Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ 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-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-745/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/QwQ-32B
+library_name: transformers
+model_name: lora_deception_model
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for lora_deception_model
+
+This model is a fine-tuned version of [Qwen/QwQ-32B](https://huggingface.co/Qwen/QwQ-32B).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.23.0
+- Transformers: 4.56.1
+- Pytorch: 2.8.0
+- Datasets: 4.1.0
+- Tokenizers: 0.22.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

checkpoint-100/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/QwQ-32B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/QwQ-32B
+- 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 0.17.1

checkpoint-100/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/QwQ-32B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c9e3a7ad16317c2eccae4f59b44365b8a1953650eb2cf4d6e3d9e6e7f15d98e
+size 536940800

checkpoint-100/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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-100/chat_template.jinja

@@ -0,0 +1,62 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- '' }}
+    {%- 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' }}
+  {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" and not message.tool_calls %}
+        {%- set content = message.content %}
+        {%- if not loop.last %}
+            {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+        {%- endif %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- if not loop.last %}
+            {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+        {%- endif %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + 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<think>\n' }}
+{%- endif %}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc83bd68b31868e7b2a87ac4d26a18cb2a44c66d073930797cd9e418bbfe4fe5
+size 1074182115

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
+size 14645

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f49eb0da5be622c56aff92e086d6523a16175266b75d1e6966a89f998a7d2ef9
+size 1465

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,156 @@
+{
+  "best_global_step": 100,
+  "best_metric": 0.8651557564735413,
+  "best_model_checkpoint": "lora_deception_model/checkpoint-100",
+  "epoch": 0.6717044500419815,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.6688848555088043,
+      "epoch": 0.06717044500419815,
+      "grad_norm": 0.3304958939552307,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.8658,
+      "mean_token_accuracy": 0.8207968935370445,
+      "num_tokens": 63133.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.6755495790392161,
+      "epoch": 0.1343408900083963,
+      "grad_norm": 0.32398757338523865,
+      "learning_rate": 1.5200000000000002e-05,
+      "loss": 0.8662,
+      "mean_token_accuracy": 0.8197331622242927,
+      "num_tokens": 124489.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.734241085499525,
+      "epoch": 0.20151133501259447,
+      "grad_norm": 0.31472697854042053,
+      "learning_rate": 2.32e-05,
+      "loss": 0.7134,
+      "mean_token_accuracy": 0.8222098298370838,
+      "num_tokens": 189081.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.8794498354196548,
+      "epoch": 0.2686817800167926,
+      "grad_norm": 0.23867088556289673,
+      "learning_rate": 3.1200000000000006e-05,
+      "loss": 0.6577,
+      "mean_token_accuracy": 0.820378091186285,
+      "num_tokens": 270096.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.9822202995419502,
+      "epoch": 0.33585222502099077,
+      "grad_norm": 0.23442600667476654,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 0.5764,
+      "mean_token_accuracy": 0.8329788409173489,
+      "num_tokens": 343034.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.33585222502099077,
+      "eval_entropy": 1.35109115924154,
+      "eval_loss": 0.9188798666000366,
+      "eval_mean_token_accuracy": 0.7514589822718075,
+      "eval_num_tokens": 343034.0,
+      "eval_runtime": 5.1522,
+      "eval_samples_per_second": 10.869,
+      "eval_steps_per_second": 10.869,
+      "step": 50
+    },
+    {
+      "entropy": 0.8484722189605236,
+      "epoch": 0.40302267002518893,
+      "grad_norm": 0.27580252289772034,
+      "learning_rate": 3.948201438848921e-05,
+      "loss": 0.4939,
+      "mean_token_accuracy": 0.8525501079857349,
+      "num_tokens": 407346.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.7665611129254103,
+      "epoch": 0.47019311502938704,
+      "grad_norm": 0.32506343722343445,
+      "learning_rate": 3.8906474820143886e-05,
+      "loss": 0.4095,
+      "mean_token_accuracy": 0.8701820805668831,
+      "num_tokens": 466070.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.7331306278705597,
+      "epoch": 0.5373635600335852,
+      "grad_norm": 0.3568798899650574,
+      "learning_rate": 3.833093525179856e-05,
+      "loss": 0.448,
+      "mean_token_accuracy": 0.863949628919363,
+      "num_tokens": 536560.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.7565343648195266,
+      "epoch": 0.6045340050377834,
+      "grad_norm": 0.3249973952770233,
+      "learning_rate": 3.775539568345324e-05,
+      "loss": 0.4065,
+      "mean_token_accuracy": 0.8672126568853855,
+      "num_tokens": 597642.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.6388500925153494,
+      "epoch": 0.6717044500419815,
+      "grad_norm": 0.36163443326950073,
+      "learning_rate": 3.7179856115107914e-05,
+      "loss": 0.3693,
+      "mean_token_accuracy": 0.8828025683760643,
+      "num_tokens": 663210.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.6717044500419815,
+      "eval_entropy": 1.0956847156797136,
+      "eval_loss": 0.8651557564735413,
+      "eval_mean_token_accuracy": 0.7637390036668096,
+      "eval_num_tokens": 663210.0,
+      "eval_runtime": 4.9833,
+      "eval_samples_per_second": 11.237,
+      "eval_steps_per_second": 11.237,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 745,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.27811946622464e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce196e5bc1fecba594008114c4c5772643cb32ef5927e83c6ed6f3b11728deb6
+size 6161

checkpoint-700/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/QwQ-32B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/QwQ-32B
+- 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 0.17.1

checkpoint-700/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/QwQ-32B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-700/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f3e871cdaef5cf533719e156a60fa1142f7bc240ff918dcb0efe45a0c71b2fd
+size 536940800

checkpoint-700/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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-700/chat_template.jinja

