Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-1386/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-462/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-924/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,202 @@
 ---
-license: openrail
+library_name: peft
+base_model: google/gemma-7b
 ---
+
+# 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 0.8.2

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 6,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58577a3150c0f4bdfa14263e69c47f6818dc0475cfdec122fd45bd7338b422d4
+size 37555048

checkpoint-1386/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-7b
+---
+
+# 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 0.8.2

checkpoint-1386/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 6,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-1386/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58577a3150c0f4bdfa14263e69c47f6818dc0475cfdec122fd45bd7338b422d4
+size 37555048

checkpoint-1386/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3394c63853ad2cd991f8c90a2df2e761e4e5db92a95c7f00f511258e9e9d9b09
+size 75341034

checkpoint-1386/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7273dacfc500b8c56f80aeded3995f9a6bcf45e05d3b62cf4481b75966865f44
+size 14244

checkpoint-1386/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:237814caa6cb88953c1896aef7b5d4120ff5268c8f006284225db712de184866
+size 1064

checkpoint-1386/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1386/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
+size 17477473

checkpoint-1386/tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1386/trainer_state.json

@@ -0,0 +1,987 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1386,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.875,
+      "learning_rate": 0.0002,
+      "loss": 18.0666,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 8.625,
+      "learning_rate": 0.0002,
+      "loss": 11.9963,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.84375,
+      "learning_rate": 0.0002,
+      "loss": 6.0667,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.375,
+      "learning_rate": 0.0002,
+      "loss": 2.4769,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.0002,
+      "loss": 2.2233,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.0002,
+      "loss": 2.1739,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 3.375,
+      "learning_rate": 0.0002,
+      "loss": 2.0811,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 4.0,
+      "learning_rate": 0.0002,
+      "loss": 1.9928,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.4140625,
+      "learning_rate": 0.0002,
+      "loss": 1.9649,
+      "step": 90
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.0002,
+      "loss": 1.9645,
+      "step": 100
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.0002,
+      "loss": 1.9812,
+      "step": 110
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.5546875,
+      "learning_rate": 0.0002,
+      "loss": 1.9106,
+      "step": 120
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.984375,
+      "learning_rate": 0.0002,
+      "loss": 1.8943,
+      "step": 130
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.0002,
+      "loss": 1.9205,
+      "step": 140
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.234375,
+      "learning_rate": 0.0002,
+      "loss": 1.9445,
+      "step": 150
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.0390625,
+      "learning_rate": 0.0002,
+      "loss": 1.8882,
+      "step": 160
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 2.984375,
+      "learning_rate": 0.0002,
+      "loss": 1.8806,
+      "step": 170
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 2.46875,
+      "learning_rate": 0.0002,
+      "loss": 1.8692,
+      "step": 180
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.4375,
+      "learning_rate": 0.0002,
+      "loss": 1.8291,
+      "step": 190
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.515625,
+      "learning_rate": 0.0002,
+      "loss": 1.8069,
+      "step": 200
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 2.671875,
+      "learning_rate": 0.0002,
+      "loss": 1.8406,
+      "step": 210
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.625,
+      "learning_rate": 0.0002,
+      "loss": 1.8694,
+      "step": 220
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.8671875,
+      "learning_rate": 0.0002,
+      "loss": 1.821,
+      "step": 230
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.03125,
+      "learning_rate": 0.0002,
+      "loss": 1.8243,
+      "step": 240
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0002,
+      "loss": 1.7678,
+      "step": 250
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.0,
