 860
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 1.8064581155776978,
+      "learning_rate": 0.0001530992366412214,
+      "loss": 2.0698,
+      "mean_token_accuracy": 0.6194617792963981,
+      "num_tokens": 981805.0,
+      "step": 870
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 1.5860410928726196,
+      "learning_rate": 0.00015248854961832063,
+      "loss": 2.0182,
+      "mean_token_accuracy": 0.6292306095361709,
+      "num_tokens": 993552.0,
+      "step": 880
+    },
+    {
+      "epoch": 0.7911111111111111,
+      "grad_norm": 1.8761259317398071,
+      "learning_rate": 0.00015187786259541984,
+      "loss": 2.0335,
+      "mean_token_accuracy": 0.6285651385784149,
+      "num_tokens": 1004400.0,
+      "step": 890
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.6973590850830078,
+      "learning_rate": 0.00015126717557251908,
+      "loss": 2.0927,
+      "mean_token_accuracy": 0.6183614790439605,
+      "num_tokens": 1015564.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.8088888888888889,
+      "grad_norm": 1.6477675437927246,
+      "learning_rate": 0.00015065648854961834,
+      "loss": 1.9187,
+      "mean_token_accuracy": 0.6427812784910202,
+      "num_tokens": 1026849.0,
+      "step": 910
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 1.6942589282989502,
+      "learning_rate": 0.00015004580152671757,
+      "loss": 2.0139,
+      "mean_token_accuracy": 0.6322552219033242,
+      "num_tokens": 1037721.0,
+      "step": 920
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 1.6394822597503662,
+      "learning_rate": 0.0001494351145038168,
+      "loss": 2.0392,
+      "mean_token_accuracy": 0.6273665294051171,
+      "num_tokens": 1048986.0,
+      "step": 930
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 1.697804570198059,
+      "learning_rate": 0.00014882442748091602,
+      "loss": 2.0412,
+      "mean_token_accuracy": 0.625536386668682,
+      "num_tokens": 1060627.0,
+      "step": 940
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 1.8058092594146729,
+      "learning_rate": 0.00014821374045801528,
+      "loss": 1.9737,
+      "mean_token_accuracy": 0.6332821652293206,
+      "num_tokens": 1071482.0,
+      "step": 950
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.773294448852539,
+      "learning_rate": 0.00014760305343511452,
+      "loss": 2.054,
+      "mean_token_accuracy": 0.6256278708577157,
+      "num_tokens": 1082672.0,
+      "step": 960
+    },
+    {
+      "epoch": 0.8622222222222222,
+      "grad_norm": 1.6936707496643066,
+      "learning_rate": 0.00014699236641221375,
+      "loss": 1.9957,
+      "mean_token_accuracy": 0.6333451583981514,
+      "num_tokens": 1093493.0,
+      "step": 970
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 1.7029008865356445,
+      "learning_rate": 0.000146381679389313,
+      "loss": 2.0526,
+      "mean_token_accuracy": 0.6244132176041604,
+      "num_tokens": 1104857.0,
+      "step": 980
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.8421082496643066,
+      "learning_rate": 0.00014577099236641223,
+      "loss": 2.0311,
+      "mean_token_accuracy": 0.6236826583743096,
+      "num_tokens": 1116131.0,
+      "step": 990
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.646053433418274,
+      "learning_rate": 0.00014516030534351146,
+      "loss": 1.9973,
+      "mean_token_accuracy": 0.6274659112095833,
+      "num_tokens": 1127612.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_loss": 1.989682674407959,
+      "eval_mean_token_accuracy": 0.633990108013153,
+      "eval_num_tokens": 1127612.0,
+      "eval_runtime": 49.3043,
+      "eval_samples_per_second": 20.282,
+      "eval_steps_per_second": 10.141,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8977777777777778,
+      "grad_norm": 1.5941271781921387,
+      "learning_rate": 0.0001445496183206107,
+      "loss": 2.0579,
+      "mean_token_accuracy": 0.6256210282444954,
+      "num_tokens": 1138866.0,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 1.7826253175735474,
+      "learning_rate": 0.00014393893129770993,
+      "loss": 1.9866,
+      "mean_token_accuracy": 0.6332772478461266,
+      "num_tokens": 1150411.0,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9155555555555556,
+      "grad_norm": 1.8722221851348877,
+      "learning_rate": 0.00014332824427480917,
+      "loss": 2.0398,
+      "mean_token_accuracy": 0.627329595386982,
+      "num_tokens": 1161360.0,
+      "step": 1030
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 1.6533294916152954,
+      "learning_rate": 0.0001427175572519084,
+      "loss": 2.0271,
+      "mean_token_accuracy": 0.6259514302015304,
+      "num_tokens": 1172683.0,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 1.5746543407440186,
+      "learning_rate": 0.00014210687022900764,
+      "loss": 1.9634,
+      "mean_token_accuracy": 0.6359310179948807,
+      "num_tokens": 1183277.0,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 1.6094276905059814,
+      "learning_rate": 0.00014149618320610688,
+      "loss": 1.9195,
+      "mean_token_accuracy": 0.649330523610115,
+      "num_tokens": 1194160.0,
+      "step": 1060
+    },
+    {
+      "epoch": 0.9511111111111111,
+      "grad_norm": 1.9643882513046265,
+      "learning_rate": 0.0001408854961832061,
+      "loss": 2.0042,
+      "mean_token_accuracy": 0.6356254667043686,
+      "num_tokens": 1205308.0,
+      "step": 1070
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.8238948583602905,
+      "learning_rate": 0.00014027480916030535,
+      "loss": 1.9172,
+      "mean_token_accuracy": 0.6497033536434174,
+      "num_tokens": 1215760.0,
+      "step": 1080
+    },
+    {
+      "epoch": 0.9688888888888889,
+      "grad_norm": 1.7422380447387695,
+      "learning_rate": 0.00013966412213740458,
+      "loss": 2.0213,
+      "mean_token_accuracy": 0.6309294819831848,
+      "num_tokens": 1226775.0,
+      "step": 1090
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.651795744895935,
+      "learning_rate": 0.00013905343511450382,
+      "loss": 2.033,
+      "mean_token_accuracy": 0.6295390352606773,
+      "num_tokens": 1238191.0,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 1.673543095588684,
+      "learning_rate": 0.00013844274809160308,
+      "loss": 2.0085,
+      "mean_token_accuracy": 0.6329691678285598,
+      "num_tokens": 1249561.0,
+      "step": 1110
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 1.7423163652420044,
+      "learning_rate": 0.0001378320610687023,
+      "loss": 1.9751,
+      "mean_token_accuracy": 0.6307685926556588,
+      "num_tokens": 1260429.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.0044444444444445,
+      "grad_norm": 1.4878981113433838,
+      "learning_rate": 0.00013722137404580153,
+      "loss": 1.9171,
+      "mean_token_accuracy": 0.644737622141838,
+      "num_tokens": 1271111.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 1.5343797206878662,
+      "learning_rate": 0.00013661068702290076,
+      "loss": 1.8544,
+      "mean_token_accuracy": 0.6503374725580215,
+      "num_tokens": 1282434.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.0222222222222221,
+      "grad_norm": 1.5450340509414673,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 1.828,
+      "mean_token_accuracy": 0.6514182686805725,
+      "num_tokens": 1294382.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.031111111111111,
+      "grad_norm": 1.8313877582550049,
+      "learning_rate": 0.00013538931297709923,
+      "loss": 1.7704,
+      "mean_token_accuracy": 0.6693721905350685,
+      "num_tokens": 1305343.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.8418430089950562,
+      "learning_rate": 0.00013477862595419847,
+      "loss": 1.7591,
+      "mean_token_accuracy": 0.67226582467556,
+      "num_tokens": 1316558.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.048888888888889,
+      "grad_norm": 1.6022825241088867,
+      "learning_rate": 0.0001341679389312977,
+      "loss": 1.8048,
+      "mean_token_accuracy": 0.6629651457071304,
+      "num_tokens": 1327938.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.0577777777777777,
+      "grad_norm": 1.5888707637786865,
+      "learning_rate": 0.00013355725190839697,
+      "loss": 1.773,
+      "mean_token_accuracy": 0.6730352655053139,
+      "num_tokens": 1338732.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 1.833946943283081,
+      "learning_rate": 0.0001329465648854962,
+      "loss": 1.7887,
+      "mean_token_accuracy": 0.6616317644715309,
+      "num_tokens": 1350096.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "eval_loss": 1.9697085618972778,
+      "eval_mean_token_accuracy": 0.6378205664157868,
+      "eval_num_tokens": 1350096.0,
+      "eval_runtime": 49.9237,
+      "eval_samples_per_second": 20.031,
+      "eval_steps_per_second": 10.015,
+      "step": 1200
+    },
+    {
+      "epoch": 1.0755555555555556,
+      "grad_norm": 1.6338160037994385,
+      "learning_rate": 0.00013233587786259541,
+      "loss": 1.7889,
+      "mean_token_accuracy": 0.6668319672346115,
+      "num_tokens": 1360771.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.0844444444444445,
+      "grad_norm": 1.8737561702728271,
+      "learning_rate": 0.00013172519083969465,
+      "loss": 1.7997,
+      "mean_token_accuracy": 0.6570939287543297,
+      "num_tokens": 1372450.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.0933333333333333,
+      "grad_norm": 1.758074402809143,
+      "learning_rate": 0.0001311145038167939,
+      "loss": 1.8457,
+      "mean_token_accuracy": 0.653074924647808,
+      "num_tokens": 1383711.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.1022222222222222,
+      "grad_norm": 1.839158296585083,
+      "learning_rate": 0.00013050381679389315,
+      "loss": 1.8013,
+      "mean_token_accuracy": 0.6608111187815666,
+      "num_tokens": 1394856.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 1.733567476272583,
+      "learning_rate": 0.00012989312977099238,
+      "loss": 1.7814,
+      "mean_token_accuracy": 0.6655508041381836,
+      "num_tokens": 1406193.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.6274900436401367,
+      "learning_rate": 0.0001292824427480916,
+      "loss": 1.858,
+      "mean_token_accuracy": 0.6488608077168465,
+      "num_tokens": 1417607.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.1288888888888888,
+      "grad_norm": 1.690090537071228,
+      "learning_rate": 0.00012867175572519086,
+      "loss": 1.8256,
+      "mean_token_accuracy": 0.6595686703920365,
+      "num_tokens": 1429073.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.1377777777777778,
+      "grad_norm": 1.6638071537017822,
+      "learning_rate": 0.0001280610687022901,
+      "loss": 1.8334,
+      "mean_token_accuracy": 0.6580470725893974,
+      "num_tokens": 1440194.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.1466666666666667,
+      "grad_norm": 1.8339307308197021,
+      "learning_rate": 0.00012745038167938933,
+      "loss": 1.783,
+      "mean_token_accuracy": 0.6632378786802292,
+      "num_tokens": 1451221.0,
+      "step": 1290
+    },
+    {
+      "epoch": 1.1555555555555554,
+      "grad_norm": 1.7621415853500366,
+      "learning_rate": 0.00012683969465648854,
+      "loss": 1.844,
+      "mean_token_accuracy": 0.6506654173135757,
+      "num_tokens": 1462493.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.1644444444444444,
+      "grad_norm": 1.7811567783355713,
+      "learning_rate": 0.00012622900763358777,
+      "loss": 1.8235,
+      "mean_token_accuracy": 0.6505810797214509,
+      "num_tokens": 1473710.0,
+      "step": 1310
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 1.9157836437225342,
+      "learning_rate": 0.00012561832061068704,
+      "loss": 1.8885,
+      "mean_token_accuracy": 0.6459546625614166,
+      "num_tokens": 1485215.0,
+      "step": 1320
+    },
+    {
+      "epoch": 1.1822222222222223,
+      "grad_norm": 1.6572569608688354,
+      "learning_rate": 0.00012500763358778627,
+      "loss": 1.813,
+      "mean_token_accuracy": 0.6597578257322312,
+      "num_tokens": 1496371.0,
+      "step": 1330
+    },
+    {
+      "epoch": 1.1911111111111112,
+      "grad_norm": 1.8602449893951416,
+      "learning_rate": 0.0001243969465648855,
+      "loss": 1.8179,
+      "mean_token_accuracy": 0.6519266426563263,
+      "num_tokens": 1508348.0,
+      "step": 1340
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.8736369609832764,
+      "learning_rate": 0.00012378625954198472,
+      "loss": 1.8029,
+      "mean_token_accuracy": 0.6621162816882133,
+      "num_tokens": 1519322.0,
+      "step": 1350
+    },
+    {
+      "epoch": 1.208888888888889,
+      "grad_norm": 2.026744842529297,
+      "learning_rate": 0.00012317557251908398,
+      "loss": 1.8168,
+      "mean_token_accuracy": 0.6635635286569596,
+      "num_tokens": 1530183.0,
+      "step": 1360
+    },
+    {
+      "epoch": 1.2177777777777778,
+      "grad_norm": 1.7360782623291016,
+      "learning_rate": 0.00012256488549618322,
+      "loss": 1.7521,
+      "mean_token_accuracy": 0.6706348299980164,
+      "num_tokens": 1540862.0,
+      "step": 1370
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 1.9620578289031982,
+      "learning_rate": 0.00012195419847328244,
+      "loss": 1.8228,
+      "mean_token_accuracy": 0.6569086670875549,
+      "num_tokens": 1552212.0,
+      "step": 1380
+    },
+    {
+      "epoch": 1.2355555555555555,
+      "grad_norm": 1.6294327974319458,
+      "learning_rate": 0.00012134351145038167,
+      "loss": 1.7654,
+      "mean_token_accuracy": 0.6697377026081085,
+      "num_tokens": 1563356.0,
+      "step": 1390
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 1.7311524152755737,
+      "learning_rate": 0.00012073282442748092,
+      "loss": 1.9019,
+      "mean_token_accuracy": 0.6457875579595566,
+      "num_tokens": 1574569.0,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "eval_loss": 1.9411770105361938,
+      "eval_mean_token_accuracy": 0.6407178282737732,
+      "eval_num_tokens": 1574569.0,
+      "eval_runtime": 48.3309,
+      "eval_samples_per_second": 20.691,
+      "eval_steps_per_second": 10.345,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2533333333333334,
+      "grad_norm": 1.8629728555679321,
+      "learning_rate": 0.00012012213740458016,
+      "loss": 1.7585,
+      "mean_token_accuracy": 0.671015702188015,
+      "num_tokens": 1585308.0,
+      "step": 1410
+    },
+    {
+      "epoch": 1.2622222222222224,
+      "grad_norm": 1.958808183670044,
+      "learning_rate": 0.0001195114503816794,
+      "loss": 1.8479,
+      "mean_token_accuracy": 0.6535898372530937,
+      "num_tokens": 1596886.0,
+      "step": 1420
+    },
+    {
+      "epoch": 1.271111111111111,
+      "grad_norm": 1.950421690940857,
+      "learning_rate": 0.00011890076335877862,
+      "loss": 1.8173,
+      "mean_token_accuracy": 0.6655478686094284,
+      "num_tokens": 1607683.0,
+      "step": 1430
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.8152872323989868,
+      "learning_rate": 0.00011829007633587788,
+      "loss": 1.8791,
+      "mean_token_accuracy": 0.6531546950340271,
+      "num_tokens": 1618906.0,
+      "step": 1440
+    },
+    {
+      "epoch": 1.2888888888888888,
+      "grad_norm": 1.7857719659805298,
+      "learning_rate": 0.0001176793893129771,
+      "loss": 1.7887,
+      "mean_token_accuracy": 0.6610255971550941,
+      "num_tokens": 1629981.0,
+      "step": 1450
+    },
+    {
+      "epoch": 1.2977777777777777,
+      "grad_norm": 1.8434971570968628,
+      "learning_rate": 0.00011706870229007634,
+      "loss": 1.8368,
+      "mean_token_accuracy": 0.653369964659214,
+      "num_tokens": 1641429.0,
+      "step": 1460
+    },
+    {
+      "epoch": 1.3066666666666666,
+      "grad_norm": 1.8877320289611816,
+      "learning_rate": 0.00011645801526717557,
+      "loss": 1.7938,
+      "mean_token_accuracy": 0.6639183640480042,
+      "num_tokens": 1652601.0,
+      "step": 1470
+    },
+    {
+      "epoch": 1.3155555555555556,
+      "grad_norm": 1.8121625185012817,
+      "learning_rate": 0.00011584732824427482,
+      "loss": 1.7862,
+      "mean_token_accuracy": 0.661414910852909,
+      "num_tokens": 1663837.0,
+      "step": 1480
+    },
+    {
+      "epoch": 1.3244444444444445,
+      "grad_norm": 1.7919855117797852,
+      "learning_rate": 0.00011523664122137406,
+      "loss": 1.8148,
+      "mean_token_accuracy": 0.6654411420226097,
+      "num_tokens": 1675018.0,
+      "step": 1490
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.828735589981079,
+      "learning_rate": 0.00011462595419847328,
+      "loss": 1.8456,
+      "mean_token_accuracy": 0.6496043875813484,
+      "num_tokens": 1686136.0,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3422222222222222,
+      "grad_norm": 1.9462794065475464,
+      "learning_rate": 0.00011401526717557252,
+      "loss": 1.8412,
+      "mean_token_accuracy": 0.6603908941149712,
+      "num_tokens": 1697160.0,
+      "step": 1510
+    },
+    {
+      "epoch": 1.3511111111111112,
+      "grad_norm": 1.6794313192367554,
+      "learning_rate": 0.00011340458015267177,
+      "loss": 1.7774,
+      "mean_token_accuracy": 0.6664682924747467,
+      "num_tokens": 1707831.0,
+      "step": 1520
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 1.8189337253570557,
+      "learning_rate": 0.000112793893129771,
+      "loss": 1.8031,
+      "mean_token_accuracy": 0.6627006307244301,
+      "num_tokens": 1719074.0,
+      "step": 1530
+    },
+    {
+      "epoch": 1.3688888888888888,
+      "grad_norm": 2.073533296585083,
+      "learning_rate": 0.00011218320610687022,
+      "loss": 1.8657,
+      "mean_token_accuracy": 0.6476830393075943,
+      "num_tokens": 1730388.0,
+      "step": 1540
+    },
+    {
+      "epoch": 1.3777777777777778,
+      "grad_norm": 2.1564207077026367,
+      "learning_rate": 0.00011157251908396946,
+      "loss": 1.8261,
+      "mean_token_accuracy": 0.6567840203642845,
+      "num_tokens": 1741806.0,
+      "step": 1550
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 1.6113232374191284,
+      "learning_rate": 0.00011096183206106871,
+      "loss": 1.7753,
+      "mean_token_accuracy": 0.6659888163208961,
+      "num_tokens": 1753313.0,
+      "step": 1560
+    },
+    {
+      "epoch": 1.3955555555555557,
+      "grad_norm": 1.8112174272537231,
+      "learning_rate": 0.00011035114503816795,
+      "loss": 1.8046,
+      "mean_token_accuracy": 0.6593015149235726,
+      "num_tokens": 1765144.0,
+      "step": 1570
+    },
+    {
+      "epoch": 1.4044444444444444,
+      "grad_norm": 1.8377541303634644,
+      "learning_rate": 0.00010974045801526718,
+      "loss": 1.8848,
+      "mean_token_accuracy": 0.6533517614006996,
+      "num_tokens": 1776783.0,
+      "step": 1580
+    },
+    {
+      "epoch": 1.4133333333333333,
+      "grad_norm": 1.8384325504302979,
+      "learning_rate": 0.0001091297709923664,
+      "loss": 1.7669,
+      "mean_token_accuracy": 0.6613995045423507,
+      "num_tokens": 1788274.0,
+      "step": 1590
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 1.8124533891677856,
+      "learning_rate": 0.00010851908396946567,
+      "loss": 1.8164,
+      "mean_token_accuracy": 0.6591159239411354,
+      "num_tokens": 1799707.0,
+      "step": 1600
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "eval_loss": 1.9286668300628662,
+      "eval_mean_token_accuracy": 0.6434953879117966,
+      "eval_num_tokens": 1799707.0,
+      "eval_runtime": 48.6198,
+      "eval_samples_per_second": 20.568,
+      "eval_steps_per_second": 10.284,
+      "step": 1600
+    },
+    {
+      "epoch": 1.431111111111111,
+      "grad_norm": 1.6931661367416382,
+      "learning_rate": 0.00010790839694656489,
+      "loss": 1.7548,
+      "mean_token_accuracy": 0.664087076485157,
+      "num_tokens": 1810865.0,
+      "step": 1610
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.7501254081726074,
+      "learning_rate": 0.00010729770992366413,
+      "loss": 1.7652,
+      "mean_token_accuracy": 0.6640020117163659,
+      "num_tokens": 1821807.0,
+      "step": 1620
+    },
+    {
+      "epoch": 1.448888888888889,
+      "grad_norm": 1.8411732912063599,
+      "learning_rate": 0.00010668702290076336,
+      "loss": 1.831,
+      "mean_token_accuracy": 0.6564242169260979,
+      "num_tokens": 1832886.0,
+      "step": 1630
+    },
+    {
+      "epoch": 1.4577777777777778,
+      "grad_norm": 2.003892183303833,
+      "learning_rate": 0.00010607633587786261,
+      "loss": 1.7791,
+      "mean_token_accuracy": 0.6632592365145683,
+      "num_tokens": 1843989.0,
+      "step": 1640
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 1.7987340688705444,
+      "learning_rate": 0.00010546564885496185,
+      "loss": 1.7627,
+      "mean_token_accuracy": 0.6713873609900475,
+      "num_tokens": 1855106.0,
+      "step": 1650
+    },
+    {
+      "epoch": 1.4755555555555555,
+      "grad_norm": 1.931877851486206,
+      "learning_rate": 0.00010485496183206107,
+      "loss": 1.7976,
+      "mean_token_accuracy": 0.6631382897496223,
+      "num_tokens": 1866900.0,
+      "step": 1660
+    },
+    {
+      "epoch": 1.4844444444444445,
+      "grad_norm": 1.7883687019348145,
+      "learning_rate": 0.0001042442748091603,
+      "loss": 1.7671,
+      "mean_token_accuracy": 0.6675158813595772,
+      "num_tokens": 1877911.0,
+      "step": 1670
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 1.8195563554763794,
+      "learning_rate": 0.00010363358778625955,
+      "loss": 1.8346,
+      "mean_token_accuracy": 0.652577318251133,
+      "num_tokens": 1889580.0,
+      "step": 1680
+    },
+    {
+      "epoch": 1.5022222222222221,
+      "grad_norm": 1.7439149618148804,
+      "learning_rate": 0.00010302290076335879,
+      "loss": 1.7476,
+      "mean_token_accuracy": 0.6717594474554062,
+      "num_tokens": 1901133.0,
+      "step": 1690
+    },
+    {
+      "epoch": 1.511111111111111,
+      "grad_norm": 1.8155314922332764,
+      "learning_rate": 0.00010241221374045801,
+      "loss": 1.8044,
+      "mean_token_accuracy": 0.6617274522781372,
+      "num_tokens": 1911796.0,
+      "step": 1700
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.7685112953186035,
+      "learning_rate": 0.00010180152671755725,
+      "loss": 1.7727,
+      "mean_token_accuracy": 0.665304908156395,
+      "num_tokens": 1923217.0,
+      "step": 1710
+    },
+    {
+      "epoch": 1.528888888888889,
+      "grad_norm": 1.737053632736206,
+      "learning_rate": 0.0001011908396946565,
+      "loss": 1.8345,
+      "mean_token_accuracy": 0.6577870160341263,
+      "num_tokens": 1934355.0,
+      "step": 1720
+    },
+    {
+      "epoch": 1.537777777777778,
+      "grad_norm": 1.9686291217803955,
+      "learning_rate": 0.00010058015267175573,
+      "loss": 1.8165,
+      "mean_token_accuracy": 0.6594037398695946,
+      "num_tokens": 1945653.0,
+      "step": 1730
+    },
+    {
+      "epoch": 1.5466666666666666,
+      "grad_norm": 1.844651699066162,
+      "learning_rate": 9.996946564885497e-05,
+      "loss": 1.8273,
+      "mean_token_accuracy": 0.6566928923130035,
+      "num_tokens": 1956891.0,
+      "step": 1740
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 1.8607743978500366,
+      "learning_rate": 9.93587786259542e-05,
+      "loss": 1.785,
+      "mean_token_accuracy": 0.6692357853055,
+      "num_tokens": 1967789.0,
+      "step": 1750
+    },
+    {
+      "epoch": 1.5644444444444443,
+      "grad_norm": 1.9204373359680176,
+      "learning_rate": 9.874809160305344e-05,
+      "loss": 1.8264,
+      "mean_token_accuracy": 0.6549209818243981,
+      "num_tokens": 1979224.0,
+      "step": 1760
+    },
+    {
+      "epoch": 1.5733333333333333,
+      "grad_norm": 1.7754265069961548,
+      "learning_rate": 9.813740458015268e-05,
+      "loss": 1.7467,
+      "mean_token_accuracy": 0.6670090600848197,
+      "num_tokens": 1990255.0,
+      "step": 1770
+    },
+    {
+      "epoch": 1.5822222222222222,
+      "grad_norm": 2.069091796875,
+      "learning_rate": 9.752671755725191e-05,
+      "loss": 1.7731,
+      "mean_token_accuracy": 0.6609751120209694,
+      "num_tokens": 2001606.0,
+      "step": 1780
+    },
+    {
+      "epoch": 1.5911111111111111,
+      "grad_norm": 2.1375646591186523,
+      "learning_rate": 9.691603053435115e-05,
+      "loss": 1.8009,
+      "mean_token_accuracy": 0.6624869346618653,
+      "num_tokens": 2012912.0,
+      "step": 1790
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.5623434782028198,
+      "learning_rate": 9.630534351145038e-05,
+      "loss": 1.7383,
+      "mean_token_accuracy": 0.6694582119584084,
+      "num_tokens": 2024571.0,
+      "step": 1800
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.90510892868042,
+      "eval_mean_token_accuracy": 0.6464553346633911,
+      "eval_num_tokens": 2024571.0,
+      "eval_runtime": 48.9449,
+      "eval_samples_per_second": 20.431,
+      "eval_steps_per_second": 10.216,
+      "step": 1800
+    },
+    {
+      "epoch": 1.608888888888889,
+      "grad_norm": 1.745969295501709,
+      "learning_rate": 9.569465648854963e-05,
+      "loss": 1.7552,
+      "mean_token_accuracy": 0.6786300778388977,
+      "num_tokens": 2035783.0,
+      "step": 1810
+    },
+    {
+      "epoch": 1.6177777777777778,
+      "grad_norm": 1.7463303804397583,
+      "learning_rate": 9.508396946564886e-05,
+      "loss": 1.7495,
+      "mean_token_accuracy": 0.6666959136724472,
+      "num_tokens": 2047304.0,
+      "step": 1820
+    },
+    {
+      "epoch": 1.6266666666666667,
+      "grad_norm": 1.9058139324188232,
+      "learning_rate": 9.44732824427481e-05,
+      "loss": 1.8365,
+      "mean_token_accuracy": 0.6536470741033554,
+      "num_tokens": 2058792.0,
+      "step": 1830
+    },
+    {
+      "epoch": 1.6355555555555554,
+      "grad_norm": 2.065488576889038,
+      "learning_rate": 9.386259541984733e-05,
+      "loss": 1.7939,
+      "mean_token_accuracy": 0.6519258007407188,
+      "num_tokens": 2070175.0,
+      "step": 1840
+    },
+    {
+      "epoch": 1.6444444444444444,
+      "grad_norm": 1.778023600578308,
+      "learning_rate": 9.325190839694658e-05,
+      "loss": 1.8155,
+      "mean_token_accuracy": 0.655296416580677,
+      "num_tokens": 2081343.0,
+      "step": 1850
+    },
+    {
+      "epoch": 1.6533333333333333,
+      "grad_norm": 1.7437517642974854,
+      "learning_rate": 9.26412213740458e-05,
+      "loss": 1.7996,
+      "mean_token_accuracy": 0.6618543311953544,
+      "num_tokens": 2093074.0,
+      "step": 1860
+    },
+    {
+      "epoch": 1.6622222222222223,
+      "grad_norm": 1.7666471004486084,
+      "learning_rate": 9.203053435114505e-05,
+      "loss": 1.7658,
+      "mean_token_accuracy": 0.6631957843899727,
+      "num_tokens": 2104640.0,
+      "step": 1870
+    },
+    {
+      "epoch": 1.6711111111111112,
+      "grad_norm": 1.912842869758606,
+      "learning_rate": 9.141984732824428e-05,
+      "loss": 1.7996,
+      "mean_token_accuracy": 0.6606781020760536,
+      "num_tokens": 2115628.0,
+      "step": 1880
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 1.7230331897735596,
+      "learning_rate": 9.080916030534351e-05,
+      "loss": 1.8042,
+      "mean_token_accuracy": 0.6600380197167397,
+      "num_tokens": 2126505.0,
+      "step": 1890
+    },
+    {
+      "epoch": 1.6888888888888889,
+      "grad_norm": 1.7043401002883911,
+      "learning_rate": 9.019847328244276e-05,
+      "loss": 1.7993,
+      "mean_token_accuracy": 0.6613149493932724,
+      "num_tokens": 2138364.0,
+      "step": 1900
+    },
+    {
+      "epoch": 1.6977777777777778,
+      "grad_norm": 1.9145572185516357,
+      "learning_rate": 8.958778625954198e-05,
+      "loss": 1.8046,
+      "mean_token_accuracy": 0.662477345764637,
+      "num_tokens": 2149425.0,
+      "step": 1910
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 1.7448140382766724,
+      "learning_rate": 8.897709923664123e-05,
+      "loss": 1.8004,
+      "mean_token_accuracy": 0.6539181426167489,
+      "num_tokens": 2160843.0,
+      "step": 1920
+    },
+    {
+      "epoch": 1.7155555555555555,
+      "grad_norm": 1.8304840326309204,
+      "learning_rate": 8.836641221374045e-05,
+      "loss": 1.8404,
+      "mean_token_accuracy": 0.6593489304184914,
+      "num_tokens": 2172044.0,
+      "step": 1930
+    },
+    {
+      "epoch": 1.7244444444444444,
+      "grad_norm": 1.802331566810608,
+      "learning_rate": 8.77557251908397e-05,
+      "loss": 1.7995,
+      "mean_token_accuracy": 0.6634193584322929,
+      "num_tokens": 2182916.0,
+      "step": 1940
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 1.9834682941436768,
+      "learning_rate": 8.714503816793894e-05,
+      "loss": 1.7525,
+      "mean_token_accuracy": 0.6685526207089424,
+      "num_tokens": 2194913.0,
+      "step": 1950
+    },
+    {
+      "epoch": 1.7422222222222223,
+      "grad_norm": 1.8077235221862793,
+      "learning_rate": 8.653435114503817e-05,
+      "loss": 1.7612,
+      "mean_token_accuracy": 0.6704939991235733,
+      "num_tokens": 2205721.0,
+      "step": 1960
+    },
+    {
+      "epoch": 1.751111111111111,
+      "grad_norm": 1.957993745803833,
+      "learning_rate": 8.592366412213741e-05,
+      "loss": 1.8059,
+      "mean_token_accuracy": 0.6547697961330414,
+      "num_tokens": 2217489.0,