@@ -0,0 +1,62 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- '' }}
+    {%- 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' }}
+  {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" and not message.tool_calls %}
+        {%- set content = message.content %}
+        {%- if not loop.last %}
+            {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+        {%- endif %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- if not loop.last %}
+            {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+        {%- endif %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + 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<think>\n' }}
+{%- endif %}

checkpoint-700/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246b3839f76784a12be9ef8cd92ab683c6ed697d9a655c04951afd0f4f666214
+size 1074182115

checkpoint-700/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e51a42ec5ffac256f3cd0ee0ccd7a6d3befe58914ad400c0cc707bc4a5ee283
+size 14645

checkpoint-700/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6212244cd383093e86f66c4f822ebb8240180137e2d6008e05065da283ddee21
+size 1465

checkpoint-700/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-700/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-700/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-700/trainer_state.json

@@ -0,0 +1,888 @@
+{
+  "best_global_step": 150,
+  "best_metric": 0.8634624481201172,
+  "best_model_checkpoint": "lora_deception_model/checkpoint-100",
+  "epoch": 4.698572628043661,
+  "eval_steps": 50,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.6688848555088043,
+      "epoch": 0.06717044500419815,
+      "grad_norm": 0.3304958939552307,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.8658,
+      "mean_token_accuracy": 0.8207968935370445,
+      "num_tokens": 63133.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.6755495790392161,
+      "epoch": 0.1343408900083963,
+      "grad_norm": 0.32398757338523865,
+      "learning_rate": 1.5200000000000002e-05,
+      "loss": 0.8662,
+      "mean_token_accuracy": 0.8197331622242927,
+      "num_tokens": 124489.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.734241085499525,
+      "epoch": 0.20151133501259447,
+      "grad_norm": 0.31472697854042053,
+      "learning_rate": 2.32e-05,
+      "loss": 0.7134,
+      "mean_token_accuracy": 0.8222098298370838,
+      "num_tokens": 189081.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.8794498354196548,
+      "epoch": 0.2686817800167926,
+      "grad_norm": 0.23867088556289673,
+      "learning_rate": 3.1200000000000006e-05,
+      "loss": 0.6577,
+      "mean_token_accuracy": 0.820378091186285,
+      "num_tokens": 270096.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.9822202995419502,
+      "epoch": 0.33585222502099077,
+      "grad_norm": 0.23442600667476654,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 0.5764,
+      "mean_token_accuracy": 0.8329788409173489,
+      "num_tokens": 343034.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.33585222502099077,
+      "eval_entropy": 1.35109115924154,
+      "eval_loss": 0.9188798666000366,
+      "eval_mean_token_accuracy": 0.7514589822718075,
+      "eval_num_tokens": 343034.0,
+      "eval_runtime": 5.1522,
+      "eval_samples_per_second": 10.869,
+      "eval_steps_per_second": 10.869,
+      "step": 50
+    },
+    {
+      "entropy": 0.8484722189605236,
+      "epoch": 0.40302267002518893,
+      "grad_norm": 0.27580252289772034,
+      "learning_rate": 3.948201438848921e-05,
+      "loss": 0.4939,
+      "mean_token_accuracy": 0.8525501079857349,
+      "num_tokens": 407346.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.7665611129254103,
+      "epoch": 0.47019311502938704,
+      "grad_norm": 0.32506343722343445,
+      "learning_rate": 3.8906474820143886e-05,
+      "loss": 0.4095,
+      "mean_token_accuracy": 0.8701820805668831,
+      "num_tokens": 466070.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.7331306278705597,
+      "epoch": 0.5373635600335852,
+      "grad_norm": 0.3568798899650574,
+      "learning_rate": 3.833093525179856e-05,
+      "loss": 0.448,
+      "mean_token_accuracy": 0.863949628919363,
+      "num_tokens": 536560.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.7565343648195266,
+      "epoch": 0.6045340050377834,
+      "grad_norm": 0.3249973952770233,
+      "learning_rate": 3.775539568345324e-05,
+      "loss": 0.4065,
+      "mean_token_accuracy": 0.8672126568853855,
+      "num_tokens": 597642.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.6388500925153494,
+      "epoch": 0.6717044500419815,
+      "grad_norm": 0.36163443326950073,
+      "learning_rate": 3.7179856115107914e-05,
+      "loss": 0.3693,
+      "mean_token_accuracy": 0.8828025683760643,
+      "num_tokens": 663210.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.6717044500419815,
+      "eval_entropy": 1.0956847156797136,
+      "eval_loss": 0.8651557564735413,
+      "eval_mean_token_accuracy": 0.7637390036668096,
+      "eval_num_tokens": 663210.0,
+      "eval_runtime": 4.9833,
+      "eval_samples_per_second": 11.237,
+      "eval_steps_per_second": 11.237,
+      "step": 100
+    },
+    {
+      "entropy": 0.6128827821463346,
+      "epoch": 0.7388748950461796,
+      "grad_norm": 0.29096513986587524,
+      "learning_rate": 3.6604316546762595e-05,
+      "loss": 0.3719,
+      "mean_token_accuracy": 0.8851677082479,
+      "num_tokens": 726617.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.6564031228423118,