+      "learning_rate": 0.0002,
+      "loss": 1.8301,
+      "step": 260
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.0002,
+      "loss": 1.8845,
+      "step": 270
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.078125,
+      "learning_rate": 0.0002,
+      "loss": 1.8901,
+      "step": 280
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.015625,
+      "learning_rate": 0.0002,
+      "loss": 1.8198,
+      "step": 290
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.0002,
+      "loss": 1.7615,
+      "step": 300
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.0002,
+      "loss": 1.8717,
+      "step": 310
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.515625,
+      "learning_rate": 0.0002,
+      "loss": 1.7862,
+      "step": 320
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.6796875,
+      "learning_rate": 0.0002,
+      "loss": 1.8674,
+      "step": 330
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.0002,
+      "loss": 1.822,
+      "step": 340
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.921875,
+      "learning_rate": 0.0002,
+      "loss": 1.7834,
+      "step": 350
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.4921875,
+      "learning_rate": 0.0002,
+      "loss": 1.8157,
+      "step": 360
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.0002,
+      "loss": 1.7164,
+      "step": 370
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.875,
+      "learning_rate": 0.0002,
+      "loss": 1.835,
+      "step": 380
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.0002,
+      "loss": 1.7927,
+      "step": 390
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.8046875,
+      "learning_rate": 0.0002,
+      "loss": 1.7038,
+      "step": 400
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.0002,
+      "loss": 1.7914,
+      "step": 410
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 2.921875,
+      "learning_rate": 0.0002,
+      "loss": 1.7892,
+      "step": 420
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.0002,
+      "loss": 1.7335,
+      "step": 430
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.453125,
+      "learning_rate": 0.0002,
+      "loss": 1.8013,
+      "step": 440
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.5078125,
+      "learning_rate": 0.0002,
+      "loss": 1.7118,
+      "step": 450
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4140625,
+      "learning_rate": 0.0002,
+      "loss": 1.8202,
+      "step": 460
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 2.265625,
+      "learning_rate": 0.0002,
+      "loss": 1.7011,
+      "step": 470
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0002,
+      "loss": 1.6769,
+      "step": 480
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 1.1015625,
+      "learning_rate": 0.0002,
+      "loss": 1.6393,
+      "step": 490
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 1.25,
+      "learning_rate": 0.0002,
+      "loss": 1.6685,
+      "step": 500
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0002,
+      "loss": 1.665,
+      "step": 510
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 2.046875,
+      "learning_rate": 0.0002,
+      "loss": 1.6446,
+      "step": 520
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.0002,
+      "loss": 1.5743,
+      "step": 530
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.9765625,
+      "learning_rate": 0.0002,
+      "loss": 1.6622,
+      "step": 540
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 1.125,
+      "learning_rate": 0.0002,
+      "loss": 1.5741,
+      "step": 550
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.0002,
+      "loss": 1.6434,
+      "step": 560
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0002,
+      "loss": 1.6343,
+      "step": 570
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.0002,
+      "loss": 1.662,
+      "step": 580
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.28125,
+      "learning_rate": 0.0002,
+      "loss": 1.6246,
+      "step": 590
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.96875,
+      "learning_rate": 0.0002,
+      "loss": 1.614,
+      "step": 600
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 2.703125,
+      "learning_rate": 0.0002,
+      "loss": 1.6817,
+      "step": 610
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.0002,
+      "loss": 1.6343,
+      "step": 620
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 1.578125,
+      "learning_rate": 0.0002,
+      "loss": 1.6237,
+      "step": 630
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.97265625,
+      "learning_rate": 0.0002,
+      "loss": 1.6367,
+      "step": 640