+      "step": 1970
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.7215981483459473,
+      "learning_rate": 8.531297709923664e-05,
+      "loss": 1.7913,
+      "mean_token_accuracy": 0.657075221836567,
+      "num_tokens": 2228972.0,
+      "step": 1980
+    },
+    {
+      "epoch": 1.7688888888888887,
+      "grad_norm": 1.8760231733322144,
+      "learning_rate": 8.470229007633588e-05,
+      "loss": 1.7923,
+      "mean_token_accuracy": 0.6629065066576004,
+      "num_tokens": 2240239.0,
+      "step": 1990
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 2.092407703399658,
+      "learning_rate": 8.409160305343512e-05,
+      "loss": 1.7593,
+      "mean_token_accuracy": 0.6686230883002281,
+      "num_tokens": 2251436.0,
+      "step": 2000
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "eval_loss": 1.893255591392517,
+      "eval_mean_token_accuracy": 0.6482590944766998,
+      "eval_num_tokens": 2251436.0,
+      "eval_runtime": 49.0676,
+      "eval_samples_per_second": 20.38,
+      "eval_steps_per_second": 10.19,
+      "step": 2000
+    },
+    {
+      "epoch": 1.7866666666666666,
+      "grad_norm": 1.7836107015609741,
+      "learning_rate": 8.348091603053435e-05,
+      "loss": 1.8033,
+      "mean_token_accuracy": 0.6598399996757507,
+      "num_tokens": 2263069.0,
+      "step": 2010
+    },
+    {
+      "epoch": 1.7955555555555556,
+      "grad_norm": 1.7955141067504883,
+      "learning_rate": 8.287022900763359e-05,
+      "loss": 1.7922,
+      "mean_token_accuracy": 0.6619856491684913,
+      "num_tokens": 2274050.0,
+      "step": 2020
+    },
+    {
+      "epoch": 1.8044444444444445,
+      "grad_norm": 1.7887564897537231,
+      "learning_rate": 8.225954198473282e-05,
+      "loss": 1.8353,
+      "mean_token_accuracy": 0.658150726556778,
+      "num_tokens": 2285060.0,
+      "step": 2030
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 1.8892567157745361,
+      "learning_rate": 8.164885496183207e-05,
+      "loss": 1.7266,
+      "mean_token_accuracy": 0.6728688895702362,
+      "num_tokens": 2296211.0,
+      "step": 2040
+    },
+    {
+      "epoch": 1.8222222222222222,
+      "grad_norm": 1.9226106405258179,
+      "learning_rate": 8.10381679389313e-05,
+      "loss": 1.7243,
+      "mean_token_accuracy": 0.6712497785687447,
+      "num_tokens": 2307184.0,
+      "step": 2050
+    },
+    {
+      "epoch": 1.8311111111111111,
+      "grad_norm": 1.735863208770752,
+      "learning_rate": 8.042748091603054e-05,
+      "loss": 1.7739,
+      "mean_token_accuracy": 0.6621047109365463,
+      "num_tokens": 2318602.0,
+      "step": 2060
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 1.8361355066299438,
+      "learning_rate": 7.981679389312977e-05,
+      "loss": 1.8223,
+      "mean_token_accuracy": 0.6560095950961113,
+      "num_tokens": 2330193.0,
+      "step": 2070
+    },
+    {
+      "epoch": 1.8488888888888888,
+      "grad_norm": 1.8159486055374146,
+      "learning_rate": 7.920610687022902e-05,
+      "loss": 1.7695,
+      "mean_token_accuracy": 0.6657541528344154,
+      "num_tokens": 2341442.0,
+      "step": 2080
+    },
+    {
+      "epoch": 1.8577777777777778,
+      "grad_norm": 1.9189419746398926,
+      "learning_rate": 7.859541984732824e-05,
+      "loss": 1.8333,
+      "mean_token_accuracy": 0.6628425523638726,
+      "num_tokens": 2352479.0,
+      "step": 2090
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 1.8809512853622437,
+      "learning_rate": 7.798473282442749e-05,
+      "loss": 1.7371,
+      "mean_token_accuracy": 0.6683435723185539,
+      "num_tokens": 2363642.0,
+      "step": 2100
+    },
+    {
+      "epoch": 1.8755555555555556,
+      "grad_norm": 1.845886468887329,
+      "learning_rate": 7.737404580152672e-05,
+      "loss": 1.7774,
+      "mean_token_accuracy": 0.6559944331645966,
+      "num_tokens": 2375376.0,
+      "step": 2110
+    },
+    {
+      "epoch": 1.8844444444444446,
+      "grad_norm": 1.7780894041061401,
+      "learning_rate": 7.676335877862596e-05,
+      "loss": 1.7823,
+      "mean_token_accuracy": 0.6601730152964592,
+      "num_tokens": 2386944.0,
+      "step": 2120
+    },
+    {
+      "epoch": 1.8933333333333333,
+      "grad_norm": 1.9167022705078125,
+      "learning_rate": 7.61526717557252e-05,
+      "loss": 1.7869,
+      "mean_token_accuracy": 0.6573449537158013,
+      "num_tokens": 2398391.0,
+      "step": 2130
+    },
+    {
+      "epoch": 1.9022222222222223,
+      "grad_norm": 2.037911891937256,
+      "learning_rate": 7.554198473282443e-05,
+      "loss": 1.7858,
+      "mean_token_accuracy": 0.6593190267682075,
+      "num_tokens": 2409837.0,
+      "step": 2140
+    },
+    {
+      "epoch": 1.911111111111111,
+      "grad_norm": 1.7496647834777832,
+      "learning_rate": 7.493129770992367e-05,
+      "loss": 1.7241,
+      "mean_token_accuracy": 0.6702290028333664,
+      "num_tokens": 2421607.0,
+      "step": 2150
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 2.0227596759796143,
+      "learning_rate": 7.43206106870229e-05,
+      "loss": 1.7731,
+      "mean_token_accuracy": 0.6679618924856185,
+      "num_tokens": 2432376.0,
+      "step": 2160
+    },
+    {
+      "epoch": 1.9288888888888889,
+      "grad_norm": 1.7401562929153442,
+      "learning_rate": 7.370992366412214e-05,
+      "loss": 1.7684,
+      "mean_token_accuracy": 0.6676609605550766,
+      "num_tokens": 2443683.0,
+      "step": 2170
+    },
+    {
+      "epoch": 1.9377777777777778,
+      "grad_norm": 2.709106922149658,
+      "learning_rate": 7.309923664122137e-05,
+      "loss": 1.709,
+      "mean_token_accuracy": 0.6738818466663361,
+      "num_tokens": 2454757.0,
+      "step": 2180
+    },
+    {
+      "epoch": 1.9466666666666668,
+      "grad_norm": 1.8504191637039185,
+      "learning_rate": 7.248854961832061e-05,
+      "loss": 1.7411,
+      "mean_token_accuracy": 0.6681609645485878,
+      "num_tokens": 2465562.0,
+      "step": 2190
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 1.9488162994384766,
+      "learning_rate": 7.187786259541986e-05,
+      "loss": 1.7927,
+      "mean_token_accuracy": 0.6587553441524505,
+      "num_tokens": 2476869.0,
+      "step": 2200
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "eval_loss": 1.8803235292434692,
+      "eval_mean_token_accuracy": 0.6499251070022583,
+      "eval_num_tokens": 2476869.0,
+      "eval_runtime": 47.7648,
+      "eval_samples_per_second": 20.936,
+      "eval_steps_per_second": 10.468,
+      "step": 2200
+    },
+    {
+      "epoch": 1.9644444444444444,
+      "grad_norm": 1.9747337102890015,
+      "learning_rate": 7.132824427480917e-05,
+      "loss": 1.7689,
+      "mean_token_accuracy": 0.666295376420021,
+      "num_tokens": 2487704.0,
+      "step": 2210
+    },
+    {
+      "epoch": 1.9733333333333334,
+      "grad_norm": 1.8904316425323486,
+      "learning_rate": 7.071755725190839e-05,
+      "loss": 1.7538,
+      "mean_token_accuracy": 0.6645636394619941,
+      "num_tokens": 2498918.0,
+      "step": 2220
+    },
+    {
+      "epoch": 1.982222222222222,
+      "grad_norm": 1.8791844844818115,
+      "learning_rate": 7.010687022900764e-05,
+      "loss": 1.7926,
+      "mean_token_accuracy": 0.6631673067808151,
+      "num_tokens": 2509728.0,
+      "step": 2230
+    },
+    {
+      "epoch": 1.991111111111111,
+      "grad_norm": 1.9756606817245483,
+      "learning_rate": 6.949618320610687e-05,
+      "loss": 1.7863,
+      "mean_token_accuracy": 0.6628521859645844,
+      "num_tokens": 2521073.0,
+      "step": 2240
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7894699573516846,
+      "learning_rate": 6.888549618320611e-05,
+      "loss": 1.7539,
+      "mean_token_accuracy": 0.6728802308440208,
+      "num_tokens": 2531820.0,
+      "step": 2250
+    },
+    {
+      "epoch": 2.008888888888889,
+      "grad_norm": 1.702850341796875,
+      "learning_rate": 6.827480916030535e-05,
+      "loss": 1.4903,
+      "mean_token_accuracy": 0.7138098135590554,
+      "num_tokens": 2542512.0,
+      "step": 2260
+    },
+    {
+      "epoch": 2.017777777777778,
+      "grad_norm": 1.7931528091430664,
+      "learning_rate": 6.766412213740458e-05,
+      "loss": 1.601,
+      "mean_token_accuracy": 0.6894692406058311,
+      "num_tokens": 2553338.0,
+      "step": 2270
+    },
+    {
+      "epoch": 2.026666666666667,
+      "grad_norm": 2.228480339050293,
+      "learning_rate": 6.705343511450382e-05,
+      "loss": 1.609,
+      "mean_token_accuracy": 0.6943154886364937,
+      "num_tokens": 2564182.0,
+      "step": 2280
+    },
+    {
+      "epoch": 2.0355555555555553,
+      "grad_norm": 1.9658042192459106,
+      "learning_rate": 6.644274809160305e-05,
+      "loss": 1.6545,
+      "mean_token_accuracy": 0.6824306204915047,
+      "num_tokens": 2575789.0,
+      "step": 2290
+    },
+    {
+      "epoch": 2.0444444444444443,
+      "grad_norm": 1.7540594339370728,
+      "learning_rate": 6.583206106870229e-05,
+      "loss": 1.6229,
+      "mean_token_accuracy": 0.6881745710968972,
+      "num_tokens": 2587147.0,
+      "step": 2300
+    },
+    {
+      "epoch": 2.0533333333333332,
+      "grad_norm": 1.799501895904541,
+      "learning_rate": 6.522137404580153e-05,
+      "loss": 1.6119,
+      "mean_token_accuracy": 0.6896049126982688,
+      "num_tokens": 2598282.0,
+      "step": 2310
+    },
+    {
+      "epoch": 2.062222222222222,
+      "grad_norm": 1.7720867395401,
+      "learning_rate": 6.461068702290076e-05,
+      "loss": 1.5519,
+      "mean_token_accuracy": 0.7038252353668213,
+      "num_tokens": 2609125.0,
+      "step": 2320
+    },
+    {
+      "epoch": 2.071111111111111,
+      "grad_norm": 1.994992971420288,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 1.5872,
+      "mean_token_accuracy": 0.690100908279419,
+      "num_tokens": 2620411.0,
+      "step": 2330
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.9283640384674072,
+      "learning_rate": 6.338931297709923e-05,
+      "loss": 1.5867,
+      "mean_token_accuracy": 0.6923216238617897,
+      "num_tokens": 2631795.0,
+      "step": 2340
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 1.9957973957061768,
+      "learning_rate": 6.277862595419848e-05,
+      "loss": 1.5996,
+      "mean_token_accuracy": 0.6924369186162949,
+      "num_tokens": 2643179.0,
+      "step": 2350
+    },
+    {
+      "epoch": 2.097777777777778,
+      "grad_norm": 2.0207560062408447,
+      "learning_rate": 6.21679389312977e-05,
+      "loss": 1.515,
+      "mean_token_accuracy": 0.7066755428910255,
+      "num_tokens": 2654206.0,
+      "step": 2360
+    },
+    {
+      "epoch": 2.1066666666666665,
+      "grad_norm": 1.8871878385543823,
+      "learning_rate": 6.155725190839695e-05,
+      "loss": 1.6139,
+      "mean_token_accuracy": 0.687422800064087,
+      "num_tokens": 2665582.0,
+      "step": 2370
+    },
+    {
+      "epoch": 2.1155555555555554,
+      "grad_norm": 1.717610478401184,
+      "learning_rate": 6.094656488549618e-05,
+      "loss": 1.6388,
+      "mean_token_accuracy": 0.6870575189590454,
+      "num_tokens": 2677533.0,
+      "step": 2380
+    },
+    {
+      "epoch": 2.1244444444444444,
+      "grad_norm": 1.8574187755584717,
+      "learning_rate": 6.0335877862595426e-05,
+      "loss": 1.557,
+      "mean_token_accuracy": 0.6999430671334267,
+      "num_tokens": 2688755.0,
+      "step": 2390
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 1.9739580154418945,
+      "learning_rate": 5.9725190839694655e-05,
+      "loss": 1.6553,
+      "mean_token_accuracy": 0.6819543272256852,
+      "num_tokens": 2700558.0,
+      "step": 2400
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "eval_loss": 1.8970768451690674,
+      "eval_mean_token_accuracy": 0.6490416256189346,
+      "eval_num_tokens": 2700558.0,
+      "eval_runtime": 47.6704,
+      "eval_samples_per_second": 20.977,
+      "eval_steps_per_second": 10.489,
+      "step": 2400
+    },
+    {
+      "epoch": 2.1422222222222222,
+      "grad_norm": 1.893918514251709,
+      "learning_rate": 5.91145038167939e-05,
+      "loss": 1.5459,
+      "mean_token_accuracy": 0.6963777393102646,
+      "num_tokens": 2711713.0,
+      "step": 2410
+    },
+    {
+      "epoch": 2.151111111111111,
+      "grad_norm": 1.9607445001602173,
+      "learning_rate": 5.850381679389313e-05,
+      "loss": 1.6373,
+      "mean_token_accuracy": 0.6815788432955742,
+      "num_tokens": 2723686.0,
+      "step": 2420
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 2.091732978820801,
+      "learning_rate": 5.789312977099237e-05,
+      "loss": 1.6422,
+      "mean_token_accuracy": 0.6811213716864586,
+      "num_tokens": 2735300.0,
+      "step": 2430
+    },
+    {
+      "epoch": 2.168888888888889,
+      "grad_norm": 2.1138076782226562,
+      "learning_rate": 5.7282442748091605e-05,
+      "loss": 1.5848,
+      "mean_token_accuracy": 0.6962573245167732,
+      "num_tokens": 2746248.0,
+      "step": 2440
+    },
+    {
+      "epoch": 2.1777777777777776,
+      "grad_norm": 2.1495392322540283,
+      "learning_rate": 5.667175572519085e-05,
+      "loss": 1.576,
+      "mean_token_accuracy": 0.6990228727459907,
+      "num_tokens": 2757259.0,
+      "step": 2450
+    },
+    {
+      "epoch": 2.1866666666666665,
+      "grad_norm": 2.1444251537323,
+      "learning_rate": 5.606106870229008e-05,
+      "loss": 1.5979,
+      "mean_token_accuracy": 0.6916472837328911,
+      "num_tokens": 2768228.0,
+      "step": 2460
+    },
+    {
+      "epoch": 2.1955555555555555,
+      "grad_norm": 1.945489525794983,
+      "learning_rate": 5.545038167938932e-05,
+      "loss": 1.5663,
+      "mean_token_accuracy": 0.7005513325333595,
+      "num_tokens": 2779254.0,
+      "step": 2470
+    },
+    {
+      "epoch": 2.2044444444444444,
+      "grad_norm": 1.8256646394729614,
+      "learning_rate": 5.483969465648855e-05,
+      "loss": 1.5751,
+      "mean_token_accuracy": 0.6961624413728714,
+      "num_tokens": 2790326.0,
+      "step": 2480
+    },
+    {
+      "epoch": 2.2133333333333334,
+      "grad_norm": 1.9541441202163696,
+      "learning_rate": 5.422900763358779e-05,
+      "loss": 1.6268,
+      "mean_token_accuracy": 0.6893054991960526,
+      "num_tokens": 2801625.0,
+      "step": 2490
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 2.0127615928649902,
+      "learning_rate": 5.361832061068702e-05,
+      "loss": 1.6096,
+      "mean_token_accuracy": 0.6923437744379044,
+      "num_tokens": 2813010.0,
+      "step": 2500
+    },
+    {
+      "epoch": 2.2311111111111113,
+      "grad_norm": 2.0325839519500732,
+      "learning_rate": 5.300763358778626e-05,
+      "loss": 1.5963,
+      "mean_token_accuracy": 0.6913090571761131,
+      "num_tokens": 2824021.0,
+      "step": 2510
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 2.1595821380615234,
+      "learning_rate": 5.23969465648855e-05,
+      "loss": 1.5617,
+      "mean_token_accuracy": 0.7037980020046234,
+      "num_tokens": 2835232.0,
+      "step": 2520
+    },
+    {
+      "epoch": 2.2488888888888887,
+      "grad_norm": 2.11661958694458,
+      "learning_rate": 5.178625954198474e-05,
+      "loss": 1.6213,
+      "mean_token_accuracy": 0.6836483731865883,
+      "num_tokens": 2846524.0,
+      "step": 2530
+    },
+    {
+      "epoch": 2.2577777777777777,
+      "grad_norm": 1.88747239112854,
+      "learning_rate": 5.117557251908397e-05,
+      "loss": 1.6408,
+      "mean_token_accuracy": 0.6860729962587356,
+      "num_tokens": 2857788.0,
+      "step": 2540
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 1.9622093439102173,
+      "learning_rate": 5.056488549618321e-05,
+      "loss": 1.5519,
+      "mean_token_accuracy": 0.7002682030200958,
+      "num_tokens": 2868618.0,
+      "step": 2550
+    },
+    {
+      "epoch": 2.2755555555555556,
+      "grad_norm": 1.9343371391296387,
+      "learning_rate": 4.995419847328244e-05,
+      "loss": 1.5795,
+      "mean_token_accuracy": 0.6934511423110962,
+      "num_tokens": 2879999.0,
+      "step": 2560
+    },
+    {
+      "epoch": 2.2844444444444445,
+      "grad_norm": 1.9991627931594849,
+      "learning_rate": 4.934351145038168e-05,
+      "loss": 1.6183,
+      "mean_token_accuracy": 0.6901679039001465,
+      "num_tokens": 2891053.0,
+      "step": 2570
+    },
+    {
+      "epoch": 2.2933333333333334,
+      "grad_norm": 1.9480003118515015,
+      "learning_rate": 4.8732824427480914e-05,
+      "loss": 1.5826,
+      "mean_token_accuracy": 0.7007558569312096,
+      "num_tokens": 2901905.0,
+      "step": 2580
+    },
+    {
+      "epoch": 2.3022222222222224,
+      "grad_norm": 2.021207332611084,
+      "learning_rate": 4.812213740458015e-05,
+      "loss": 1.6348,
+      "mean_token_accuracy": 0.6848765298724174,
+      "num_tokens": 2913571.0,
+      "step": 2590
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 1.8385164737701416,
+      "learning_rate": 4.751145038167939e-05,
+      "loss": 1.5763,
+      "mean_token_accuracy": 0.6912240386009216,
+      "num_tokens": 2925533.0,
+      "step": 2600
+    },
+    {
+      "epoch": 2.311111111111111,
+      "eval_loss": 1.8940143585205078,
+      "eval_mean_token_accuracy": 0.6499911918640137,
+      "eval_num_tokens": 2925533.0,
+      "eval_runtime": 47.456,
+      "eval_samples_per_second": 21.072,
+      "eval_steps_per_second": 10.536,
+      "step": 2600
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 1.9455375671386719,
+      "learning_rate": 4.690076335877863e-05,
+      "loss": 1.598,
+      "mean_token_accuracy": 0.6915700435638428,
+      "num_tokens": 2936620.0,
+      "step": 2610
+    },
+    {
+      "epoch": 2.328888888888889,
+      "grad_norm": 1.863487720489502,
+      "learning_rate": 4.6290076335877864e-05,
+      "loss": 1.5512,
+      "mean_token_accuracy": 0.7025073647499085,
+      "num_tokens": 2947753.0,
+      "step": 2620
+    },
+    {
+      "epoch": 2.3377777777777777,
+      "grad_norm": 1.9756685495376587,
+      "learning_rate": 4.56793893129771e-05,
+      "loss": 1.5973,
+      "mean_token_accuracy": 0.6870647758245468,
+      "num_tokens": 2959635.0,
+      "step": 2630
+    },
+    {
+      "epoch": 2.3466666666666667,
+      "grad_norm": 2.190765142440796,
+      "learning_rate": 4.5068702290076336e-05,
+      "loss": 1.5948,
+      "mean_token_accuracy": 0.6888303905725479,
+      "num_tokens": 2971675.0,
+      "step": 2640
+    },
+    {
+      "epoch": 2.3555555555555556,
+      "grad_norm": 1.827318787574768,
+      "learning_rate": 4.445801526717557e-05,
+      "loss": 1.5682,
+      "mean_token_accuracy": 0.6952902913093567,
+      "num_tokens": 2982744.0,
+      "step": 2650
+    },
+    {
+      "epoch": 2.3644444444444446,
+      "grad_norm": 2.11799693107605,
+      "learning_rate": 4.384732824427481e-05,
+      "loss": 1.6221,
+      "mean_token_accuracy": 0.6794109031558037,
+      "num_tokens": 2994347.0,
+      "step": 2660
+    },
+    {
+      "epoch": 2.3733333333333335,
+      "grad_norm": 2.1472220420837402,
+      "learning_rate": 4.3236641221374044e-05,
+      "loss": 1.6353,
+      "mean_token_accuracy": 0.6876759916543961,
+      "num_tokens": 3005174.0,
+      "step": 2670
+    },
+    {
+      "epoch": 2.3822222222222225,
+      "grad_norm": 1.9971054792404175,
+      "learning_rate": 4.2625954198473286e-05,
+      "loss": 1.5372,
+      "mean_token_accuracy": 0.7059834420680999,
+      "num_tokens": 3016492.0,
+      "step": 2680
+    },
+    {
+      "epoch": 2.391111111111111,
+      "grad_norm": 2.067861318588257,
+      "learning_rate": 4.201526717557252e-05,
+      "loss": 1.572,
+      "mean_token_accuracy": 0.6911077201366425,
+      "num_tokens": 3027826.0,
+      "step": 2690
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.0372536182403564,
+      "learning_rate": 4.140458015267176e-05,
+      "loss": 1.5615,
+      "mean_token_accuracy": 0.6972797185182571,
+      "num_tokens": 3038770.0,
+      "step": 2700
+    },
+    {
+      "epoch": 2.408888888888889,
+      "grad_norm": 2.15972638130188,
+      "learning_rate": 4.0793893129770994e-05,
+      "loss": 1.5806,
+      "mean_token_accuracy": 0.6947444006800652,
+      "num_tokens": 3050159.0,
+      "step": 2710
+    },
+    {
+      "epoch": 2.417777777777778,
+      "grad_norm": 2.059760808944702,
+      "learning_rate": 4.018320610687023e-05,
+      "loss": 1.6167,
+      "mean_token_accuracy": 0.6882677704095841,
+      "num_tokens": 3061009.0,
+      "step": 2720
+    },
+    {
+      "epoch": 2.4266666666666667,
+      "grad_norm": 1.9914629459381104,
+      "learning_rate": 3.9572519083969466e-05,
+      "loss": 1.5508,
+      "mean_token_accuracy": 0.6985371947288513,
+      "num_tokens": 3072232.0,
+      "step": 2730
+    },
+    {
+      "epoch": 2.4355555555555557,
+      "grad_norm": 2.0151119232177734,
+      "learning_rate": 3.89618320610687e-05,
+      "loss": 1.663,
+      "mean_token_accuracy": 0.6849021047353745,
+      "num_tokens": 3083939.0,
+      "step": 2740
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 2.02457332611084,
+      "learning_rate": 3.835114503816794e-05,
+      "loss": 1.6043,
+      "mean_token_accuracy": 0.6891427770256996,
+      "num_tokens": 3095354.0,
+      "step": 2750
+    },
+    {
+      "epoch": 2.453333333333333,
+      "grad_norm": 1.930341362953186,
+      "learning_rate": 3.774045801526718e-05,
+      "loss": 1.5648,
+      "mean_token_accuracy": 0.6962095096707344,
+      "num_tokens": 3106679.0,
+      "step": 2760
+    },
+    {
+      "epoch": 2.462222222222222,
+      "grad_norm": 2.1718850135803223,
+      "learning_rate": 3.7129770992366416e-05,
+      "loss": 1.5514,
+      "mean_token_accuracy": 0.6997211873531342,
+      "num_tokens": 3117440.0,
+      "step": 2770
+    },
+    {
+      "epoch": 2.471111111111111,
+      "grad_norm": 1.89506196975708,
+      "learning_rate": 3.651908396946565e-05,
+      "loss": 1.6102,
+      "mean_token_accuracy": 0.6865462198853493,
+      "num_tokens": 3128685.0,
+      "step": 2780
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 2.1102652549743652,
+      "learning_rate": 3.590839694656489e-05,
+      "loss": 1.6092,
+      "mean_token_accuracy": 0.6845578849315643,
+      "num_tokens": 3140574.0,
+      "step": 2790
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 1.9541523456573486,
+      "learning_rate": 3.5297709923664124e-05,
+      "loss": 1.6245,
+      "mean_token_accuracy": 0.6867643877863884,
+      "num_tokens": 3151937.0,
+      "step": 2800
+    },
+    {
+      "epoch": 2.488888888888889,
+      "eval_loss": 1.8869248628616333,
+      "eval_mean_token_accuracy": 0.6508636207580566,
+      "eval_num_tokens": 3151937.0,
+      "eval_runtime": 46.9872,
+      "eval_samples_per_second": 21.282,
+      "eval_steps_per_second": 10.641,
+      "step": 2800
+    },
+    {
+      "epoch": 2.497777777777778,
+      "grad_norm": 2.006448984146118,
+      "learning_rate": 3.468702290076336e-05,
+      "loss": 1.6458,
+      "mean_token_accuracy": 0.6835160732269288,
+      "num_tokens": 3163343.0,
+      "step": 2810
+    },
+    {
+      "epoch": 2.506666666666667,
+      "grad_norm": 2.0644562244415283,
+      "learning_rate": 3.4076335877862595e-05,
+      "loss": 1.5841,
+      "mean_token_accuracy": 0.699130979180336,
+      "num_tokens": 3174278.0,
+      "step": 2820
+    },
+    {
+      "epoch": 2.5155555555555553,
+      "grad_norm": 2.5352766513824463,
+      "learning_rate": 3.346564885496183e-05,
+      "loss": 1.6411,
+      "mean_token_accuracy": 0.687686163187027,
+      "num_tokens": 3185529.0,
+      "step": 2830
+    },
+    {
+      "epoch": 2.5244444444444447,
+      "grad_norm": 2.2506706714630127,
+      "learning_rate": 3.2854961832061074e-05,
+      "loss": 1.5334,
+      "mean_token_accuracy": 0.7042266175150871,
+      "num_tokens": 3196422.0,
+      "step": 2840
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 2.038456439971924,
+      "learning_rate": 3.224427480916031e-05,
+      "loss": 1.5226,
+      "mean_token_accuracy": 0.7002356797456741,
+      "num_tokens": 3207640.0,
+      "step": 2850
+    },
+    {
+      "epoch": 2.542222222222222,
+      "grad_norm": 2.0818448066711426,
+      "learning_rate": 3.1633587786259545e-05,
+      "loss": 1.5136,
+      "mean_token_accuracy": 0.7040936380624772,
+      "num_tokens": 3218742.0,
+      "step": 2860
+    },
+    {
+      "epoch": 2.551111111111111,
+      "grad_norm": 1.9810820817947388,
+      "learning_rate": 3.102290076335878e-05,
+      "loss": 1.6515,
+      "mean_token_accuracy": 0.6826088905334473,
+      "num_tokens": 3230062.0,
+      "step": 2870
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 2.1830689907073975,
+      "learning_rate": 3.0412213740458017e-05,
+      "loss": 1.5792,
+      "mean_token_accuracy": 0.699496129155159,
+      "num_tokens": 3240533.0,
+      "step": 2880
+    },
+    {
+      "epoch": 2.568888888888889,
+      "grad_norm": 2.101184368133545,
+      "learning_rate": 2.9801526717557253e-05,
+      "loss": 1.6538,
+      "mean_token_accuracy": 0.6724523141980171,
+      "num_tokens": 3252476.0,
+      "step": 2890
+    },
+    {
+      "epoch": 2.5777777777777775,
+      "grad_norm": 2.021524429321289,
+      "learning_rate": 2.9190839694656492e-05,
+      "loss": 1.6146,
+      "mean_token_accuracy": 0.6886414483189582,
+      "num_tokens": 3263799.0,
+      "step": 2900
+    },
+    {
+      "epoch": 2.586666666666667,
+      "grad_norm": 1.9668735265731812,
+      "learning_rate": 2.8580152671755728e-05,
+      "loss": 1.6477,
+      "mean_token_accuracy": 0.678925508260727,
+      "num_tokens": 3275511.0,
+      "step": 2910
+    },
+    {
+      "epoch": 2.5955555555555554,
+      "grad_norm": 2.088491201400757,
+      "learning_rate": 2.7969465648854964e-05,
+      "loss": 1.6265,
+      "mean_token_accuracy": 0.6857595339417457,
+      "num_tokens": 3286752.0,
+      "step": 2920
+    },
+    {
+      "epoch": 2.6044444444444443,
+      "grad_norm": 2.0536880493164062,
+      "learning_rate": 2.73587786259542e-05,
+      "loss": 1.66,
+      "mean_token_accuracy": 0.681273227930069,
+      "num_tokens": 3297945.0,
+      "step": 2930
+    },
+    {
+      "epoch": 2.6133333333333333,
+      "grad_norm": 2.0063817501068115,
+      "learning_rate": 2.674809160305344e-05,
+      "loss": 1.5102,
+      "mean_token_accuracy": 0.7025244757533073,
+      "num_tokens": 3309112.0,
+      "step": 2940
+    },
+    {
+      "epoch": 2.6222222222222222,
+      "grad_norm": 1.9980206489562988,
+      "learning_rate": 2.6137404580152675e-05,
+      "loss": 1.5142,
+      "mean_token_accuracy": 0.7049572348594666,
+      "num_tokens": 3320544.0,
+      "step": 2950
+    },
+    {
+      "epoch": 2.631111111111111,
+      "grad_norm": 2.1506435871124268,
+      "learning_rate": 2.552671755725191e-05,
+      "loss": 1.5826,
+      "mean_token_accuracy": 0.694467018544674,
+      "num_tokens": 3331309.0,
+      "step": 2960
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.9890793561935425,
+      "learning_rate": 2.4916030534351147e-05,
+      "loss": 1.5631,
+      "mean_token_accuracy": 0.6945617944002151,
+      "num_tokens": 3343068.0,
+      "step": 2970
+    },
+    {
+      "epoch": 2.648888888888889,
+      "grad_norm": 2.1102676391601562,
+      "learning_rate": 2.4305343511450383e-05,
+      "loss": 1.6145,
+      "mean_token_accuracy": 0.6866093754768372,
+      "num_tokens": 3354691.0,
+      "step": 2980
+    },
+    {
+      "epoch": 2.6577777777777776,
+      "grad_norm": 2.2881674766540527,
+      "learning_rate": 2.369465648854962e-05,
+      "loss": 1.5796,
+      "mean_token_accuracy": 0.6961612686514854,
+      "num_tokens": 3365512.0,
+      "step": 2990
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.973838210105896,
+      "learning_rate": 2.3083969465648854e-05,
+      "loss": 1.5456,
+      "mean_token_accuracy": 0.703473174571991,
+      "num_tokens": 3376406.0,
+      "step": 3000
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "eval_loss": 1.881131649017334,
+      "eval_mean_token_accuracy": 0.6518214672803879,
+      "eval_num_tokens": 3376406.0,
+      "eval_runtime": 47.794,
+      "eval_samples_per_second": 20.923,
+      "eval_steps_per_second": 10.462,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0707043350011904e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-3200/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-3200/added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "<EMAIL>": 110521,
+  "<KEY>": 110522,
+  "<NAME>": 110520,
+  "<PASSWORD>": 110523,
+  "<code_to_intermediate>": 110502,
+  "<empty_output>": 110501,
+  "<file_sep>": 110492,
+  "<intermediate_to_code>": 110503,
+  "<issue_closed>": 110495,
+  "<issue_comment>": 110494,
+  "<issue_start>": 110493,
+  "<jupyter_code>": 110498,
+  "<jupyter_output>": 110499,
+  "<jupyter_script>": 110500,
+  "<jupyter_start>": 110496,
+  "<jupyter_text>": 110497,
+  "<pr>": 110504,
+  "<pr_base>": 110507,
+  "<pr_base_code>": 110509,
+  "<pr_comment>": 110512,
+  "<pr_diff>": 110510,
+  "<pr_diff_hunk>": 110511,
+  "<pr_diff_hunk_comment_line>": 110519,
+  "<pr_event_id>": 110513,
+  "<pr_file>": 110508,
+  "<pr_in_reply_to_comment_id>": 110518,
+  "<pr_in_reply_to_review_id>": 110517,
+  "<pr_is_merged>": 110506,
+  "<pr_review>": 110514,
+  "<pr_review_comment>": 110516,
+  "<pr_review_state>": 110515,
+  "<pr_status>": 110505,
+  "<repo_name>": 110491
+}

