Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 checkpoint-189/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-750/tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "q_proj",
     "up_proj",
-    "k_proj",
-    "v_proj",
-    "gate_proj",
     "down_proj",
-    "q_proj"
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8824c005978df2676729c45a758b3d9ad7b62e8fa01d5eb2f0f94a63592ee291
+oid sha256:de3f743ee0d6156dbccd9a34d93ca37a8cb1445eff714cd40a1d71c2ba8b5b49
 size 147770496

checkpoint-500/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-1.5B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.0

checkpoint-500/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a19cd2ac1dff0f1fc639b4989d4f201e907f4c23234feb4d6a7c8a9254a715e6
+size 147770496

checkpoint-500/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-500/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f41f133cb09a3f513a95aff6f848c13bff2e219a95171b4bfba54917d345ae29
+size 295766331

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0fcd917f81c5da546d7df8067d9d78330a53d7b673bcb63d8fd9ea02536101
+size 14645

checkpoint-500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77569c2e850b04af982cc8c1389f1430851448915c593b69e5da36ce05b71d7
+size 1383

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96d05788156ac34450d3daabd7bddf7960db53ecb62c8e14504b610d18590687
+size 1465

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

checkpoint-500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,534 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.8118590474128723,
+      "epoch": 0.04,
+      "grad_norm": 0.05997199937701225,
+      "learning_rate": 7.82608695652174e-05,
+      "loss": 1.0028,
+      "mean_token_accuracy": 0.767544125020504,
+      "num_tokens": 327384.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.8525841124355793,
+      "epoch": 0.08,
+      "grad_norm": 0.09163825213909149,
+      "learning_rate": 0.00016521739130434784,
+      "loss": 0.8959,
+      "mean_token_accuracy": 0.7876047976315022,
+      "num_tokens": 582000.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.9385534837841988,
+      "epoch": 0.12,
+      "grad_norm": 0.11509037017822266,
+      "learning_rate": 0.00019996638918070336,
+      "loss": 0.918,
+      "mean_token_accuracy": 0.782110495865345,
+      "num_tokens": 745292.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.911478316783905,
+      "epoch": 0.16,
+      "grad_norm": 0.14333251118659973,
+      "learning_rate": 0.0001997610715447061,
+      "loss": 0.9173,
+      "mean_token_accuracy": 0.780673997104168,
+      "num_tokens": 843998.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.9255619779229164,
+      "epoch": 0.2,
+      "grad_norm": 0.37470874190330505,
+      "learning_rate": 0.0001993694918299864,
+      "loss": 0.9095,
+      "mean_token_accuracy": 0.7824992008507252,
+      "num_tokens": 886161.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.9085440292954445,
+      "epoch": 0.24,
+      "grad_norm": 0.06702009588479996,
+      "learning_rate": 0.00019879238114789373,
+      "loss": 0.9319,
+      "mean_token_accuracy": 0.7772408030927181,
+      "num_tokens": 1213472.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.8186310566961765,
+      "epoch": 0.28,
+      "grad_norm": 0.08344472944736481,
+      "learning_rate": 0.0001980308170112659,
+      "loss": 0.8226,
+      "mean_token_accuracy": 0.8009889200329781,
+      "num_tokens": 1468934.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.8451250180602073,
+      "epoch": 0.32,
+      "grad_norm": 0.10779275745153427,
+      "learning_rate": 0.0001970862213226244,
+      "loss": 0.836,
+      "mean_token_accuracy": 0.7983625620603562,
+      "num_tokens": 1633249.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.8599591284990311,
+      "epoch": 0.36,
+      "grad_norm": 0.15631401538848877,
+      "learning_rate": 0.00019596035771936592,
+      "loss": 0.8486,
+      "mean_token_accuracy": 0.7960575334727764,
+      "num_tokens": 1730768.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.876547134667635,
+      "epoch": 0.4,
+      "grad_norm": 0.3903079032897949,
+      "learning_rate": 0.00019465532828090735,
+      "loss": 0.8639,
+      "mean_token_accuracy": 0.7935161642730236,
+      "num_tokens": 1771280.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.9069034807384014,
+      "epoch": 0.44,
+      "grad_norm": 0.07801498472690582,
+      "learning_rate": 0.00019317356960393156,
+      "loss": 0.9173,
+      "mean_token_accuracy": 0.7792488023638725,
+      "num_tokens": 2098922.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.8098581977188587,
+      "epoch": 0.48,
+      "grad_norm": 0.08503358066082001,
+      "learning_rate": 0.00019151784825306205,
+      "loss": 0.8102,
+      "mean_token_accuracy": 0.8027891904115677,
+      "num_tokens": 2358277.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.8039502821862697,
+      "epoch": 0.52,
+      "grad_norm": 0.11073547601699829,
+      "learning_rate": 0.00018969125559546054,
+      "loss": 0.81,
+      "mean_token_accuracy": 0.8007699891924858,
+      "num_tokens": 2522737.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.8364543087780476,
+      "epoch": 0.56,