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.0002,
+      "loss": 1.6304,
+      "step": 650
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 1.09375,
+      "learning_rate": 0.0002,
+      "loss": 1.5319,
+      "step": 660
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.921875,
+      "learning_rate": 0.0002,
+      "loss": 1.643,
+      "step": 670
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.0002,
+      "loss": 1.6247,
+      "step": 680
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 1.6796875,
+      "learning_rate": 0.0002,
+      "loss": 1.5913,
+      "step": 690
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0002,
+      "loss": 1.6415,
+      "step": 700
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.0002,
+      "loss": 1.636,
+      "step": 710
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 1.28125,
+      "learning_rate": 0.0002,
+      "loss": 1.6304,
+      "step": 720
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0002,
+      "loss": 1.6156,
+      "step": 730
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.0002,
+      "loss": 1.5906,
+      "step": 740
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.0002,
+      "loss": 1.5717,
+      "step": 750
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 1.25,
+      "learning_rate": 0.0002,
+      "loss": 1.6747,
+      "step": 760
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0002,
+      "loss": 1.6095,
+      "step": 770
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 1.109375,
+      "learning_rate": 0.0002,
+      "loss": 1.6571,
+      "step": 780
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 1.5,
+      "learning_rate": 0.0002,
+      "loss": 1.5913,
+      "step": 790
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0002,
+      "loss": 1.592,
+      "step": 800
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 1.7578125,
+      "learning_rate": 0.0002,
+      "loss": 1.5279,
+      "step": 810
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.0002,
+      "loss": 1.6599,
+      "step": 820
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.1015625,
+      "learning_rate": 0.0002,
+      "loss": 1.6947,
+      "step": 830
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.0002,
+      "loss": 1.608,
+      "step": 840
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 1.4140625,
+      "learning_rate": 0.0002,
+      "loss": 1.6716,
+      "step": 850
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 1.4453125,
+      "learning_rate": 0.0002,
+      "loss": 1.6847,
+      "step": 860
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 1.203125,
+      "learning_rate": 0.0002,
+      "loss": 1.5283,
+      "step": 870
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.0002,
+      "loss": 1.6639,
+      "step": 880
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 1.0625,
+      "learning_rate": 0.0002,
+      "loss": 1.6154,
+      "step": 890
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.0002,
+      "loss": 1.6248,
+      "step": 900
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.0002,
+      "loss": 1.5525,
+      "step": 910
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 1.8203125,
+      "learning_rate": 0.0002,
+      "loss": 1.5069,
+      "step": 920
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 1.296875,
+      "learning_rate": 0.0002,
+      "loss": 1.5104,
+      "step": 930
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 1.1484375,
+      "learning_rate": 0.0002,
+      "loss": 1.3058,
+      "step": 940
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 1.25,
+      "learning_rate": 0.0002,
+      "loss": 1.4888,
+      "step": 950
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.0234375,
+      "learning_rate": 0.0002,
+      "loss": 1.3972,
+      "step": 960
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 1.375,
+      "learning_rate": 0.0002,
+      "loss": 1.4524,
+      "step": 970
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0002,
+      "loss": 1.4534,
+      "step": 980
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 1.6484375,
+      "learning_rate": 0.0002,
+      "loss": 1.4601,
+      "step": 990
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.0002,
+      "loss": 1.4352,
+      "step": 1000
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.0002,
+      "loss": 1.4183,
+      "step": 1010
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 1.1796875,
+      "learning_rate": 0.0002,
+      "loss": 1.3654,
+      "step": 1020
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 1.453125,
+      "learning_rate": 0.0002,
+      "loss": 1.4216,
+      "step": 1030
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 1.3359375,