checkpoint-3200/chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-3200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7312eb539871a9d26e9f27442e07b9ee29e9f0cb17f6fdbbd03c79475217c218
+size 14244

checkpoint-3200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94590cbe77c48314bba8fc5ea19e62e4c2fd31ca42a1022d1337608a88ad9d8e
+size 988

checkpoint-3200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c008f624a769f2c06373201d98b59ce88f962ffd48ffa1d7cbe66cd59b13d4d
+size 1064

checkpoint-3200/special_tokens_map.json

@@ -0,0 +1,86 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endofturn|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-3200/tokenizer_config.json

@@ -0,0 +1,501 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|_unuse_missing_100256|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<|_unuse_missing_100261|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<|_unuse_missing_100262|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<|_unuse_missing_100263|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|_unuse_missing_100264|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|_unuse_missing_100265|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|_unuse_missing_100266|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|_unuse_missing_100267|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|_unuse_missing_100268|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|_unuse_missing_100269|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<|_unuse_missing_100270|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<|_unuse_missing_100271|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<|stop|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<|endofturn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110491": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110492": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110493": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110494": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110495": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110496": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110497": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110498": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110499": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110500": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110501": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110502": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110503": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110504": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110505": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110506": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110507": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110508": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110509": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110510": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110511": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110512": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110513": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110514": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110515": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110516": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110517": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110518": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110519": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110520": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110521": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110522": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110523": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endofturn|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-3200/trainer_state.json