+      "epoch": 0.8060453400503779,
+      "grad_norm": 0.27515140175819397,
+      "learning_rate": 3.602877697841727e-05,
+      "loss": 0.3935,
+      "mean_token_accuracy": 0.8752141006290912,
+      "num_tokens": 800821.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.6125180713832379,
+      "epoch": 0.873215785054576,
+      "grad_norm": 0.3126560151576996,
+      "learning_rate": 3.545323741007194e-05,
+      "loss": 0.3847,
+      "mean_token_accuracy": 0.8818505816161633,
+      "num_tokens": 868710.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.6347699824720621,
+      "epoch": 0.9403862300587741,
+      "grad_norm": 0.23533445596694946,
+      "learning_rate": 3.487769784172662e-05,
+      "loss": 0.385,
+      "mean_token_accuracy": 0.8835290059447288,
+      "num_tokens": 935575.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.579044715513157,
+      "epoch": 1.0067170445004199,
+      "grad_norm": 0.2643934488296509,
+      "learning_rate": 3.43021582733813e-05,
+      "loss": 0.3224,
+      "mean_token_accuracy": 0.8946574262425869,
+      "num_tokens": 996466.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.0067170445004199,
+      "eval_entropy": 0.9877308234572411,
+      "eval_loss": 0.8634624481201172,
+      "eval_mean_token_accuracy": 0.7611759411437171,
+      "eval_num_tokens": 996466.0,
+      "eval_runtime": 4.9854,
+      "eval_samples_per_second": 11.233,
+      "eval_steps_per_second": 11.233,
+      "step": 150
+    },
+    {
+      "entropy": 0.552555637806654,
+      "epoch": 1.073887489504618,
+      "grad_norm": 0.2633912265300751,
+      "learning_rate": 3.372661870503598e-05,
+      "loss": 0.3265,
+      "mean_token_accuracy": 0.8968047671020031,
+      "num_tokens": 1066789.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.5594113569706678,
+      "epoch": 1.141057934508816,
+      "grad_norm": 0.2680589258670807,
+      "learning_rate": 3.315107913669065e-05,
+      "loss": 0.3519,
+      "mean_token_accuracy": 0.8886663600802421,
+      "num_tokens": 1138401.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.5540055774152279,
+      "epoch": 1.2082283795130142,
+      "grad_norm": 0.27169251441955566,
+      "learning_rate": 3.2575539568345325e-05,
+      "loss": 0.3436,
+      "mean_token_accuracy": 0.8913260444998741,
+      "num_tokens": 1202735.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.5612262919545173,
+      "epoch": 1.2753988245172123,
+      "grad_norm": 0.3151009976863861,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.351,
+      "mean_token_accuracy": 0.8909851491451264,
+      "num_tokens": 1266476.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.5354872807860375,
+      "epoch": 1.3425692695214106,
+      "grad_norm": 0.29847052693367004,
+      "learning_rate": 3.142446043165468e-05,
+      "loss": 0.3045,
+      "mean_token_accuracy": 0.9023352213203907,
+      "num_tokens": 1327389.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.3425692695214106,
+      "eval_entropy": 0.9606236421636173,
+      "eval_loss": 0.8751164078712463,
+      "eval_mean_token_accuracy": 0.7617330902389118,
+      "eval_num_tokens": 1327389.0,
+      "eval_runtime": 4.9901,
+      "eval_samples_per_second": 11.222,
+      "eval_steps_per_second": 11.222,
+      "step": 200
+    },
+    {
+      "entropy": 0.5093934688717127,
+      "epoch": 1.4097397145256088,
+      "grad_norm": 0.31276237964630127,
+      "learning_rate": 3.084892086330935e-05,
+      "loss": 0.2882,
+      "mean_token_accuracy": 0.9080218151211739,
+      "num_tokens": 1390647.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.49913822263479235,
+      "epoch": 1.4769101595298069,
+      "grad_norm": 0.2638222575187683,
+      "learning_rate": 3.027338129496403e-05,
+      "loss": 0.32,
+      "mean_token_accuracy": 0.9011362835764885,
+      "num_tokens": 1458413.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.5291724860668182,
+      "epoch": 1.5440806045340052,
+      "grad_norm": 0.7974303960800171,
+      "learning_rate": 2.9697841726618707e-05,
+      "loss": 0.3437,
+      "mean_token_accuracy": 0.8957020588219166,
+      "num_tokens": 1529069.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.5148157492280007,
+      "epoch": 1.611251049538203,
+      "grad_norm": 0.3252256512641907,
+      "learning_rate": 2.9122302158273384e-05,
+      "loss": 0.3078,
+      "mean_token_accuracy": 0.8965719811618328,
+      "num_tokens": 1593891.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.5439612463116645,
+      "epoch": 1.6784214945424014,
+      "grad_norm": 0.3167729079723358,
+      "learning_rate": 2.854676258992806e-05,
+      "loss": 0.3331,
+      "mean_token_accuracy": 0.8926876865327358,
+      "num_tokens": 1658563.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.6784214945424014,
+      "eval_entropy": 0.8733608674790178,
+      "eval_loss": 0.8773566484451294,
+      "eval_mean_token_accuracy": 0.7638165514383998,
+      "eval_num_tokens": 1658563.0,
+      "eval_runtime": 4.9846,
+      "eval_samples_per_second": 11.235,
+      "eval_steps_per_second": 11.235,
+      "step": 250
+    },
+    {
+      "entropy": 0.5023419760167599,
+      "epoch": 1.7455919395465995,
+      "grad_norm": 0.30670592188835144,
+      "learning_rate": 2.7971223021582735e-05,
+      "loss": 0.3503,
+      "mean_token_accuracy": 0.8920910514891147,
+      "num_tokens": 1735767.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.5167030651122332,