+      "learning_rate": 0.0002,
+      "loss": 1.3554,
+      "step": 1040
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 2.5,
+      "learning_rate": 0.0002,
+      "loss": 1.3716,
+      "step": 1050
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.0002,
+      "loss": 1.426,
+      "step": 1060
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 1.203125,
+      "learning_rate": 0.0002,
+      "loss": 1.4755,
+      "step": 1070
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 1.7578125,
+      "learning_rate": 0.0002,
+      "loss": 1.3976,
+      "step": 1080
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 1.140625,
+      "learning_rate": 0.0002,
+      "loss": 1.472,
+      "step": 1090
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 1.28125,
+      "learning_rate": 0.0002,
+      "loss": 1.461,
+      "step": 1100
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.0002,
+      "loss": 1.4307,
+      "step": 1110
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 1.625,
+      "learning_rate": 0.0002,
+      "loss": 1.4603,
+      "step": 1120
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 2.03125,
+      "learning_rate": 0.0002,
+      "loss": 1.573,
+      "step": 1130
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 1.984375,
+      "learning_rate": 0.0002,
+      "loss": 1.3899,
+      "step": 1140
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 1.3984375,
+      "learning_rate": 0.0002,
+      "loss": 1.463,
+      "step": 1150
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 1.296875,
+      "learning_rate": 0.0002,
+      "loss": 1.3866,
+      "step": 1160
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 1.125,
+      "learning_rate": 0.0002,
+      "loss": 1.3927,
+      "step": 1170
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 1.1484375,
+      "learning_rate": 0.0002,
+      "loss": 1.3956,
+      "step": 1180
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 8.75,
+      "learning_rate": 0.0002,
+      "loss": 1.335,
+      "step": 1190
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 1.1796875,
+      "learning_rate": 0.0002,
+      "loss": 1.4117,
+      "step": 1200
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 1.28125,
+      "learning_rate": 0.0002,
+      "loss": 1.385,
+      "step": 1210
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.25,
+      "learning_rate": 0.0002,
+      "loss": 1.414,
+      "step": 1220
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.0002,
+      "loss": 1.3831,
+      "step": 1230
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.0002,
+      "loss": 1.5191,
+      "step": 1240
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 1.453125,
+      "learning_rate": 0.0002,
+      "loss": 1.3568,
+      "step": 1250
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 1.5078125,
+      "learning_rate": 0.0002,
+      "loss": 1.4097,
+      "step": 1260
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0002,
+      "loss": 1.4798,
+      "step": 1270
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.0002,
+      "loss": 1.3602,
+      "step": 1280
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 1.671875,
+      "learning_rate": 0.0002,
+      "loss": 1.4344,
+      "step": 1290
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 1.40625,
+      "learning_rate": 0.0002,
+      "loss": 1.4734,
+      "step": 1300
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 1.1796875,
+      "learning_rate": 0.0002,
+      "loss": 1.4536,
+      "step": 1310
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 1.28125,
+      "learning_rate": 0.0002,
+      "loss": 1.3822,
+      "step": 1320
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0002,
+      "loss": 1.4099,
+      "step": 1330
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 1.09375,
+      "learning_rate": 0.0002,
+      "loss": 1.4668,
+      "step": 1340
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 1.75,
+      "learning_rate": 0.0002,
+      "loss": 1.4382,
+      "step": 1350
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 1.8515625,
+      "learning_rate": 0.0002,
+      "loss": 1.4847,
+      "step": 1360
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0002,
+      "loss": 1.4274,
+      "step": 1370
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 1.9453125,
+      "learning_rate": 0.0002,
+      "loss": 1.4039,
+      "step": 1380
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1386,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3.907934746733445e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1386/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f8f1dde34a04f423ad4f7eeb4fdba148f7ccdbdfc912d7d21dfebe62086807
+size 4920