@@ -0,0 +1,3074 @@
+{
+  "best_global_step": 3200,
+  "best_metric": 1.8764336109161377,
+  "best_model_checkpoint": "/content/drive/MyDrive/hyperclova-deobfuscation-lora/checkpoint-3200",
+  "epoch": 2.8444444444444446,
+  "eval_steps": 200,
+  "global_step": 3200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008888888888888889,
+      "grad_norm": 3.629798412322998,
+      "learning_rate": 1.8e-05,
+      "loss": 4.1483,
+      "mean_token_accuracy": 0.34797456339001653,
+      "num_tokens": 11242.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 2.6125221252441406,
+      "learning_rate": 3.8e-05,
+      "loss": 3.7515,
+      "mean_token_accuracy": 0.4058148756623268,
+      "num_tokens": 22106.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 2.9313137531280518,
+      "learning_rate": 5.8e-05,
+      "loss": 3.3279,
+      "mean_token_accuracy": 0.4703808955848217,
+      "num_tokens": 33774.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 2.0496416091918945,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 2.9114,
+      "mean_token_accuracy": 0.5239812344312668,
+      "num_tokens": 44943.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 2.282668352127075,
+      "learning_rate": 9.8e-05,
+      "loss": 2.8468,
+      "mean_token_accuracy": 0.534189497679472,
+      "num_tokens": 56341.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 2.168651819229126,
+      "learning_rate": 0.000118,
+      "loss": 2.7785,
+      "mean_token_accuracy": 0.5407359585165977,
+      "num_tokens": 67397.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.06222222222222222,
+      "grad_norm": 2.289881467819214,
+      "learning_rate": 0.000138,
+      "loss": 2.736,
+      "mean_token_accuracy": 0.5326176360249519,
+      "num_tokens": 78482.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 2.1038105487823486,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 2.5855,
+      "mean_token_accuracy": 0.5618595249950886,
+      "num_tokens": 89803.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.24312686920166,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 2.5365,
+      "mean_token_accuracy": 0.5661972932517528,
+      "num_tokens": 101015.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.9482938051223755,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 2.5634,
+      "mean_token_accuracy": 0.5538406319916248,
+      "num_tokens": 112364.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.09777777777777778,
+      "grad_norm": 1.86210298538208,
+      "learning_rate": 0.00019945038167938932,
+      "loss": 2.4629,
+      "mean_token_accuracy": 0.5780388668179512,
+      "num_tokens": 122882.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 1.8806918859481812,
+      "learning_rate": 0.00019883969465648855,
+      "loss": 2.5022,
+      "mean_token_accuracy": 0.563551553338766,
+      "num_tokens": 134028.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.11555555555555555,
+      "grad_norm": 2.3264434337615967,
+      "learning_rate": 0.00019829007633587786,
+      "loss": 2.4065,
+      "mean_token_accuracy": 0.5807355619966984,
+      "num_tokens": 145192.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 1.8537976741790771,
+      "learning_rate": 0.00019767938931297712,
+      "loss": 2.4838,
+      "mean_token_accuracy": 0.566282794624567,
+      "num_tokens": 156703.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 2.0960652828216553,
+      "learning_rate": 0.00019706870229007636,
+      "loss": 2.4119,
+      "mean_token_accuracy": 0.5830203481018543,
+      "num_tokens": 168041.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 2.2244813442230225,
+      "learning_rate": 0.00019645801526717557,
+      "loss": 2.3726,
+      "mean_token_accuracy": 0.5844443172216416,
+      "num_tokens": 178986.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.1511111111111111,
+      "grad_norm": 1.8238722085952759,
+      "learning_rate": 0.0001958473282442748,
+      "loss": 2.4419,
+      "mean_token_accuracy": 0.5708602093160152,
+      "num_tokens": 190391.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.7154136896133423,
+      "learning_rate": 0.00019523664122137407,
+      "loss": 2.4293,
+      "mean_token_accuracy": 0.5748118035495281,
+      "num_tokens": 201989.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.1688888888888889,
+      "grad_norm": 1.7582788467407227,
+      "learning_rate": 0.0001946259541984733,
+      "loss": 2.3577,
+      "mean_token_accuracy": 0.5877166777849198,
+      "num_tokens": 212914.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.8613263368606567,
+      "learning_rate": 0.0001940152671755725,
+      "loss": 2.3486,
+      "mean_token_accuracy": 0.5889834299683571,
+      "num_tokens": 223936.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_loss": 2.3320820331573486,
+      "eval_mean_token_accuracy": 0.5868698905706405,
+      "eval_num_tokens": 223936.0,
+      "eval_runtime": 49.2429,
+      "eval_samples_per_second": 20.307,
+      "eval_steps_per_second": 10.154,
+      "step": 200
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 1.8486477136611938,
+      "learning_rate": 0.00019340458015267175,
+      "loss": 2.3666,
+      "mean_token_accuracy": 0.5847611322999,
+      "num_tokens": 235036.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 2.018049478530884,
+      "learning_rate": 0.000192793893129771,
+      "loss": 2.2689,
+      "mean_token_accuracy": 0.59971177354455,
+      "num_tokens": 246101.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.20444444444444446,
+      "grad_norm": 1.7244890928268433,
+      "learning_rate": 0.00019218320610687024,
+      "loss": 2.3262,
+      "mean_token_accuracy": 0.5855986528098583,
+      "num_tokens": 257953.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.8928934335708618,
+      "learning_rate": 0.00019157251908396948,
+      "loss": 2.3318,
+      "mean_token_accuracy": 0.5885626815259457,
+      "num_tokens": 269187.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.7358920574188232,
+      "learning_rate": 0.0001909618320610687,
+      "loss": 2.2145,
+      "mean_token_accuracy": 0.6092555984854698,
+      "num_tokens": 279762.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 1.6779032945632935,
+      "learning_rate": 0.00019035114503816795,
+      "loss": 2.3152,
+      "mean_token_accuracy": 0.584602715075016,
+      "num_tokens": 291454.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.6310207843780518,
+      "learning_rate": 0.0001897404580152672,
+      "loss": 2.2669,
+      "mean_token_accuracy": 0.5965895019471645,
+      "num_tokens": 302969.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 1.6765615940093994,
+      "learning_rate": 0.00018912977099236642,
+      "loss": 2.269,
+      "mean_token_accuracy": 0.5934441670775413,
+      "num_tokens": 314204.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.2577777777777778,
+      "grad_norm": 1.793959617614746,
+      "learning_rate": 0.00018851908396946566,
+      "loss": 2.2554,
+      "mean_token_accuracy": 0.600947193801403,
+      "num_tokens": 325649.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.7492129802703857,
+      "learning_rate": 0.0001879083969465649,
+      "loss": 2.2157,
+      "mean_token_accuracy": 0.6022505328059197,
+      "num_tokens": 337167.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.27555555555555555,
+      "grad_norm": 1.803576946258545,
+      "learning_rate": 0.00018729770992366413,
+      "loss": 2.2854,
+      "mean_token_accuracy": 0.5923042424023152,
+      "num_tokens": 348621.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 1.9662351608276367,
+      "learning_rate": 0.00018668702290076337,
+      "loss": 2.2639,
+      "mean_token_accuracy": 0.588193366676569,
+      "num_tokens": 360272.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 1.6725891828536987,
+      "learning_rate": 0.0001860763358778626,
+      "loss": 2.2249,
+      "mean_token_accuracy": 0.6054098337888718,
+      "num_tokens": 371346.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 1.68416166305542,
+      "learning_rate": 0.00018546564885496184,
+      "loss": 2.1678,
+      "mean_token_accuracy": 0.6146526508033275,
+      "num_tokens": 382779.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 1.7218507528305054,
+      "learning_rate": 0.00018485496183206108,
+      "loss": 2.2011,
+      "mean_token_accuracy": 0.6104303196072578,
+      "num_tokens": 393823.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.6817256212234497,
+      "learning_rate": 0.0001842442748091603,
+      "loss": 2.2264,
+      "mean_token_accuracy": 0.5987282857298851,
+      "num_tokens": 405438.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.3288888888888889,
+      "grad_norm": 1.7454718351364136,
+      "learning_rate": 0.00018363358778625955,
+      "loss": 2.2712,
+      "mean_token_accuracy": 0.5939777493476868,
+      "num_tokens": 417299.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 2.011315107345581,
+      "learning_rate": 0.00018302290076335878,
+      "loss": 2.2247,
+      "mean_token_accuracy": 0.6061037018895149,
+      "num_tokens": 428660.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 1.6242053508758545,
+      "learning_rate": 0.00018241221374045802,
+      "loss": 2.232,
+      "mean_token_accuracy": 0.6062197655439376,
+      "num_tokens": 439768.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 1.9328559637069702,
+      "learning_rate": 0.00018180152671755725,
+      "loss": 2.1291,
+      "mean_token_accuracy": 0.6168317429721355,
+      "num_tokens": 450808.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_loss": 2.1662538051605225,
+      "eval_mean_token_accuracy": 0.6099509916305542,
+      "eval_num_tokens": 450808.0,
+      "eval_runtime": 49.4213,
+      "eval_samples_per_second": 20.234,
+      "eval_steps_per_second": 10.117,
+      "step": 400
+    },
+    {
+      "epoch": 0.36444444444444446,
+      "grad_norm": 1.8797143697738647,
+      "learning_rate": 0.0001811908396946565,
+      "loss": 2.2086,
+      "mean_token_accuracy": 0.6012695133686066,
+      "num_tokens": 461592.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.7558225393295288,
+      "learning_rate": 0.00018058015267175575,
+      "loss": 2.1771,
+      "mean_token_accuracy": 0.6060668036341668,
+      "num_tokens": 473434.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.38222222222222224,
+      "grad_norm": 1.845051884651184,
+      "learning_rate": 0.00017996946564885496,
+      "loss": 2.2576,
+      "mean_token_accuracy": 0.5929104581475257,
+      "num_tokens": 485130.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 1.6992298364639282,
+      "learning_rate": 0.0001793587786259542,
+      "loss": 2.1815,
+      "mean_token_accuracy": 0.6100690707564353,
+      "num_tokens": 496482.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.7239253520965576,
+      "learning_rate": 0.00017874809160305343,
+      "loss": 2.2082,
+      "mean_token_accuracy": 0.6001435503363609,
+      "num_tokens": 508218.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 1.7856336832046509,
+      "learning_rate": 0.0001781374045801527,
+      "loss": 2.1593,
+      "mean_token_accuracy": 0.6118309393525123,
+      "num_tokens": 519379.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.4177777777777778,
+      "grad_norm": 1.611831545829773,
+      "learning_rate": 0.00017752671755725193,
+      "loss": 2.1797,
+      "mean_token_accuracy": 0.6033190444111824,
+      "num_tokens": 530561.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.7420586347579956,
+      "learning_rate": 0.00017691603053435114,
+      "loss": 2.2027,
+      "mean_token_accuracy": 0.6067790001630783,
+      "num_tokens": 542631.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.43555555555555553,
+      "grad_norm": 1.948723316192627,
+      "learning_rate": 0.00017630534351145038,
+      "loss": 2.1753,
+      "mean_token_accuracy": 0.6109650492668152,
+      "num_tokens": 553477.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.7983819246292114,
+      "learning_rate": 0.00017569465648854964,
+      "loss": 2.158,
+      "mean_token_accuracy": 0.5996212616562844,
+      "num_tokens": 565400.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 1.842372179031372,
+      "learning_rate": 0.00017508396946564888,
+      "loss": 2.0825,
+      "mean_token_accuracy": 0.6168116196990013,
+      "num_tokens": 576953.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 1.91799795627594,
+      "learning_rate": 0.00017447328244274809,
+      "loss": 2.1022,
+      "mean_token_accuracy": 0.6168905258178711,
+      "num_tokens": 588003.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.4711111111111111,
+      "grad_norm": 1.7727124691009521,
+      "learning_rate": 0.00017386259541984732,
+      "loss": 2.1695,
+      "mean_token_accuracy": 0.5997609972953797,
+      "num_tokens": 600043.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.8602296113967896,
+      "learning_rate": 0.00017325190839694658,
+      "loss": 2.0849,
+      "mean_token_accuracy": 0.6266478568315506,
+      "num_tokens": 610974.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 1.545620083808899,
+      "learning_rate": 0.00017264122137404582,
+      "loss": 2.1824,
+      "mean_token_accuracy": 0.6072694823145867,
+      "num_tokens": 622632.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 1.7485988140106201,
+      "learning_rate": 0.00017203053435114506,
+      "loss": 2.1374,
+      "mean_token_accuracy": 0.6164417043328285,
+      "num_tokens": 634093.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 1.8591196537017822,
+      "learning_rate": 0.00017141984732824426,
+      "loss": 2.0928,
+      "mean_token_accuracy": 0.6241554819047451,
+      "num_tokens": 645226.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 1.8163517713546753,
+      "learning_rate": 0.00017080916030534353,
+      "loss": 2.0476,
+      "mean_token_accuracy": 0.6285594403743744,
+      "num_tokens": 656188.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.5244444444444445,
+      "grad_norm": 1.7729696035385132,
+      "learning_rate": 0.00017019847328244276,
+      "loss": 2.1036,
+      "mean_token_accuracy": 0.6208315283060074,
+      "num_tokens": 667642.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.7804032564163208,
+      "learning_rate": 0.000169587786259542,
+      "loss": 2.1174,
+      "mean_token_accuracy": 0.6148250237107277,
+      "num_tokens": 678769.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 2.0850696563720703,
+      "eval_mean_token_accuracy": 0.6197466601729393,
+      "eval_num_tokens": 678769.0,
+      "eval_runtime": 49.7611,
+      "eval_samples_per_second": 20.096,
+      "eval_steps_per_second": 10.048,
+      "step": 600
+    },
+    {
+      "epoch": 0.5422222222222223,
+      "grad_norm": 1.8643274307250977,
+      "learning_rate": 0.00016897709923664124,
+      "loss": 2.0485,
+      "mean_token_accuracy": 0.6331146821379662,
+      "num_tokens": 690014.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 1.8060939311981201,
+      "learning_rate": 0.00016836641221374047,
+      "loss": 2.1117,
+      "mean_token_accuracy": 0.612041813135147,
+      "num_tokens": 701734.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.7059085369110107,
+      "learning_rate": 0.0001677557251908397,
+      "loss": 2.0747,
+      "mean_token_accuracy": 0.6174572542309761,
+      "num_tokens": 713570.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 1.6600592136383057,
+      "learning_rate": 0.00016714503816793894,
+      "loss": 2.0685,
+      "mean_token_accuracy": 0.6293445661664009,
+      "num_tokens": 724815.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 1.6598913669586182,
+      "learning_rate": 0.00016653435114503818,
+      "loss": 2.0255,
+      "mean_token_accuracy": 0.6309839904308319,
+      "num_tokens": 735777.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 1.8306963443756104,
+      "learning_rate": 0.00016592366412213741,
+      "loss": 2.1249,
+      "mean_token_accuracy": 0.6147443532943726,
+      "num_tokens": 746903.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.5955555555555555,
+      "grad_norm": 1.626795768737793,
+      "learning_rate": 0.00016531297709923665,
+      "loss": 2.0694,
+      "mean_token_accuracy": 0.6254988595843315,
+      "num_tokens": 757881.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 1.710806131362915,
+      "learning_rate": 0.00016470229007633589,
+      "loss": 2.0397,
+      "mean_token_accuracy": 0.6233279958367348,
+      "num_tokens": 768982.0,
+      "step": 680
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 1.7051280736923218,
+      "learning_rate": 0.00016409160305343512,
+      "loss": 2.116,
+      "mean_token_accuracy": 0.6183760315179825,
+      "num_tokens": 780072.0,
+      "step": 690
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 1.607917070388794,
+      "learning_rate": 0.00016348091603053436,
+      "loss": 2.0478,
+      "mean_token_accuracy": 0.6331974640488625,
+      "num_tokens": 791061.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.6311111111111111,
+      "grad_norm": 1.7803592681884766,
+      "learning_rate": 0.0001628702290076336,
+      "loss": 2.0595,
+      "mean_token_accuracy": 0.6249041527509689,
+      "num_tokens": 801867.0,
+      "step": 710
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.6132373809814453,
+      "learning_rate": 0.00016225954198473283,
+      "loss": 2.0789,
+      "mean_token_accuracy": 0.6235784366726875,
+      "num_tokens": 813112.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.6488888888888888,
+      "grad_norm": 1.790528655052185,
+      "learning_rate": 0.00016164885496183207,
+      "loss": 2.0632,
+      "mean_token_accuracy": 0.6268924325704575,
+      "num_tokens": 824133.0,
+      "step": 730
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 2.0007362365722656,
+      "learning_rate": 0.0001610381679389313,
+      "loss": 2.0701,
+      "mean_token_accuracy": 0.6189413338899612,
+      "num_tokens": 835469.0,
+      "step": 740
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.227158546447754,
+      "learning_rate": 0.00016042748091603054,
+      "loss": 2.0339,
+      "mean_token_accuracy": 0.621903920173645,
+      "num_tokens": 846572.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 1.80472731590271,
+      "learning_rate": 0.00015981679389312977,
+      "loss": 2.1285,
+      "mean_token_accuracy": 0.604806374013424,
+      "num_tokens": 857795.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.6844444444444444,
+      "grad_norm": 1.7893937826156616,
+      "learning_rate": 0.000159206106870229,
+      "loss": 2.0347,
+      "mean_token_accuracy": 0.6292635962367058,
+      "num_tokens": 868429.0,
+      "step": 770
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 1.6761573553085327,
+      "learning_rate": 0.00015859541984732824,
+      "loss": 2.0591,
+      "mean_token_accuracy": 0.6254431992769242,
+      "num_tokens": 879659.0,
+      "step": 780
+    },
+    {
+      "epoch": 0.7022222222222222,
+      "grad_norm": 1.803045630455017,
+      "learning_rate": 0.0001579847328244275,
+      "loss": 2.0293,
+      "mean_token_accuracy": 0.6273573949933052,
+      "num_tokens": 890911.0,
+      "step": 790
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 1.7385220527648926,
+      "learning_rate": 0.00015737404580152672,
+      "loss": 2.0197,
+      "mean_token_accuracy": 0.63025072067976,
+      "num_tokens": 902240.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 2.0297935009002686,
+      "eval_mean_token_accuracy": 0.628437293112278,
+      "eval_num_tokens": 902240.0,
+      "eval_runtime": 49.3011,
+      "eval_samples_per_second": 20.284,
+      "eval_steps_per_second": 10.142,
+      "step": 800
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.8906656503677368,
+      "learning_rate": 0.00015676335877862595,
+      "loss": 2.0806,
+      "mean_token_accuracy": 0.619849094748497,
+      "num_tokens": 914009.0,
+      "step": 810
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 1.714268684387207,
+      "learning_rate": 0.0001561526717557252,
+      "loss": 2.0343,
+      "mean_token_accuracy": 0.632188580930233,
+      "num_tokens": 925091.0,
+      "step": 820
+    },
+    {
+      "epoch": 0.7377777777777778,
+      "grad_norm": 1.833918809890747,
+      "learning_rate": 0.00015554198473282445,
+      "loss": 2.0747,
+      "mean_token_accuracy": 0.6280180156230927,
+      "num_tokens": 936675.0,
+      "step": 830
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.9817575216293335,
+      "learning_rate": 0.00015493129770992366,
+      "loss": 2.0859,
+      "mean_token_accuracy": 0.6128378361463547,
+      "num_tokens": 948151.0,
+      "step": 840
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 1.5982656478881836,
+      "learning_rate": 0.0001543206106870229,
+      "loss": 2.0455,
+      "mean_token_accuracy": 0.6276382938027382,
+      "num_tokens": 959266.0,
+      "step": 850
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 1.7298970222473145,
+      "learning_rate": 0.00015370992366412213,
+      "loss": 1.9604,
+      "mean_token_accuracy": 0.6377590849995614,
+      "num_tokens": 970339.0,
+      "step": 860
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 1.8064581155776978,
+      "learning_rate": 0.0001530992366412214,
+      "loss": 2.0698,
+      "mean_token_accuracy": 0.6194617792963981,
+      "num_tokens": 981805.0,
+      "step": 870
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 1.5860410928726196,
+      "learning_rate": 0.00015248854961832063,
+      "loss": 2.0182,
+      "mean_token_accuracy": 0.6292306095361709,
+      "num_tokens": 993552.0,
+      "step": 880
+    },
+    {
+      "epoch": 0.7911111111111111,
+      "grad_norm": 1.8761259317398071,
+      "learning_rate": 0.00015187786259541984,
+      "loss": 2.0335,
+      "mean_token_accuracy": 0.6285651385784149,
+      "num_tokens": 1004400.0,
+      "step": 890
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.6973590850830078,
+      "learning_rate": 0.00015126717557251908,
+      "loss": 2.0927,
+      "mean_token_accuracy": 0.6183614790439605,
+      "num_tokens": 1015564.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.8088888888888889,
+      "grad_norm": 1.6477675437927246,
+      "learning_rate": 0.00015065648854961834,
+      "loss": 1.9187,
+      "mean_token_accuracy": 0.6427812784910202,
+      "num_tokens": 1026849.0,
+      "step": 910
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 1.6942589282989502,
+      "learning_rate": 0.00015004580152671757,
+      "loss": 2.0139,
+      "mean_token_accuracy": 0.6322552219033242,
+      "num_tokens": 1037721.0,
+      "step": 920
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 1.6394822597503662,
+      "learning_rate": 0.0001494351145038168,
+      "loss": 2.0392,
+      "mean_token_accuracy": 0.6273665294051171,
+      "num_tokens": 1048986.0,
+      "step": 930
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 1.697804570198059,
+      "learning_rate": 0.00014882442748091602,
+      "loss": 2.0412,
+      "mean_token_accuracy": 0.625536386668682,
+      "num_tokens": 1060627.0,
+      "step": 940
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 1.8058092594146729,
+      "learning_rate": 0.00014821374045801528,
+      "loss": 1.9737,
+      "mean_token_accuracy": 0.6332821652293206,
+      "num_tokens": 1071482.0,
+      "step": 950
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.773294448852539,
+      "learning_rate": 0.00014760305343511452,
+      "loss": 2.054,
+      "mean_token_accuracy": 0.6256278708577157,
+      "num_tokens": 1082672.0,
+      "step": 960
+    },
+    {
+      "epoch": 0.8622222222222222,
+      "grad_norm": 1.6936707496643066,
+      "learning_rate": 0.00014699236641221375,
+      "loss": 1.9957,
+      "mean_token_accuracy": 0.6333451583981514,
+      "num_tokens": 1093493.0,
+      "step": 970
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 1.7029008865356445,
+      "learning_rate": 0.000146381679389313,
+      "loss": 2.0526,
+      "mean_token_accuracy": 0.6244132176041604,
+      "num_tokens": 1104857.0,
+      "step": 980
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.8421082496643066,
+      "learning_rate": 0.00014577099236641223,
+      "loss": 2.0311,
+      "mean_token_accuracy": 0.6236826583743096,
+      "num_tokens": 1116131.0,
+      "step": 990
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.646053433418274,
+      "learning_rate": 0.00014516030534351146,
+      "loss": 1.9973,
+      "mean_token_accuracy": 0.6274659112095833,
+      "num_tokens": 1127612.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_loss": 1.989682674407959,
+      "eval_mean_token_accuracy": 0.633990108013153,
+      "eval_num_tokens": 1127612.0,
+      "eval_runtime": 49.3043,
+      "eval_samples_per_second": 20.282,
+      "eval_steps_per_second": 10.141,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8977777777777778,
+      "grad_norm": 1.5941271781921387,
+      "learning_rate": 0.0001445496183206107,
+      "loss": 2.0579,
+      "mean_token_accuracy": 0.6256210282444954,
+      "num_tokens": 1138866.0,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 1.7826253175735474,
+      "learning_rate": 0.00014393893129770993,
+      "loss": 1.9866,
+      "mean_token_accuracy": 0.6332772478461266,
+      "num_tokens": 1150411.0,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9155555555555556,
+      "grad_norm": 1.8722221851348877,
+      "learning_rate": 0.00014332824427480917,
+      "loss": 2.0398,
+      "mean_token_accuracy": 0.627329595386982,
+      "num_tokens": 1161360.0,
+      "step": 1030
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 1.6533294916152954,
+      "learning_rate": 0.0001427175572519084,
+      "loss": 2.0271,
+      "mean_token_accuracy": 0.6259514302015304,
+      "num_tokens": 1172683.0,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 1.5746543407440186,
+      "learning_rate": 0.00014210687022900764,
+      "loss": 1.9634,
+      "mean_token_accuracy": 0.6359310179948807,
+      "num_tokens": 1183277.0,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 1.6094276905059814,
+      "learning_rate": 0.00014149618320610688,
+      "loss": 1.9195,
+      "mean_token_accuracy": 0.649330523610115,
+      "num_tokens": 1194160.0,
+      "step": 1060
+    },
+    {
+      "epoch": 0.9511111111111111,
+      "grad_norm": 1.9643882513046265,
+      "learning_rate": 0.0001408854961832061,
+      "loss": 2.0042,
+      "mean_token_accuracy": 0.6356254667043686,
+      "num_tokens": 1205308.0,
+      "step": 1070
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.8238948583602905,
+      "learning_rate": 0.00014027480916030535,
+      "loss": 1.9172,
+      "mean_token_accuracy": 0.6497033536434174,
+      "num_tokens": 1215760.0,
+      "step": 1080
+    },
+    {
+      "epoch": 0.9688888888888889,
+      "grad_norm": 1.7422380447387695,
+      "learning_rate": 0.00013966412213740458,
+      "loss": 2.0213,
+      "mean_token_accuracy": 0.6309294819831848,
+      "num_tokens": 1226775.0,
+      "step": 1090
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.651795744895935,
+      "learning_rate": 0.00013905343511450382,
+      "loss": 2.033,
+      "mean_token_accuracy": 0.6295390352606773,
+      "num_tokens": 1238191.0,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 1.673543095588684,
+      "learning_rate": 0.00013844274809160308,
+      "loss": 2.0085,
+      "mean_token_accuracy": 0.6329691678285598,
+      "num_tokens": 1249561.0,
+      "step": 1110
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 1.7423163652420044,
+      "learning_rate": 0.0001378320610687023,
+      "loss": 1.9751,
+      "mean_token_accuracy": 0.6307685926556588,
+      "num_tokens": 1260429.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.0044444444444445,
+      "grad_norm": 1.4878981113433838,
+      "learning_rate": 0.00013722137404580153,
+      "loss": 1.9171,
+      "mean_token_accuracy": 0.644737622141838,
+      "num_tokens": 1271111.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 1.5343797206878662,
+      "learning_rate": 0.00013661068702290076,
+      "loss": 1.8544,
+      "mean_token_accuracy": 0.6503374725580215,
+      "num_tokens": 1282434.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.0222222222222221,
+      "grad_norm": 1.5450340509414673,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 1.828,
+      "mean_token_accuracy": 0.6514182686805725,
+      "num_tokens": 1294382.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.031111111111111,
+      "grad_norm": 1.8313877582550049,
+      "learning_rate": 0.00013538931297709923,
+      "loss": 1.7704,
+      "mean_token_accuracy": 0.6693721905350685,
+      "num_tokens": 1305343.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.8418430089950562,
+      "learning_rate": 0.00013477862595419847,
+      "loss": 1.7591,
+      "mean_token_accuracy": 0.67226582467556,
+      "num_tokens": 1316558.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.048888888888889,
+      "grad_norm": 1.6022825241088867,
+      "learning_rate": 0.0001341679389312977,
+      "loss": 1.8048,
+      "mean_token_accuracy": 0.6629651457071304,
+      "num_tokens": 1327938.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.0577777777777777,
+      "grad_norm": 1.5888707637786865,
+      "learning_rate": 0.00013355725190839697,
+      "loss": 1.773,
+      "mean_token_accuracy": 0.6730352655053139,
+      "num_tokens": 1338732.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 1.833946943283081,
+      "learning_rate": 0.0001329465648854962,
+      "loss": 1.7887,
+      "mean_token_accuracy": 0.6616317644715309,
+      "num_tokens": 1350096.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "eval_loss": 1.9697085618972778,
+      "eval_mean_token_accuracy": 0.6378205664157868,
+      "eval_num_tokens": 1350096.0,
+      "eval_runtime": 49.9237,
+      "eval_samples_per_second": 20.031,
+      "eval_steps_per_second": 10.015,
+      "step": 1200
+    },
+    {
+      "epoch": 1.0755555555555556,
+      "grad_norm": 1.6338160037994385,
+      "learning_rate": 0.00013233587786259541,
+      "loss": 1.7889,
+      "mean_token_accuracy": 0.6668319672346115,
+      "num_tokens": 1360771.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.0844444444444445,
+      "grad_norm": 1.8737561702728271,
+      "learning_rate": 0.00013172519083969465,
+      "loss": 1.7997,
+      "mean_token_accuracy": 0.6570939287543297,
+      "num_tokens": 1372450.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.0933333333333333,
+      "grad_norm": 1.758074402809143,
+      "learning_rate": 0.0001311145038167939,
+      "loss": 1.8457,
+      "mean_token_accuracy": 0.653074924647808,
+      "num_tokens": 1383711.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.1022222222222222,
+      "grad_norm": 1.839158296585083,
+      "learning_rate": 0.00013050381679389315,
+      "loss": 1.8013,
+      "mean_token_accuracy": 0.6608111187815666,
+      "num_tokens": 1394856.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 1.733567476272583,
+      "learning_rate": 0.00012989312977099238,
+      "loss": 1.7814,
+      "mean_token_accuracy": 0.6655508041381836,
+      "num_tokens": 1406193.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.6274900436401367,
+      "learning_rate": 0.0001292824427480916,
+      "loss": 1.858,
+      "mean_token_accuracy": 0.6488608077168465,
+      "num_tokens": 1417607.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.1288888888888888,
+      "grad_norm": 1.690090537071228,
+      "learning_rate": 0.00012867175572519086,
+      "loss": 1.8256,
+      "mean_token_accuracy": 0.6595686703920365,
+      "num_tokens": 1429073.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.1377777777777778,
+      "grad_norm": 1.6638071537017822,
+      "learning_rate": 0.0001280610687022901,
+      "loss": 1.8334,
+      "mean_token_accuracy": 0.6580470725893974,
+      "num_tokens": 1440194.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.1466666666666667,
+      "grad_norm": 1.8339307308197021,
+      "learning_rate": 0.00012745038167938933,
+      "loss": 1.783,
+      "mean_token_accuracy": 0.6632378786802292,
+      "num_tokens": 1451221.0,
+      "step": 1290
+    },
+    {
+      "epoch": 1.1555555555555554,
+      "grad_norm": 1.7621415853500366,
+      "learning_rate": 0.00012683969465648854,
+      "loss": 1.844,
+      "mean_token_accuracy": 0.6506654173135757,
+      "num_tokens": 1462493.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.1644444444444444,
+      "grad_norm": 1.7811567783355713,
+      "learning_rate": 0.00012622900763358777,
+      "loss": 1.8235,
+      "mean_token_accuracy": 0.6505810797214509,
+      "num_tokens": 1473710.0,
+      "step": 1310
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 1.9157836437225342,
+      "learning_rate": 0.00012561832061068704,
+      "loss": 1.8885,
+      "mean_token_accuracy": 0.6459546625614166,
+      "num_tokens": 1485215.0,
+      "step": 1320
+    },
+    {
+      "epoch": 1.1822222222222223,
+      "grad_norm": 1.6572569608688354,
+      "learning_rate": 0.00012500763358778627,
+      "loss": 1.813,
+      "mean_token_accuracy": 0.6597578257322312,
+      "num_tokens": 1496371.0,
+      "step": 1330
+    },
+    {
+      "epoch": 1.1911111111111112,
+      "grad_norm": 1.8602449893951416,
+      "learning_rate": 0.0001243969465648855,
+      "loss": 1.8179,
+      "mean_token_accuracy": 0.6519266426563263,
+      "num_tokens": 1508348.0,
+      "step": 1340
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.8736369609832764,
+      "learning_rate": 0.00012378625954198472,
+      "loss": 1.8029,
+      "mean_token_accuracy": 0.6621162816882133,
+      "num_tokens": 1519322.0,
+      "step": 1350
+    },
+    {
+      "epoch": 1.208888888888889,
+      "grad_norm": 2.026744842529297,
+      "learning_rate": 0.00012317557251908398,
+      "loss": 1.8168,
+      "mean_token_accuracy": 0.6635635286569596,
+      "num_tokens": 1530183.0,
+      "step": 1360
+    },
+    {
+      "epoch": 1.2177777777777778,
+      "grad_norm": 1.7360782623291016,
+      "learning_rate": 0.00012256488549618322,
+      "loss": 1.7521,
+      "mean_token_accuracy": 0.6706348299980164,
+      "num_tokens": 1540862.0,
+      "step": 1370
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 1.9620578289031982,
+      "learning_rate": 0.00012195419847328244,
+      "loss": 1.8228,
+      "mean_token_accuracy": 0.6569086670875549,
+      "num_tokens": 1552212.0,
+      "step": 1380
+    },
+    {
+      "epoch": 1.2355555555555555,
+      "grad_norm": 1.6294327974319458,
+      "learning_rate": 0.00012134351145038167,
+      "loss": 1.7654,
+      "mean_token_accuracy": 0.6697377026081085,
+      "num_tokens": 1563356.0,
+      "step": 1390
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 1.7311524152755737,
+      "learning_rate": 0.00012073282442748092,
+      "loss": 1.9019,
+      "mean_token_accuracy": 0.6457875579595566,
+      "num_tokens": 1574569.0,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "eval_loss": 1.9411770105361938,
+      "eval_mean_token_accuracy": 0.6407178282737732,
+      "eval_num_tokens": 1574569.0,
+      "eval_runtime": 48.3309,
+      "eval_samples_per_second": 20.691,
+      "eval_steps_per_second": 10.345,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2533333333333334,
+      "grad_norm": 1.8629728555679321,
+      "learning_rate": 0.00012012213740458016,
+      "loss": 1.7585,
+      "mean_token_accuracy": 0.671015702188015,
+      "num_tokens": 1585308.0,
+      "step": 1410
+    },
+    {
+      "epoch": 1.2622222222222224,
+      "grad_norm": 1.958808183670044,
+      "learning_rate": 0.0001195114503816794,
+      "loss": 1.8479,
+      "mean_token_accuracy": 0.6535898372530937,
+      "num_tokens": 1596886.0,
+      "step": 1420
+    },
+    {
+      "epoch": 1.271111111111111,
+      "grad_norm": 1.950421690940857,
+      "learning_rate": 0.00011890076335877862,
+      "loss": 1.8173,
+      "mean_token_accuracy": 0.6655478686094284,
+      "num_tokens": 1607683.0,
+      "step": 1430
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.8152872323989868,
+      "learning_rate": 0.00011829007633587788,
+      "loss": 1.8791,
+      "mean_token_accuracy": 0.6531546950340271,
+      "num_tokens": 1618906.0,
+      "step": 1440
+    },
+    {
+      "epoch": 1.2888888888888888,
+      "grad_norm": 1.7857719659805298,
+      "learning_rate": 0.0001176793893129771,
+      "loss": 1.7887,
+      "mean_token_accuracy": 0.6610255971550941,
+      "num_tokens": 1629981.0,
+      "step": 1450
+    },
+    {
+      "epoch": 1.2977777777777777,
+      "grad_norm": 1.8434971570968628,
+      "learning_rate": 0.00011706870229007634,
+      "loss": 1.8368,
+      "mean_token_accuracy": 0.653369964659214,
+      "num_tokens": 1641429.0,
+      "step": 1460
+    },
+    {
+      "epoch": 1.3066666666666666,
+      "grad_norm": 1.8877320289611816,
+      "learning_rate": 0.00011645801526717557,
+      "loss": 1.7938,
+      "mean_token_accuracy": 0.6639183640480042,
+      "num_tokens": 1652601.0,
+      "step": 1470
+    },
+    {
+      "epoch": 1.3155555555555556,
+      "grad_norm": 1.8121625185012817,
+      "learning_rate": 0.00011584732824427482,
+      "loss": 1.7862,
+      "mean_token_accuracy": 0.661414910852909,
+      "num_tokens": 1663837.0,
+      "step": 1480
+    },
+    {
+      "epoch": 1.3244444444444445,
+      "grad_norm": 1.7919855117797852,
+      "learning_rate": 0.00011523664122137406,
+      "loss": 1.8148,
+      "mean_token_accuracy": 0.6654411420226097,
+      "num_tokens": 1675018.0,
+      "step": 1490
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.828735589981079,
+      "learning_rate": 0.00011462595419847328,
+      "loss": 1.8456,
+      "mean_token_accuracy": 0.6496043875813484,
+      "num_tokens": 1686136.0,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3422222222222222,
+      "grad_norm": 1.9462794065475464,
+      "learning_rate": 0.00011401526717557252,
+      "loss": 1.8412,
+      "mean_token_accuracy": 0.6603908941149712,
+      "num_tokens": 1697160.0,
+      "step": 1510
+    },
+    {
+      "epoch": 1.3511111111111112,
+      "grad_norm": 1.6794313192367554,
+      "learning_rate": 0.00011340458015267177,
+      "loss": 1.7774,
+      "mean_token_accuracy": 0.6664682924747467,
+      "num_tokens": 1707831.0,
+      "step": 1520
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 1.8189337253570557,
+      "learning_rate": 0.000112793893129771,
+      "loss": 1.8031,
+      "mean_token_accuracy": 0.6627006307244301,
+      "num_tokens": 1719074.0,
+      "step": 1530
+    },
+    {
+      "epoch": 1.3688888888888888,
+      "grad_norm": 2.073533296585083,
+      "learning_rate": 0.00011218320610687022,
+      "loss": 1.8657,
+      "mean_token_accuracy": 0.6476830393075943,
+      "num_tokens": 1730388.0,
+      "step": 1540
+    },
+    {
+      "epoch": 1.3777777777777778,
+      "grad_norm": 2.1564207077026367,
+      "learning_rate": 0.00011157251908396946,
+      "loss": 1.8261,
+      "mean_token_accuracy": 0.6567840203642845,
+      "num_tokens": 1741806.0,
+      "step": 1550
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 1.6113232374191284,
+      "learning_rate": 0.00011096183206106871,
+      "loss": 1.7753,
+      "mean_token_accuracy": 0.6659888163208961,
+      "num_tokens": 1753313.0,
+      "step": 1560
+    },
+    {
+      "epoch": 1.3955555555555557,
+      "grad_norm": 1.8112174272537231,
+      "learning_rate": 0.00011035114503816795,
+      "loss": 1.8046,
+      "mean_token_accuracy": 0.6593015149235726,
+      "num_tokens": 1765144.0,
+      "step": 1570
+    },
+    {
+      "epoch": 1.4044444444444444,
+      "grad_norm": 1.8377541303634644,
+      "learning_rate": 0.00010974045801526718,
+      "loss": 1.8848,
+      "mean_token_accuracy": 0.6533517614006996,
+      "num_tokens": 1776783.0,
+      "step": 1580
+    },
+    {
+      "epoch": 1.4133333333333333,
+      "grad_norm": 1.8384325504302979,
+      "learning_rate": 0.0001091297709923664,
+      "loss": 1.7669,
+      "mean_token_accuracy": 0.6613995045423507,
+      "num_tokens": 1788274.0,
+      "step": 1590
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 1.8124533891677856,
+      "learning_rate": 0.00010851908396946567,
+      "loss": 1.8164,
+      "mean_token_accuracy": 0.6591159239411354,
+      "num_tokens": 1799707.0,
+      "step": 1600
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "eval_loss": 1.9286668300628662,
+      "eval_mean_token_accuracy": 0.6434953879117966,
+      "eval_num_tokens": 1799707.0,
+      "eval_runtime": 48.6198,
+      "eval_samples_per_second": 20.568,
+      "eval_steps_per_second": 10.284,
+      "step": 1600
+    },
+    {
+      "epoch": 1.431111111111111,
+      "grad_norm": 1.6931661367416382,
+      "learning_rate": 0.00010790839694656489,
+      "loss": 1.7548,
+      "mean_token_accuracy": 0.664087076485157,
+      "num_tokens": 1810865.0,
+      "step": 1610
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.7501254081726074,
+      "learning_rate": 0.00010729770992366413,
+      "loss": 1.7652,
+      "mean_token_accuracy": 0.6640020117163659,
+      "num_tokens": 1821807.0,
+      "step": 1620
+    },
+    {
+      "epoch": 1.448888888888889,
+      "grad_norm": 1.8411732912063599,
+      "learning_rate": 0.00010668702290076336,
+      "loss": 1.831,
+      "mean_token_accuracy": 0.6564242169260979,
+      "num_tokens": 1832886.0,
+      "step": 1630
+    },
+    {
+      "epoch": 1.4577777777777778,
+      "grad_norm": 2.003892183303833,
+      "learning_rate": 0.00010607633587786261,
+      "loss": 1.7791,
+      "mean_token_accuracy": 0.6632592365145683,
+      "num_tokens": 1843989.0,
+      "step": 1640
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 1.7987340688705444,
+      "learning_rate": 0.00010546564885496185,
+      "loss": 1.7627,
+      "mean_token_accuracy": 0.6713873609900475,
+      "num_tokens": 1855106.0,
+      "step": 1650
+    },
+    {
+      "epoch": 1.4755555555555555,