+      "epoch": 1.8127623845507976,
+      "grad_norm": 0.25313618779182434,
+      "learning_rate": 2.7395683453237412e-05,
+      "loss": 0.3242,
+      "mean_token_accuracy": 0.8931105189025402,
+      "num_tokens": 1802895.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.5199910126626491,
+      "epoch": 1.879932829554996,
+      "grad_norm": 0.3637166917324066,
+      "learning_rate": 2.6820143884892086e-05,
+      "loss": 0.3145,
+      "mean_token_accuracy": 0.8975049994885922,
+      "num_tokens": 1865468.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.5213575050234794,
+      "epoch": 1.9471032745591939,
+      "grad_norm": 0.3701685965061188,
+      "learning_rate": 2.6244604316546767e-05,
+      "loss": 0.3398,
+      "mean_token_accuracy": 0.896855977922678,
+      "num_tokens": 1932031.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.4997344066070605,
+      "epoch": 2.0134340890008398,
+      "grad_norm": 0.331307590007782,
+      "learning_rate": 2.566906474820144e-05,
+      "loss": 0.2637,
+      "mean_token_accuracy": 0.9088972090165827,
+      "num_tokens": 1992713.0,
+      "step": 300
+    },
+    {
+      "epoch": 2.0134340890008398,
+      "eval_entropy": 0.9004479699901172,
+      "eval_loss": 0.8707331418991089,
+      "eval_mean_token_accuracy": 0.7641822940536908,
+      "eval_num_tokens": 1992713.0,
+      "eval_runtime": 4.9809,
+      "eval_samples_per_second": 11.243,
+      "eval_steps_per_second": 11.243,
+      "step": 300
+    },
+    {
+      "entropy": 0.47825686521828176,
+      "epoch": 2.0806045340050376,
+      "grad_norm": 0.3079531192779541,
+      "learning_rate": 2.5093525179856118e-05,
+      "loss": 0.2863,
+      "mean_token_accuracy": 0.908924800157547,
+      "num_tokens": 2061833.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.48984590619802476,
+      "epoch": 2.147774979009236,
+      "grad_norm": 0.2569948434829712,
+      "learning_rate": 2.451798561151079e-05,
+      "loss": 0.3162,
+      "mean_token_accuracy": 0.903419229388237,
+      "num_tokens": 2132082.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.46938193738460543,
+      "epoch": 2.2149454240134343,
+      "grad_norm": 0.29792118072509766,
+      "learning_rate": 2.394244604316547e-05,
+      "loss": 0.2943,
+      "mean_token_accuracy": 0.9081865437328815,
+      "num_tokens": 2202270.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.4853254608809948,
+      "epoch": 2.282115869017632,
+      "grad_norm": 0.26585960388183594,
+      "learning_rate": 2.336690647482015e-05,
+      "loss": 0.2682,
+      "mean_token_accuracy": 0.9112951382994652,
+      "num_tokens": 2263789.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.49189864136278627,
+      "epoch": 2.3492863140218305,
+      "grad_norm": 0.2741142213344574,
+      "learning_rate": 2.2791366906474823e-05,
+      "loss": 0.313,
+      "mean_token_accuracy": 0.8986666277050972,
+      "num_tokens": 2334071.0,
+      "step": 350
+    },
+    {
+      "epoch": 2.3492863140218305,
+      "eval_entropy": 0.8618932158819267,
+      "eval_loss": 0.8953577280044556,
+      "eval_mean_token_accuracy": 0.7628704607486725,
+      "eval_num_tokens": 2334071.0,
+      "eval_runtime": 4.984,
+      "eval_samples_per_second": 11.236,
+      "eval_steps_per_second": 11.236,
+      "step": 350
+    },
+    {
+      "entropy": 0.49905899055302144,
+      "epoch": 2.4164567590260284,
+      "grad_norm": 0.3090650141239166,
+      "learning_rate": 2.22158273381295e-05,
+      "loss": 0.2886,
+      "mean_token_accuracy": 0.9060709603130818,
+      "num_tokens": 2396966.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.49515552036464217,
+      "epoch": 2.4836272040302267,
+      "grad_norm": 0.3477407991886139,
+      "learning_rate": 2.1640287769784174e-05,
+      "loss": 0.2685,
+      "mean_token_accuracy": 0.9104222223162651,
+      "num_tokens": 2457974.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.5188349276781082,
+      "epoch": 2.5507976490344246,
+      "grad_norm": 0.2762923538684845,
+      "learning_rate": 2.1064748201438848e-05,
+      "loss": 0.2911,
+      "mean_token_accuracy": 0.9037038788199425,
+      "num_tokens": 2526344.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.5011733949184418,
+      "epoch": 2.617968094038623,
+      "grad_norm": 0.2646786570549011,
+      "learning_rate": 2.0489208633093525e-05,
+      "loss": 0.3158,
+      "mean_token_accuracy": 0.9090628199279308,
+      "num_tokens": 2596395.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.49840320982038977,
+      "epoch": 2.6851385390428213,
+      "grad_norm": 0.4310755431652069,
+      "learning_rate": 1.9913669064748202e-05,
+      "loss": 0.2887,
+      "mean_token_accuracy": 0.9083616696298122,
+      "num_tokens": 2657920.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.6851385390428213,
+      "eval_entropy": 0.8837019130587578,
+      "eval_loss": 0.88917475938797,
+      "eval_mean_token_accuracy": 0.763011426797935,
+      "eval_num_tokens": 2657920.0,
+      "eval_runtime": 4.9877,
+      "eval_samples_per_second": 11.228,
+      "eval_steps_per_second": 11.228,
+      "step": 400
+    },
+    {
+      "entropy": 0.4771813187748194,
+      "epoch": 2.752308984047019,
+      "grad_norm": 0.32867103815078735,
+      "learning_rate": 1.933812949640288e-05,
+      "loss": 0.2668,
+      "mean_token_accuracy": 0.9088380873203278,
+      "num_tokens": 2725640.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.47720473557710646,