+      "grad_norm": 0.1541292369365692,
+      "learning_rate": 0.00018769720202899194,
+      "loss": 0.8251,
+      "mean_token_accuracy": 0.7973810255527496,
+      "num_tokens": 2621039.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.8665640391409397,
+      "epoch": 0.6,
+      "grad_norm": 0.3610881567001343,
+      "learning_rate": 0.00018553941061473218,
+      "loss": 0.8458,
+      "mean_token_accuracy": 0.7960383057594299,
+      "num_tokens": 2662897.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.8594730854034424,
+      "epoch": 0.64,
+      "grad_norm": 0.10022123903036118,
+      "learning_rate": 0.00018322191012570919,
+      "loss": 0.8785,
+      "mean_token_accuracy": 0.7877491846680641,
+      "num_tokens": 2990339.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.7944531835615635,
+      "epoch": 0.68,
+      "grad_norm": 0.10204905271530151,
+      "learning_rate": 0.0001807490275248539,
+      "loss": 0.7889,
+      "mean_token_accuracy": 0.8073874406516552,
+      "num_tokens": 3245518.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.8212005525827408,
+      "epoch": 0.72,
+      "grad_norm": 0.11545777320861816,
+      "learning_rate": 0.00017812537988620675,
+      "loss": 0.8253,
+      "mean_token_accuracy": 0.7982150033116341,
+      "num_tokens": 3404933.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.8301504630595445,
+      "epoch": 0.76,
+      "grad_norm": 0.17408080399036407,
+      "learning_rate": 0.00017535586577446276,
+      "loss": 0.8171,
+      "mean_token_accuracy": 0.8009781941771508,
+      "num_tokens": 3497564.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.81050028167665,
+      "epoch": 0.8,
+      "grad_norm": 0.35289013385772705,
+      "learning_rate": 0.00017244565609895074,
+      "loss": 0.7865,
+      "mean_token_accuracy": 0.8109133973717689,
+      "num_tokens": 3534086.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.837448638677597,
+      "epoch": 0.84,
+      "grad_norm": 0.08503283560276031,
+      "learning_rate": 0.00016940018445912272,
+      "loss": 0.8648,
+      "mean_token_accuracy": 0.7916912771761417,
+      "num_tokens": 3861579.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.7994868710637093,
+      "epoch": 0.88,
+      "grad_norm": 0.09771085530519485,
+      "learning_rate": 0.00016622513699957948,
+      "loss": 0.7858,
+      "mean_token_accuracy": 0.8064859353005887,
+      "num_tokens": 4119938.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.7886113189160824,
+      "epoch": 0.92,
+      "grad_norm": 0.12538443505764008,
+      "learning_rate": 0.00016292644179357336,
+      "loss": 0.798,
+      "mean_token_accuracy": 0.8042714856564999,
+      "num_tokens": 4283327.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.801911610364914,
+      "epoch": 0.96,
+      "grad_norm": 0.16356100142002106,
+      "learning_rate": 0.00015951025777481096,
+      "loss": 0.7861,
+      "mean_token_accuracy": 0.8082708492875099,
+      "num_tokens": 4379704.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.8030880324542522,
+      "epoch": 1.0,
+      "grad_norm": 0.2906339168548584,
+      "learning_rate": 0.00015598296323822024,
+      "loss": 0.7752,
+      "mean_token_accuracy": 0.8124107919633389,
+      "num_tokens": 4419741.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.8512323558330536,
+      "epoch": 1.04,
+      "grad_norm": 0.0769343450665474,
+      "learning_rate": 0.00015235114393115202,
+      "loss": 0.8714,
+      "mean_token_accuracy": 0.7885661020874977,
+      "num_tokens": 4747421.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.7640283957123757,
+      "epoch": 1.08,
+      "grad_norm": 0.09265792369842529,
+      "learning_rate": 0.0001486215807572515,
+      "loss": 0.7566,
+      "mean_token_accuracy": 0.8131284601986408,
+      "num_tokens": 5013839.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.7704206634312868,
+      "epoch": 1.12,
+      "grad_norm": 0.1475331336259842,
+      "learning_rate": 0.00014480123711595636,
+      "loss": 0.7635,
+      "mean_token_accuracy": 0.8108469642698765,
+      "num_tokens": 5183957.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.7694178409874439,
+      "epoch": 1.16,
+      "grad_norm": 0.17722958326339722,
+      "learning_rate": 0.0001408972459012606,
+      "loss": 0.7517,
+      "mean_token_accuracy": 0.8132740050554276,
+      "num_tokens": 5284281.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.6807048697024584,
+      "epoch": 1.2,
+      "grad_norm": 0.358539342880249,
+      "learning_rate": 0.00013691689618401835,
+      "loss": 0.6343,
+      "mean_token_accuracy": 0.8411179468035698,
+      "num_tokens": 5325202.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.8084883399307727,
+      "epoch": 1.24,
+      "grad_norm": 0.09149754047393799,
+      "learning_rate": 0.00013286761960265214,
+      "loss": 0.8618,
+      "mean_token_accuracy": 0.7917799115180969,
+      "num_tokens": 5652739.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.7762876857072115,
+      "epoch": 1.28,
+      "grad_norm": 0.09918583184480667,
+      "learning_rate": 0.00012875697648767663,
+      "loss": 0.7423,
+      "mean_token_accuracy": 0.8153080217540264,
+      "num_tokens": 5909823.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.7344005398452282,