+      "grad_norm": 1.931877851486206,
+      "learning_rate": 0.00010485496183206107,
+      "loss": 1.7976,
+      "mean_token_accuracy": 0.6631382897496223,
+      "num_tokens": 1866900.0,
+      "step": 1660
+    },
+    {
+      "epoch": 1.4844444444444445,
+      "grad_norm": 1.7883687019348145,
+      "learning_rate": 0.0001042442748091603,
+      "loss": 1.7671,
+      "mean_token_accuracy": 0.6675158813595772,
+      "num_tokens": 1877911.0,
+      "step": 1670
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 1.8195563554763794,
+      "learning_rate": 0.00010363358778625955,
+      "loss": 1.8346,
+      "mean_token_accuracy": 0.652577318251133,
+      "num_tokens": 1889580.0,
+      "step": 1680
+    },
+    {
+      "epoch": 1.5022222222222221,
+      "grad_norm": 1.7439149618148804,
+      "learning_rate": 0.00010302290076335879,
+      "loss": 1.7476,
+      "mean_token_accuracy": 0.6717594474554062,
+      "num_tokens": 1901133.0,
+      "step": 1690
+    },
+    {
+      "epoch": 1.511111111111111,
+      "grad_norm": 1.8155314922332764,
+      "learning_rate": 0.00010241221374045801,
+      "loss": 1.8044,
+      "mean_token_accuracy": 0.6617274522781372,
+      "num_tokens": 1911796.0,
+      "step": 1700
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.7685112953186035,
+      "learning_rate": 0.00010180152671755725,
+      "loss": 1.7727,
+      "mean_token_accuracy": 0.665304908156395,
+      "num_tokens": 1923217.0,
+      "step": 1710
+    },
+    {
+      "epoch": 1.528888888888889,
+      "grad_norm": 1.737053632736206,
+      "learning_rate": 0.0001011908396946565,
+      "loss": 1.8345,
+      "mean_token_accuracy": 0.6577870160341263,
+      "num_tokens": 1934355.0,
+      "step": 1720
+    },
+    {
+      "epoch": 1.537777777777778,
+      "grad_norm": 1.9686291217803955,
+      "learning_rate": 0.00010058015267175573,
+      "loss": 1.8165,
+      "mean_token_accuracy": 0.6594037398695946,
+      "num_tokens": 1945653.0,
+      "step": 1730
+    },
+    {
+      "epoch": 1.5466666666666666,
+      "grad_norm": 1.844651699066162,
+      "learning_rate": 9.996946564885497e-05,
+      "loss": 1.8273,
+      "mean_token_accuracy": 0.6566928923130035,
+      "num_tokens": 1956891.0,
+      "step": 1740
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 1.8607743978500366,
+      "learning_rate": 9.93587786259542e-05,
+      "loss": 1.785,
+      "mean_token_accuracy": 0.6692357853055,
+      "num_tokens": 1967789.0,
+      "step": 1750
+    },
+    {
+      "epoch": 1.5644444444444443,
+      "grad_norm": 1.9204373359680176,
+      "learning_rate": 9.874809160305344e-05,
+      "loss": 1.8264,
+      "mean_token_accuracy": 0.6549209818243981,
+      "num_tokens": 1979224.0,
+      "step": 1760
+    },
+    {
+      "epoch": 1.5733333333333333,
+      "grad_norm": 1.7754265069961548,
+      "learning_rate": 9.813740458015268e-05,
+      "loss": 1.7467,
+      "mean_token_accuracy": 0.6670090600848197,
+      "num_tokens": 1990255.0,
+      "step": 1770
+    },
+    {
+      "epoch": 1.5822222222222222,
+      "grad_norm": 2.069091796875,
+      "learning_rate": 9.752671755725191e-05,
+      "loss": 1.7731,
+      "mean_token_accuracy": 0.6609751120209694,
+      "num_tokens": 2001606.0,
+      "step": 1780
+    },
+    {
+      "epoch": 1.5911111111111111,
+      "grad_norm": 2.1375646591186523,
+      "learning_rate": 9.691603053435115e-05,
+      "loss": 1.8009,
+      "mean_token_accuracy": 0.6624869346618653,
+      "num_tokens": 2012912.0,
+      "step": 1790
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.5623434782028198,
+      "learning_rate": 9.630534351145038e-05,
+      "loss": 1.7383,
+      "mean_token_accuracy": 0.6694582119584084,
+      "num_tokens": 2024571.0,
+      "step": 1800
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.90510892868042,
+      "eval_mean_token_accuracy": 0.6464553346633911,
+      "eval_num_tokens": 2024571.0,
+      "eval_runtime": 48.9449,
+      "eval_samples_per_second": 20.431,
+      "eval_steps_per_second": 10.216,
+      "step": 1800
+    },
+    {
+      "epoch": 1.608888888888889,
+      "grad_norm": 1.745969295501709,
+      "learning_rate": 9.569465648854963e-05,
+      "loss": 1.7552,
+      "mean_token_accuracy": 0.6786300778388977,
+      "num_tokens": 2035783.0,
+      "step": 1810
+    },
+    {
+      "epoch": 1.6177777777777778,
+      "grad_norm": 1.7463303804397583,
+      "learning_rate": 9.508396946564886e-05,
+      "loss": 1.7495,
+      "mean_token_accuracy": 0.6666959136724472,
+      "num_tokens": 2047304.0,
+      "step": 1820
+    },
+    {
+      "epoch": 1.6266666666666667,
+      "grad_norm": 1.9058139324188232,
+      "learning_rate": 9.44732824427481e-05,
+      "loss": 1.8365,
+      "mean_token_accuracy": 0.6536470741033554,
+      "num_tokens": 2058792.0,
+      "step": 1830
+    },
+    {
+      "epoch": 1.6355555555555554,
+      "grad_norm": 2.065488576889038,
+      "learning_rate": 9.386259541984733e-05,
+      "loss": 1.7939,
+      "mean_token_accuracy": 0.6519258007407188,
+      "num_tokens": 2070175.0,
+      "step": 1840
+    },
+    {
+      "epoch": 1.6444444444444444,
+      "grad_norm": 1.778023600578308,
+      "learning_rate": 9.325190839694658e-05,
+      "loss": 1.8155,
+      "mean_token_accuracy": 0.655296416580677,
+      "num_tokens": 2081343.0,
+      "step": 1850
+    },
+    {
+      "epoch": 1.6533333333333333,
+      "grad_norm": 1.7437517642974854,
+      "learning_rate": 9.26412213740458e-05,
+      "loss": 1.7996,
+      "mean_token_accuracy": 0.6618543311953544,
+      "num_tokens": 2093074.0,
+      "step": 1860
+    },
+    {
+      "epoch": 1.6622222222222223,
+      "grad_norm": 1.7666471004486084,
+      "learning_rate": 9.203053435114505e-05,
+      "loss": 1.7658,
+      "mean_token_accuracy": 0.6631957843899727,
+      "num_tokens": 2104640.0,
+      "step": 1870
+    },
+    {
+      "epoch": 1.6711111111111112,
+      "grad_norm": 1.912842869758606,
+      "learning_rate": 9.141984732824428e-05,
+      "loss": 1.7996,
+      "mean_token_accuracy": 0.6606781020760536,
+      "num_tokens": 2115628.0,
+      "step": 1880
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 1.7230331897735596,
+      "learning_rate": 9.080916030534351e-05,
+      "loss": 1.8042,
+      "mean_token_accuracy": 0.6600380197167397,
+      "num_tokens": 2126505.0,
+      "step": 1890
+    },
+    {
+      "epoch": 1.6888888888888889,
+      "grad_norm": 1.7043401002883911,
+      "learning_rate": 9.019847328244276e-05,
+      "loss": 1.7993,
+      "mean_token_accuracy": 0.6613149493932724,
+      "num_tokens": 2138364.0,
+      "step": 1900
+    },
+    {
+      "epoch": 1.6977777777777778,
+      "grad_norm": 1.9145572185516357,
+      "learning_rate": 8.958778625954198e-05,
+      "loss": 1.8046,
+      "mean_token_accuracy": 0.662477345764637,
+      "num_tokens": 2149425.0,
+      "step": 1910
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 1.7448140382766724,
+      "learning_rate": 8.897709923664123e-05,
+      "loss": 1.8004,
+      "mean_token_accuracy": 0.6539181426167489,
+      "num_tokens": 2160843.0,
+      "step": 1920
+    },
+    {
+      "epoch": 1.7155555555555555,
+      "grad_norm": 1.8304840326309204,
+      "learning_rate": 8.836641221374045e-05,
+      "loss": 1.8404,
+      "mean_token_accuracy": 0.6593489304184914,
+      "num_tokens": 2172044.0,
+      "step": 1930
+    },
+    {
+      "epoch": 1.7244444444444444,
+      "grad_norm": 1.802331566810608,
+      "learning_rate": 8.77557251908397e-05,
+      "loss": 1.7995,
+      "mean_token_accuracy": 0.6634193584322929,
+      "num_tokens": 2182916.0,
+      "step": 1940
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 1.9834682941436768,
+      "learning_rate": 8.714503816793894e-05,
+      "loss": 1.7525,
+      "mean_token_accuracy": 0.6685526207089424,
+      "num_tokens": 2194913.0,
+      "step": 1950
+    },
+    {
+      "epoch": 1.7422222222222223,
+      "grad_norm": 1.8077235221862793,
+      "learning_rate": 8.653435114503817e-05,
+      "loss": 1.7612,
+      "mean_token_accuracy": 0.6704939991235733,
+      "num_tokens": 2205721.0,
+      "step": 1960
+    },
+    {
+      "epoch": 1.751111111111111,
+      "grad_norm": 1.957993745803833,
+      "learning_rate": 8.592366412213741e-05,
+      "loss": 1.8059,
+      "mean_token_accuracy": 0.6547697961330414,
+      "num_tokens": 2217489.0,
+      "step": 1970
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.7215981483459473,
+      "learning_rate": 8.531297709923664e-05,
+      "loss": 1.7913,
+      "mean_token_accuracy": 0.657075221836567,
+      "num_tokens": 2228972.0,
+      "step": 1980
+    },
+    {
+      "epoch": 1.7688888888888887,
+      "grad_norm": 1.8760231733322144,
+      "learning_rate": 8.470229007633588e-05,
+      "loss": 1.7923,
+      "mean_token_accuracy": 0.6629065066576004,
+      "num_tokens": 2240239.0,
+      "step": 1990
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 2.092407703399658,
+      "learning_rate": 8.409160305343512e-05,
+      "loss": 1.7593,
+      "mean_token_accuracy": 0.6686230883002281,
+      "num_tokens": 2251436.0,
+      "step": 2000
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "eval_loss": 1.893255591392517,
+      "eval_mean_token_accuracy": 0.6482590944766998,
+      "eval_num_tokens": 2251436.0,
+      "eval_runtime": 49.0676,
+      "eval_samples_per_second": 20.38,
+      "eval_steps_per_second": 10.19,
+      "step": 2000
+    },
+    {
+      "epoch": 1.7866666666666666,
+      "grad_norm": 1.7836107015609741,
+      "learning_rate": 8.348091603053435e-05,
+      "loss": 1.8033,
+      "mean_token_accuracy": 0.6598399996757507,
+      "num_tokens": 2263069.0,
+      "step": 2010
+    },
+    {
+      "epoch": 1.7955555555555556,
+      "grad_norm": 1.7955141067504883,
+      "learning_rate": 8.287022900763359e-05,
+      "loss": 1.7922,
+      "mean_token_accuracy": 0.6619856491684913,
+      "num_tokens": 2274050.0,
+      "step": 2020
+    },
+    {
+      "epoch": 1.8044444444444445,
+      "grad_norm": 1.7887564897537231,
+      "learning_rate": 8.225954198473282e-05,
+      "loss": 1.8353,
+      "mean_token_accuracy": 0.658150726556778,
+      "num_tokens": 2285060.0,
+      "step": 2030
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 1.8892567157745361,
+      "learning_rate": 8.164885496183207e-05,
+      "loss": 1.7266,
+      "mean_token_accuracy": 0.6728688895702362,
+      "num_tokens": 2296211.0,
+      "step": 2040
+    },
+    {
+      "epoch": 1.8222222222222222,
+      "grad_norm": 1.9226106405258179,
+      "learning_rate": 8.10381679389313e-05,
+      "loss": 1.7243,
+      "mean_token_accuracy": 0.6712497785687447,
+      "num_tokens": 2307184.0,
+      "step": 2050
+    },
+    {
+      "epoch": 1.8311111111111111,
+      "grad_norm": 1.735863208770752,
+      "learning_rate": 8.042748091603054e-05,
+      "loss": 1.7739,
+      "mean_token_accuracy": 0.6621047109365463,
+      "num_tokens": 2318602.0,
+      "step": 2060
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 1.8361355066299438,
+      "learning_rate": 7.981679389312977e-05,
+      "loss": 1.8223,
+      "mean_token_accuracy": 0.6560095950961113,
+      "num_tokens": 2330193.0,
+      "step": 2070
+    },
+    {
+      "epoch": 1.8488888888888888,
+      "grad_norm": 1.8159486055374146,
+      "learning_rate": 7.920610687022902e-05,
+      "loss": 1.7695,
+      "mean_token_accuracy": 0.6657541528344154,
+      "num_tokens": 2341442.0,
+      "step": 2080
+    },
+    {
+      "epoch": 1.8577777777777778,
+      "grad_norm": 1.9189419746398926,
+      "learning_rate": 7.859541984732824e-05,
+      "loss": 1.8333,
+      "mean_token_accuracy": 0.6628425523638726,
+      "num_tokens": 2352479.0,
+      "step": 2090
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 1.8809512853622437,
+      "learning_rate": 7.798473282442749e-05,
+      "loss": 1.7371,
+      "mean_token_accuracy": 0.6683435723185539,
+      "num_tokens": 2363642.0,
+      "step": 2100
+    },
+    {
+      "epoch": 1.8755555555555556,
+      "grad_norm": 1.845886468887329,
+      "learning_rate": 7.737404580152672e-05,
+      "loss": 1.7774,
+      "mean_token_accuracy": 0.6559944331645966,
+      "num_tokens": 2375376.0,
+      "step": 2110
+    },
+    {
+      "epoch": 1.8844444444444446,
+      "grad_norm": 1.7780894041061401,
+      "learning_rate": 7.676335877862596e-05,
+      "loss": 1.7823,
+      "mean_token_accuracy": 0.6601730152964592,
+      "num_tokens": 2386944.0,
+      "step": 2120
+    },
+    {
+      "epoch": 1.8933333333333333,
+      "grad_norm": 1.9167022705078125,
+      "learning_rate": 7.61526717557252e-05,
+      "loss": 1.7869,
+      "mean_token_accuracy": 0.6573449537158013,
+      "num_tokens": 2398391.0,
+      "step": 2130
+    },
+    {
+      "epoch": 1.9022222222222223,
+      "grad_norm": 2.037911891937256,
+      "learning_rate": 7.554198473282443e-05,
+      "loss": 1.7858,
+      "mean_token_accuracy": 0.6593190267682075,
+      "num_tokens": 2409837.0,
+      "step": 2140
+    },
+    {
+      "epoch": 1.911111111111111,
+      "grad_norm": 1.7496647834777832,
+      "learning_rate": 7.493129770992367e-05,
+      "loss": 1.7241,
+      "mean_token_accuracy": 0.6702290028333664,
+      "num_tokens": 2421607.0,
+      "step": 2150
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 2.0227596759796143,
+      "learning_rate": 7.43206106870229e-05,
+      "loss": 1.7731,
+      "mean_token_accuracy": 0.6679618924856185,
+      "num_tokens": 2432376.0,
+      "step": 2160
+    },
+    {
+      "epoch": 1.9288888888888889,
+      "grad_norm": 1.7401562929153442,
+      "learning_rate": 7.370992366412214e-05,
+      "loss": 1.7684,
+      "mean_token_accuracy": 0.6676609605550766,
+      "num_tokens": 2443683.0,
+      "step": 2170
+    },
+    {
+      "epoch": 1.9377777777777778,
+      "grad_norm": 2.709106922149658,
+      "learning_rate": 7.309923664122137e-05,
+      "loss": 1.709,
+      "mean_token_accuracy": 0.6738818466663361,
+      "num_tokens": 2454757.0,
+      "step": 2180
+    },
+    {
+      "epoch": 1.9466666666666668,
+      "grad_norm": 1.8504191637039185,
+      "learning_rate": 7.248854961832061e-05,
+      "loss": 1.7411,
+      "mean_token_accuracy": 0.6681609645485878,
+      "num_tokens": 2465562.0,
+      "step": 2190
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 1.9488162994384766,
+      "learning_rate": 7.187786259541986e-05,
+      "loss": 1.7927,
+      "mean_token_accuracy": 0.6587553441524505,
+      "num_tokens": 2476869.0,
+      "step": 2200
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "eval_loss": 1.8803235292434692,
+      "eval_mean_token_accuracy": 0.6499251070022583,
+      "eval_num_tokens": 2476869.0,
+      "eval_runtime": 47.7648,
+      "eval_samples_per_second": 20.936,
+      "eval_steps_per_second": 10.468,
+      "step": 2200
+    },
+    {
+      "epoch": 1.9644444444444444,
+      "grad_norm": 1.9747337102890015,
+      "learning_rate": 7.132824427480917e-05,
+      "loss": 1.7689,
+      "mean_token_accuracy": 0.666295376420021,
+      "num_tokens": 2487704.0,
+      "step": 2210
+    },
+    {
+      "epoch": 1.9733333333333334,
+      "grad_norm": 1.8904316425323486,
+      "learning_rate": 7.071755725190839e-05,
+      "loss": 1.7538,
+      "mean_token_accuracy": 0.6645636394619941,
+      "num_tokens": 2498918.0,
+      "step": 2220
+    },
+    {
+      "epoch": 1.982222222222222,
+      "grad_norm": 1.8791844844818115,
+      "learning_rate": 7.010687022900764e-05,
+      "loss": 1.7926,
+      "mean_token_accuracy": 0.6631673067808151,
+      "num_tokens": 2509728.0,
+      "step": 2230
+    },
+    {
+      "epoch": 1.991111111111111,
+      "grad_norm": 1.9756606817245483,
+      "learning_rate": 6.949618320610687e-05,
+      "loss": 1.7863,
+      "mean_token_accuracy": 0.6628521859645844,
+      "num_tokens": 2521073.0,
+      "step": 2240
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7894699573516846,
+      "learning_rate": 6.888549618320611e-05,
+      "loss": 1.7539,
+      "mean_token_accuracy": 0.6728802308440208,
+      "num_tokens": 2531820.0,
+      "step": 2250
+    },
+    {
+      "epoch": 2.008888888888889,
+      "grad_norm": 1.702850341796875,
+      "learning_rate": 6.827480916030535e-05,
+      "loss": 1.4903,
+      "mean_token_accuracy": 0.7138098135590554,
+      "num_tokens": 2542512.0,
+      "step": 2260
+    },
+    {
+      "epoch": 2.017777777777778,
+      "grad_norm": 1.7931528091430664,
+      "learning_rate": 6.766412213740458e-05,
+      "loss": 1.601,
+      "mean_token_accuracy": 0.6894692406058311,
+      "num_tokens": 2553338.0,
+      "step": 2270
+    },
+    {
+      "epoch": 2.026666666666667,
+      "grad_norm": 2.228480339050293,
+      "learning_rate": 6.705343511450382e-05,
+      "loss": 1.609,
+      "mean_token_accuracy": 0.6943154886364937,
+      "num_tokens": 2564182.0,
+      "step": 2280
+    },
+    {
+      "epoch": 2.0355555555555553,
+      "grad_norm": 1.9658042192459106,
+      "learning_rate": 6.644274809160305e-05,
+      "loss": 1.6545,
+      "mean_token_accuracy": 0.6824306204915047,
+      "num_tokens": 2575789.0,
+      "step": 2290
+    },
+    {
+      "epoch": 2.0444444444444443,
+      "grad_norm": 1.7540594339370728,
+      "learning_rate": 6.583206106870229e-05,
+      "loss": 1.6229,
+      "mean_token_accuracy": 0.6881745710968972,
+      "num_tokens": 2587147.0,
+      "step": 2300
+    },
+    {
+      "epoch": 2.0533333333333332,
+      "grad_norm": 1.799501895904541,
+      "learning_rate": 6.522137404580153e-05,
+      "loss": 1.6119,
+      "mean_token_accuracy": 0.6896049126982688,
+      "num_tokens": 2598282.0,
+      "step": 2310
+    },
+    {
+      "epoch": 2.062222222222222,
+      "grad_norm": 1.7720867395401,
+      "learning_rate": 6.461068702290076e-05,
+      "loss": 1.5519,
+      "mean_token_accuracy": 0.7038252353668213,
+      "num_tokens": 2609125.0,
+      "step": 2320
+    },
+    {
+      "epoch": 2.071111111111111,
+      "grad_norm": 1.994992971420288,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 1.5872,
+      "mean_token_accuracy": 0.690100908279419,
+      "num_tokens": 2620411.0,
+      "step": 2330
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.9283640384674072,
+      "learning_rate": 6.338931297709923e-05,
+      "loss": 1.5867,
+      "mean_token_accuracy": 0.6923216238617897,
+      "num_tokens": 2631795.0,
+      "step": 2340
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 1.9957973957061768,
+      "learning_rate": 6.277862595419848e-05,
+      "loss": 1.5996,
+      "mean_token_accuracy": 0.6924369186162949,
+      "num_tokens": 2643179.0,
+      "step": 2350
+    },
+    {
+      "epoch": 2.097777777777778,
+      "grad_norm": 2.0207560062408447,
+      "learning_rate": 6.21679389312977e-05,
+      "loss": 1.515,
+      "mean_token_accuracy": 0.7066755428910255,
+      "num_tokens": 2654206.0,
+      "step": 2360
+    },
+    {
+      "epoch": 2.1066666666666665,
+      "grad_norm": 1.8871878385543823,
+      "learning_rate": 6.155725190839695e-05,
+      "loss": 1.6139,
+      "mean_token_accuracy": 0.687422800064087,
+      "num_tokens": 2665582.0,
+      "step": 2370
+    },
+    {
+      "epoch": 2.1155555555555554,
+      "grad_norm": 1.717610478401184,
+      "learning_rate": 6.094656488549618e-05,
+      "loss": 1.6388,
+      "mean_token_accuracy": 0.6870575189590454,
+      "num_tokens": 2677533.0,
+      "step": 2380
+    },
+    {
+      "epoch": 2.1244444444444444,
+      "grad_norm": 1.8574187755584717,
+      "learning_rate": 6.0335877862595426e-05,
+      "loss": 1.557,
+      "mean_token_accuracy": 0.6999430671334267,
+      "num_tokens": 2688755.0,
+      "step": 2390
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 1.9739580154418945,
+      "learning_rate": 5.9725190839694655e-05,
+      "loss": 1.6553,
+      "mean_token_accuracy": 0.6819543272256852,
+      "num_tokens": 2700558.0,
+      "step": 2400
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "eval_loss": 1.8970768451690674,
+      "eval_mean_token_accuracy": 0.6490416256189346,
+      "eval_num_tokens": 2700558.0,
+      "eval_runtime": 47.6704,
+      "eval_samples_per_second": 20.977,
+      "eval_steps_per_second": 10.489,
+      "step": 2400
+    },
+    {
+      "epoch": 2.1422222222222222,
+      "grad_norm": 1.893918514251709,
+      "learning_rate": 5.91145038167939e-05,
+      "loss": 1.5459,
+      "mean_token_accuracy": 0.6963777393102646,
+      "num_tokens": 2711713.0,
+      "step": 2410
+    },
+    {
+      "epoch": 2.151111111111111,
+      "grad_norm": 1.9607445001602173,
+      "learning_rate": 5.850381679389313e-05,
+      "loss": 1.6373,
+      "mean_token_accuracy": 0.6815788432955742,
+      "num_tokens": 2723686.0,
+      "step": 2420
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 2.091732978820801,
+      "learning_rate": 5.789312977099237e-05,
+      "loss": 1.6422,
+      "mean_token_accuracy": 0.6811213716864586,
+      "num_tokens": 2735300.0,
+      "step": 2430
+    },
+    {
+      "epoch": 2.168888888888889,
+      "grad_norm": 2.1138076782226562,
+      "learning_rate": 5.7282442748091605e-05,
+      "loss": 1.5848,
+      "mean_token_accuracy": 0.6962573245167732,
+      "num_tokens": 2746248.0,
+      "step": 2440
+    },
+    {
+      "epoch": 2.1777777777777776,
+      "grad_norm": 2.1495392322540283,
+      "learning_rate": 5.667175572519085e-05,
+      "loss": 1.576,
+      "mean_token_accuracy": 0.6990228727459907,
+      "num_tokens": 2757259.0,
+      "step": 2450
+    },
+    {
+      "epoch": 2.1866666666666665,
+      "grad_norm": 2.1444251537323,
+      "learning_rate": 5.606106870229008e-05,
+      "loss": 1.5979,
+      "mean_token_accuracy": 0.6916472837328911,
+      "num_tokens": 2768228.0,
+      "step": 2460
+    },
+    {
+      "epoch": 2.1955555555555555,
+      "grad_norm": 1.945489525794983,
+      "learning_rate": 5.545038167938932e-05,
+      "loss": 1.5663,
+      "mean_token_accuracy": 0.7005513325333595,
+      "num_tokens": 2779254.0,
+      "step": 2470
+    },
+    {
+      "epoch": 2.2044444444444444,
+      "grad_norm": 1.8256646394729614,
+      "learning_rate": 5.483969465648855e-05,
+      "loss": 1.5751,
+      "mean_token_accuracy": 0.6961624413728714,
+      "num_tokens": 2790326.0,
+      "step": 2480
+    },
+    {
+      "epoch": 2.2133333333333334,
+      "grad_norm": 1.9541441202163696,
+      "learning_rate": 5.422900763358779e-05,
+      "loss": 1.6268,
+      "mean_token_accuracy": 0.6893054991960526,
+      "num_tokens": 2801625.0,
+      "step": 2490
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 2.0127615928649902,
+      "learning_rate": 5.361832061068702e-05,
+      "loss": 1.6096,
+      "mean_token_accuracy": 0.6923437744379044,
+      "num_tokens": 2813010.0,
+      "step": 2500
+    },
+    {
+      "epoch": 2.2311111111111113,
+      "grad_norm": 2.0325839519500732,
+      "learning_rate": 5.300763358778626e-05,
+      "loss": 1.5963,
+      "mean_token_accuracy": 0.6913090571761131,
+      "num_tokens": 2824021.0,
+      "step": 2510
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 2.1595821380615234,
+      "learning_rate": 5.23969465648855e-05,
+      "loss": 1.5617,
+      "mean_token_accuracy": 0.7037980020046234,
+      "num_tokens": 2835232.0,
+      "step": 2520
+    },
+    {
+      "epoch": 2.2488888888888887,
+      "grad_norm": 2.11661958694458,
+      "learning_rate": 5.178625954198474e-05,
+      "loss": 1.6213,
+      "mean_token_accuracy": 0.6836483731865883,
+      "num_tokens": 2846524.0,
+      "step": 2530
+    },
+    {
+      "epoch": 2.2577777777777777,
+      "grad_norm": 1.88747239112854,
+      "learning_rate": 5.117557251908397e-05,
+      "loss": 1.6408,
+      "mean_token_accuracy": 0.6860729962587356,
+      "num_tokens": 2857788.0,
+      "step": 2540
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 1.9622093439102173,
+      "learning_rate": 5.056488549618321e-05,
+      "loss": 1.5519,
+      "mean_token_accuracy": 0.7002682030200958,
+      "num_tokens": 2868618.0,
+      "step": 2550
+    },
+    {
+      "epoch": 2.2755555555555556,
+      "grad_norm": 1.9343371391296387,
+      "learning_rate": 4.995419847328244e-05,
+      "loss": 1.5795,
+      "mean_token_accuracy": 0.6934511423110962,
+      "num_tokens": 2879999.0,
+      "step": 2560
+    },
+    {
+      "epoch": 2.2844444444444445,
+      "grad_norm": 1.9991627931594849,
+      "learning_rate": 4.934351145038168e-05,
+      "loss": 1.6183,
+      "mean_token_accuracy": 0.6901679039001465,
+      "num_tokens": 2891053.0,
+      "step": 2570
+    },
+    {
+      "epoch": 2.2933333333333334,
+      "grad_norm": 1.9480003118515015,
+      "learning_rate": 4.8732824427480914e-05,
+      "loss": 1.5826,
+      "mean_token_accuracy": 0.7007558569312096,
+      "num_tokens": 2901905.0,
+      "step": 2580
+    },
+    {
+      "epoch": 2.3022222222222224,
+      "grad_norm": 2.021207332611084,
+      "learning_rate": 4.812213740458015e-05,
+      "loss": 1.6348,
+      "mean_token_accuracy": 0.6848765298724174,
+      "num_tokens": 2913571.0,
+      "step": 2590
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 1.8385164737701416,
+      "learning_rate": 4.751145038167939e-05,
+      "loss": 1.5763,
+      "mean_token_accuracy": 0.6912240386009216,
+      "num_tokens": 2925533.0,
+      "step": 2600
+    },
+    {
+      "epoch": 2.311111111111111,
+      "eval_loss": 1.8940143585205078,
+      "eval_mean_token_accuracy": 0.6499911918640137,
+      "eval_num_tokens": 2925533.0,
+      "eval_runtime": 47.456,
+      "eval_samples_per_second": 21.072,
+      "eval_steps_per_second": 10.536,
+      "step": 2600
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 1.9455375671386719,
+      "learning_rate": 4.690076335877863e-05,
+      "loss": 1.598,
+      "mean_token_accuracy": 0.6915700435638428,
+      "num_tokens": 2936620.0,
+      "step": 2610
+    },
+    {
+      "epoch": 2.328888888888889,
+      "grad_norm": 1.863487720489502,
+      "learning_rate": 4.6290076335877864e-05,
+      "loss": 1.5512,
+      "mean_token_accuracy": 0.7025073647499085,
+      "num_tokens": 2947753.0,
+      "step": 2620
+    },
+    {
+      "epoch": 2.3377777777777777,
+      "grad_norm": 1.9756685495376587,
+      "learning_rate": 4.56793893129771e-05,
+      "loss": 1.5973,
+      "mean_token_accuracy": 0.6870647758245468,
+      "num_tokens": 2959635.0,
+      "step": 2630
+    },
+    {
+      "epoch": 2.3466666666666667,
+      "grad_norm": 2.190765142440796,
+      "learning_rate": 4.5068702290076336e-05,
+      "loss": 1.5948,
+      "mean_token_accuracy": 0.6888303905725479,
+      "num_tokens": 2971675.0,
+      "step": 2640
+    },
+    {
+      "epoch": 2.3555555555555556,
+      "grad_norm": 1.827318787574768,
+      "learning_rate": 4.445801526717557e-05,
+      "loss": 1.5682,
+      "mean_token_accuracy": 0.6952902913093567,
+      "num_tokens": 2982744.0,
+      "step": 2650
+    },
+    {
+      "epoch": 2.3644444444444446,
+      "grad_norm": 2.11799693107605,
+      "learning_rate": 4.384732824427481e-05,
+      "loss": 1.6221,
+      "mean_token_accuracy": 0.6794109031558037,
+      "num_tokens": 2994347.0,
+      "step": 2660
+    },
+    {
+      "epoch": 2.3733333333333335,
+      "grad_norm": 2.1472220420837402,
+      "learning_rate": 4.3236641221374044e-05,
+      "loss": 1.6353,
+      "mean_token_accuracy": 0.6876759916543961,
+      "num_tokens": 3005174.0,
+      "step": 2670
+    },
+    {
+      "epoch": 2.3822222222222225,
+      "grad_norm": 1.9971054792404175,
+      "learning_rate": 4.2625954198473286e-05,
+      "loss": 1.5372,
+      "mean_token_accuracy": 0.7059834420680999,
+      "num_tokens": 3016492.0,
+      "step": 2680
+    },
+    {
+      "epoch": 2.391111111111111,
+      "grad_norm": 2.067861318588257,
+      "learning_rate": 4.201526717557252e-05,
+      "loss": 1.572,
+      "mean_token_accuracy": 0.6911077201366425,
+      "num_tokens": 3027826.0,
+      "step": 2690
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.0372536182403564,
+      "learning_rate": 4.140458015267176e-05,
+      "loss": 1.5615,
+      "mean_token_accuracy": 0.6972797185182571,
+      "num_tokens": 3038770.0,
+      "step": 2700
+    },
+    {
+      "epoch": 2.408888888888889,
+      "grad_norm": 2.15972638130188,
+      "learning_rate": 4.0793893129770994e-05,
+      "loss": 1.5806,
+      "mean_token_accuracy": 0.6947444006800652,
+      "num_tokens": 3050159.0,
+      "step": 2710
+    },
+    {
+      "epoch": 2.417777777777778,
+      "grad_norm": 2.059760808944702,
+      "learning_rate": 4.018320610687023e-05,
+      "loss": 1.6167,
+      "mean_token_accuracy": 0.6882677704095841,
+      "num_tokens": 3061009.0,
+      "step": 2720
+    },
+    {
+      "epoch": 2.4266666666666667,
+      "grad_norm": 1.9914629459381104,
+      "learning_rate": 3.9572519083969466e-05,
+      "loss": 1.5508,
+      "mean_token_accuracy": 0.6985371947288513,
+      "num_tokens": 3072232.0,
+      "step": 2730
+    },
+    {
+      "epoch": 2.4355555555555557,
+      "grad_norm": 2.0151119232177734,
+      "learning_rate": 3.89618320610687e-05,
+      "loss": 1.663,
+      "mean_token_accuracy": 0.6849021047353745,
+      "num_tokens": 3083939.0,
+      "step": 2740
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 2.02457332611084,
+      "learning_rate": 3.835114503816794e-05,
+      "loss": 1.6043,
+      "mean_token_accuracy": 0.6891427770256996,
+      "num_tokens": 3095354.0,
+      "step": 2750
+    },
+    {
+      "epoch": 2.453333333333333,
+      "grad_norm": 1.930341362953186,
+      "learning_rate": 3.774045801526718e-05,
+      "loss": 1.5648,
+      "mean_token_accuracy": 0.6962095096707344,
+      "num_tokens": 3106679.0,
+      "step": 2760
+    },
+    {
+      "epoch": 2.462222222222222,
+      "grad_norm": 2.1718850135803223,
+      "learning_rate": 3.7129770992366416e-05,
+      "loss": 1.5514,
+      "mean_token_accuracy": 0.6997211873531342,
+      "num_tokens": 3117440.0,
+      "step": 2770
+    },
+    {
+      "epoch": 2.471111111111111,
+      "grad_norm": 1.89506196975708,
+      "learning_rate": 3.651908396946565e-05,
+      "loss": 1.6102,
+      "mean_token_accuracy": 0.6865462198853493,
+      "num_tokens": 3128685.0,
+      "step": 2780
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 2.1102652549743652,
+      "learning_rate": 3.590839694656489e-05,
+      "loss": 1.6092,
+      "mean_token_accuracy": 0.6845578849315643,
+      "num_tokens": 3140574.0,
+      "step": 2790
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 1.9541523456573486,
+      "learning_rate": 3.5297709923664124e-05,
+      "loss": 1.6245,
+      "mean_token_accuracy": 0.6867643877863884,
+      "num_tokens": 3151937.0,
+      "step": 2800
+    },
+    {
+      "epoch": 2.488888888888889,
+      "eval_loss": 1.8869248628616333,
+      "eval_mean_token_accuracy": 0.6508636207580566,
+      "eval_num_tokens": 3151937.0,
+      "eval_runtime": 46.9872,
+      "eval_samples_per_second": 21.282,
+      "eval_steps_per_second": 10.641,
+      "step": 2800
+    },
+    {
+      "epoch": 2.497777777777778,
+      "grad_norm": 2.006448984146118,
+      "learning_rate": 3.468702290076336e-05,
+      "loss": 1.6458,
+      "mean_token_accuracy": 0.6835160732269288,
+      "num_tokens": 3163343.0,
+      "step": 2810
+    },
+    {
+      "epoch": 2.506666666666667,
+      "grad_norm": 2.0644562244415283,
+      "learning_rate": 3.4076335877862595e-05,
+      "loss": 1.5841,
+      "mean_token_accuracy": 0.699130979180336,
+      "num_tokens": 3174278.0,
+      "step": 2820
+    },
+    {
+      "epoch": 2.5155555555555553,
+      "grad_norm": 2.5352766513824463,
+      "learning_rate": 3.346564885496183e-05,
+      "loss": 1.6411,
+      "mean_token_accuracy": 0.687686163187027,
+      "num_tokens": 3185529.0,
+      "step": 2830
+    },
+    {
+      "epoch": 2.5244444444444447,
+      "grad_norm": 2.2506706714630127,
+      "learning_rate": 3.2854961832061074e-05,
+      "loss": 1.5334,
+      "mean_token_accuracy": 0.7042266175150871,
+      "num_tokens": 3196422.0,
+      "step": 2840
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 2.038456439971924,
+      "learning_rate": 3.224427480916031e-05,
+      "loss": 1.5226,
+      "mean_token_accuracy": 0.7002356797456741,
+      "num_tokens": 3207640.0,
+      "step": 2850
+    },
+    {
+      "epoch": 2.542222222222222,
+      "grad_norm": 2.0818448066711426,
+      "learning_rate": 3.1633587786259545e-05,
+      "loss": 1.5136,
+      "mean_token_accuracy": 0.7040936380624772,
+      "num_tokens": 3218742.0,
+      "step": 2860
+    },
+    {
+      "epoch": 2.551111111111111,
+      "grad_norm": 1.9810820817947388,
+      "learning_rate": 3.102290076335878e-05,
+      "loss": 1.6515,
+      "mean_token_accuracy": 0.6826088905334473,
+      "num_tokens": 3230062.0,
+      "step": 2870
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 2.1830689907073975,
+      "learning_rate": 3.0412213740458017e-05,
+      "loss": 1.5792,
+      "mean_token_accuracy": 0.699496129155159,
+      "num_tokens": 3240533.0,
+      "step": 2880
+    },
+    {
+      "epoch": 2.568888888888889,
+      "grad_norm": 2.101184368133545,
+      "learning_rate": 2.9801526717557253e-05,
+      "loss": 1.6538,
+      "mean_token_accuracy": 0.6724523141980171,
+      "num_tokens": 3252476.0,
+      "step": 2890
+    },
+    {
+      "epoch": 2.5777777777777775,
+      "grad_norm": 2.021524429321289,
+      "learning_rate": 2.9190839694656492e-05,
+      "loss": 1.6146,
+      "mean_token_accuracy": 0.6886414483189582,
+      "num_tokens": 3263799.0,
+      "step": 2900
+    },
+    {
+      "epoch": 2.586666666666667,
+      "grad_norm": 1.9668735265731812,
+      "learning_rate": 2.8580152671755728e-05,
+      "loss": 1.6477,
+      "mean_token_accuracy": 0.678925508260727,
+      "num_tokens": 3275511.0,
+      "step": 2910
+    },
+    {
+      "epoch": 2.5955555555555554,
+      "grad_norm": 2.088491201400757,
+      "learning_rate": 2.7969465648854964e-05,
+      "loss": 1.6265,
+      "mean_token_accuracy": 0.6857595339417457,
+      "num_tokens": 3286752.0,
+      "step": 2920
+    },
+    {
+      "epoch": 2.6044444444444443,
+      "grad_norm": 2.0536880493164062,
+      "learning_rate": 2.73587786259542e-05,
+      "loss": 1.66,
+      "mean_token_accuracy": 0.681273227930069,
+      "num_tokens": 3297945.0,
+      "step": 2930
+    },
+    {
+      "epoch": 2.6133333333333333,
+      "grad_norm": 2.0063817501068115,
+      "learning_rate": 2.674809160305344e-05,
+      "loss": 1.5102,
+      "mean_token_accuracy": 0.7025244757533073,
+      "num_tokens": 3309112.0,
+      "step": 2940
+    },
+    {
+      "epoch": 2.6222222222222222,
+      "grad_norm": 1.9980206489562988,
+      "learning_rate": 2.6137404580152675e-05,
+      "loss": 1.5142,
+      "mean_token_accuracy": 0.7049572348594666,
+      "num_tokens": 3320544.0,
+      "step": 2950
+    },
+    {
+      "epoch": 2.631111111111111,
+      "grad_norm": 2.1506435871124268,
+      "learning_rate": 2.552671755725191e-05,
+      "loss": 1.5826,
+      "mean_token_accuracy": 0.694467018544674,
+      "num_tokens": 3331309.0,
+      "step": 2960
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.9890793561935425,
+      "learning_rate": 2.4916030534351147e-05,
+      "loss": 1.5631,
+      "mean_token_accuracy": 0.6945617944002151,
+      "num_tokens": 3343068.0,
+      "step": 2970
+    },
+    {
+      "epoch": 2.648888888888889,
+      "grad_norm": 2.1102676391601562,
+      "learning_rate": 2.4305343511450383e-05,
+      "loss": 1.6145,
+      "mean_token_accuracy": 0.6866093754768372,
+      "num_tokens": 3354691.0,
+      "step": 2980
+    },
+    {
+      "epoch": 2.6577777777777776,
+      "grad_norm": 2.2881674766540527,
+      "learning_rate": 2.369465648854962e-05,
+      "loss": 1.5796,
+      "mean_token_accuracy": 0.6961612686514854,
+      "num_tokens": 3365512.0,
+      "step": 2990
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.973838210105896,
+      "learning_rate": 2.3083969465648854e-05,
+      "loss": 1.5456,
+      "mean_token_accuracy": 0.703473174571991,
+      "num_tokens": 3376406.0,
+      "step": 3000
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "eval_loss": 1.881131649017334,
+      "eval_mean_token_accuracy": 0.6518214672803879,
+      "eval_num_tokens": 3376406.0,
+      "eval_runtime": 47.794,
+      "eval_samples_per_second": 20.923,
+      "eval_steps_per_second": 10.462,
+      "step": 3000
+    },
+    {
+      "epoch": 2.6755555555555555,
+      "grad_norm": 1.9779133796691895,
+      "learning_rate": 2.2473282442748094e-05,
+      "loss": 1.6538,
+      "mean_token_accuracy": 0.6778925880789757,
+      "num_tokens": 3388024.0,
+      "step": 3010
+    },
+    {
+      "epoch": 2.6844444444444444,
+      "grad_norm": 1.848136305809021,
+      "learning_rate": 2.186259541984733e-05,
+      "loss": 1.5608,
+      "mean_token_accuracy": 0.6985713213682174,
+      "num_tokens": 3399547.0,
+      "step": 3020
+    },
+    {
+      "epoch": 2.6933333333333334,
+      "grad_norm": 2.101651191711426,
+      "learning_rate": 2.1251908396946565e-05,
+      "loss": 1.5501,
+      "mean_token_accuracy": 0.6979974433779716,
+      "num_tokens": 3410179.0,
+      "step": 3030
+    },
+    {
+      "epoch": 2.7022222222222223,
+      "grad_norm": 1.8398933410644531,
+      "learning_rate": 2.06412213740458e-05,
+      "loss": 1.5843,
+      "mean_token_accuracy": 0.6883544474840164,
+      "num_tokens": 3421454.0,
+      "step": 3040
+    },
+    {
+      "epoch": 2.7111111111111112,
+      "grad_norm": 2.011132001876831,
+      "learning_rate": 2.003053435114504e-05,
+      "loss": 1.6012,
+      "mean_token_accuracy": 0.6917843446135521,
+      "num_tokens": 3432951.0,
+      "step": 3050
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 2.005140542984009,
+      "learning_rate": 1.9419847328244276e-05,
+      "loss": 1.5421,
+      "mean_token_accuracy": 0.6976893007755279,
+      "num_tokens": 3444007.0,
+      "step": 3060
+    },
+    {
+      "epoch": 2.728888888888889,
+      "grad_norm": 2.146664619445801,
+      "learning_rate": 1.8809160305343512e-05,
+      "loss": 1.5799,
+      "mean_token_accuracy": 0.6956974431872368,
+      "num_tokens": 3455510.0,
+      "step": 3070
+    },
+    {
+      "epoch": 2.7377777777777776,
+      "grad_norm": 2.0788283348083496,
+      "learning_rate": 1.8198473282442748e-05,
+      "loss": 1.6043,
+      "mean_token_accuracy": 0.6913327068090439,
+      "num_tokens": 3466684.0,
+      "step": 3080
+    },
+    {
+      "epoch": 2.7466666666666666,
+      "grad_norm": 1.8829123973846436,
+      "learning_rate": 1.7587786259541984e-05,
+      "loss": 1.5649,
+      "mean_token_accuracy": 0.6947105377912521,
+      "num_tokens": 3477804.0,
+      "step": 3090
+    },
+    {
+      "epoch": 2.7555555555555555,
+      "grad_norm": 1.9475817680358887,
+      "learning_rate": 1.6977099236641223e-05,
+      "loss": 1.5568,
+      "mean_token_accuracy": 0.7034636497497558,
+      "num_tokens": 3488846.0,
+      "step": 3100
+    },
+    {
+      "epoch": 2.7644444444444445,
+      "grad_norm": 2.098478317260742,
+      "learning_rate": 1.636641221374046e-05,
+      "loss": 1.5575,
+      "mean_token_accuracy": 0.7053634539246559,
+      "num_tokens": 3499405.0,
+      "step": 3110
+    },
+    {
+      "epoch": 2.7733333333333334,
+      "grad_norm": 2.041572093963623,
+      "learning_rate": 1.5755725190839695e-05,
+      "loss": 1.619,
+      "mean_token_accuracy": 0.6887963160872459,
+      "num_tokens": 3511004.0,
+      "step": 3120
+    },
+    {
+      "epoch": 2.7822222222222224,
+      "grad_norm": 2.0892608165740967,
+      "learning_rate": 1.5145038167938933e-05,
+      "loss": 1.55,
+      "mean_token_accuracy": 0.6963776037096977,
+      "num_tokens": 3521755.0,
+      "step": 3130
+    },
+    {
+      "epoch": 2.7911111111111113,
+      "grad_norm": 1.9754984378814697,
+      "learning_rate": 1.4534351145038168e-05,
+      "loss": 1.5459,
+      "mean_token_accuracy": 0.7077917411923409,
+      "num_tokens": 3532621.0,
+      "step": 3140
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.9490447044372559,
+      "learning_rate": 1.3923664122137406e-05,
+      "loss": 1.6047,
+      "mean_token_accuracy": 0.6932125955820083,
+      "num_tokens": 3543418.0,
+      "step": 3150
+    },
+    {
+      "epoch": 2.8088888888888888,
+      "grad_norm": 2.12741756439209,
+      "learning_rate": 1.3312977099236642e-05,
+      "loss": 1.6336,
+      "mean_token_accuracy": 0.6868860185146332,
+      "num_tokens": 3555172.0,
+      "step": 3160
+    },
+    {
+      "epoch": 2.8177777777777777,
+      "grad_norm": 1.9473916292190552,
+      "learning_rate": 1.270229007633588e-05,
+      "loss": 1.5765,
+      "mean_token_accuracy": 0.696508777141571,
+      "num_tokens": 3565975.0,
+      "step": 3170
+    },
+    {
+      "epoch": 2.8266666666666667,
+      "grad_norm": 2.065030336380005,
+      "learning_rate": 1.2091603053435115e-05,
+      "loss": 1.6127,
+      "mean_token_accuracy": 0.6915735498070716,
+      "num_tokens": 3578154.0,
+      "step": 3180
+    },
+    {
+      "epoch": 2.8355555555555556,
+      "grad_norm": 2.1202714443206787,
+      "learning_rate": 1.1480916030534351e-05,
+      "loss": 1.5786,
+      "mean_token_accuracy": 0.702069939672947,
+      "num_tokens": 3589470.0,
+      "step": 3190
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 2.081028699874878,
+      "learning_rate": 1.0870229007633589e-05,
+      "loss": 1.6146,
+      "mean_token_accuracy": 0.6874286815524101,
+      "num_tokens": 3600489.0,
+      "step": 3200
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "eval_loss": 1.8764336109161377,
+      "eval_mean_token_accuracy": 0.6531118412017822,
+      "eval_num_tokens": 3600489.0,
+      "eval_runtime": 47.0874,
+      "eval_samples_per_second": 21.237,
+      "eval_steps_per_second": 10.619,
+      "step": 3200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1419054395445248e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7dcfbb520eaa72697f1d45b91e159189ecefb58152a35a5fa5a95eb7d53aa9
+size 5624