+      "epoch": 2.8194794290512175,
+      "grad_norm": 0.27547284960746765,
+      "learning_rate": 1.8762589928057556e-05,
+      "loss": 0.2725,
+      "mean_token_accuracy": 0.9101646140217781,
+      "num_tokens": 2789853.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.45747280344367025,
+      "epoch": 2.886649874055416,
+      "grad_norm": 0.3139909505844116,
+      "learning_rate": 1.8187050359712234e-05,
+      "loss": 0.267,
+      "mean_token_accuracy": 0.9148379288613796,
+      "num_tokens": 2857093.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.46566248275339606,
+      "epoch": 2.9538203190596137,
+      "grad_norm": 0.3694741427898407,
+      "learning_rate": 1.7611510791366907e-05,
+      "loss": 0.2995,
+      "mean_token_accuracy": 0.901902287453413,
+      "num_tokens": 2928087.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.47634567490106894,
+      "epoch": 3.0201511335012596,
+      "grad_norm": 0.26703643798828125,
+      "learning_rate": 1.7035971223021584e-05,
+      "loss": 0.3174,
+      "mean_token_accuracy": 0.9040401434596581,
+      "num_tokens": 2993485.0,
+      "step": 450
+    },
+    {
+      "epoch": 3.0201511335012596,
+      "eval_entropy": 0.8348773148443017,
+      "eval_loss": 0.8874495625495911,
+      "eval_mean_token_accuracy": 0.7612802609801292,
+      "eval_num_tokens": 2993485.0,
+      "eval_runtime": 4.9913,
+      "eval_samples_per_second": 11.22,
+      "eval_steps_per_second": 11.22,
+      "step": 450
+    },
+    {
+      "entropy": 0.44407146945595743,
+      "epoch": 3.0873215785054575,
+      "grad_norm": 0.27298107743263245,
+      "learning_rate": 1.646043165467626e-05,
+      "loss": 0.2888,
+      "mean_token_accuracy": 0.9176116026937962,
+      "num_tokens": 3062721.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.4276166781783104,
+      "epoch": 3.154492023509656,
+      "grad_norm": 0.2755906879901886,
+      "learning_rate": 1.5884892086330935e-05,
+      "loss": 0.2419,
+      "mean_token_accuracy": 0.9195634700357914,
+      "num_tokens": 3129709.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.4346423916518688,
+      "epoch": 3.2216624685138537,
+      "grad_norm": 0.39296212792396545,
+      "learning_rate": 1.5309352517985613e-05,
+      "loss": 0.233,
+      "mean_token_accuracy": 0.9278727151453495,
+      "num_tokens": 3189161.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.44294624738395216,
+      "epoch": 3.288832913518052,
+      "grad_norm": 0.39035606384277344,
+      "learning_rate": 1.473381294964029e-05,
+      "loss": 0.2781,
+      "mean_token_accuracy": 0.9181225150823593,
+      "num_tokens": 3255403.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.4794738654047251,
+      "epoch": 3.3560033585222504,
+      "grad_norm": 0.3938174545764923,
+      "learning_rate": 1.4158273381294965e-05,
+      "loss": 0.2942,
+      "mean_token_accuracy": 0.9075012236833573,
+      "num_tokens": 3320554.0,
+      "step": 500
+    },
+    {
+      "epoch": 3.3560033585222504,
+      "eval_entropy": 0.817679978374924,
+      "eval_loss": 0.9140912294387817,
+      "eval_mean_token_accuracy": 0.761023474591119,
+      "eval_num_tokens": 3320554.0,
+      "eval_runtime": 4.9833,
+      "eval_samples_per_second": 11.238,
+      "eval_steps_per_second": 11.238,
+      "step": 500
+    },
+    {
+      "entropy": 0.4701398782432079,
+      "epoch": 3.4231738035264483,
+      "grad_norm": 0.4412434697151184,
+      "learning_rate": 1.3582733812949642e-05,
+      "loss": 0.2707,
+      "mean_token_accuracy": 0.9106249861419201,
+      "num_tokens": 3384303.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.45122345685958865,
+      "epoch": 3.4903442485306466,
+      "grad_norm": 0.26691338419914246,
+      "learning_rate": 1.3007194244604318e-05,
+      "loss": 0.258,
+      "mean_token_accuracy": 0.9156571164727211,
+      "num_tokens": 3451764.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.4313320998102427,
+      "epoch": 3.5575146935348445,
+      "grad_norm": 0.34582847356796265,
+      "learning_rate": 1.2431654676258993e-05,
+      "loss": 0.2612,
+      "mean_token_accuracy": 0.916472752392292,
+      "num_tokens": 3522461.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.43578826524317266,
+      "epoch": 3.624685138539043,
+      "grad_norm": 0.4498523771762848,
+      "learning_rate": 1.185611510791367e-05,
+      "loss": 0.2834,
+      "mean_token_accuracy": 0.9140046447515487,
+      "num_tokens": 3591502.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.4625163245946169,
+      "epoch": 3.6918555835432407,
+      "grad_norm": 0.3399084806442261,
+      "learning_rate": 1.1280575539568346e-05,
+      "loss": 0.2906,
+      "mean_token_accuracy": 0.9062492586672306,
+      "num_tokens": 3659203.0,
+      "step": 550
+    },
+    {
+      "epoch": 3.6918555835432407,
+      "eval_entropy": 0.8242657040911061,
+      "eval_loss": 0.9106144905090332,
+      "eval_mean_token_accuracy": 0.7601779720612934,
+      "eval_num_tokens": 3659203.0,
+      "eval_runtime": 4.9925,
+      "eval_samples_per_second": 11.217,
+      "eval_steps_per_second": 11.217,
+      "step": 550
+    },
+    {
+      "entropy": 0.44798229187726973,
+      "epoch": 3.759026028547439,
+      "grad_norm": 0.28008008003234863,
+      "learning_rate": 1.0705035971223023e-05,
+      "loss": 0.2947,
+      "mean_token_accuracy": 0.9083551168441772,
+      "num_tokens": 3735002.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.438993413746357,