+      "epoch": 1.32,
+      "grad_norm": 0.13750393688678741,
+      "learning_rate": 0.00012459264174594304,
+      "loss": 0.7361,
+      "mean_token_accuracy": 0.8177524119615555,
+      "num_tokens": 6071844.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.702471449971199,
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.17901532351970673,
+      "learning_rate": 0.00012038239053096038,
+      "loss": 0.69,
+      "mean_token_accuracy": 0.8283238030970097,
+      "num_tokens": 6172369.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.7282323956489563,
+      "epoch": 1.4,
+      "grad_norm": 0.38415881991386414,
+      "learning_rate": 0.00011613408372604825,
+      "loss": 0.6688,
+      "mean_token_accuracy": 0.8334715165197849,
+      "num_tokens": 6215094.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.7796667337417602,
+      "epoch": 1.44,
+      "grad_norm": 0.09978846460580826,
+      "learning_rate": 0.00011185565326742473,
+      "loss": 0.838,
+      "mean_token_accuracy": 0.7973373785614968,
+      "num_tokens": 6541959.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.7431464415043593,
+      "epoch": 1.48,
+      "grad_norm": 0.11637846380472183,
+      "learning_rate": 0.00010755508733463265,
+      "loss": 0.732,
+      "mean_token_accuracy": 0.8180491633713245,
+      "num_tokens": 6795064.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.7368700005114078,
+      "epoch": 1.52,
+      "grad_norm": 0.1580406278371811,
+      "learning_rate": 0.00010324041543595535,
+      "loss": 0.7115,
+      "mean_token_accuracy": 0.8229206502437592,
+      "num_tokens": 6951520.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.6850949611514807,
+      "epoch": 1.56,
+      "grad_norm": 0.19380679726600647,
+      "learning_rate": 9.891969341666809e-05,
+      "loss": 0.6795,
+      "mean_token_accuracy": 0.8305462062358856,
+      "num_tokens": 7042539.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.6874195206910372,
+      "epoch": 1.6,
+      "grad_norm": 0.3993852734565735,
+      "learning_rate": 9.460098841811601e-05,
+      "loss": 0.6464,
+      "mean_token_accuracy": 0.840615575760603,
+      "num_tokens": 7081928.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.8238836076110602,
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.11308339983224869,
+      "learning_rate": 9.029236381570161e-05,
+      "loss": 0.858,
+      "mean_token_accuracy": 0.7912634812295437,
+      "num_tokens": 7408986.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.7328622534871101,
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.13542936742305756,
+      "learning_rate": 8.600186416390342e-05,
+      "loss": 0.7257,
+      "mean_token_accuracy": 0.8204753622412682,
+      "num_tokens": 7657210.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.7326431553810835,
+      "epoch": 1.72,
+      "grad_norm": 0.14785650372505188,
+      "learning_rate": 8.173750017643504e-05,
+      "loss": 0.7114,
+      "mean_token_accuracy": 0.8220926195383071,
+      "num_tokens": 7816248.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.6878415960818529,
+      "epoch": 1.76,
+      "grad_norm": 0.2059694081544876,
+      "learning_rate": 7.750723376958733e-05,
+      "loss": 0.6827,
+      "mean_token_accuracy": 0.8304854579269886,
+      "num_tokens": 7910352.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.6678356051445007,
+      "epoch": 1.8,
+      "grad_norm": 0.4371260404586792,
+      "learning_rate": 7.33189631966799e-05,
+      "loss": 0.6174,
+      "mean_token_accuracy": 0.8434398949146271,
+      "num_tokens": 7949474.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.7557789146900177,
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.10683777183294296,
+      "learning_rate": 6.918050830137609e-05,
+      "loss": 0.8036,
+      "mean_token_accuracy": 0.8040532894432545,
+      "num_tokens": 8277100.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.7231194365769624,
+      "epoch": 1.88,
+      "grad_norm": 0.1221792995929718,
+      "learning_rate": 6.509959591739522e-05,
+      "loss": 0.7248,
+      "mean_token_accuracy": 0.820059847086668,
+      "num_tokens": 8534755.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.7624214310199022,
+      "epoch": 1.92,
+      "grad_norm": 0.1458406001329422,
+      "learning_rate": 6.10838454418825e-05,
+      "loss": 0.7402,
+      "mean_token_accuracy": 0.8160238958895206,
+      "num_tokens": 8702155.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.7613711394369602,
+      "epoch": 1.96,
+      "grad_norm": 0.21833185851573944,
+      "learning_rate": 5.714075460937125e-05,
+      "loss": 0.7412,
+      "mean_token_accuracy": 0.8151491984724999,
+      "num_tokens": 8800560.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.6537208616733551,
+      "epoch": 2.0,
+      "grad_norm": 0.39814066886901855,
+      "learning_rate": 5.327768549289934e-05,
+      "loss": 0.6092,
+      "mean_token_accuracy": 0.8473344258964062,
+      "num_tokens": 8839482.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.157457787473101e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aca68e7e398fed919c2a2ae61301f7aa32090dd99ac1369ce2dc788bd6c4d76
+size 6161