checkpoint-462/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-7b
+---
+
+# 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 0.8.2

checkpoint-462/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 6,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-462/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b4bd1618668b3178ace550b723b85944a7316ef680e57d763680820e2f9eb6d
+size 37555048

checkpoint-462/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe5108af8e51a3427c738fe01ea50acd381ad5a586057d268c24b4ace518363
+size 75341034

checkpoint-462/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8cef990eb72d2f788d0061daead5ea738eefd764c6018e7287f1a2d652208c
+size 14244

checkpoint-462/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e495bfa00beb945e3a55469ddbb1a99e945802d35bb39907e60c746dfcb9585
+size 1064

checkpoint-462/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-462/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
+size 17477473

checkpoint-462/tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-462/trainer_state.json

@@ -0,0 +1,343 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 462,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.875,
+      "learning_rate": 0.0002,
+      "loss": 18.0666,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 8.625,
+      "learning_rate": 0.0002,
+      "loss": 11.9963,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.84375,
+      "learning_rate": 0.0002,
+      "loss": 6.0667,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.375,
+      "learning_rate": 0.0002,
+      "loss": 2.4769,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.0002,
+      "loss": 2.2233,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.0002,
+      "loss": 2.1739,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 3.375,
+      "learning_rate": 0.0002,
+      "loss": 2.0811,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 4.0,
+      "learning_rate": 0.0002,
+      "loss": 1.9928,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.4140625,
+      "learning_rate": 0.0002,
+      "loss": 1.9649,
+      "step": 90
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.0002,
+      "loss": 1.9645,
+      "step": 100
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.0002,
+      "loss": 1.9812,
+      "step": 110
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.5546875,
+      "learning_rate": 0.0002,
+      "loss": 1.9106,
+      "step": 120
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.984375,
+      "learning_rate": 0.0002,
+      "loss": 1.8943,
+      "step": 130
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.0002,
+      "loss": 1.9205,
+      "step": 140
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.234375,
+      "learning_rate": 0.0002,
+      "loss": 1.9445,
+      "step": 150
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.0390625,
+      "learning_rate": 0.0002,
+      "loss": 1.8882,
+      "step": 160
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 2.984375,
+      "learning_rate": 0.0002,
+      "loss": 1.8806,
+      "step": 170
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 2.46875,
+      "learning_rate": 0.0002,
+      "loss": 1.8692,
+      "step": 180
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.4375,
+      "learning_rate": 0.0002,
+      "loss": 1.8291,
+      "step": 190
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.515625,
+      "learning_rate": 0.0002,
+      "loss": 1.8069,
+      "step": 200
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 2.671875,
+      "learning_rate": 0.0002,
+      "loss": 1.8406,
+      "step": 210
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.625,
+      "learning_rate": 0.0002,
+      "loss": 1.8694,
+      "step": 220
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.8671875,
+      "learning_rate": 0.0002,
+      "loss": 1.821,
+      "step": 230
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.03125,
+      "learning_rate": 0.0002,
+      "loss": 1.8243,
+      "step": 240
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0002,
+      "loss": 1.7678,
+      "step": 250
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.0,
+      "learning_rate": 0.0002,
+      "loss": 1.8301,
+      "step": 260
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.0002,
+      "loss": 1.8845,
+      "step": 270
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.078125,
+      "learning_rate": 0.0002,
+      "loss": 1.8901,
+      "step": 280
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.015625,
+      "learning_rate": 0.0002,
+      "loss": 1.8198,
+      "step": 290
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.0002,
+      "loss": 1.7615,
+      "step": 300
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.0002,
+      "loss": 1.8717,
+      "step": 310
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.515625,
+      "learning_rate": 0.0002,
+      "loss": 1.7862,
+      "step": 320
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.6796875,
+      "learning_rate": 0.0002,
+      "loss": 1.8674,
+      "step": 330
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.0002,
+      "loss": 1.822,
+      "step": 340
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.921875,
+      "learning_rate": 0.0002,
+      "loss": 1.7834,
+      "step": 350
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.4921875,
+      "learning_rate": 0.0002,
+      "loss": 1.8157,
+      "step": 360
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.0002,
+      "loss": 1.7164,
+      "step": 370
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.875,
+      "learning_rate": 0.0002,
+      "loss": 1.835,
+      "step": 380
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.0002,
+      "loss": 1.7927,
+      "step": 390
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.8046875,
+      "learning_rate": 0.0002,
+      "loss": 1.7038,
+      "step": 400
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.0002,
+      "loss": 1.7914,
+      "step": 410
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 2.921875,
+      "learning_rate": 0.0002,
+      "loss": 1.7892,
+      "step": 420
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.0002,
+      "loss": 1.7335,
+      "step": 430
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.453125,
+      "learning_rate": 0.0002,
+      "loss": 1.8013,
+      "step": 440
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.5078125,
+      "learning_rate": 0.0002,
+      "loss": 1.7118,
+      "step": 450
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4140625,
+      "learning_rate": 0.0002,
+      "loss": 1.8202,
+      "step": 460
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1386,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.302644915577815e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-462/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f8f1dde34a04f423ad4f7eeb4fdba148f7ccdbdfc912d7d21dfebe62086807
+size 4920

checkpoint-924/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-7b
+---
+
+# 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 0.8.2

checkpoint-924/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 6,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-924/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57bad846e721e291c982c1f9d74677411bc13b5a9d589ca901a4bbb2116c5a81
+size 37555048

checkpoint-924/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17500d3457b1c5d58ecfbf6911b203f841a6af4bb2afcc1e9a36c4178fe7bafd
+size 75341034

checkpoint-924/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21bde94e49f7e437c40bc500883ceb29ea382d4d259d7304717f083aac592c35
+size 14244

checkpoint-924/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35daf1defdc7953653c5c35a112176d49cddceb8294a5b758efa7b32550383c
+size 1064

checkpoint-924/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-924/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
+size 17477473

checkpoint-924/tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-924/trainer_state.json