checkpoint-3375/README.md

@@ -0,0 +1,202 @@
+---
+base_model: naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-3375/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-3375/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:312d13462cd7449243d76d3d53001e607283f1375d116df2efc112756649f1f3
+size 39366152

checkpoint-3375/added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "<EMAIL>": 110521,
+  "<KEY>": 110522,
+  "<NAME>": 110520,
+  "<PASSWORD>": 110523,
+  "<code_to_intermediate>": 110502,
+  "<empty_output>": 110501,
+  "<file_sep>": 110492,
+  "<intermediate_to_code>": 110503,
+  "<issue_closed>": 110495,
+  "<issue_comment>": 110494,
+  "<issue_start>": 110493,
+  "<jupyter_code>": 110498,
+  "<jupyter_output>": 110499,
+  "<jupyter_script>": 110500,
+  "<jupyter_start>": 110496,
+  "<jupyter_text>": 110497,
+  "<pr>": 110504,
+  "<pr_base>": 110507,
+  "<pr_base_code>": 110509,
+  "<pr_comment>": 110512,
+  "<pr_diff>": 110510,
+  "<pr_diff_hunk>": 110511,
+  "<pr_diff_hunk_comment_line>": 110519,
+  "<pr_event_id>": 110513,
+  "<pr_file>": 110508,
+  "<pr_in_reply_to_comment_id>": 110518,
+  "<pr_in_reply_to_review_id>": 110517,
+  "<pr_is_merged>": 110506,
+  "<pr_review>": 110514,
+  "<pr_review_comment>": 110516,
+  "<pr_review_state>": 110515,
+  "<pr_status>": 110505,
+  "<repo_name>": 110491
+}

checkpoint-3375/chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-3375/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07d60418b383317f571e91debf117825c79793f4ee64ec7b2ea978b61b64b3b4
+size 14244

checkpoint-3375/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947399a05506c2e46af067da8feaec1b314f23e1a1053d9ababad786abd55f2b
+size 988

checkpoint-3375/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f746b05629bb941ef28c25523458a3f637fb70f0c6a02c362d1aa3c1c3761bd
+size 1064

checkpoint-3375/special_tokens_map.json

@@ -0,0 +1,86 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endofturn|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-3375/tokenizer_config.json

@@ -0,0 +1,501 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|_unuse_missing_100256|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<|_unuse_missing_100261|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<|_unuse_missing_100262|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<|_unuse_missing_100263|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|_unuse_missing_100264|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|_unuse_missing_100265|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|_unuse_missing_100266|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|_unuse_missing_100267|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|_unuse_missing_100268|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|_unuse_missing_100269|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<|_unuse_missing_100270|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<|_unuse_missing_100271|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<|stop|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<|endofturn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110491": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110492": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110493": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110494": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110495": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110496": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110497": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110498": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110499": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110500": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110501": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110502": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110503": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110504": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110505": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110506": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110507": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110508": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110509": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110510": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110511": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110512": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110513": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110514": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110515": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110516": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110517": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110518": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110519": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110520": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110521": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110522": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110523": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endofturn|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-3375/trainer_state.json