checkpoint-750/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-1.5B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.0

checkpoint-750/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-750/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de3f743ee0d6156dbccd9a34d93ca37a8cb1445eff714cd40a1d71c2ba8b5b49
+size 147770496

checkpoint-750/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-750/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb40e414b4b26a17d650c0eccd0111892a3b1511664fa6225d0f4a94caf7edc
+size 295766331

checkpoint-750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:137f9827565c50b717c1641be9e461f74d08a2616328b8ba5e759f8142dc4edc
+size 14645

checkpoint-750/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca8377b2ea0b440a1b7c1913409d5ce08c05c7f94eb3857477a86af97a6ec03
+size 1383

checkpoint-750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da6cffd29d107485fd65a3291d66df7b87424f25de973bb529c2fbe605d9c752
+size 1465

checkpoint-750/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

checkpoint-750/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-750/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-750/trainer_state.json

@@ -0,0 +1,784 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.8118590474128723,
+      "epoch": 0.04,
+      "grad_norm": 0.05997199937701225,
+      "learning_rate": 7.82608695652174e-05,
+      "loss": 1.0028,
+      "mean_token_accuracy": 0.767544125020504,
+      "num_tokens": 327384.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.8525841124355793,
+      "epoch": 0.08,
+      "grad_norm": 0.09163825213909149,
+      "learning_rate": 0.00016521739130434784,
+      "loss": 0.8959,
+      "mean_token_accuracy": 0.7876047976315022,
+      "num_tokens": 582000.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.9385534837841988,
+      "epoch": 0.12,
+      "grad_norm": 0.11509037017822266,
+      "learning_rate": 0.00019996638918070336,
+      "loss": 0.918,
+      "mean_token_accuracy": 0.782110495865345,
+      "num_tokens": 745292.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.911478316783905,
+      "epoch": 0.16,
+      "grad_norm": 0.14333251118659973,
+      "learning_rate": 0.0001997610715447061,
+      "loss": 0.9173,
+      "mean_token_accuracy": 0.780673997104168,
+      "num_tokens": 843998.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.9255619779229164,
+      "epoch": 0.2,
+      "grad_norm": 0.37470874190330505,
+      "learning_rate": 0.0001993694918299864,
+      "loss": 0.9095,
+      "mean_token_accuracy": 0.7824992008507252,
+      "num_tokens": 886161.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.9085440292954445,
+      "epoch": 0.24,
+      "grad_norm": 0.06702009588479996,
+      "learning_rate": 0.00019879238114789373,
+      "loss": 0.9319,
+      "mean_token_accuracy": 0.7772408030927181,
+      "num_tokens": 1213472.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.8186310566961765,
+      "epoch": 0.28,
+      "grad_norm": 0.08344472944736481,
+      "learning_rate": 0.0001980308170112659,
+      "loss": 0.8226,
+      "mean_token_accuracy": 0.8009889200329781,
+      "num_tokens": 1468934.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.8451250180602073,
+      "epoch": 0.32,
+      "grad_norm": 0.10779275745153427,
+      "learning_rate": 0.0001970862213226244,
+      "loss": 0.836,
+      "mean_token_accuracy": 0.7983625620603562,
+      "num_tokens": 1633249.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.8599591284990311,
+      "epoch": 0.36,
+      "grad_norm": 0.15631401538848877,
+      "learning_rate": 0.00019596035771936592,
+      "loss": 0.8486,
+      "mean_token_accuracy": 0.7960575334727764,
+      "num_tokens": 1730768.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.876547134667635,
+      "epoch": 0.4,
+      "grad_norm": 0.3903079032897949,
+      "learning_rate": 0.00019465532828090735,
+      "loss": 0.8639,
+      "mean_token_accuracy": 0.7935161642730236,
+      "num_tokens": 1771280.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.9069034807384014,
+      "epoch": 0.44,
+      "grad_norm": 0.07801498472690582,
+      "learning_rate": 0.00019317356960393156,
+      "loss": 0.9173,
+      "mean_token_accuracy": 0.7792488023638725,
+      "num_tokens": 2098922.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.8098581977188587,
+      "epoch": 0.48,
+      "grad_norm": 0.08503358066082001,
+      "learning_rate": 0.00019151784825306205,
+      "loss": 0.8102,