+      "epoch": 3.8261964735516374,
+      "grad_norm": 0.33622145652770996,
+      "learning_rate": 1.0129496402877699e-05,
+      "loss": 0.2536,
+      "mean_token_accuracy": 0.9168887868523597,
+      "num_tokens": 3798345.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.43377807587385175,
+      "epoch": 3.8933669185558353,
+      "grad_norm": 0.41980335116386414,
+      "learning_rate": 9.553956834532376e-06,
+      "loss": 0.2414,
+      "mean_token_accuracy": 0.925646186619997,
+      "num_tokens": 3859139.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.43494608998298645,
+      "epoch": 3.9605373635600336,
+      "grad_norm": 0.29723235964775085,
+      "learning_rate": 8.978417266187051e-06,
+      "loss": 0.2619,
+      "mean_token_accuracy": 0.9199615843594074,
+      "num_tokens": 3923018.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.42559608741651606,
+      "epoch": 4.0268681780016795,
+      "grad_norm": 0.32702481746673584,
+      "learning_rate": 8.402877697841727e-06,
+      "loss": 0.2393,
+      "mean_token_accuracy": 0.9227683498889585,
+      "num_tokens": 3985896.0,
+      "step": 600
+    },
+    {
+      "epoch": 4.0268681780016795,
+      "eval_entropy": 0.790077348372766,
+      "eval_loss": 0.929413378238678,
+      "eval_mean_token_accuracy": 0.7607843939747129,
+      "eval_num_tokens": 3985896.0,
+      "eval_runtime": 4.9875,
+      "eval_samples_per_second": 11.228,
+      "eval_steps_per_second": 11.228,
+      "step": 600
+    },
+    {
+      "entropy": 0.4118167482316494,
+      "epoch": 4.094038623005877,
+      "grad_norm": 0.3099454641342163,
+      "learning_rate": 7.827338129496404e-06,
+      "loss": 0.2197,
+      "mean_token_accuracy": 0.9286121532320977,
+      "num_tokens": 4046640.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.42818755134940145,
+      "epoch": 4.161209068010075,
+      "grad_norm": 0.3183671236038208,
+      "learning_rate": 7.25179856115108e-06,
+      "loss": 0.2681,
+      "mean_token_accuracy": 0.9148878164589405,
+      "num_tokens": 4115433.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.4235291346907616,
+      "epoch": 4.228379513014274,
+      "grad_norm": 0.3553420603275299,
+      "learning_rate": 6.6762589928057564e-06,
+      "loss": 0.2386,
+      "mean_token_accuracy": 0.9219062335789203,
+      "num_tokens": 4177541.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.43433762453496455,
+      "epoch": 4.295549958018472,
+      "grad_norm": 0.47075527906417847,
+      "learning_rate": 6.100719424460432e-06,
+      "loss": 0.2696,
+      "mean_token_accuracy": 0.9177930898964405,
+      "num_tokens": 4248216.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.43204528763890265,
+      "epoch": 4.36272040302267,
+      "grad_norm": 0.34699931740760803,
+      "learning_rate": 5.525179856115108e-06,
+      "loss": 0.2697,
+      "mean_token_accuracy": 0.9196366496384144,
+      "num_tokens": 4319252.0,
+      "step": 650
+    },
+    {
+      "epoch": 4.36272040302267,
+      "eval_entropy": 0.7843316655073848,
+      "eval_loss": 0.9468327164649963,
+      "eval_mean_token_accuracy": 0.7589835811938558,
+      "eval_num_tokens": 4319252.0,
+      "eval_runtime": 4.9823,
+      "eval_samples_per_second": 11.24,
+      "eval_steps_per_second": 11.24,
+      "step": 650
+    },
+    {
+      "entropy": 0.4113185711205006,
+      "epoch": 4.429890848026869,
+      "grad_norm": 0.3835369050502777,
+      "learning_rate": 4.9496402877697845e-06,
+      "loss": 0.2489,
+      "mean_token_accuracy": 0.9217935107648373,
+      "num_tokens": 4389439.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.4268360245972872,
+      "epoch": 4.4970612930310665,
+      "grad_norm": 0.32893145084381104,
+      "learning_rate": 4.374100719424461e-06,
+      "loss": 0.2546,
+      "mean_token_accuracy": 0.9204200245440006,
+      "num_tokens": 4454296.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.43092771619558334,
+      "epoch": 4.564231738035264,
+      "grad_norm": 0.35402655601501465,
+      "learning_rate": 3.798561151079137e-06,
+      "loss": 0.2528,
+      "mean_token_accuracy": 0.9206391289830208,
+      "num_tokens": 4516174.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.40939035564661025,
+      "epoch": 4.631402183039462,
+      "grad_norm": 0.32696768641471863,
+      "learning_rate": 3.223021582733813e-06,
+      "loss": 0.2567,
+      "mean_token_accuracy": 0.9263360798358917,
+      "num_tokens": 4586677.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.42081440389156344,
+      "epoch": 4.698572628043661,
+      "grad_norm": 0.3911837637424469,
+      "learning_rate": 2.6474820143884894e-06,
+      "loss": 0.21,
+      "mean_token_accuracy": 0.9308864399790764,
+      "num_tokens": 4643628.0,
+      "step": 700
+    },
+    {
+      "epoch": 4.698572628043661,
+      "eval_entropy": 0.7831281987684113,
+      "eval_loss": 0.9461870789527893,
+      "eval_mean_token_accuracy": 0.7588864458458764,
+      "eval_num_tokens": 4643628.0,
+      "eval_runtime": 4.9942,
+      "eval_samples_per_second": 11.213,
+      "eval_steps_per_second": 11.213,
+      "step": 700
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 745,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.949067928266752e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-700/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce196e5bc1fecba594008114c4c5772643cb32ef5927e83c6ed6f3b11728deb6
+size 6161