@@ -0,0 +1,3227 @@
+{
+  "best_global_step": 3200,
+  "best_metric": 1.8764336109161377,
+  "best_model_checkpoint": "/content/drive/MyDrive/hyperclova-deobfuscation-lora/checkpoint-3200",
+  "epoch": 3.0,
+  "eval_steps": 200,
+  "global_step": 3375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008888888888888889,
+      "grad_norm": 3.629798412322998,
+      "learning_rate": 1.8e-05,
+      "loss": 4.1483,
+      "mean_token_accuracy": 0.34797456339001653,
+      "num_tokens": 11242.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 2.6125221252441406,
+      "learning_rate": 3.8e-05,
+      "loss": 3.7515,
+      "mean_token_accuracy": 0.4058148756623268,
+      "num_tokens": 22106.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 2.9313137531280518,
+      "learning_rate": 5.8e-05,
+      "loss": 3.3279,
+      "mean_token_accuracy": 0.4703808955848217,
+      "num_tokens": 33774.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 2.0496416091918945,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 2.9114,
+      "mean_token_accuracy": 0.5239812344312668,
+      "num_tokens": 44943.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 2.282668352127075,
+      "learning_rate": 9.8e-05,
+      "loss": 2.8468,
+      "mean_token_accuracy": 0.534189497679472,
+      "num_tokens": 56341.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 2.168651819229126,
+      "learning_rate": 0.000118,
+      "loss": 2.7785,
+      "mean_token_accuracy": 0.5407359585165977,
+      "num_tokens": 67397.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.06222222222222222,
+      "grad_norm": 2.289881467819214,
+      "learning_rate": 0.000138,
+      "loss": 2.736,
+      "mean_token_accuracy": 0.5326176360249519,
+      "num_tokens": 78482.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 2.1038105487823486,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 2.5855,
+      "mean_token_accuracy": 0.5618595249950886,
+      "num_tokens": 89803.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.24312686920166,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 2.5365,
+      "mean_token_accuracy": 0.5661972932517528,
+      "num_tokens": 101015.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.9482938051223755,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 2.5634,
+      "mean_token_accuracy": 0.5538406319916248,
+      "num_tokens": 112364.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.09777777777777778,
+      "grad_norm": 1.86210298538208,
+      "learning_rate": 0.00019945038167938932,
+      "loss": 2.4629,
+      "mean_token_accuracy": 0.5780388668179512,
+      "num_tokens": 122882.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 1.8806918859481812,
+      "learning_rate": 0.00019883969465648855,
+      "loss": 2.5022,
+      "mean_token_accuracy": 0.563551553338766,
+      "num_tokens": 134028.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.11555555555555555,
+      "grad_norm": 2.3264434337615967,
+      "learning_rate": 0.00019829007633587786,
+      "loss": 2.4065,
+      "mean_token_accuracy": 0.5807355619966984,
+      "num_tokens": 145192.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 1.8537976741790771,
+      "learning_rate": 0.00019767938931297712,
+      "loss": 2.4838,
+      "mean_token_accuracy": 0.566282794624567,
+      "num_tokens": 156703.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 2.0960652828216553,
+      "learning_rate": 0.00019706870229007636,
+      "loss": 2.4119,
+      "mean_token_accuracy": 0.5830203481018543,
+      "num_tokens": 168041.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 2.2244813442230225,
+      "learning_rate": 0.00019645801526717557,
+      "loss": 2.3726,
+      "mean_token_accuracy": 0.5844443172216416,
+      "num_tokens": 178986.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.1511111111111111,
+      "grad_norm": 1.8238722085952759,
+      "learning_rate": 0.0001958473282442748,
+      "loss": 2.4419,
+      "mean_token_accuracy": 0.5708602093160152,
+      "num_tokens": 190391.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.7154136896133423,
+      "learning_rate": 0.00019523664122137407,
+      "loss": 2.4293,
+      "mean_token_accuracy": 0.5748118035495281,
+      "num_tokens": 201989.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.1688888888888889,
+      "grad_norm": 1.7582788467407227,
+      "learning_rate": 0.0001946259541984733,
+      "loss": 2.3577,
+      "mean_token_accuracy": 0.5877166777849198,
+      "num_tokens": 212914.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.8613263368606567,
+      "learning_rate": 0.0001940152671755725,
+      "loss": 2.3486,
+      "mean_token_accuracy": 0.5889834299683571,
+      "num_tokens": 223936.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_loss": 2.3320820331573486,
+      "eval_mean_token_accuracy": 0.5868698905706405,
+      "eval_num_tokens": 223936.0,
+      "eval_runtime": 49.2429,
+      "eval_samples_per_second": 20.307,
+      "eval_steps_per_second": 10.154,
+      "step": 200
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 1.8486477136611938,
+      "learning_rate": 0.00019340458015267175,
+      "loss": 2.3666,
+      "mean_token_accuracy": 0.5847611322999,
+      "num_tokens": 235036.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 2.018049478530884,
+      "learning_rate": 0.000192793893129771,
+      "loss": 2.2689,
+      "mean_token_accuracy": 0.59971177354455,
+      "num_tokens": 246101.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.20444444444444446,
+      "grad_norm": 1.7244890928268433,
+      "learning_rate": 0.00019218320610687024,
+      "loss": 2.3262,
+      "mean_token_accuracy": 0.5855986528098583,
+      "num_tokens": 257953.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.8928934335708618,
+      "learning_rate": 0.00019157251908396948,
+      "loss": 2.3318,
+      "mean_token_accuracy": 0.5885626815259457,
+      "num_tokens": 269187.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.7358920574188232,
+      "learning_rate": 0.0001909618320610687,
+      "loss": 2.2145,
+      "mean_token_accuracy": 0.6092555984854698,
+      "num_tokens": 279762.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 1.6779032945632935,
+      "learning_rate": 0.00019035114503816795,
+      "loss": 2.3152,
+      "mean_token_accuracy": 0.584602715075016,
+      "num_tokens": 291454.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.6310207843780518,
+      "learning_rate": 0.0001897404580152672,
+      "loss": 2.2669,
+      "mean_token_accuracy": 0.5965895019471645,
+      "num_tokens": 302969.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 1.6765615940093994,
+      "learning_rate": 0.00018912977099236642,
+      "loss": 2.269,
+      "mean_token_accuracy": 0.5934441670775413,
+      "num_tokens": 314204.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.2577777777777778,
+      "grad_norm": 1.793959617614746,
+      "learning_rate": 0.00018851908396946566,
+      "loss": 2.2554,
+      "mean_token_accuracy": 0.600947193801403,
+      "num_tokens": 325649.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.7492129802703857,
+      "learning_rate": 0.0001879083969465649,
+      "loss": 2.2157,
+      "mean_token_accuracy": 0.6022505328059197,
+      "num_tokens": 337167.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.27555555555555555,
+      "grad_norm": 1.803576946258545,
+      "learning_rate": 0.00018729770992366413,
+      "loss": 2.2854,
+      "mean_token_accuracy": 0.5923042424023152,
+      "num_tokens": 348621.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 1.9662351608276367,
+      "learning_rate": 0.00018668702290076337,
+      "loss": 2.2639,
+      "mean_token_accuracy": 0.588193366676569,
+      "num_tokens": 360272.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 1.6725891828536987,
+      "learning_rate": 0.0001860763358778626,
+      "loss": 2.2249,
+      "mean_token_accuracy": 0.6054098337888718,
+      "num_tokens": 371346.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 1.68416166305542,
+      "learning_rate": 0.00018546564885496184,
+      "loss": 2.1678,
+      "mean_token_accuracy": 0.6146526508033275,
+      "num_tokens": 382779.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 1.7218507528305054,
+      "learning_rate": 0.00018485496183206108,
+      "loss": 2.2011,
+      "mean_token_accuracy": 0.6104303196072578,
+      "num_tokens": 393823.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.6817256212234497,
+      "learning_rate": 0.0001842442748091603,
+      "loss": 2.2264,
+      "mean_token_accuracy": 0.5987282857298851,
+      "num_tokens": 405438.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.3288888888888889,
+      "grad_norm": 1.7454718351364136,
+      "learning_rate": 0.00018363358778625955,
+      "loss": 2.2712,
+      "mean_token_accuracy": 0.5939777493476868,
+      "num_tokens": 417299.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 2.011315107345581,
+      "learning_rate": 0.00018302290076335878,
+      "loss": 2.2247,
+      "mean_token_accuracy": 0.6061037018895149,
+      "num_tokens": 428660.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 1.6242053508758545,
+      "learning_rate": 0.00018241221374045802,
+      "loss": 2.232,
+      "mean_token_accuracy": 0.6062197655439376,
+      "num_tokens": 439768.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 1.9328559637069702,
+      "learning_rate": 0.00018180152671755725,
+      "loss": 2.1291,
+      "mean_token_accuracy": 0.6168317429721355,
+      "num_tokens": 450808.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_loss": 2.1662538051605225,
+      "eval_mean_token_accuracy": 0.6099509916305542,
+      "eval_num_tokens": 450808.0,
+      "eval_runtime": 49.4213,
+      "eval_samples_per_second": 20.234,
+      "eval_steps_per_second": 10.117,
+      "step": 400
+    },
+    {
+      "epoch": 0.36444444444444446,
+      "grad_norm": 1.8797143697738647,
+      "learning_rate": 0.0001811908396946565,
+      "loss": 2.2086,
+      "mean_token_accuracy": 0.6012695133686066,
+      "num_tokens": 461592.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.7558225393295288,
+      "learning_rate": 0.00018058015267175575,
+      "loss": 2.1771,
+      "mean_token_accuracy": 0.6060668036341668,
+      "num_tokens": 473434.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.38222222222222224,
+      "grad_norm": 1.845051884651184,
+      "learning_rate": 0.00017996946564885496,
+      "loss": 2.2576,
+      "mean_token_accuracy": 0.5929104581475257,
+      "num_tokens": 485130.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 1.6992298364639282,
+      "learning_rate": 0.0001793587786259542,
+      "loss": 2.1815,
+      "mean_token_accuracy": 0.6100690707564353,
+      "num_tokens": 496482.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.7239253520965576,
+      "learning_rate": 0.00017874809160305343,
+      "loss": 2.2082,
+      "mean_token_accuracy": 0.6001435503363609,
+      "num_tokens": 508218.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 1.7856336832046509,
+      "learning_rate": 0.0001781374045801527,
+      "loss": 2.1593,
+      "mean_token_accuracy": 0.6118309393525123,
+      "num_tokens": 519379.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.4177777777777778,
+      "grad_norm": 1.611831545829773,
+      "learning_rate": 0.00017752671755725193,
+      "loss": 2.1797,
+      "mean_token_accuracy": 0.6033190444111824,
+      "num_tokens": 530561.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.7420586347579956,
+      "learning_rate": 0.00017691603053435114,
+      "loss": 2.2027,
+      "mean_token_accuracy": 0.6067790001630783,
+      "num_tokens": 542631.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.43555555555555553,
+      "grad_norm": 1.948723316192627,
+      "learning_rate": 0.00017630534351145038,
+      "loss": 2.1753,
+      "mean_token_accuracy": 0.6109650492668152,
+      "num_tokens": 553477.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.7983819246292114,
+      "learning_rate": 0.00017569465648854964,
+      "loss": 2.158,
+      "mean_token_accuracy": 0.5996212616562844,
+      "num_tokens": 565400.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 1.842372179031372,
+      "learning_rate": 0.00017508396946564888,
+      "loss": 2.0825,
+      "mean_token_accuracy": 0.6168116196990013,
+      "num_tokens": 576953.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 1.91799795627594,
+      "learning_rate": 0.00017447328244274809,
+      "loss": 2.1022,
+      "mean_token_accuracy": 0.6168905258178711,
+      "num_tokens": 588003.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.4711111111111111,
+      "grad_norm": 1.7727124691009521,
+      "learning_rate": 0.00017386259541984732,
+      "loss": 2.1695,
+      "mean_token_accuracy": 0.5997609972953797,
+      "num_tokens": 600043.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.8602296113967896,
+      "learning_rate": 0.00017325190839694658,
+      "loss": 2.0849,
+      "mean_token_accuracy": 0.6266478568315506,
+      "num_tokens": 610974.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 1.545620083808899,
+      "learning_rate": 0.00017264122137404582,
+      "loss": 2.1824,
+      "mean_token_accuracy": 0.6072694823145867,
+      "num_tokens": 622632.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 1.7485988140106201,
+      "learning_rate": 0.00017203053435114506,
+      "loss": 2.1374,
+      "mean_token_accuracy": 0.6164417043328285,
+      "num_tokens": 634093.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 1.8591196537017822,
+      "learning_rate": 0.00017141984732824426,
+      "loss": 2.0928,
+      "mean_token_accuracy": 0.6241554819047451,
+      "num_tokens": 645226.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 1.8163517713546753,
+      "learning_rate": 0.00017080916030534353,
+      "loss": 2.0476,
+      "mean_token_accuracy": 0.6285594403743744,
+      "num_tokens": 656188.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.5244444444444445,
+      "grad_norm": 1.7729696035385132,
+      "learning_rate": 0.00017019847328244276,
+      "loss": 2.1036,
+      "mean_token_accuracy": 0.6208315283060074,
+      "num_tokens": 667642.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.7804032564163208,
+      "learning_rate": 0.000169587786259542,
+      "loss": 2.1174,
+      "mean_token_accuracy": 0.6148250237107277,
+      "num_tokens": 678769.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 2.0850696563720703,
+      "eval_mean_token_accuracy": 0.6197466601729393,
+      "eval_num_tokens": 678769.0,
+      "eval_runtime": 49.7611,
+      "eval_samples_per_second": 20.096,
+      "eval_steps_per_second": 10.048,
+      "step": 600
+    },
+    {
+      "epoch": 0.5422222222222223,
+      "grad_norm": 1.8643274307250977,
+      "learning_rate": 0.00016897709923664124,
+      "loss": 2.0485,
+      "mean_token_accuracy": 0.6331146821379662,
+      "num_tokens": 690014.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 1.8060939311981201,
+      "learning_rate": 0.00016836641221374047,
+      "loss": 2.1117,
+      "mean_token_accuracy": 0.612041813135147,
+      "num_tokens": 701734.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.7059085369110107,
+      "learning_rate": 0.0001677557251908397,
+      "loss": 2.0747,
+      "mean_token_accuracy": 0.6174572542309761,
+      "num_tokens": 713570.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 1.6600592136383057,
+      "learning_rate": 0.00016714503816793894,
+      "loss": 2.0685,
+      "mean_token_accuracy": 0.6293445661664009,
+      "num_tokens": 724815.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 1.6598913669586182,
+      "learning_rate": 0.00016653435114503818,
+      "loss": 2.0255,
+      "mean_token_accuracy": 0.6309839904308319,
+      "num_tokens": 735777.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 1.8306963443756104,
+      "learning_rate": 0.00016592366412213741,
+      "loss": 2.1249,
+      "mean_token_accuracy": 0.6147443532943726,
+      "num_tokens": 746903.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.5955555555555555,
+      "grad_norm": 1.626795768737793,
+      "learning_rate": 0.00016531297709923665,
+      "loss": 2.0694,
+      "mean_token_accuracy": 0.6254988595843315,
+      "num_tokens": 757881.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 1.710806131362915,
+      "learning_rate": 0.00016470229007633589,
+      "loss": 2.0397,
+      "mean_token_accuracy": 0.6233279958367348,
+      "num_tokens": 768982.0,
+      "step": 680
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 1.7051280736923218,
+      "learning_rate": 0.00016409160305343512,
+      "loss": 2.116,
+      "mean_token_accuracy": 0.6183760315179825,
+      "num_tokens": 780072.0,
+      "step": 690
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 1.607917070388794,
+      "learning_rate": 0.00016348091603053436,
+      "loss": 2.0478,
+      "mean_token_accuracy": 0.6331974640488625,
+      "num_tokens": 791061.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.6311111111111111,
+      "grad_norm": 1.7803592681884766,
+      "learning_rate": 0.0001628702290076336,
+      "loss": 2.0595,
+      "mean_token_accuracy": 0.6249041527509689,
+      "num_tokens": 801867.0,
+      "step": 710
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.6132373809814453,
+      "learning_rate": 0.00016225954198473283,
+      "loss": 2.0789,
+      "mean_token_accuracy": 0.6235784366726875,
+      "num_tokens": 813112.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.6488888888888888,
+      "grad_norm": 1.790528655052185,
+      "learning_rate": 0.00016164885496183207,
+      "loss": 2.0632,
+      "mean_token_accuracy": 0.6268924325704575,
+      "num_tokens": 824133.0,
+      "step": 730
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 2.0007362365722656,
+      "learning_rate": 0.0001610381679389313,
+      "loss": 2.0701,
+      "mean_token_accuracy": 0.6189413338899612,
+      "num_tokens": 835469.0,
+      "step": 740
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.227158546447754,
+      "learning_rate": 0.00016042748091603054,
+      "loss": 2.0339,
+      "mean_token_accuracy": 0.621903920173645,
+      "num_tokens": 846572.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 1.80472731590271,
+      "learning_rate": 0.00015981679389312977,
+      "loss": 2.1285,
+      "mean_token_accuracy": 0.604806374013424,
+      "num_tokens": 857795.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.6844444444444444,
+      "grad_norm": 1.7893937826156616,
+      "learning_rate": 0.000159206106870229,
+      "loss": 2.0347,
+      "mean_token_accuracy": 0.6292635962367058,
+      "num_tokens": 868429.0,
+      "step": 770
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 1.6761573553085327,
+      "learning_rate": 0.00015859541984732824,
+      "loss": 2.0591,
+      "mean_token_accuracy": 0.6254431992769242,
+      "num_tokens": 879659.0,
+      "step": 780
+    },
+    {
+      "epoch": 0.7022222222222222,
+      "grad_norm": 1.803045630455017,
+      "learning_rate": 0.0001579847328244275,
+      "loss": 2.0293,
+      "mean_token_accuracy": 0.6273573949933052,
+      "num_tokens": 890911.0,
+      "step": 790
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 1.7385220527648926,
+      "learning_rate": 0.00015737404580152672,
+      "loss": 2.0197,
+      "mean_token_accuracy": 0.63025072067976,
+      "num_tokens": 902240.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 2.0297935009002686,
+      "eval_mean_token_accuracy": 0.628437293112278,
+      "eval_num_tokens": 902240.0,
+      "eval_runtime": 49.3011,
+      "eval_samples_per_second": 20.284,
+      "eval_steps_per_second": 10.142,
+      "step": 800
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.8906656503677368,
+      "learning_rate": 0.00015676335877862595,
+      "loss": 2.0806,
+      "mean_token_accuracy": 0.619849094748497,
+      "num_tokens": 914009.0,
+      "step": 810
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 1.714268684387207,
+      "learning_rate": 0.0001561526717557252,
+      "loss": 2.0343,
+      "mean_token_accuracy": 0.632188580930233,
+      "num_tokens": 925091.0,
+      "step": 820
+    },
+    {
+      "epoch": 0.7377777777777778,
+      "grad_norm": 1.833918809890747,
+      "learning_rate": 0.00015554198473282445,
+      "loss": 2.0747,
+      "mean_token_accuracy": 0.6280180156230927,
+      "num_tokens": 936675.0,
+      "step": 830
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.9817575216293335,
+      "learning_rate": 0.00015493129770992366,
+      "loss": 2.0859,
+      "mean_token_accuracy": 0.6128378361463547,
+      "num_tokens": 948151.0,
+      "step": 840
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 1.5982656478881836,
+      "learning_rate": 0.0001543206106870229,
+      "loss": 2.0455,
+      "mean_token_accuracy": 0.6276382938027382,
+      "num_tokens": 959266.0,
+      "step": 850
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 1.7298970222473145,
+      "learning_rate": 0.00015370992366412213,
+      "loss": 1.9604,
+      "mean_token_accuracy": 0.6377590849995614,
+      "num_tokens": 970339.0,
+      "step": 860
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 1.8064581155776978,
+      "learning_rate": 0.0001530992366412214,
+      "loss": 2.0698,
+      "mean_token_accuracy": 0.6194617792963981,
+      "num_tokens": 981805.0,
+      "step": 870
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 1.5860410928726196,
+      "learning_rate": 0.00015248854961832063,
+      "loss": 2.0182,
+      "mean_token_accuracy": 0.6292306095361709,
+      "num_tokens": 993552.0,
+      "step": 880
+    },
+    {
+      "epoch": 0.7911111111111111,
+      "grad_norm": 1.8761259317398071,
+      "learning_rate": 0.00015187786259541984,
+      "loss": 2.0335,
+      "mean_token_accuracy": 0.6285651385784149,
+      "num_tokens": 1004400.0,
+      "step": 890
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.6973590850830078,
+      "learning_rate": 0.00015126717557251908,
+      "loss": 2.0927,
+      "mean_token_accuracy": 0.6183614790439605,
+      "num_tokens": 1015564.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.8088888888888889,
+      "grad_norm": 1.6477675437927246,
+      "learning_rate": 0.00015065648854961834,
+      "loss": 1.9187,
+      "mean_token_accuracy": 0.6427812784910202,
+      "num_tokens": 1026849.0,
+      "step": 910
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 1.6942589282989502,
+      "learning_rate": 0.00015004580152671757,
+      "loss": 2.0139,
+      "mean_token_accuracy": 0.6322552219033242,
+      "num_tokens": 1037721.0,
+      "step": 920
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 1.6394822597503662,
+      "learning_rate": 0.0001494351145038168,
+      "loss": 2.0392,
+      "mean_token_accuracy": 0.6273665294051171,
+      "num_tokens": 1048986.0,
+      "step": 930
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 1.697804570198059,
+      "learning_rate": 0.00014882442748091602,
+      "loss": 2.0412,
+      "mean_token_accuracy": 0.625536386668682,
+      "num_tokens": 1060627.0,
+      "step": 940
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 1.8058092594146729,
+      "learning_rate": 0.00014821374045801528,
+      "loss": 1.9737,
+      "mean_token_accuracy": 0.6332821652293206,
+      "num_tokens": 1071482.0,
+      "step": 950
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.773294448852539,
+      "learning_rate": 0.00014760305343511452,
+      "loss": 2.054,
+      "mean_token_accuracy": 0.6256278708577157,
+      "num_tokens": 1082672.0,
+      "step": 960
+    },
+    {
+      "epoch": 0.8622222222222222,
+      "grad_norm": 1.6936707496643066,
+      "learning_rate": 0.00014699236641221375,
+      "loss": 1.9957,
+      "mean_token_accuracy": 0.6333451583981514,
+      "num_tokens": 1093493.0,
+      "step": 970
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 1.7029008865356445,
+      "learning_rate": 0.000146381679389313,
+      "loss": 2.0526,
+      "mean_token_accuracy": 0.6244132176041604,
+      "num_tokens": 1104857.0,
+      "step": 980
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.8421082496643066,
+      "learning_rate": 0.00014577099236641223,
+      "loss": 2.0311,
+      "mean_token_accuracy": 0.6236826583743096,
+      "num_tokens": 1116131.0,
+      "step": 990
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.646053433418274,
+      "learning_rate": 0.00014516030534351146,
+      "loss": 1.9973,
+      "mean_token_accuracy": 0.6274659112095833,
+      "num_tokens": 1127612.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_loss": 1.989682674407959,
+      "eval_mean_token_accuracy": 0.633990108013153,
+      "eval_num_tokens": 1127612.0,
+      "eval_runtime": 49.3043,
+      "eval_samples_per_second": 20.282,
+      "eval_steps_per_second": 10.141,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8977777777777778,
+      "grad_norm": 1.5941271781921387,
+      "learning_rate": 0.0001445496183206107,
+      "loss": 2.0579,
+      "mean_token_accuracy": 0.6256210282444954,
+      "num_tokens": 1138866.0,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 1.7826253175735474,
+      "learning_rate": 0.00014393893129770993,
+      "loss": 1.9866,
+      "mean_token_accuracy": 0.6332772478461266,
+      "num_tokens": 1150411.0,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9155555555555556,
+      "grad_norm": 1.8722221851348877,
+      "learning_rate": 0.00014332824427480917,
+      "loss": 2.0398,
+      "mean_token_accuracy": 0.627329595386982,
+      "num_tokens": 1161360.0,
+      "step": 1030
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 1.6533294916152954,
+      "learning_rate": 0.0001427175572519084,
+      "loss": 2.0271,
+      "mean_token_accuracy": 0.6259514302015304,
+      "num_tokens": 1172683.0,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 1.5746543407440186,
+      "learning_rate": 0.00014210687022900764,
+      "loss": 1.9634,
+      "mean_token_accuracy": 0.6359310179948807,
+      "num_tokens": 1183277.0,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 1.6094276905059814,
+      "learning_rate": 0.00014149618320610688,
+      "loss": 1.9195,
+      "mean_token_accuracy": 0.649330523610115,
+      "num_tokens": 1194160.0,
+      "step": 1060
+    },
+    {
+      "epoch": 0.9511111111111111,
+      "grad_norm": 1.9643882513046265,
+      "learning_rate": 0.0001408854961832061,
+      "loss": 2.0042,
+      "mean_token_accuracy": 0.6356254667043686,
+      "num_tokens": 1205308.0,
+      "step": 1070
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.8238948583602905,
+      "learning_rate": 0.00014027480916030535,
+      "loss": 1.9172,
+      "mean_token_accuracy": 0.6497033536434174,
+      "num_tokens": 1215760.0,
+      "step": 1080
+    },
+    {
+      "epoch": 0.9688888888888889,
+      "grad_norm": 1.7422380447387695,
+      "learning_rate": 0.00013966412213740458,
+      "loss": 2.0213,
+      "mean_token_accuracy": 0.6309294819831848,
+      "num_tokens": 1226775.0,
+      "step": 1090
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.651795744895935,
+      "learning_rate": 0.00013905343511450382,
+      "loss": 2.033,
+      "mean_token_accuracy": 0.6295390352606773,
+      "num_tokens": 1238191.0,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 1.673543095588684,
+      "learning_rate": 0.00013844274809160308,
+      "loss": 2.0085,
+      "mean_token_accuracy": 0.6329691678285598,
+      "num_tokens": 1249561.0,
+      "step": 1110
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 1.7423163652420044,
+      "learning_rate": 0.0001378320610687023,
+      "loss": 1.9751,
+      "mean_token_accuracy": 0.6307685926556588,
+      "num_tokens": 1260429.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.0044444444444445,
+      "grad_norm": 1.4878981113433838,
+      "learning_rate": 0.00013722137404580153,
+      "loss": 1.9171,
+      "mean_token_accuracy": 0.644737622141838,
+      "num_tokens": 1271111.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 1.5343797206878662,
+      "learning_rate": 0.00013661068702290076,
+      "loss": 1.8544,
+      "mean_token_accuracy": 0.6503374725580215,
+      "num_tokens": 1282434.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.0222222222222221,
+      "grad_norm": 1.5450340509414673,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 1.828,
+      "mean_token_accuracy": 0.6514182686805725,
+      "num_tokens": 1294382.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.031111111111111,
+      "grad_norm": 1.8313877582550049,
+      "learning_rate": 0.00013538931297709923,
+      "loss": 1.7704,
+      "mean_token_accuracy": 0.6693721905350685,
+      "num_tokens": 1305343.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.8418430089950562,
+      "learning_rate": 0.00013477862595419847,
+      "loss": 1.7591,
+      "mean_token_accuracy": 0.67226582467556,
+      "num_tokens": 1316558.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.048888888888889,
+      "grad_norm": 1.6022825241088867,
+      "learning_rate": 0.0001341679389312977,
+      "loss": 1.8048,
+      "mean_token_accuracy": 0.6629651457071304,
+      "num_tokens": 1327938.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.0577777777777777,
+      "grad_norm": 1.5888707637786865,
+      "learning_rate": 0.00013355725190839697,
+      "loss": 1.773,
+      "mean_token_accuracy": 0.6730352655053139,
+      "num_tokens": 1338732.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 1.833946943283081,
+      "learning_rate": 0.0001329465648854962,
+      "loss": 1.7887,
+      "mean_token_accuracy": 0.6616317644715309,
+      "num_tokens": 1350096.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "eval_loss": 1.9697085618972778,
+      "eval_mean_token_accuracy": 0.6378205664157868,
+      "eval_num_tokens": 1350096.0,
+      "eval_runtime": 49.9237,
+      "eval_samples_per_second": 20.031,
+      "eval_steps_per_second": 10.015,
+      "step": 1200
+    },
+    {
+      "epoch": 1.0755555555555556,
+      "grad_norm": 1.6338160037994385,
+      "learning_rate": 0.00013233587786259541,
+      "loss": 1.7889,
+      "mean_token_accuracy": 0.6668319672346115,
+      "num_tokens": 1360771.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.0844444444444445,
+      "grad_norm": 1.8737561702728271,
+      "learning_rate": 0.00013172519083969465,
+      "loss": 1.7997,
+      "mean_token_accuracy": 0.6570939287543297,
+      "num_tokens": 1372450.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.0933333333333333,
+      "grad_norm": 1.758074402809143,
+      "learning_rate": 0.0001311145038167939,
+      "loss": 1.8457,
+      "mean_token_accuracy": 0.653074924647808,
+      "num_tokens": 1383711.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.1022222222222222,
+      "grad_norm": 1.839158296585083,
+      "learning_rate": 0.00013050381679389315,
+      "loss": 1.8013,
+      "mean_token_accuracy": 0.6608111187815666,
+      "num_tokens": 1394856.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 1.733567476272583,
+      "learning_rate": 0.00012989312977099238,
+      "loss": 1.7814,
+      "mean_token_accuracy": 0.6655508041381836,
+      "num_tokens": 1406193.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.6274900436401367,
+      "learning_rate": 0.0001292824427480916,
+      "loss": 1.858,
+      "mean_token_accuracy": 0.6488608077168465,
+      "num_tokens": 1417607.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.1288888888888888,
+      "grad_norm": 1.690090537071228,
+      "learning_rate": 0.00012867175572519086,
+      "loss": 1.8256,
+      "mean_token_accuracy": 0.6595686703920365,
+      "num_tokens": 1429073.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.1377777777777778,
+      "grad_norm": 1.6638071537017822,
+      "learning_rate": 0.0001280610687022901,
+      "loss": 1.8334,
+      "mean_token_accuracy": 0.6580470725893974,
+      "num_tokens": 1440194.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.1466666666666667,
+      "grad_norm": 1.8339307308197021,
+      "learning_rate": 0.00012745038167938933,
+      "loss": 1.783,
+      "mean_token_accuracy": 0.6632378786802292,
+      "num_tokens": 1451221.0,
+      "step": 1290
+    },
+    {
+      "epoch": 1.1555555555555554,
+      "grad_norm": 1.7621415853500366,
+      "learning_rate": 0.00012683969465648854,
+      "loss": 1.844,
+      "mean_token_accuracy": 0.6506654173135757,
+      "num_tokens": 1462493.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.1644444444444444,
+      "grad_norm": 1.7811567783355713,
+      "learning_rate": 0.00012622900763358777,
+      "loss": 1.8235,
+      "mean_token_accuracy": 0.6505810797214509,
+      "num_tokens": 1473710.0,
+      "step": 1310
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 1.9157836437225342,
+      "learning_rate": 0.00012561832061068704,
+      "loss": 1.8885,
+      "mean_token_accuracy": 0.6459546625614166,
+      "num_tokens": 1485215.0,
+      "step": 1320
+    },
+    {
+      "epoch": 1.1822222222222223,
+      "grad_norm": 1.6572569608688354,
+      "learning_rate": 0.00012500763358778627,
+      "loss": 1.813,
+      "mean_token_accuracy": 0.6597578257322312,
+      "num_tokens": 1496371.0,
+      "step": 1330
+    },
+    {
+      "epoch": 1.1911111111111112,
+      "grad_norm": 1.8602449893951416,
+      "learning_rate": 0.0001243969465648855,
+      "loss": 1.8179,
+      "mean_token_accuracy": 0.6519266426563263,
+      "num_tokens": 1508348.0,
+      "step": 1340
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.8736369609832764,
+      "learning_rate": 0.00012378625954198472,
+      "loss": 1.8029,
+      "mean_token_accuracy": 0.6621162816882133,
+      "num_tokens": 1519322.0,
+      "step": 1350
+    },
+    {
+      "epoch": 1.208888888888889,
+      "grad_norm": 2.026744842529297,
+      "learning_rate": 0.00012317557251908398,
+      "loss": 1.8168,
+      "mean_token_accuracy": 0.6635635286569596,
+      "num_tokens": 1530183.0,
+      "step": 1360
+    },
+    {
+      "epoch": 1.2177777777777778,
+      "grad_norm": 1.7360782623291016,
+      "learning_rate": 0.00012256488549618322,
+      "loss": 1.7521,
+      "mean_token_accuracy": 0.6706348299980164,
+      "num_tokens": 1540862.0,
+      "step": 1370
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 1.9620578289031982,
+      "learning_rate": 0.00012195419847328244,
+      "loss": 1.8228,
+      "mean_token_accuracy": 0.6569086670875549,
+      "num_tokens": 1552212.0,
+      "step": 1380
+    },
+    {
+      "epoch": 1.2355555555555555,
+      "grad_norm": 1.6294327974319458,
+      "learning_rate": 0.00012134351145038167,
+      "loss": 1.7654,
+      "mean_token_accuracy": 0.6697377026081085,
+      "num_tokens": 1563356.0,
+      "step": 1390
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 1.7311524152755737,
+      "learning_rate": 0.00012073282442748092,
+      "loss": 1.9019,
+      "mean_token_accuracy": 0.6457875579595566,
+      "num_tokens": 1574569.0,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "eval_loss": 1.9411770105361938,
+      "eval_mean_token_accuracy": 0.6407178282737732,
+      "eval_num_tokens": 1574569.0,
+      "eval_runtime": 48.3309,
+      "eval_samples_per_second": 20.691,
+      "eval_steps_per_second": 10.345,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2533333333333334,
+      "grad_norm": 1.8629728555679321,
+      "learning_rate": 0.00012012213740458016,
+      "loss": 1.7585,
+      "mean_token_accuracy": 0.671015702188015,
+      "num_tokens": 1585308.0,
+      "step": 1410
+    },
+    {
+      "epoch": 1.2622222222222224,
+      "grad_norm": 1.958808183670044,
+      "learning_rate": 0.0001195114503816794,
+      "loss": 1.8479,
+      "mean_token_accuracy": 0.6535898372530937,
+      "num_tokens": 1596886.0,
+      "step": 1420
+    },
+    {
+      "epoch": 1.271111111111111,
+      "grad_norm": 1.950421690940857,
+      "learning_rate": 0.00011890076335877862,
+      "loss": 1.8173,
+      "mean_token_accuracy": 0.6655478686094284,
+      "num_tokens": 1607683.0,
+      "step": 1430
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.8152872323989868,
+      "learning_rate": 0.00011829007633587788,
+      "loss": 1.8791,
+      "mean_token_accuracy": 0.6531546950340271,
+      "num_tokens": 1618906.0,
+      "step": 1440
+    },
+    {
+      "epoch": 1.2888888888888888,
+      "grad_norm": 1.7857719659805298,
+      "learning_rate": 0.0001176793893129771,
+      "loss": 1.7887,
+      "mean_token_accuracy": 0.6610255971550941,
+      "num_tokens": 1629981.0,
+      "step": 1450
+    },
+    {
+      "epoch": 1.2977777777777777,
+      "grad_norm": 1.8434971570968628,
+      "learning_rate": 0.00011706870229007634,
+      "loss": 1.8368,
+      "mean_token_accuracy": 0.653369964659214,
+      "num_tokens": 1641429.0,
+      "step": 1460
+    },
+    {
+      "epoch": 1.3066666666666666,
+      "grad_norm": 1.8877320289611816,
+      "learning_rate": 0.00011645801526717557,
+      "loss": 1.7938,
+      "mean_token_accuracy": 0.6639183640480042,
+      "num_tokens": 1652601.0,
+      "step": 1470
+    },
+    {
+      "epoch": 1.3155555555555556,
+      "grad_norm": 1.8121625185012817,
+      "learning_rate": 0.00011584732824427482,
+      "loss": 1.7862,
+      "mean_token_accuracy": 0.661414910852909,
+      "num_tokens": 1663837.0,
+      "step": 1480
+    },
+    {
+      "epoch": 1.3244444444444445,
+      "grad_norm": 1.7919855117797852,
+      "learning_rate": 0.00011523664122137406,
+      "loss": 1.8148,
+      "mean_token_accuracy": 0.6654411420226097,
+      "num_tokens": 1675018.0,
+      "step": 1490
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.828735589981079,
+      "learning_rate": 0.00011462595419847328,
+      "loss": 1.8456,
+      "mean_token_accuracy": 0.6496043875813484,
+      "num_tokens": 1686136.0,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3422222222222222,
+      "grad_norm": 1.9462794065475464,
+      "learning_rate": 0.00011401526717557252,
+      "loss": 1.8412,
+      "mean_token_accuracy": 0.6603908941149712,
+      "num_tokens": 1697160.0,
+      "step": 1510
+    },
+    {
+      "epoch": 1.3511111111111112,
+      "grad_norm": 1.6794313192367554,
+      "learning_rate": 0.00011340458015267177,
+      "loss": 1.7774,
+      "mean_token_accuracy": 0.6664682924747467,
+      "num_tokens": 1707831.0,
+      "step": 1520
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 1.8189337253570557,
+      "learning_rate": 0.000112793893129771,
+      "loss": 1.8031,
+      "mean_token_accuracy": 0.6627006307244301,
+      "num_tokens": 1719074.0,
+      "step": 1530
+    },
+    {
+      "epoch": 1.3688888888888888,
+      "grad_norm": 2.073533296585083,
+      "learning_rate": 0.00011218320610687022,
+      "loss": 1.8657,
+      "mean_token_accuracy": 0.6476830393075943,
+      "num_tokens": 1730388.0,
+      "step": 1540
+    },
+    {
+      "epoch": 1.3777777777777778,
+      "grad_norm": 2.1564207077026367,
+      "learning_rate": 0.00011157251908396946,
+      "loss": 1.8261,
+      "mean_token_accuracy": 0.6567840203642845,
+      "num_tokens": 1741806.0,
+      "step": 1550
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 1.6113232374191284,
+      "learning_rate": 0.00011096183206106871,
+      "loss": 1.7753,
+      "mean_token_accuracy": 0.6659888163208961,
+      "num_tokens": 1753313.0,
+      "step": 1560
+    },
+    {
+      "epoch": 1.3955555555555557,
+      "grad_norm": 1.8112174272537231,
+      "learning_rate": 0.00011035114503816795,
+      "loss": 1.8046,
+      "mean_token_accuracy": 0.6593015149235726,
+      "num_tokens": 1765144.0,
+      "step": 1570
+    },
+    {
+      "epoch": 1.4044444444444444,
+      "grad_norm": 1.8377541303634644,
+      "learning_rate": 0.00010974045801526718,
+      "loss": 1.8848,
+      "mean_token_accuracy": 0.6533517614006996,
+      "num_tokens": 1776783.0,
+      "step": 1580
+    },
+    {
+      "epoch": 1.4133333333333333,
+      "grad_norm": 1.8384325504302979,
+      "learning_rate": 0.0001091297709923664,
+      "loss": 1.7669,
+      "mean_token_accuracy": 0.6613995045423507,
+      "num_tokens": 1788274.0,
+      "step": 1590
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 1.8124533891677856,
+      "learning_rate": 0.00010851908396946567,
+      "loss": 1.8164,
+      "mean_token_accuracy": 0.6591159239411354,
+      "num_tokens": 1799707.0,
+      "step": 1600
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "eval_loss": 1.9286668300628662,
+      "eval_mean_token_accuracy": 0.6434953879117966,
+      "eval_num_tokens": 1799707.0,
+      "eval_runtime": 48.6198,
+      "eval_samples_per_second": 20.568,
+      "eval_steps_per_second": 10.284,
+      "step": 1600
+    },
+    {
+      "epoch": 1.431111111111111,
+      "grad_norm": 1.6931661367416382,
+      "learning_rate": 0.00010790839694656489,
+      "loss": 1.7548,
+      "mean_token_accuracy": 0.664087076485157,
+      "num_tokens": 1810865.0,
+      "step": 1610
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.7501254081726074,
+      "learning_rate": 0.00010729770992366413,
+      "loss": 1.7652,
+      "mean_token_accuracy": 0.6640020117163659,
+      "num_tokens": 1821807.0,
+      "step": 1620
+    },
+    {
+      "epoch": 1.448888888888889,
+      "grad_norm": 1.8411732912063599,
+      "learning_rate": 0.00010668702290076336,
+      "loss": 1.831,
+      "mean_token_accuracy": 0.6564242169260979,
+      "num_tokens": 1832886.0,
+      "step": 1630
+    },
+    {
+      "epoch": 1.4577777777777778,
+      "grad_norm": 2.003892183303833,
+      "learning_rate": 0.00010607633587786261,
+      "loss": 1.7791,
+      "mean_token_accuracy": 0.6632592365145683,
+      "num_tokens": 1843989.0,
+      "step": 1640
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 1.7987340688705444,
+      "learning_rate": 0.00010546564885496185,
+      "loss": 1.7627,
+      "mean_token_accuracy": 0.6713873609900475,
+      "num_tokens": 1855106.0,
+      "step": 1650
+    },
+    {
+      "epoch": 1.4755555555555555,
+      "grad_norm": 1.931877851486206,
+      "learning_rate": 0.00010485496183206107,
+      "loss": 1.7976,
+      "mean_token_accuracy": 0.6631382897496223,
+      "num_tokens": 1866900.0,
+      "step": 1660
+    },
+    {
+      "epoch": 1.4844444444444445,
+      "grad_norm": 1.7883687019348145,
+      "learning_rate": 0.0001042442748091603,
+      "loss": 1.7671,
+      "mean_token_accuracy": 0.6675158813595772,
+      "num_tokens": 1877911.0,
+      "step": 1670
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 1.8195563554763794,
+      "learning_rate": 0.00010363358778625955,
+      "loss": 1.8346,
+      "mean_token_accuracy": 0.652577318251133,
+      "num_tokens": 1889580.0,
+      "step": 1680
+    },
+    {
+      "epoch": 1.5022222222222221,
+      "grad_norm": 1.7439149618148804,
+      "learning_rate": 0.00010302290076335879,
+      "loss": 1.7476,
+      "mean_token_accuracy": 0.6717594474554062,
+      "num_tokens": 1901133.0,
+      "step": 1690
+    },
+    {
+      "epoch": 1.511111111111111,
+      "grad_norm": 1.8155314922332764,
+      "learning_rate": 0.00010241221374045801,
+      "loss": 1.8044,
+      "mean_token_accuracy": 0.6617274522781372,
+      "num_tokens": 1911796.0,
+      "step": 1700
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.7685112953186035,
+      "learning_rate": 0.00010180152671755725,
+      "loss": 1.7727,
+      "mean_token_accuracy": 0.665304908156395,
+      "num_tokens": 1923217.0,
+      "step": 1710
+    },
+    {
+      "epoch": 1.528888888888889,
+      "grad_norm": 1.737053632736206,
+      "learning_rate": 0.0001011908396946565,
+      "loss": 1.8345,
+      "mean_token_accuracy": 0.6577870160341263,
+      "num_tokens": 1934355.0,
+      "step": 1720
+    },
+    {
+      "epoch": 1.537777777777778,
+      "grad_norm": 1.9686291217803955,
+      "learning_rate": 0.00010058015267175573,
+      "loss": 1.8165,
+      "mean_token_accuracy": 0.6594037398695946,
+      "num_tokens": 1945653.0,
+      "step": 1730
+    },
+    {
+      "epoch": 1.5466666666666666,
+      "grad_norm": 1.844651699066162,
+      "learning_rate": 9.996946564885497e-05,
+      "loss": 1.8273,
+      "mean_token_accuracy": 0.6566928923130035,
+      "num_tokens": 1956891.0,
+      "step": 1740
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 1.8607743978500366,
+      "learning_rate": 9.93587786259542e-05,
+      "loss": 1.785,
+      "mean_token_accuracy": 0.6692357853055,
+      "num_tokens": 1967789.0,
+      "step": 1750
+    },
+    {
+      "epoch": 1.5644444444444443,
+      "grad_norm": 1.9204373359680176,
+      "learning_rate": 9.874809160305344e-05,
+      "loss": 1.8264,
+      "mean_token_accuracy": 0.6549209818243981,
+      "num_tokens": 1979224.0,
+      "step": 1760
+    },
+    {
+      "epoch": 1.5733333333333333,
+      "grad_norm": 1.7754265069961548,
+      "learning_rate": 9.813740458015268e-05,
+      "loss": 1.7467,
+      "mean_token_accuracy": 0.6670090600848197,
+      "num_tokens": 1990255.0,
+      "step": 1770
+    },
+    {
+      "epoch": 1.5822222222222222,
+      "grad_norm": 2.069091796875,
+      "learning_rate": 9.752671755725191e-05,
+      "loss": 1.7731,
+      "mean_token_accuracy": 0.6609751120209694,
+      "num_tokens": 2001606.0,
+      "step": 1780
+    },
+    {
+      "epoch": 1.5911111111111111,
+      "grad_norm": 2.1375646591186523,
+      "learning_rate": 9.691603053435115e-05,
+      "loss": 1.8009,
+      "mean_token_accuracy": 0.6624869346618653,
+      "num_tokens": 2012912.0,
+      "step": 1790
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.5623434782028198,
+      "learning_rate": 9.630534351145038e-05,
+      "loss": 1.7383,
+      "mean_token_accuracy": 0.6694582119584084,
+      "num_tokens": 2024571.0,
+      "step": 1800
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.90510892868042,
+      "eval_mean_token_accuracy": 0.6464553346633911,
+      "eval_num_tokens": 2024571.0,