+      "mean_token_accuracy": 0.8027891904115677,
+      "num_tokens": 2358277.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.8039502821862697,
+      "epoch": 0.52,
+      "grad_norm": 0.11073547601699829,
+      "learning_rate": 0.00018969125559546054,
+      "loss": 0.81,
+      "mean_token_accuracy": 0.8007699891924858,
+      "num_tokens": 2522737.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.8364543087780476,
+      "epoch": 0.56,
+      "grad_norm": 0.1541292369365692,
+      "learning_rate": 0.00018769720202899194,
+      "loss": 0.8251,
+      "mean_token_accuracy": 0.7973810255527496,
+      "num_tokens": 2621039.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.8665640391409397,
+      "epoch": 0.6,
+      "grad_norm": 0.3610881567001343,
+      "learning_rate": 0.00018553941061473218,
+      "loss": 0.8458,
+      "mean_token_accuracy": 0.7960383057594299,
+      "num_tokens": 2662897.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.8594730854034424,
+      "epoch": 0.64,
+      "grad_norm": 0.10022123903036118,
+      "learning_rate": 0.00018322191012570919,
+      "loss": 0.8785,
+      "mean_token_accuracy": 0.7877491846680641,
+      "num_tokens": 2990339.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.7944531835615635,
+      "epoch": 0.68,
+      "grad_norm": 0.10204905271530151,
+      "learning_rate": 0.0001807490275248539,
+      "loss": 0.7889,
+      "mean_token_accuracy": 0.8073874406516552,
+      "num_tokens": 3245518.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.8212005525827408,
+      "epoch": 0.72,
+      "grad_norm": 0.11545777320861816,
+      "learning_rate": 0.00017812537988620675,
+      "loss": 0.8253,
+      "mean_token_accuracy": 0.7982150033116341,
+      "num_tokens": 3404933.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.8301504630595445,
+      "epoch": 0.76,
+      "grad_norm": 0.17408080399036407,
+      "learning_rate": 0.00017535586577446276,
+      "loss": 0.8171,
+      "mean_token_accuracy": 0.8009781941771508,
+      "num_tokens": 3497564.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.81050028167665,
+      "epoch": 0.8,
+      "grad_norm": 0.35289013385772705,
+      "learning_rate": 0.00017244565609895074,
+      "loss": 0.7865,
+      "mean_token_accuracy": 0.8109133973717689,
+      "num_tokens": 3534086.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.837448638677597,
+      "epoch": 0.84,
+      "grad_norm": 0.08503283560276031,
+      "learning_rate": 0.00016940018445912272,
+      "loss": 0.8648,
+      "mean_token_accuracy": 0.7916912771761417,
+      "num_tokens": 3861579.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.7994868710637093,
+      "epoch": 0.88,
+      "grad_norm": 0.09771085530519485,
+      "learning_rate": 0.00016622513699957948,
+      "loss": 0.7858,
+      "mean_token_accuracy": 0.8064859353005887,
+      "num_tokens": 4119938.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.7886113189160824,
+      "epoch": 0.92,
+      "grad_norm": 0.12538443505764008,
+      "learning_rate": 0.00016292644179357336,
+      "loss": 0.798,
+      "mean_token_accuracy": 0.8042714856564999,
+      "num_tokens": 4283327.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.801911610364914,
+      "epoch": 0.96,
+      "grad_norm": 0.16356100142002106,
+      "learning_rate": 0.00015951025777481096,
+      "loss": 0.7861,
+      "mean_token_accuracy": 0.8082708492875099,
+      "num_tokens": 4379704.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.8030880324542522,
+      "epoch": 1.0,
+      "grad_norm": 0.2906339168548584,
+      "learning_rate": 0.00015598296323822024,
+      "loss": 0.7752,
+      "mean_token_accuracy": 0.8124107919633389,
+      "num_tokens": 4419741.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.8512323558330536,
+      "epoch": 1.04,
+      "grad_norm": 0.0769343450665474,
+      "learning_rate": 0.00015235114393115202,
+      "loss": 0.8714,
+      "mean_token_accuracy": 0.7885661020874977,
+      "num_tokens": 4747421.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.7640283957123757,
+      "epoch": 1.08,
+      "grad_norm": 0.09265792369842529,
+      "learning_rate": 0.0001486215807572515,
+      "loss": 0.7566,
+      "mean_token_accuracy": 0.8131284601986408,
+      "num_tokens": 5013839.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.7704206634312868,
+      "epoch": 1.12,
+      "grad_norm": 0.1475331336259842,
+      "learning_rate": 0.00014480123711595636,
+      "loss": 0.7635,
+      "mean_token_accuracy": 0.8108469642698765,