@@ -0,0 +1,665 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 924,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.875,
+      "learning_rate": 0.0002,
+      "loss": 18.0666,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 8.625,
+      "learning_rate": 0.0002,
+      "loss": 11.9963,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.84375,
+      "learning_rate": 0.0002,
+      "loss": 6.0667,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.375,
+      "learning_rate": 0.0002,
+      "loss": 2.4769,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.0002,
+      "loss": 2.2233,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.0002,
+      "loss": 2.1739,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 3.375,
+      "learning_rate": 0.0002,
+      "loss": 2.0811,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 4.0,
+      "learning_rate": 0.0002,
+      "loss": 1.9928,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.4140625,
+      "learning_rate": 0.0002,
+      "loss": 1.9649,
+      "step": 90
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.0002,
+      "loss": 1.9645,
+      "step": 100
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.0002,
+      "loss": 1.9812,
+      "step": 110
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.5546875,
+      "learning_rate": 0.0002,
+      "loss": 1.9106,
+      "step": 120
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.984375,
+      "learning_rate": 0.0002,
+      "loss": 1.8943,
+      "step": 130
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.0002,
+      "loss": 1.9205,
+      "step": 140
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.234375,
+      "learning_rate": 0.0002,
+      "loss": 1.9445,
+      "step": 150
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.0390625,
+      "learning_rate": 0.0002,
+      "loss": 1.8882,
+      "step": 160
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 2.984375,
+      "learning_rate": 0.0002,
+      "loss": 1.8806,
+      "step": 170
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 2.46875,
+      "learning_rate": 0.0002,
+      "loss": 1.8692,
+      "step": 180
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.4375,
+      "learning_rate": 0.0002,
+      "loss": 1.8291,
+      "step": 190
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.515625,
+      "learning_rate": 0.0002,
+      "loss": 1.8069,
+      "step": 200
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 2.671875,
+      "learning_rate": 0.0002,
+      "loss": 1.8406,
+      "step": 210
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.625,
+      "learning_rate": 0.0002,
+      "loss": 1.8694,
+      "step": 220
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.8671875,
+      "learning_rate": 0.0002,
+      "loss": 1.821,
+      "step": 230
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.03125,
+      "learning_rate": 0.0002,
+      "loss": 1.8243,
+      "step": 240
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0002,
+      "loss": 1.7678,
+      "step": 250
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.0,
+      "learning_rate": 0.0002,
+      "loss": 1.8301,
+      "step": 260
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.0002,
+      "loss": 1.8845,
+      "step": 270
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.078125,
+      "learning_rate": 0.0002,
+      "loss": 1.8901,
+      "step": 280
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.015625,
+      "learning_rate": 0.0002,
+      "loss": 1.8198,
+      "step": 290
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.0002,
+      "loss": 1.7615,
+      "step": 300
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.0002,
+      "loss": 1.8717,
+      "step": 310
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.515625,
+      "learning_rate": 0.0002,
+      "loss": 1.7862,
+      "step": 320
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.6796875,
+      "learning_rate": 0.0002,
+      "loss": 1.8674,
+      "step": 330
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.0002,
+      "loss": 1.822,
+      "step": 340
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.921875,
+      "learning_rate": 0.0002,
+      "loss": 1.7834,
+      "step": 350
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.4921875,
+      "learning_rate": 0.0002,
+      "loss": 1.8157,
+      "step": 360
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.0002,
+      "loss": 1.7164,
+      "step": 370
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.875,
+      "learning_rate": 0.0002,
+      "loss": 1.835,
+      "step": 380
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.0002,
+      "loss": 1.7927,
+      "step": 390
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.8046875,
+      "learning_rate": 0.0002,
+      "loss": 1.7038,
+      "step": 400
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.0002,
+      "loss": 1.7914,
+      "step": 410
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 2.921875,
+      "learning_rate": 0.0002,
+      "loss": 1.7892,
+      "step": 420
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.0002,
+      "loss": 1.7335,
+      "step": 430
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.453125,
+      "learning_rate": 0.0002,
+      "loss": 1.8013,
+      "step": 440
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.5078125,
+      "learning_rate": 0.0002,
+      "loss": 1.7118,
+      "step": 450
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4140625,
+      "learning_rate": 0.0002,
+      "loss": 1.8202,
+      "step": 460
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 2.265625,
+      "learning_rate": 0.0002,
+      "loss": 1.7011,
+      "step": 470
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0002,
+      "loss": 1.6769,
+      "step": 480
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 1.1015625,