checkpoint-745/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/QwQ-32B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/QwQ-32B
+- 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 0.17.1

checkpoint-745/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/QwQ-32B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-745/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ce34ab4b06df6d0713cdcc16c5dd3631c9ec79c7e34e40da9416529ab1b90e
+size 536940800

checkpoint-745/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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-745/chat_template.jinja

@@ -0,0 +1,62 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- '' }}
+    {%- 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' }}
+  {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" and not message.tool_calls %}
+        {%- set content = message.content %}
+        {%- if not loop.last %}
+            {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+        {%- endif %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- if not loop.last %}
+            {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+        {%- endif %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + 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<think>\n' }}
+{%- endif %}

checkpoint-745/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de83ee6ba6d61f417990795c29463cbe348d9f7924abadf0d546355f005078e
+size 1074182115

checkpoint-745/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e51a42ec5ffac256f3cd0ee0ccd7a6d3befe58914ad400c0cc707bc4a5ee283
+size 14645

checkpoint-745/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa27e8582d741b9c0d8dd9c1fcd2f706d12284bfd905266c1590ad674aedadd
+size 1465

checkpoint-745/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-745/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-745/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-745/trainer_state.json

@@ -0,0 +1,928 @@
+{
+  "best_global_step": 150,
+  "best_metric": 0.8634624481201172,
+  "best_model_checkpoint": "lora_deception_model/checkpoint-100",
+  "epoch": 5.0,
+  "eval_steps": 50,
+  "global_step": 745,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.6688848555088043,
+      "epoch": 0.06717044500419815,
+      "grad_norm": 0.3304958939552307,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.8658,
+      "mean_token_accuracy": 0.8207968935370445,
+      "num_tokens": 63133.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.6755495790392161,
+      "epoch": 0.1343408900083963,
+      "grad_norm": 0.32398757338523865,
+      "learning_rate": 1.5200000000000002e-05,
+      "loss": 0.8662,
+      "mean_token_accuracy": 0.8197331622242927,
+      "num_tokens": 124489.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.734241085499525,
+      "epoch": 0.20151133501259447,
+      "grad_norm": 0.31472697854042053,
+      "learning_rate": 2.32e-05,
+      "loss": 0.7134,
+      "mean_token_accuracy": 0.8222098298370838,
+      "num_tokens": 189081.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.8794498354196548,
+      "epoch": 0.2686817800167926,
+      "grad_norm": 0.23867088556289673,
+      "learning_rate": 3.1200000000000006e-05,
+      "loss": 0.6577,
+      "mean_token_accuracy": 0.820378091186285,
+      "num_tokens": 270096.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.9822202995419502,
+      "epoch": 0.33585222502099077,
+      "grad_norm": 0.23442600667476654,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 0.5764,
+      "mean_token_accuracy": 0.8329788409173489,
+      "num_tokens": 343034.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.33585222502099077,
+      "eval_entropy": 1.35109115924154,
+      "eval_loss": 0.9188798666000366,
+      "eval_mean_token_accuracy": 0.7514589822718075,
+      "eval_num_tokens": 343034.0,
+      "eval_runtime": 5.1522,
+      "eval_samples_per_second": 10.869,
+      "eval_steps_per_second": 10.869,
+      "step": 50
+    },
+    {
+      "entropy": 0.8484722189605236,
+      "epoch": 0.40302267002518893,
+      "grad_norm": 0.27580252289772034,
+      "learning_rate": 3.948201438848921e-05,
+      "loss": 0.4939,
+      "mean_token_accuracy": 0.8525501079857349,
+      "num_tokens": 407346.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.7665611129254103,
+      "epoch": 0.47019311502938704,
+      "grad_norm": 0.32506343722343445,
+      "learning_rate": 3.8906474820143886e-05,
+      "loss": 0.4095,
+      "mean_token_accuracy": 0.8701820805668831,
+      "num_tokens": 466070.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.7331306278705597,
+      "epoch": 0.5373635600335852,
+      "grad_norm": 0.3568798899650574,
+      "learning_rate": 3.833093525179856e-05,
+      "loss": 0.448,
+      "mean_token_accuracy": 0.863949628919363,
+      "num_tokens": 536560.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.7565343648195266,
+      "epoch": 0.6045340050377834,
+      "grad_norm": 0.3249973952770233,
+      "learning_rate": 3.775539568345324e-05,
+      "loss": 0.4065,
+      "mean_token_accuracy": 0.8672126568853855,
+      "num_tokens": 597642.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.6388500925153494,
+      "epoch": 0.6717044500419815,
+      "grad_norm": 0.36163443326950073,
+      "learning_rate": 3.7179856115107914e-05,
+      "loss": 0.3693,
+      "mean_token_accuracy": 0.8828025683760643,
+      "num_tokens": 663210.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.6717044500419815,
+      "eval_entropy": 1.0956847156797136,
+      "eval_loss": 0.8651557564735413,
+      "eval_mean_token_accuracy": 0.7637390036668096,
+      "eval_num_tokens": 663210.0,
+      "eval_runtime": 4.9833,
+      "eval_samples_per_second": 11.237,
+      "eval_steps_per_second": 11.237,
+      "step": 100
+    },
+    {
+      "entropy": 0.6128827821463346,
+      "epoch": 0.7388748950461796,
+      "grad_norm": 0.29096513986587524,
+      "learning_rate": 3.6604316546762595e-05,
+      "loss": 0.3719,
+      "mean_token_accuracy": 0.8851677082479,
+      "num_tokens": 726617.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.6564031228423118,
+      "epoch": 0.8060453400503779,
+      "grad_norm": 0.27515140175819397,
+      "learning_rate": 3.602877697841727e-05,
+      "loss": 0.3935,
+      "mean_token_accuracy": 0.8752141006290912,
+      "num_tokens": 800821.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.6125180713832379,
+      "epoch": 0.873215785054576,
+      "grad_norm": 0.3126560151576996,
+      "learning_rate": 3.545323741007194e-05,
+      "loss": 0.3847,
+      "mean_token_accuracy": 0.8818505816161633,
+      "num_tokens": 868710.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.6347699824720621,
+      "epoch": 0.9403862300587741,
+      "grad_norm": 0.23533445596694946,
+      "learning_rate": 3.487769784172662e-05,
+      "loss": 0.385,
+      "mean_token_accuracy": 0.8835290059447288,
+      "num_tokens": 935575.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.579044715513157,
+      "epoch": 1.0067170445004199,
+      "grad_norm": 0.2643934488296509,
+      "learning_rate": 3.43021582733813e-05,
+      "loss": 0.3224,
+      "mean_token_accuracy": 0.8946574262425869,