+      "num_tokens": 5183957.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.7694178409874439,
+      "epoch": 1.16,
+      "grad_norm": 0.17722958326339722,
+      "learning_rate": 0.0001408972459012606,
+      "loss": 0.7517,
+      "mean_token_accuracy": 0.8132740050554276,
+      "num_tokens": 5284281.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.6807048697024584,
+      "epoch": 1.2,
+      "grad_norm": 0.358539342880249,
+      "learning_rate": 0.00013691689618401835,
+      "loss": 0.6343,
+      "mean_token_accuracy": 0.8411179468035698,
+      "num_tokens": 5325202.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.8084883399307727,
+      "epoch": 1.24,
+      "grad_norm": 0.09149754047393799,
+      "learning_rate": 0.00013286761960265214,
+      "loss": 0.8618,
+      "mean_token_accuracy": 0.7917799115180969,
+      "num_tokens": 5652739.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.7762876857072115,
+      "epoch": 1.28,
+      "grad_norm": 0.09918583184480667,
+      "learning_rate": 0.00012875697648767663,
+      "loss": 0.7423,
+      "mean_token_accuracy": 0.8153080217540264,
+      "num_tokens": 5909823.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.7344005398452282,
+      "epoch": 1.32,
+      "grad_norm": 0.13750393688678741,
+      "learning_rate": 0.00012459264174594304,
+      "loss": 0.7361,
+      "mean_token_accuracy": 0.8177524119615555,
+      "num_tokens": 6071844.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.702471449971199,
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.17901532351970673,
+      "learning_rate": 0.00012038239053096038,
+      "loss": 0.69,
+      "mean_token_accuracy": 0.8283238030970097,
+      "num_tokens": 6172369.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.7282323956489563,
+      "epoch": 1.4,
+      "grad_norm": 0.38415881991386414,
+      "learning_rate": 0.00011613408372604825,
+      "loss": 0.6688,
+      "mean_token_accuracy": 0.8334715165197849,
+      "num_tokens": 6215094.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.7796667337417602,
+      "epoch": 1.44,
+      "grad_norm": 0.09978846460580826,
+      "learning_rate": 0.00011185565326742473,
+      "loss": 0.838,
+      "mean_token_accuracy": 0.7973373785614968,
+      "num_tokens": 6541959.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.7431464415043593,
+      "epoch": 1.48,
+      "grad_norm": 0.11637846380472183,
+      "learning_rate": 0.00010755508733463265,
+      "loss": 0.732,
+      "mean_token_accuracy": 0.8180491633713245,
+      "num_tokens": 6795064.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.7368700005114078,
+      "epoch": 1.52,
+      "grad_norm": 0.1580406278371811,
+      "learning_rate": 0.00010324041543595535,
+      "loss": 0.7115,
+      "mean_token_accuracy": 0.8229206502437592,
+      "num_tokens": 6951520.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.6850949611514807,
+      "epoch": 1.56,
+      "grad_norm": 0.19380679726600647,
+      "learning_rate": 9.891969341666809e-05,
+      "loss": 0.6795,
+      "mean_token_accuracy": 0.8305462062358856,
+      "num_tokens": 7042539.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.6874195206910372,
+      "epoch": 1.6,
+      "grad_norm": 0.3993852734565735,
+      "learning_rate": 9.460098841811601e-05,
+      "loss": 0.6464,
+      "mean_token_accuracy": 0.840615575760603,
+      "num_tokens": 7081928.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.8238836076110602,
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.11308339983224869,
+      "learning_rate": 9.029236381570161e-05,
+      "loss": 0.858,
+      "mean_token_accuracy": 0.7912634812295437,
+      "num_tokens": 7408986.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.7328622534871101,
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.13542936742305756,
+      "learning_rate": 8.600186416390342e-05,
+      "loss": 0.7257,
+      "mean_token_accuracy": 0.8204753622412682,
+      "num_tokens": 7657210.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.7326431553810835,
+      "epoch": 1.72,
+      "grad_norm": 0.14785650372505188,
+      "learning_rate": 8.173750017643504e-05,
+      "loss": 0.7114,
+      "mean_token_accuracy": 0.8220926195383071,
+      "num_tokens": 7816248.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.6878415960818529,
+      "epoch": 1.76,
+      "grad_norm": 0.2059694081544876,
+      "learning_rate": 7.750723376958733e-05,
+      "loss": 0.6827,