+      "learning_rate": 0.0002,
+      "loss": 1.6393,
+      "step": 490
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 1.25,
+      "learning_rate": 0.0002,
+      "loss": 1.6685,
+      "step": 500
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0002,
+      "loss": 1.665,
+      "step": 510
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 2.046875,
+      "learning_rate": 0.0002,
+      "loss": 1.6446,
+      "step": 520
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.0002,
+      "loss": 1.5743,
+      "step": 530
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.9765625,
+      "learning_rate": 0.0002,
+      "loss": 1.6622,
+      "step": 540
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 1.125,
+      "learning_rate": 0.0002,
+      "loss": 1.5741,
+      "step": 550
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.0002,
+      "loss": 1.6434,
+      "step": 560
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0002,
+      "loss": 1.6343,
+      "step": 570
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.0002,
+      "loss": 1.662,
+      "step": 580
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.28125,
+      "learning_rate": 0.0002,
+      "loss": 1.6246,
+      "step": 590
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.96875,
+      "learning_rate": 0.0002,
+      "loss": 1.614,
+      "step": 600
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 2.703125,
+      "learning_rate": 0.0002,
+      "loss": 1.6817,
+      "step": 610
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.0002,
+      "loss": 1.6343,
+      "step": 620
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 1.578125,
+      "learning_rate": 0.0002,
+      "loss": 1.6237,
+      "step": 630
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.97265625,
+      "learning_rate": 0.0002,
+      "loss": 1.6367,
+      "step": 640
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.0002,
+      "loss": 1.6304,
+      "step": 650
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 1.09375,
+      "learning_rate": 0.0002,
+      "loss": 1.5319,
+      "step": 660
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.921875,
+      "learning_rate": 0.0002,
+      "loss": 1.643,
+      "step": 670
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.0002,
+      "loss": 1.6247,
+      "step": 680
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 1.6796875,
+      "learning_rate": 0.0002,
+      "loss": 1.5913,
+      "step": 690
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0002,
+      "loss": 1.6415,
+      "step": 700
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.0002,
+      "loss": 1.636,
+      "step": 710
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 1.28125,
+      "learning_rate": 0.0002,
+      "loss": 1.6304,
+      "step": 720
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0002,
+      "loss": 1.6156,
+      "step": 730
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.0002,
+      "loss": 1.5906,
+      "step": 740
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.0002,
+      "loss": 1.5717,
+      "step": 750
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 1.25,
+      "learning_rate": 0.0002,
+      "loss": 1.6747,
+      "step": 760
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0002,
+      "loss": 1.6095,
+      "step": 770
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 1.109375,
+      "learning_rate": 0.0002,
+      "loss": 1.6571,
+      "step": 780
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 1.5,
+      "learning_rate": 0.0002,
+      "loss": 1.5913,
+      "step": 790
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0002,
+      "loss": 1.592,
+      "step": 800
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 1.7578125,
+      "learning_rate": 0.0002,
+      "loss": 1.5279,
+      "step": 810
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.0002,
+      "loss": 1.6599,
+      "step": 820
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.1015625,
+      "learning_rate": 0.0002,
+      "loss": 1.6947,
+      "step": 830
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.0002,
+      "loss": 1.608,
+      "step": 840
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 1.4140625,
+      "learning_rate": 0.0002,
+      "loss": 1.6716,
+      "step": 850
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 1.4453125,
+      "learning_rate": 0.0002,
+      "loss": 1.6847,
+      "step": 860
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 1.203125,
+      "learning_rate": 0.0002,
+      "loss": 1.5283,
+      "step": 870
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.0002,
+      "loss": 1.6639,
+      "step": 880
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 1.0625,
+      "learning_rate": 0.0002,
+      "loss": 1.6154,
+      "step": 890
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.0002,
+      "loss": 1.6248,
+      "step": 900
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.0002,
+      "loss": 1.5525,
+      "step": 910
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 1.8203125,
+      "learning_rate": 0.0002,
+      "loss": 1.5069,
+      "step": 920
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1386,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2.60528983115563e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-924/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f8f1dde34a04f423ad4f7eeb4fdba148f7ccdbdfc912d7d21dfebe62086807
+size 4920

runs/Mar07_05-20-13_66453cc17dea/events.out.tfevents.1709789011.66453cc17dea.427.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4eb6c92493db9ee046bacb48f3f88b6fd94618f3dbcc017e45b8b638138f60b
+size 34466

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
+size 17477473

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f8f1dde34a04f423ad4f7eeb4fdba148f7ccdbdfc912d7d21dfebe62086807
+size 4920