+      "eval_runtime": 48.9449,
+      "eval_samples_per_second": 20.431,
+      "eval_steps_per_second": 10.216,
+      "step": 1800
+    },
+    {
+      "epoch": 1.608888888888889,
+      "grad_norm": 1.745969295501709,
+      "learning_rate": 9.569465648854963e-05,
+      "loss": 1.7552,
+      "mean_token_accuracy": 0.6786300778388977,
+      "num_tokens": 2035783.0,
+      "step": 1810
+    },
+    {
+      "epoch": 1.6177777777777778,
+      "grad_norm": 1.7463303804397583,
+      "learning_rate": 9.508396946564886e-05,
+      "loss": 1.7495,
+      "mean_token_accuracy": 0.6666959136724472,
+      "num_tokens": 2047304.0,
+      "step": 1820
+    },
+    {
+      "epoch": 1.6266666666666667,
+      "grad_norm": 1.9058139324188232,
+      "learning_rate": 9.44732824427481e-05,
+      "loss": 1.8365,
+      "mean_token_accuracy": 0.6536470741033554,
+      "num_tokens": 2058792.0,
+      "step": 1830
+    },
+    {
+      "epoch": 1.6355555555555554,
+      "grad_norm": 2.065488576889038,
+      "learning_rate": 9.386259541984733e-05,
+      "loss": 1.7939,
+      "mean_token_accuracy": 0.6519258007407188,
+      "num_tokens": 2070175.0,
+      "step": 1840
+    },
+    {
+      "epoch": 1.6444444444444444,
+      "grad_norm": 1.778023600578308,
+      "learning_rate": 9.325190839694658e-05,
+      "loss": 1.8155,
+      "mean_token_accuracy": 0.655296416580677,
+      "num_tokens": 2081343.0,
+      "step": 1850
+    },
+    {
+      "epoch": 1.6533333333333333,
+      "grad_norm": 1.7437517642974854,
+      "learning_rate": 9.26412213740458e-05,
+      "loss": 1.7996,
+      "mean_token_accuracy": 0.6618543311953544,
+      "num_tokens": 2093074.0,
+      "step": 1860
+    },
+    {
+      "epoch": 1.6622222222222223,
+      "grad_norm": 1.7666471004486084,
+      "learning_rate": 9.203053435114505e-05,
+      "loss": 1.7658,
+      "mean_token_accuracy": 0.6631957843899727,
+      "num_tokens": 2104640.0,
+      "step": 1870
+    },
+    {
+      "epoch": 1.6711111111111112,
+      "grad_norm": 1.912842869758606,
+      "learning_rate": 9.141984732824428e-05,
+      "loss": 1.7996,
+      "mean_token_accuracy": 0.6606781020760536,
+      "num_tokens": 2115628.0,
+      "step": 1880
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 1.7230331897735596,
+      "learning_rate": 9.080916030534351e-05,
+      "loss": 1.8042,
+      "mean_token_accuracy": 0.6600380197167397,
+      "num_tokens": 2126505.0,
+      "step": 1890
+    },
+    {
+      "epoch": 1.6888888888888889,
+      "grad_norm": 1.7043401002883911,
+      "learning_rate": 9.019847328244276e-05,
+      "loss": 1.7993,
+      "mean_token_accuracy": 0.6613149493932724,
+      "num_tokens": 2138364.0,
+      "step": 1900
+    },
+    {
+      "epoch": 1.6977777777777778,
+      "grad_norm": 1.9145572185516357,
+      "learning_rate": 8.958778625954198e-05,
+      "loss": 1.8046,
+      "mean_token_accuracy": 0.662477345764637,
+      "num_tokens": 2149425.0,
+      "step": 1910
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 1.7448140382766724,
+      "learning_rate": 8.897709923664123e-05,
+      "loss": 1.8004,
+      "mean_token_accuracy": 0.6539181426167489,
+      "num_tokens": 2160843.0,
+      "step": 1920
+    },
+    {
+      "epoch": 1.7155555555555555,
+      "grad_norm": 1.8304840326309204,
+      "learning_rate": 8.836641221374045e-05,
+      "loss": 1.8404,
+      "mean_token_accuracy": 0.6593489304184914,
+      "num_tokens": 2172044.0,
+      "step": 1930
+    },
+    {
+      "epoch": 1.7244444444444444,
+      "grad_norm": 1.802331566810608,
+      "learning_rate": 8.77557251908397e-05,
+      "loss": 1.7995,
+      "mean_token_accuracy": 0.6634193584322929,
+      "num_tokens": 2182916.0,
+      "step": 1940
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 1.9834682941436768,
+      "learning_rate": 8.714503816793894e-05,
+      "loss": 1.7525,
+      "mean_token_accuracy": 0.6685526207089424,
+      "num_tokens": 2194913.0,
+      "step": 1950
+    },
+    {
+      "epoch": 1.7422222222222223,
+      "grad_norm": 1.8077235221862793,
+      "learning_rate": 8.653435114503817e-05,
+      "loss": 1.7612,
+      "mean_token_accuracy": 0.6704939991235733,
+      "num_tokens": 2205721.0,
+      "step": 1960
+    },
+    {
+      "epoch": 1.751111111111111,
+      "grad_norm": 1.957993745803833,
+      "learning_rate": 8.592366412213741e-05,
+      "loss": 1.8059,
+      "mean_token_accuracy": 0.6547697961330414,
+      "num_tokens": 2217489.0,
+      "step": 1970
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.7215981483459473,
+      "learning_rate": 8.531297709923664e-05,
+      "loss": 1.7913,
+      "mean_token_accuracy": 0.657075221836567,
+      "num_tokens": 2228972.0,
+      "step": 1980
+    },
+    {
+      "epoch": 1.7688888888888887,
+      "grad_norm": 1.8760231733322144,
+      "learning_rate": 8.470229007633588e-05,
+      "loss": 1.7923,
+      "mean_token_accuracy": 0.6629065066576004,
+      "num_tokens": 2240239.0,
+      "step": 1990
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 2.092407703399658,
+      "learning_rate": 8.409160305343512e-05,
+      "loss": 1.7593,
+      "mean_token_accuracy": 0.6686230883002281,
+      "num_tokens": 2251436.0,
+      "step": 2000
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "eval_loss": 1.893255591392517,
+      "eval_mean_token_accuracy": 0.6482590944766998,
+      "eval_num_tokens": 2251436.0,
+      "eval_runtime": 49.0676,
+      "eval_samples_per_second": 20.38,
+      "eval_steps_per_second": 10.19,
+      "step": 2000
+    },
+    {
+      "epoch": 1.7866666666666666,
+      "grad_norm": 1.7836107015609741,
+      "learning_rate": 8.348091603053435e-05,
+      "loss": 1.8033,
+      "mean_token_accuracy": 0.6598399996757507,
+      "num_tokens": 2263069.0,
+      "step": 2010
+    },
+    {
+      "epoch": 1.7955555555555556,
+      "grad_norm": 1.7955141067504883,
+      "learning_rate": 8.287022900763359e-05,
+      "loss": 1.7922,
+      "mean_token_accuracy": 0.6619856491684913,
+      "num_tokens": 2274050.0,
+      "step": 2020
+    },
+    {
+      "epoch": 1.8044444444444445,
+      "grad_norm": 1.7887564897537231,
+      "learning_rate": 8.225954198473282e-05,
+      "loss": 1.8353,
+      "mean_token_accuracy": 0.658150726556778,
+      "num_tokens": 2285060.0,
+      "step": 2030
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 1.8892567157745361,
+      "learning_rate": 8.164885496183207e-05,
+      "loss": 1.7266,
+      "mean_token_accuracy": 0.6728688895702362,
+      "num_tokens": 2296211.0,
+      "step": 2040
+    },
+    {
+      "epoch": 1.8222222222222222,
+      "grad_norm": 1.9226106405258179,
+      "learning_rate": 8.10381679389313e-05,
+      "loss": 1.7243,
+      "mean_token_accuracy": 0.6712497785687447,
+      "num_tokens": 2307184.0,
+      "step": 2050
+    },
+    {
+      "epoch": 1.8311111111111111,
+      "grad_norm": 1.735863208770752,
+      "learning_rate": 8.042748091603054e-05,
+      "loss": 1.7739,
+      "mean_token_accuracy": 0.6621047109365463,
+      "num_tokens": 2318602.0,
+      "step": 2060
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 1.8361355066299438,
+      "learning_rate": 7.981679389312977e-05,
+      "loss": 1.8223,
+      "mean_token_accuracy": 0.6560095950961113,
+      "num_tokens": 2330193.0,
+      "step": 2070
+    },
+    {
+      "epoch": 1.8488888888888888,
+      "grad_norm": 1.8159486055374146,
+      "learning_rate": 7.920610687022902e-05,
+      "loss": 1.7695,
+      "mean_token_accuracy": 0.6657541528344154,
+      "num_tokens": 2341442.0,
+      "step": 2080
+    },
+    {
+      "epoch": 1.8577777777777778,
+      "grad_norm": 1.9189419746398926,
+      "learning_rate": 7.859541984732824e-05,
+      "loss": 1.8333,
+      "mean_token_accuracy": 0.6628425523638726,
+      "num_tokens": 2352479.0,
+      "step": 2090
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 1.8809512853622437,
+      "learning_rate": 7.798473282442749e-05,
+      "loss": 1.7371,
+      "mean_token_accuracy": 0.6683435723185539,
+      "num_tokens": 2363642.0,
+      "step": 2100
+    },
+    {
+      "epoch": 1.8755555555555556,
+      "grad_norm": 1.845886468887329,
+      "learning_rate": 7.737404580152672e-05,
+      "loss": 1.7774,
+      "mean_token_accuracy": 0.6559944331645966,
+      "num_tokens": 2375376.0,
+      "step": 2110
+    },
+    {
+      "epoch": 1.8844444444444446,
+      "grad_norm": 1.7780894041061401,
+      "learning_rate": 7.676335877862596e-05,
+      "loss": 1.7823,
+      "mean_token_accuracy": 0.6601730152964592,
+      "num_tokens": 2386944.0,
+      "step": 2120
+    },
+    {
+      "epoch": 1.8933333333333333,
+      "grad_norm": 1.9167022705078125,
+      "learning_rate": 7.61526717557252e-05,
+      "loss": 1.7869,
+      "mean_token_accuracy": 0.6573449537158013,
+      "num_tokens": 2398391.0,
+      "step": 2130
+    },
+    {
+      "epoch": 1.9022222222222223,
+      "grad_norm": 2.037911891937256,
+      "learning_rate": 7.554198473282443e-05,
+      "loss": 1.7858,
+      "mean_token_accuracy": 0.6593190267682075,
+      "num_tokens": 2409837.0,
+      "step": 2140
+    },
+    {
+      "epoch": 1.911111111111111,
+      "grad_norm": 1.7496647834777832,
+      "learning_rate": 7.493129770992367e-05,
+      "loss": 1.7241,
+      "mean_token_accuracy": 0.6702290028333664,
+      "num_tokens": 2421607.0,
+      "step": 2150
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 2.0227596759796143,
+      "learning_rate": 7.43206106870229e-05,
+      "loss": 1.7731,
+      "mean_token_accuracy": 0.6679618924856185,
+      "num_tokens": 2432376.0,
+      "step": 2160
+    },
+    {
+      "epoch": 1.9288888888888889,
+      "grad_norm": 1.7401562929153442,
+      "learning_rate": 7.370992366412214e-05,
+      "loss": 1.7684,
+      "mean_token_accuracy": 0.6676609605550766,
+      "num_tokens": 2443683.0,
+      "step": 2170
+    },
+    {
+      "epoch": 1.9377777777777778,
+      "grad_norm": 2.709106922149658,
+      "learning_rate": 7.309923664122137e-05,
+      "loss": 1.709,
+      "mean_token_accuracy": 0.6738818466663361,
+      "num_tokens": 2454757.0,
+      "step": 2180
+    },
+    {
+      "epoch": 1.9466666666666668,
+      "grad_norm": 1.8504191637039185,
+      "learning_rate": 7.248854961832061e-05,
+      "loss": 1.7411,
+      "mean_token_accuracy": 0.6681609645485878,
+      "num_tokens": 2465562.0,
+      "step": 2190
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 1.9488162994384766,
+      "learning_rate": 7.187786259541986e-05,
+      "loss": 1.7927,
+      "mean_token_accuracy": 0.6587553441524505,
+      "num_tokens": 2476869.0,
+      "step": 2200
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "eval_loss": 1.8803235292434692,
+      "eval_mean_token_accuracy": 0.6499251070022583,
+      "eval_num_tokens": 2476869.0,
+      "eval_runtime": 47.7648,
+      "eval_samples_per_second": 20.936,
+      "eval_steps_per_second": 10.468,
+      "step": 2200
+    },
+    {
+      "epoch": 1.9644444444444444,
+      "grad_norm": 1.9747337102890015,
+      "learning_rate": 7.132824427480917e-05,
+      "loss": 1.7689,
+      "mean_token_accuracy": 0.666295376420021,
+      "num_tokens": 2487704.0,
+      "step": 2210
+    },
+    {
+      "epoch": 1.9733333333333334,
+      "grad_norm": 1.8904316425323486,
+      "learning_rate": 7.071755725190839e-05,
+      "loss": 1.7538,
+      "mean_token_accuracy": 0.6645636394619941,
+      "num_tokens": 2498918.0,
+      "step": 2220
+    },
+    {
+      "epoch": 1.982222222222222,
+      "grad_norm": 1.8791844844818115,
+      "learning_rate": 7.010687022900764e-05,
+      "loss": 1.7926,
+      "mean_token_accuracy": 0.6631673067808151,
+      "num_tokens": 2509728.0,
+      "step": 2230
+    },
+    {
+      "epoch": 1.991111111111111,
+      "grad_norm": 1.9756606817245483,
+      "learning_rate": 6.949618320610687e-05,
+      "loss": 1.7863,
+      "mean_token_accuracy": 0.6628521859645844,
+      "num_tokens": 2521073.0,
+      "step": 2240
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7894699573516846,
+      "learning_rate": 6.888549618320611e-05,
+      "loss": 1.7539,
+      "mean_token_accuracy": 0.6728802308440208,
+      "num_tokens": 2531820.0,
+      "step": 2250
+    },
+    {
+      "epoch": 2.008888888888889,
+      "grad_norm": 1.702850341796875,
+      "learning_rate": 6.827480916030535e-05,
+      "loss": 1.4903,
+      "mean_token_accuracy": 0.7138098135590554,
+      "num_tokens": 2542512.0,
+      "step": 2260
+    },
+    {
+      "epoch": 2.017777777777778,
+      "grad_norm": 1.7931528091430664,
+      "learning_rate": 6.766412213740458e-05,
+      "loss": 1.601,
+      "mean_token_accuracy": 0.6894692406058311,
+      "num_tokens": 2553338.0,
+      "step": 2270
+    },
+    {
+      "epoch": 2.026666666666667,
+      "grad_norm": 2.228480339050293,
+      "learning_rate": 6.705343511450382e-05,
+      "loss": 1.609,
+      "mean_token_accuracy": 0.6943154886364937,
+      "num_tokens": 2564182.0,
+      "step": 2280
+    },
+    {
+      "epoch": 2.0355555555555553,
+      "grad_norm": 1.9658042192459106,
+      "learning_rate": 6.644274809160305e-05,
+      "loss": 1.6545,
+      "mean_token_accuracy": 0.6824306204915047,
+      "num_tokens": 2575789.0,
+      "step": 2290
+    },
+    {
+      "epoch": 2.0444444444444443,
+      "grad_norm": 1.7540594339370728,
+      "learning_rate": 6.583206106870229e-05,
+      "loss": 1.6229,
+      "mean_token_accuracy": 0.6881745710968972,
+      "num_tokens": 2587147.0,
+      "step": 2300
+    },
+    {
+      "epoch": 2.0533333333333332,
+      "grad_norm": 1.799501895904541,
+      "learning_rate": 6.522137404580153e-05,
+      "loss": 1.6119,
+      "mean_token_accuracy": 0.6896049126982688,
+      "num_tokens": 2598282.0,
+      "step": 2310
+    },
+    {
+      "epoch": 2.062222222222222,
+      "grad_norm": 1.7720867395401,
+      "learning_rate": 6.461068702290076e-05,
+      "loss": 1.5519,
+      "mean_token_accuracy": 0.7038252353668213,
+      "num_tokens": 2609125.0,
+      "step": 2320
+    },
+    {
+      "epoch": 2.071111111111111,
+      "grad_norm": 1.994992971420288,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 1.5872,
+      "mean_token_accuracy": 0.690100908279419,
+      "num_tokens": 2620411.0,
+      "step": 2330
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.9283640384674072,
+      "learning_rate": 6.338931297709923e-05,
+      "loss": 1.5867,
+      "mean_token_accuracy": 0.6923216238617897,
+      "num_tokens": 2631795.0,
+      "step": 2340
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 1.9957973957061768,
+      "learning_rate": 6.277862595419848e-05,
+      "loss": 1.5996,
+      "mean_token_accuracy": 0.6924369186162949,
+      "num_tokens": 2643179.0,
+      "step": 2350
+    },
+    {
+      "epoch": 2.097777777777778,
+      "grad_norm": 2.0207560062408447,
+      "learning_rate": 6.21679389312977e-05,
+      "loss": 1.515,
+      "mean_token_accuracy": 0.7066755428910255,
+      "num_tokens": 2654206.0,
+      "step": 2360
+    },
+    {
+      "epoch": 2.1066666666666665,
+      "grad_norm": 1.8871878385543823,
+      "learning_rate": 6.155725190839695e-05,
+      "loss": 1.6139,
+      "mean_token_accuracy": 0.687422800064087,
+      "num_tokens": 2665582.0,
+      "step": 2370
+    },
+    {
+      "epoch": 2.1155555555555554,
+      "grad_norm": 1.717610478401184,
+      "learning_rate": 6.094656488549618e-05,
+      "loss": 1.6388,
+      "mean_token_accuracy": 0.6870575189590454,
+      "num_tokens": 2677533.0,
+      "step": 2380
+    },
+    {
+      "epoch": 2.1244444444444444,
+      "grad_norm": 1.8574187755584717,
+      "learning_rate": 6.0335877862595426e-05,
+      "loss": 1.557,
+      "mean_token_accuracy": 0.6999430671334267,
+      "num_tokens": 2688755.0,
+      "step": 2390
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 1.9739580154418945,
+      "learning_rate": 5.9725190839694655e-05,
+      "loss": 1.6553,
+      "mean_token_accuracy": 0.6819543272256852,
+      "num_tokens": 2700558.0,
+      "step": 2400
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "eval_loss": 1.8970768451690674,
+      "eval_mean_token_accuracy": 0.6490416256189346,
+      "eval_num_tokens": 2700558.0,
+      "eval_runtime": 47.6704,
+      "eval_samples_per_second": 20.977,
+      "eval_steps_per_second": 10.489,
+      "step": 2400
+    },
+    {
+      "epoch": 2.1422222222222222,
+      "grad_norm": 1.893918514251709,
+      "learning_rate": 5.91145038167939e-05,
+      "loss": 1.5459,
+      "mean_token_accuracy": 0.6963777393102646,
+      "num_tokens": 2711713.0,
+      "step": 2410
+    },
+    {
+      "epoch": 2.151111111111111,
+      "grad_norm": 1.9607445001602173,
+      "learning_rate": 5.850381679389313e-05,
+      "loss": 1.6373,
+      "mean_token_accuracy": 0.6815788432955742,
+      "num_tokens": 2723686.0,
+      "step": 2420
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 2.091732978820801,
+      "learning_rate": 5.789312977099237e-05,
+      "loss": 1.6422,
+      "mean_token_accuracy": 0.6811213716864586,
+      "num_tokens": 2735300.0,
+      "step": 2430
+    },
+    {
+      "epoch": 2.168888888888889,
+      "grad_norm": 2.1138076782226562,
+      "learning_rate": 5.7282442748091605e-05,
+      "loss": 1.5848,
+      "mean_token_accuracy": 0.6962573245167732,
+      "num_tokens": 2746248.0,
+      "step": 2440
+    },
+    {
+      "epoch": 2.1777777777777776,
+      "grad_norm": 2.1495392322540283,
+      "learning_rate": 5.667175572519085e-05,
+      "loss": 1.576,
+      "mean_token_accuracy": 0.6990228727459907,
+      "num_tokens": 2757259.0,
+      "step": 2450
+    },
+    {
+      "epoch": 2.1866666666666665,
+      "grad_norm": 2.1444251537323,
+      "learning_rate": 5.606106870229008e-05,
+      "loss": 1.5979,
+      "mean_token_accuracy": 0.6916472837328911,
+      "num_tokens": 2768228.0,
+      "step": 2460
+    },
+    {
+      "epoch": 2.1955555555555555,
+      "grad_norm": 1.945489525794983,
+      "learning_rate": 5.545038167938932e-05,
+      "loss": 1.5663,
+      "mean_token_accuracy": 0.7005513325333595,
+      "num_tokens": 2779254.0,
+      "step": 2470
+    },
+    {
+      "epoch": 2.2044444444444444,
+      "grad_norm": 1.8256646394729614,
+      "learning_rate": 5.483969465648855e-05,
+      "loss": 1.5751,
+      "mean_token_accuracy": 0.6961624413728714,
+      "num_tokens": 2790326.0,
+      "step": 2480
+    },
+    {
+      "epoch": 2.2133333333333334,
+      "grad_norm": 1.9541441202163696,
+      "learning_rate": 5.422900763358779e-05,
+      "loss": 1.6268,
+      "mean_token_accuracy": 0.6893054991960526,
+      "num_tokens": 2801625.0,
+      "step": 2490
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 2.0127615928649902,
+      "learning_rate": 5.361832061068702e-05,
+      "loss": 1.6096,
+      "mean_token_accuracy": 0.6923437744379044,
+      "num_tokens": 2813010.0,
+      "step": 2500
+    },
+    {
+      "epoch": 2.2311111111111113,
+      "grad_norm": 2.0325839519500732,
+      "learning_rate": 5.300763358778626e-05,
+      "loss": 1.5963,
+      "mean_token_accuracy": 0.6913090571761131,
+      "num_tokens": 2824021.0,
+      "step": 2510
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 2.1595821380615234,
+      "learning_rate": 5.23969465648855e-05,
+      "loss": 1.5617,
+      "mean_token_accuracy": 0.7037980020046234,
+      "num_tokens": 2835232.0,
+      "step": 2520
+    },
+    {
+      "epoch": 2.2488888888888887,
+      "grad_norm": 2.11661958694458,
+      "learning_rate": 5.178625954198474e-05,
+      "loss": 1.6213,
+      "mean_token_accuracy": 0.6836483731865883,
+      "num_tokens": 2846524.0,
+      "step": 2530
+    },
+    {
+      "epoch": 2.2577777777777777,
+      "grad_norm": 1.88747239112854,
+      "learning_rate": 5.117557251908397e-05,
+      "loss": 1.6408,
+      "mean_token_accuracy": 0.6860729962587356,
+      "num_tokens": 2857788.0,
+      "step": 2540
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 1.9622093439102173,
+      "learning_rate": 5.056488549618321e-05,
+      "loss": 1.5519,
+      "mean_token_accuracy": 0.7002682030200958,
+      "num_tokens": 2868618.0,
+      "step": 2550
+    },
+    {
+      "epoch": 2.2755555555555556,
+      "grad_norm": 1.9343371391296387,
+      "learning_rate": 4.995419847328244e-05,
+      "loss": 1.5795,
+      "mean_token_accuracy": 0.6934511423110962,
+      "num_tokens": 2879999.0,
+      "step": 2560
+    },
+    {
+      "epoch": 2.2844444444444445,
+      "grad_norm": 1.9991627931594849,
+      "learning_rate": 4.934351145038168e-05,
+      "loss": 1.6183,
+      "mean_token_accuracy": 0.6901679039001465,
+      "num_tokens": 2891053.0,
+      "step": 2570
+    },
+    {
+      "epoch": 2.2933333333333334,
+      "grad_norm": 1.9480003118515015,
+      "learning_rate": 4.8732824427480914e-05,
+      "loss": 1.5826,
+      "mean_token_accuracy": 0.7007558569312096,
+      "num_tokens": 2901905.0,
+      "step": 2580
+    },
+    {
+      "epoch": 2.3022222222222224,
+      "grad_norm": 2.021207332611084,
+      "learning_rate": 4.812213740458015e-05,
+      "loss": 1.6348,
+      "mean_token_accuracy": 0.6848765298724174,
+      "num_tokens": 2913571.0,
+      "step": 2590
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 1.8385164737701416,
+      "learning_rate": 4.751145038167939e-05,
+      "loss": 1.5763,
+      "mean_token_accuracy": 0.6912240386009216,
+      "num_tokens": 2925533.0,
+      "step": 2600
+    },
+    {
+      "epoch": 2.311111111111111,
+      "eval_loss": 1.8940143585205078,
+      "eval_mean_token_accuracy": 0.6499911918640137,
+      "eval_num_tokens": 2925533.0,
+      "eval_runtime": 47.456,
+      "eval_samples_per_second": 21.072,
+      "eval_steps_per_second": 10.536,
+      "step": 2600
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 1.9455375671386719,
+      "learning_rate": 4.690076335877863e-05,
+      "loss": 1.598,
+      "mean_token_accuracy": 0.6915700435638428,
+      "num_tokens": 2936620.0,
+      "step": 2610
+    },
+    {
+      "epoch": 2.328888888888889,
+      "grad_norm": 1.863487720489502,
+      "learning_rate": 4.6290076335877864e-05,
+      "loss": 1.5512,
+      "mean_token_accuracy": 0.7025073647499085,
+      "num_tokens": 2947753.0,
+      "step": 2620
+    },
+    {
+      "epoch": 2.3377777777777777,
+      "grad_norm": 1.9756685495376587,
+      "learning_rate": 4.56793893129771e-05,
+      "loss": 1.5973,
+      "mean_token_accuracy": 0.6870647758245468,
+      "num_tokens": 2959635.0,
+      "step": 2630
+    },
+    {
+      "epoch": 2.3466666666666667,
+      "grad_norm": 2.190765142440796,
+      "learning_rate": 4.5068702290076336e-05,
+      "loss": 1.5948,
+      "mean_token_accuracy": 0.6888303905725479,
+      "num_tokens": 2971675.0,
+      "step": 2640
+    },
+    {
+      "epoch": 2.3555555555555556,
+      "grad_norm": 1.827318787574768,
+      "learning_rate": 4.445801526717557e-05,
+      "loss": 1.5682,
+      "mean_token_accuracy": 0.6952902913093567,
+      "num_tokens": 2982744.0,
+      "step": 2650
+    },
+    {
+      "epoch": 2.3644444444444446,
+      "grad_norm": 2.11799693107605,
+      "learning_rate": 4.384732824427481e-05,
+      "loss": 1.6221,
+      "mean_token_accuracy": 0.6794109031558037,
+      "num_tokens": 2994347.0,
+      "step": 2660
+    },
+    {
+      "epoch": 2.3733333333333335,
+      "grad_norm": 2.1472220420837402,
+      "learning_rate": 4.3236641221374044e-05,
+      "loss": 1.6353,
+      "mean_token_accuracy": 0.6876759916543961,
+      "num_tokens": 3005174.0,
+      "step": 2670
+    },
+    {
+      "epoch": 2.3822222222222225,
+      "grad_norm": 1.9971054792404175,
+      "learning_rate": 4.2625954198473286e-05,
+      "loss": 1.5372,
+      "mean_token_accuracy": 0.7059834420680999,
+      "num_tokens": 3016492.0,
+      "step": 2680
+    },
+    {
+      "epoch": 2.391111111111111,
+      "grad_norm": 2.067861318588257,
+      "learning_rate": 4.201526717557252e-05,
+      "loss": 1.572,
+      "mean_token_accuracy": 0.6911077201366425,
+      "num_tokens": 3027826.0,
+      "step": 2690
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.0372536182403564,
+      "learning_rate": 4.140458015267176e-05,
+      "loss": 1.5615,
+      "mean_token_accuracy": 0.6972797185182571,
+      "num_tokens": 3038770.0,
+      "step": 2700
+    },
+    {
+      "epoch": 2.408888888888889,
+      "grad_norm": 2.15972638130188,
+      "learning_rate": 4.0793893129770994e-05,
+      "loss": 1.5806,
+      "mean_token_accuracy": 0.6947444006800652,
+      "num_tokens": 3050159.0,
+      "step": 2710
+    },
+    {
+      "epoch": 2.417777777777778,
+      "grad_norm": 2.059760808944702,
+      "learning_rate": 4.018320610687023e-05,
+      "loss": 1.6167,
+      "mean_token_accuracy": 0.6882677704095841,
+      "num_tokens": 3061009.0,
+      "step": 2720
+    },
+    {
+      "epoch": 2.4266666666666667,
+      "grad_norm": 1.9914629459381104,
+      "learning_rate": 3.9572519083969466e-05,
+      "loss": 1.5508,
+      "mean_token_accuracy": 0.6985371947288513,
+      "num_tokens": 3072232.0,
+      "step": 2730
+    },
+    {
+      "epoch": 2.4355555555555557,
+      "grad_norm": 2.0151119232177734,
+      "learning_rate": 3.89618320610687e-05,
+      "loss": 1.663,
+      "mean_token_accuracy": 0.6849021047353745,
+      "num_tokens": 3083939.0,
+      "step": 2740
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 2.02457332611084,
+      "learning_rate": 3.835114503816794e-05,
+      "loss": 1.6043,
+      "mean_token_accuracy": 0.6891427770256996,
+      "num_tokens": 3095354.0,
+      "step": 2750
+    },
+    {
+      "epoch": 2.453333333333333,
+      "grad_norm": 1.930341362953186,
+      "learning_rate": 3.774045801526718e-05,
+      "loss": 1.5648,
+      "mean_token_accuracy": 0.6962095096707344,
+      "num_tokens": 3106679.0,
+      "step": 2760
+    },
+    {
+      "epoch": 2.462222222222222,
+      "grad_norm": 2.1718850135803223,
+      "learning_rate": 3.7129770992366416e-05,
+      "loss": 1.5514,
+      "mean_token_accuracy": 0.6997211873531342,
+      "num_tokens": 3117440.0,
+      "step": 2770
+    },
+    {
+      "epoch": 2.471111111111111,
+      "grad_norm": 1.89506196975708,
+      "learning_rate": 3.651908396946565e-05,
+      "loss": 1.6102,
+      "mean_token_accuracy": 0.6865462198853493,
+      "num_tokens": 3128685.0,
+      "step": 2780
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 2.1102652549743652,
+      "learning_rate": 3.590839694656489e-05,
+      "loss": 1.6092,
+      "mean_token_accuracy": 0.6845578849315643,
+      "num_tokens": 3140574.0,
+      "step": 2790
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 1.9541523456573486,
+      "learning_rate": 3.5297709923664124e-05,
+      "loss": 1.6245,
+      "mean_token_accuracy": 0.6867643877863884,
+      "num_tokens": 3151937.0,
+      "step": 2800
+    },
+    {
+      "epoch": 2.488888888888889,
+      "eval_loss": 1.8869248628616333,
+      "eval_mean_token_accuracy": 0.6508636207580566,
+      "eval_num_tokens": 3151937.0,
+      "eval_runtime": 46.9872,
+      "eval_samples_per_second": 21.282,
+      "eval_steps_per_second": 10.641,
+      "step": 2800
+    },
+    {
+      "epoch": 2.497777777777778,
+      "grad_norm": 2.006448984146118,
+      "learning_rate": 3.468702290076336e-05,
+      "loss": 1.6458,
+      "mean_token_accuracy": 0.6835160732269288,
+      "num_tokens": 3163343.0,
+      "step": 2810
+    },
+    {
+      "epoch": 2.506666666666667,
+      "grad_norm": 2.0644562244415283,
+      "learning_rate": 3.4076335877862595e-05,
+      "loss": 1.5841,
+      "mean_token_accuracy": 0.699130979180336,
+      "num_tokens": 3174278.0,
+      "step": 2820
+    },
+    {
+      "epoch": 2.5155555555555553,
+      "grad_norm": 2.5352766513824463,
+      "learning_rate": 3.346564885496183e-05,
+      "loss": 1.6411,
+      "mean_token_accuracy": 0.687686163187027,
+      "num_tokens": 3185529.0,
+      "step": 2830
+    },
+    {
+      "epoch": 2.5244444444444447,
+      "grad_norm": 2.2506706714630127,
+      "learning_rate": 3.2854961832061074e-05,
+      "loss": 1.5334,
+      "mean_token_accuracy": 0.7042266175150871,
+      "num_tokens": 3196422.0,
+      "step": 2840
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 2.038456439971924,
+      "learning_rate": 3.224427480916031e-05,
+      "loss": 1.5226,
+      "mean_token_accuracy": 0.7002356797456741,
+      "num_tokens": 3207640.0,
+      "step": 2850
+    },
+    {
+      "epoch": 2.542222222222222,
+      "grad_norm": 2.0818448066711426,
+      "learning_rate": 3.1633587786259545e-05,
+      "loss": 1.5136,
+      "mean_token_accuracy": 0.7040936380624772,
+      "num_tokens": 3218742.0,
+      "step": 2860
+    },
+    {
+      "epoch": 2.551111111111111,
+      "grad_norm": 1.9810820817947388,
+      "learning_rate": 3.102290076335878e-05,
+      "loss": 1.6515,
+      "mean_token_accuracy": 0.6826088905334473,
+      "num_tokens": 3230062.0,
+      "step": 2870
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 2.1830689907073975,
+      "learning_rate": 3.0412213740458017e-05,
+      "loss": 1.5792,
+      "mean_token_accuracy": 0.699496129155159,
+      "num_tokens": 3240533.0,
+      "step": 2880
+    },
+    {
+      "epoch": 2.568888888888889,
+      "grad_norm": 2.101184368133545,
+      "learning_rate": 2.9801526717557253e-05,
+      "loss": 1.6538,
+      "mean_token_accuracy": 0.6724523141980171,
+      "num_tokens": 3252476.0,
+      "step": 2890
+    },
+    {
+      "epoch": 2.5777777777777775,
+      "grad_norm": 2.021524429321289,
+      "learning_rate": 2.9190839694656492e-05,
+      "loss": 1.6146,
+      "mean_token_accuracy": 0.6886414483189582,
+      "num_tokens": 3263799.0,
+      "step": 2900
+    },
+    {
+      "epoch": 2.586666666666667,
+      "grad_norm": 1.9668735265731812,
+      "learning_rate": 2.8580152671755728e-05,
+      "loss": 1.6477,
+      "mean_token_accuracy": 0.678925508260727,
+      "num_tokens": 3275511.0,
+      "step": 2910
+    },
+    {
+      "epoch": 2.5955555555555554,
+      "grad_norm": 2.088491201400757,
+      "learning_rate": 2.7969465648854964e-05,
+      "loss": 1.6265,
+      "mean_token_accuracy": 0.6857595339417457,
+      "num_tokens": 3286752.0,
+      "step": 2920
+    },
+    {
+      "epoch": 2.6044444444444443,
+      "grad_norm": 2.0536880493164062,
+      "learning_rate": 2.73587786259542e-05,
+      "loss": 1.66,
+      "mean_token_accuracy": 0.681273227930069,
+      "num_tokens": 3297945.0,
+      "step": 2930
+    },
+    {
+      "epoch": 2.6133333333333333,
+      "grad_norm": 2.0063817501068115,
+      "learning_rate": 2.674809160305344e-05,
+      "loss": 1.5102,
+      "mean_token_accuracy": 0.7025244757533073,
+      "num_tokens": 3309112.0,
+      "step": 2940
+    },
+    {
+      "epoch": 2.6222222222222222,
+      "grad_norm": 1.9980206489562988,
+      "learning_rate": 2.6137404580152675e-05,
+      "loss": 1.5142,
+      "mean_token_accuracy": 0.7049572348594666,
+      "num_tokens": 3320544.0,
+      "step": 2950
+    },
+    {
+      "epoch": 2.631111111111111,
+      "grad_norm": 2.1506435871124268,
+      "learning_rate": 2.552671755725191e-05,
+      "loss": 1.5826,
+      "mean_token_accuracy": 0.694467018544674,
+      "num_tokens": 3331309.0,
+      "step": 2960
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.9890793561935425,
+      "learning_rate": 2.4916030534351147e-05,
+      "loss": 1.5631,
+      "mean_token_accuracy": 0.6945617944002151,
+      "num_tokens": 3343068.0,
+      "step": 2970
+    },
+    {
+      "epoch": 2.648888888888889,
+      "grad_norm": 2.1102676391601562,
+      "learning_rate": 2.4305343511450383e-05,
+      "loss": 1.6145,
+      "mean_token_accuracy": 0.6866093754768372,
+      "num_tokens": 3354691.0,
+      "step": 2980
+    },
+    {
+      "epoch": 2.6577777777777776,
+      "grad_norm": 2.2881674766540527,
+      "learning_rate": 2.369465648854962e-05,
+      "loss": 1.5796,
+      "mean_token_accuracy": 0.6961612686514854,
+      "num_tokens": 3365512.0,
+      "step": 2990
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.973838210105896,
+      "learning_rate": 2.3083969465648854e-05,
+      "loss": 1.5456,
+      "mean_token_accuracy": 0.703473174571991,
+      "num_tokens": 3376406.0,
+      "step": 3000
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "eval_loss": 1.881131649017334,
+      "eval_mean_token_accuracy": 0.6518214672803879,
+      "eval_num_tokens": 3376406.0,
+      "eval_runtime": 47.794,
+      "eval_samples_per_second": 20.923,
+      "eval_steps_per_second": 10.462,
+      "step": 3000
+    },
+    {
+      "epoch": 2.6755555555555555,
+      "grad_norm": 1.9779133796691895,
+      "learning_rate": 2.2473282442748094e-05,
+      "loss": 1.6538,
+      "mean_token_accuracy": 0.6778925880789757,
+      "num_tokens": 3388024.0,
+      "step": 3010
+    },
+    {
+      "epoch": 2.6844444444444444,
+      "grad_norm": 1.848136305809021,
+      "learning_rate": 2.186259541984733e-05,
+      "loss": 1.5608,
+      "mean_token_accuracy": 0.6985713213682174,
+      "num_tokens": 3399547.0,
+      "step": 3020
+    },
+    {
+      "epoch": 2.6933333333333334,
+      "grad_norm": 2.101651191711426,
+      "learning_rate": 2.1251908396946565e-05,
+      "loss": 1.5501,
+      "mean_token_accuracy": 0.6979974433779716,
+      "num_tokens": 3410179.0,
+      "step": 3030
+    },
+    {
+      "epoch": 2.7022222222222223,
+      "grad_norm": 1.8398933410644531,
+      "learning_rate": 2.06412213740458e-05,
+      "loss": 1.5843,
+      "mean_token_accuracy": 0.6883544474840164,
+      "num_tokens": 3421454.0,
+      "step": 3040
+    },
+    {
+      "epoch": 2.7111111111111112,
+      "grad_norm": 2.011132001876831,
+      "learning_rate": 2.003053435114504e-05,
+      "loss": 1.6012,
+      "mean_token_accuracy": 0.6917843446135521,
+      "num_tokens": 3432951.0,
+      "step": 3050
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 2.005140542984009,
+      "learning_rate": 1.9419847328244276e-05,
+      "loss": 1.5421,
+      "mean_token_accuracy": 0.6976893007755279,
+      "num_tokens": 3444007.0,
+      "step": 3060
+    },
+    {
+      "epoch": 2.728888888888889,
+      "grad_norm": 2.146664619445801,
+      "learning_rate": 1.8809160305343512e-05,
+      "loss": 1.5799,
+      "mean_token_accuracy": 0.6956974431872368,
+      "num_tokens": 3455510.0,
+      "step": 3070
+    },
+    {
+      "epoch": 2.7377777777777776,
+      "grad_norm": 2.0788283348083496,
+      "learning_rate": 1.8198473282442748e-05,
+      "loss": 1.6043,
+      "mean_token_accuracy": 0.6913327068090439,
+      "num_tokens": 3466684.0,
+      "step": 3080
+    },
+    {
+      "epoch": 2.7466666666666666,
+      "grad_norm": 1.8829123973846436,
+      "learning_rate": 1.7587786259541984e-05,
+      "loss": 1.5649,
+      "mean_token_accuracy": 0.6947105377912521,
+      "num_tokens": 3477804.0,
+      "step": 3090
+    },
+    {
+      "epoch": 2.7555555555555555,
+      "grad_norm": 1.9475817680358887,
+      "learning_rate": 1.6977099236641223e-05,
+      "loss": 1.5568,
+      "mean_token_accuracy": 0.7034636497497558,
+      "num_tokens": 3488846.0,
+      "step": 3100
+    },
+    {
+      "epoch": 2.7644444444444445,
+      "grad_norm": 2.098478317260742,
+      "learning_rate": 1.636641221374046e-05,
+      "loss": 1.5575,
+      "mean_token_accuracy": 0.7053634539246559,
+      "num_tokens": 3499405.0,
+      "step": 3110
+    },
+    {
+      "epoch": 2.7733333333333334,
+      "grad_norm": 2.041572093963623,
+      "learning_rate": 1.5755725190839695e-05,
+      "loss": 1.619,
+      "mean_token_accuracy": 0.6887963160872459,
+      "num_tokens": 3511004.0,
+      "step": 3120
+    },
+    {
+      "epoch": 2.7822222222222224,
+      "grad_norm": 2.0892608165740967,
+      "learning_rate": 1.5145038167938933e-05,
+      "loss": 1.55,
+      "mean_token_accuracy": 0.6963776037096977,
+      "num_tokens": 3521755.0,
+      "step": 3130
+    },
+    {
+      "epoch": 2.7911111111111113,
+      "grad_norm": 1.9754984378814697,
+      "learning_rate": 1.4534351145038168e-05,
+      "loss": 1.5459,
+      "mean_token_accuracy": 0.7077917411923409,
+      "num_tokens": 3532621.0,
+      "step": 3140
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.9490447044372559,
+      "learning_rate": 1.3923664122137406e-05,
+      "loss": 1.6047,
+      "mean_token_accuracy": 0.6932125955820083,
+      "num_tokens": 3543418.0,
+      "step": 3150
+    },
+    {
+      "epoch": 2.8088888888888888,
+      "grad_norm": 2.12741756439209,
+      "learning_rate": 1.3312977099236642e-05,
+      "loss": 1.6336,
+      "mean_token_accuracy": 0.6868860185146332,
+      "num_tokens": 3555172.0,
+      "step": 3160
+    },
+    {
+      "epoch": 2.8177777777777777,
+      "grad_norm": 1.9473916292190552,
+      "learning_rate": 1.270229007633588e-05,
+      "loss": 1.5765,
+      "mean_token_accuracy": 0.696508777141571,
+      "num_tokens": 3565975.0,
+      "step": 3170
+    },
+    {
+      "epoch": 2.8266666666666667,
+      "grad_norm": 2.065030336380005,
+      "learning_rate": 1.2091603053435115e-05,
+      "loss": 1.6127,
+      "mean_token_accuracy": 0.6915735498070716,
+      "num_tokens": 3578154.0,
+      "step": 3180
+    },
+    {
+      "epoch": 2.8355555555555556,
+      "grad_norm": 2.1202714443206787,
+      "learning_rate": 1.1480916030534351e-05,
+      "loss": 1.5786,
+      "mean_token_accuracy": 0.702069939672947,
+      "num_tokens": 3589470.0,
+      "step": 3190
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 2.081028699874878,
+      "learning_rate": 1.0870229007633589e-05,
+      "loss": 1.6146,
+      "mean_token_accuracy": 0.6874286815524101,
+      "num_tokens": 3600489.0,
+      "step": 3200
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "eval_loss": 1.8764336109161377,
+      "eval_mean_token_accuracy": 0.6531118412017822,
+      "eval_num_tokens": 3600489.0,
+      "eval_runtime": 47.0874,
+      "eval_samples_per_second": 21.237,
+      "eval_steps_per_second": 10.619,
+      "step": 3200
+    },
+    {
+      "epoch": 2.8533333333333335,
+      "grad_norm": 2.002845048904419,
+      "learning_rate": 1.0259541984732825e-05,
+      "loss": 1.5998,
+      "mean_token_accuracy": 0.6930819883942604,
+      "num_tokens": 3611438.0,
+      "step": 3210
+    },
+    {
+      "epoch": 2.862222222222222,
+      "grad_norm": 1.967205286026001,
+      "learning_rate": 9.648854961832062e-06,
+      "loss": 1.5121,
+      "mean_token_accuracy": 0.7083013087511063,
+      "num_tokens": 3622326.0,
+      "step": 3220
+    },
+    {
+      "epoch": 2.871111111111111,
+      "grad_norm": 1.9093670845031738,
+      "learning_rate": 9.038167938931298e-06,
+      "loss": 1.5712,
+      "mean_token_accuracy": 0.6914584785699844,
+      "num_tokens": 3633132.0,
+      "step": 3230
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 2.0666589736938477,
+      "learning_rate": 8.427480916030536e-06,
+      "loss": 1.6203,
+      "mean_token_accuracy": 0.6882967233657837,
+      "num_tokens": 3644569.0,
+      "step": 3240
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 2.0188019275665283,
+      "learning_rate": 7.816793893129771e-06,
+      "loss": 1.5133,
+      "mean_token_accuracy": 0.7055545896291733,
+      "num_tokens": 3655650.0,
+      "step": 3250
+    },
+    {
+      "epoch": 2.897777777777778,
+      "grad_norm": 1.9436832666397095,
+      "learning_rate": 7.206106870229008e-06,
+      "loss": 1.5754,
+      "mean_token_accuracy": 0.6883370772004127,
+      "num_tokens": 3667338.0,
+      "step": 3260
+    },
+    {
+      "epoch": 2.9066666666666667,
+      "grad_norm": 1.960017442703247,
+      "learning_rate": 6.595419847328245e-06,
+      "loss": 1.6513,
+      "mean_token_accuracy": 0.6853567749261856,
+      "num_tokens": 3678543.0,
+      "step": 3270
+    },
+    {
+      "epoch": 2.9155555555555557,
+      "grad_norm": 1.8537602424621582,
+      "learning_rate": 5.984732824427481e-06,
+      "loss": 1.6711,
+      "mean_token_accuracy": 0.6820794567465782,
+      "num_tokens": 3690401.0,
+      "step": 3280
+    },
+    {
+      "epoch": 2.924444444444444,
+      "grad_norm": 1.9544005393981934,
+      "learning_rate": 5.3740458015267174e-06,
+      "loss": 1.5983,
+      "mean_token_accuracy": 0.6836786240339279,
+      "num_tokens": 3702001.0,
+      "step": 3290
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 2.035642147064209,
+      "learning_rate": 4.763358778625954e-06,
+      "loss": 1.6383,
+      "mean_token_accuracy": 0.6839755535125732,
+      "num_tokens": 3713114.0,
+      "step": 3300
+    },
+    {
+      "epoch": 2.942222222222222,
+      "grad_norm": 1.863014578819275,
+      "learning_rate": 4.152671755725191e-06,
+      "loss": 1.6363,
+      "mean_token_accuracy": 0.6912973523139954,
+      "num_tokens": 3724432.0,
+      "step": 3310
+    },
+    {
+      "epoch": 2.951111111111111,
+      "grad_norm": 2.1031157970428467,
+      "learning_rate": 3.541984732824428e-06,
+      "loss": 1.6434,
+      "mean_token_accuracy": 0.6855254426598549,
+      "num_tokens": 3735522.0,
+      "step": 3320
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 1.9777454137802124,
+      "learning_rate": 2.9312977099236643e-06,
+      "loss": 1.6118,
+      "mean_token_accuracy": 0.6878430411219597,
+      "num_tokens": 3746892.0,
+      "step": 3330
+    },
+    {
+      "epoch": 2.968888888888889,
+      "grad_norm": 1.947704553604126,
+      "learning_rate": 2.320610687022901e-06,
+      "loss": 1.6083,
+      "mean_token_accuracy": 0.6893500313162804,
+      "num_tokens": 3757984.0,
+      "step": 3340
+    },
+    {
+      "epoch": 2.977777777777778,
+      "grad_norm": 2.1452696323394775,
+      "learning_rate": 1.7099236641221375e-06,
+      "loss": 1.5432,
+      "mean_token_accuracy": 0.699726614356041,
+      "num_tokens": 3768945.0,
+      "step": 3350
+    },
+    {
+      "epoch": 2.986666666666667,
+      "grad_norm": 1.9867252111434937,
+      "learning_rate": 1.099236641221374e-06,
+      "loss": 1.6106,
+      "mean_token_accuracy": 0.6885504856705665,
+      "num_tokens": 3780272.0,
+      "step": 3360
+    },
+    {
+      "epoch": 2.9955555555555557,
+      "grad_norm": 2.084091901779175,
+      "learning_rate": 4.885496183206107e-07,
+      "loss": 1.6304,
+      "mean_token_accuracy": 0.6875804170966149,
+      "num_tokens": 3791870.0,
+      "step": 3370
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2042984005197824e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3375/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7dcfbb520eaa72697f1d45b91e159189ecefb58152a35a5fa5a95eb7d53aa9
+size 5624

special_tokens_map.json

@@ -0,0 +1,86 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endofturn|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,501 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|_unuse_missing_100256|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<|_unuse_missing_100261|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<|_unuse_missing_100262|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<|_unuse_missing_100263|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|_unuse_missing_100264|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|_unuse_missing_100265|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|_unuse_missing_100266|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|_unuse_missing_100267|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|_unuse_missing_100268|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|_unuse_missing_100269|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<|_unuse_missing_100270|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<|_unuse_missing_100271|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<|stop|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<|endofturn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110491": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110492": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110493": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110494": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110495": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110496": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110497": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110498": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110499": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110500": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110501": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110502": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110503": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110504": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110505": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110506": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110507": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110508": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110509": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110510": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110511": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110512": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110513": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110514": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110515": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110516": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110517": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110518": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110519": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110520": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110521": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110522": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "110523": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|stop|>",
+    "<|endofturn|>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endofturn|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7dcfbb520eaa72697f1d45b91e159189ecefb58152a35a5fa5a95eb7d53aa9
+size 5624