+      "mean_token_accuracy": 0.8304854579269886,
+      "num_tokens": 7910352.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.6678356051445007,
+      "epoch": 1.8,
+      "grad_norm": 0.4371260404586792,
+      "learning_rate": 7.33189631966799e-05,
+      "loss": 0.6174,
+      "mean_token_accuracy": 0.8434398949146271,
+      "num_tokens": 7949474.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.7557789146900177,
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.10683777183294296,
+      "learning_rate": 6.918050830137609e-05,
+      "loss": 0.8036,
+      "mean_token_accuracy": 0.8040532894432545,
+      "num_tokens": 8277100.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.7231194365769624,
+      "epoch": 1.88,
+      "grad_norm": 0.1221792995929718,
+      "learning_rate": 6.509959591739522e-05,
+      "loss": 0.7248,
+      "mean_token_accuracy": 0.820059847086668,
+      "num_tokens": 8534755.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.7624214310199022,
+      "epoch": 1.92,
+      "grad_norm": 0.1458406001329422,
+      "learning_rate": 6.10838454418825e-05,
+      "loss": 0.7402,
+      "mean_token_accuracy": 0.8160238958895206,
+      "num_tokens": 8702155.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.7613711394369602,
+      "epoch": 1.96,
+      "grad_norm": 0.21833185851573944,
+      "learning_rate": 5.714075460937125e-05,
+      "loss": 0.7412,
+      "mean_token_accuracy": 0.8151491984724999,
+      "num_tokens": 8800560.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.6537208616733551,
+      "epoch": 2.0,
+      "grad_norm": 0.39814066886901855,
+      "learning_rate": 5.327768549289934e-05,
+      "loss": 0.6092,
+      "mean_token_accuracy": 0.8473344258964062,
+      "num_tokens": 8839482.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.7942855045199394,
+      "epoch": 2.04,
+      "grad_norm": 0.1046057939529419,
+      "learning_rate": 4.9501850758417056e-05,
+      "loss": 0.8213,
+      "mean_token_accuracy": 0.7997106194496155,
+      "num_tokens": 9166520.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.6845901045948267,
+      "epoch": 2.08,
+      "grad_norm": 0.11944226920604706,
+      "learning_rate": 4.582030019814948e-05,
+      "loss": 0.6879,
+      "mean_token_accuracy": 0.8275571748614311,
+      "num_tokens": 9423125.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.713664248213172,
+      "epoch": 2.12,
+      "grad_norm": 0.15875312685966492,
+      "learning_rate": 4.223990756805841e-05,
+      "loss": 0.6864,
+      "mean_token_accuracy": 0.8269673593342304,
+      "num_tokens": 9587584.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.6808680634945631,
+      "epoch": 2.16,
+      "grad_norm": 0.2167051136493683,
+      "learning_rate": 3.8767357753977596e-05,
+      "loss": 0.6363,
+      "mean_token_accuracy": 0.8397710673511029,
+      "num_tokens": 9683189.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.6310655426234006,
+      "epoch": 2.2,
+      "grad_norm": 0.42550230026245117,
+      "learning_rate": 3.540913429038407e-05,
+      "loss": 0.5481,
+      "mean_token_accuracy": 0.8616865545511245,
+      "num_tokens": 9723785.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.7458249524235725,
+      "epoch": 2.24,
+      "grad_norm": 0.1268557608127594,
+      "learning_rate": 3.217150725510946e-05,
+      "loss": 0.8037,
+      "mean_token_accuracy": 0.8051810264587402,
+      "num_tokens": 10051177.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.7029979381710291,
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.13476522266864777,
+      "learning_rate": 2.9060521562591624e-05,
+      "loss": 0.732,
+      "mean_token_accuracy": 0.8179502584040165,
+      "num_tokens": 10305046.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.7075169749557972,
+      "epoch": 2.32,
+      "grad_norm": 0.15390700101852417,
+      "learning_rate": 2.608198567752512e-05,
+      "loss": 0.6863,
+      "mean_token_accuracy": 0.827414334565401,
+      "num_tokens": 10464165.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.7264889780431986,
+      "epoch": 2.36,
+      "grad_norm": 0.21259604394435883,
+      "learning_rate": 2.3241460769982814e-05,
+      "loss": 0.6886,
+      "mean_token_accuracy": 0.8280333392322063,
+      "num_tokens": 10560951.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.58490473870188,
+      "epoch": 2.4,
+      "grad_norm": 0.4374448359012604,
+      "learning_rate": 2.0544250332256276e-05,
+      "loss": 0.5086,
+      "mean_token_accuracy": 0.8706422604620456,
+      "num_tokens": 10600998.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.8061852857470513,
+      "epoch": 2.44,
+      "grad_norm": 0.12525418400764465,
+      "learning_rate": 1.799539027680216e-05,
+      "loss": 0.8365,
+      "mean_token_accuracy": 0.7974523492157459,
+      "num_tokens": 10928678.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.6682436108589173,
+      "epoch": 2.48,
+      "grad_norm": 0.1342065930366516,
+      "learning_rate": 1.5599639533781853e-05,
+      "loss": 0.6933,
+      "mean_token_accuracy": 0.8261794589459897,
+      "num_tokens": 11195766.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.6829290065914393,
+      "epoch": 2.52,
+      "grad_norm": 0.16089050471782684,
+      "learning_rate": 1.3361471165749562e-05,
+      "loss": 0.6747,
+      "mean_token_accuracy": 0.8309472300112247,
+      "num_tokens": 11364584.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.677256828173995,
+      "epoch": 2.56,
+      "grad_norm": 0.212812602519989,
+      "learning_rate": 1.1285064016078784e-05,
+      "loss": 0.6465,
+      "mean_token_accuracy": 0.8378356143832206,
+      "num_tokens": 11465749.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.6223138906061649,
+      "epoch": 2.6,
+      "grad_norm": 0.4253580570220947,
+      "learning_rate": 9.374294906720082e-06,
+      "loss": 0.5433,
+      "mean_token_accuracy": 0.8606500513851643,
+      "num_tokens": 11507652.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.7784962818026543,
+      "epoch": 2.64,
+      "grad_norm": 0.1105949729681015,
+      "learning_rate": 7.63273139985733e-06,
+      "loss": 0.7908,
+      "mean_token_accuracy": 0.8065024986863136,
+      "num_tokens": 11834885.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.6436492279171944,
+      "epoch": 2.68,
+      "grad_norm": 0.14102977514266968,
+      "learning_rate": 6.063625136977447e-06,
+      "loss": 0.6591,
+      "mean_token_accuracy": 0.8364327348768711,
+      "num_tokens": 12084559.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.6770952560007573,
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.18300692737102509,
+      "learning_rate": 4.669905767789884e-06,
+      "loss": 0.6787,
+      "mean_token_accuracy": 0.8301728747785091,
+      "num_tokens": 12245118.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.6532967071980238,
+      "epoch": 2.76,
+      "grad_norm": 0.22459393739700317,
+      "learning_rate": 3.454175480330857e-06,
+      "loss": 0.6295,
+      "mean_token_accuracy": 0.8411597743630409,
+      "num_tokens": 12341764.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.5622258361428976,
+      "epoch": 2.8,
+      "grad_norm": 0.4296166002750397,
+      "learning_rate": 2.418704142465722e-06,
+      "loss": 0.4985,
+      "mean_token_accuracy": 0.8744776912033558,
+      "num_tokens": 12382504.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.7967640496790409,
+      "epoch": 2.84,
+      "grad_norm": 0.11412588506937027,
+      "learning_rate": 1.56542506385986e-06,
+      "loss": 0.8069,
+      "mean_token_accuracy": 0.8025561511516571,
+      "num_tokens": 12710105.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.7018159870058298,
+      "epoch": 2.88,
+      "grad_norm": 0.1381121128797531,
+      "learning_rate": 8.959313863315389e-07,
+      "loss": 0.7188,
+      "mean_token_accuracy": 0.8199774742126464,
+      "num_tokens": 12965490.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.6720455687493085,
+      "epoch": 2.92,
+      "grad_norm": 0.1741972267627716,
+      "learning_rate": 4.114731093257884e-07,
+      "loss": 0.6729,
+      "mean_token_accuracy": 0.8303120598196984,
+      "num_tokens": 13127948.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.6231573238968849,
+      "epoch": 2.96,
+      "grad_norm": 0.21798616647720337,
+      "learning_rate": 1.129547560632771e-07,
+      "loss": 0.5902,
+      "mean_token_accuracy": 0.8499781206250191,
+      "num_tokens": 13221676.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.5697622459381819,
+      "epoch": 3.0,
+      "grad_norm": 0.4558388292789459,
+      "learning_rate": 9.336847214269639e-10,
+      "loss": 0.4921,
+      "mean_token_accuracy": 0.8710406333208084,
+      "num_tokens": 13259223.0,
+      "step": 750
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0736248116728218e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aca68e7e398fed919c2a2ae61301f7aa32090dd99ac1369ce2dc788bd6c4d76
+size 6161