+      "num_tokens": 996466.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.0067170445004199,
+      "eval_entropy": 0.9877308234572411,
+      "eval_loss": 0.8634624481201172,
+      "eval_mean_token_accuracy": 0.7611759411437171,
+      "eval_num_tokens": 996466.0,
+      "eval_runtime": 4.9854,
+      "eval_samples_per_second": 11.233,
+      "eval_steps_per_second": 11.233,
+      "step": 150
+    },
+    {
+      "entropy": 0.552555637806654,
+      "epoch": 1.073887489504618,
+      "grad_norm": 0.2633912265300751,
+      "learning_rate": 3.372661870503598e-05,
+      "loss": 0.3265,
+      "mean_token_accuracy": 0.8968047671020031,
+      "num_tokens": 1066789.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.5594113569706678,
+      "epoch": 1.141057934508816,
+      "grad_norm": 0.2680589258670807,
+      "learning_rate": 3.315107913669065e-05,
+      "loss": 0.3519,
+      "mean_token_accuracy": 0.8886663600802421,
+      "num_tokens": 1138401.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.5540055774152279,
+      "epoch": 1.2082283795130142,
+      "grad_norm": 0.27169251441955566,
+      "learning_rate": 3.2575539568345325e-05,
+      "loss": 0.3436,
+      "mean_token_accuracy": 0.8913260444998741,
+      "num_tokens": 1202735.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.5612262919545173,
+      "epoch": 1.2753988245172123,
+      "grad_norm": 0.3151009976863861,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.351,
+      "mean_token_accuracy": 0.8909851491451264,
+      "num_tokens": 1266476.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.5354872807860375,
+      "epoch": 1.3425692695214106,
+      "grad_norm": 0.29847052693367004,
+      "learning_rate": 3.142446043165468e-05,
+      "loss": 0.3045,
+      "mean_token_accuracy": 0.9023352213203907,
+      "num_tokens": 1327389.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.3425692695214106,
+      "eval_entropy": 0.9606236421636173,
+      "eval_loss": 0.8751164078712463,
+      "eval_mean_token_accuracy": 0.7617330902389118,
+      "eval_num_tokens": 1327389.0,
+      "eval_runtime": 4.9901,
+      "eval_samples_per_second": 11.222,
+      "eval_steps_per_second": 11.222,
+      "step": 200
+    },
+    {
+      "entropy": 0.5093934688717127,
+      "epoch": 1.4097397145256088,
+      "grad_norm": 0.31276237964630127,
+      "learning_rate": 3.084892086330935e-05,
+      "loss": 0.2882,
+      "mean_token_accuracy": 0.9080218151211739,
+      "num_tokens": 1390647.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.49913822263479235,
+      "epoch": 1.4769101595298069,
+      "grad_norm": 0.2638222575187683,
+      "learning_rate": 3.027338129496403e-05,
+      "loss": 0.32,
+      "mean_token_accuracy": 0.9011362835764885,
+      "num_tokens": 1458413.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.5291724860668182,
+      "epoch": 1.5440806045340052,
+      "grad_norm": 0.7974303960800171,
+      "learning_rate": 2.9697841726618707e-05,
+      "loss": 0.3437,
+      "mean_token_accuracy": 0.8957020588219166,
+      "num_tokens": 1529069.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.5148157492280007,
+      "epoch": 1.611251049538203,
+      "grad_norm": 0.3252256512641907,
+      "learning_rate": 2.9122302158273384e-05,
+      "loss": 0.3078,
+      "mean_token_accuracy": 0.8965719811618328,
+      "num_tokens": 1593891.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.5439612463116645,
+      "epoch": 1.6784214945424014,
+      "grad_norm": 0.3167729079723358,
+      "learning_rate": 2.854676258992806e-05,
+      "loss": 0.3331,
+      "mean_token_accuracy": 0.8926876865327358,
+      "num_tokens": 1658563.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.6784214945424014,
+      "eval_entropy": 0.8733608674790178,
+      "eval_loss": 0.8773566484451294,
+      "eval_mean_token_accuracy": 0.7638165514383998,
+      "eval_num_tokens": 1658563.0,
+      "eval_runtime": 4.9846,
+      "eval_samples_per_second": 11.235,
+      "eval_steps_per_second": 11.235,
+      "step": 250
+    },
+    {
+      "entropy": 0.5023419760167599,
+      "epoch": 1.7455919395465995,
+      "grad_norm": 0.30670592188835144,
+      "learning_rate": 2.7971223021582735e-05,
+      "loss": 0.3503,
+      "mean_token_accuracy": 0.8920910514891147,
+      "num_tokens": 1735767.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.5167030651122332,
+      "epoch": 1.8127623845507976,
+      "grad_norm": 0.25313618779182434,
+      "learning_rate": 2.7395683453237412e-05,
+      "loss": 0.3242,
+      "mean_token_accuracy": 0.8931105189025402,
+      "num_tokens": 1802895.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.5199910126626491,
+      "epoch": 1.879932829554996,
+      "grad_norm": 0.3637166917324066,
+      "learning_rate": 2.6820143884892086e-05,
+      "loss": 0.3145,
+      "mean_token_accuracy": 0.8975049994885922,
+      "num_tokens": 1865468.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.5213575050234794,
+      "epoch": 1.9471032745591939,
+      "grad_norm": 0.3701685965061188,
+      "learning_rate": 2.6244604316546767e-05,
+      "loss": 0.3398,
+      "mean_token_accuracy": 0.896855977922678,
+      "num_tokens": 1932031.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.4997344066070605,
+      "epoch": 2.0134340890008398,
+      "grad_norm": 0.331307590007782,
+      "learning_rate": 2.566906474820144e-05,
+      "loss": 0.2637,
+      "mean_token_accuracy": 0.9088972090165827,
+      "num_tokens": 1992713.0,
+      "step": 300
+    },
+    {
+      "epoch": 2.0134340890008398,
+      "eval_entropy": 0.9004479699901172,
+      "eval_loss": 0.8707331418991089,
+      "eval_mean_token_accuracy": 0.7641822940536908,
+      "eval_num_tokens": 1992713.0,
+      "eval_runtime": 4.9809,
+      "eval_samples_per_second": 11.243,
+      "eval_steps_per_second": 11.243,
+      "step": 300
+    },
+    {
+      "entropy": 0.47825686521828176,
+      "epoch": 2.0806045340050376,
+      "grad_norm": 0.3079531192779541,
+      "learning_rate": 2.5093525179856118e-05,
+      "loss": 0.2863,
+      "mean_token_accuracy": 0.908924800157547,
+      "num_tokens": 2061833.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.48984590619802476,
+      "epoch": 2.147774979009236,
+      "grad_norm": 0.2569948434829712,
+      "learning_rate": 2.451798561151079e-05,
+      "loss": 0.3162,
+      "mean_token_accuracy": 0.903419229388237,
+      "num_tokens": 2132082.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.46938193738460543,
+      "epoch": 2.2149454240134343,
+      "grad_norm": 0.29792118072509766,
+      "learning_rate": 2.394244604316547e-05,
+      "loss": 0.2943,
+      "mean_token_accuracy": 0.9081865437328815,
+      "num_tokens": 2202270.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.4853254608809948,
+      "epoch": 2.282115869017632,
+      "grad_norm": 0.26585960388183594,
+      "learning_rate": 2.336690647482015e-05,
+      "loss": 0.2682,
+      "mean_token_accuracy": 0.9112951382994652,
+      "num_tokens": 2263789.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.49189864136278627,
+      "epoch": 2.3492863140218305,
+      "grad_norm": 0.2741142213344574,
+      "learning_rate": 2.2791366906474823e-05,
+      "loss": 0.313,
+      "mean_token_accuracy": 0.8986666277050972,
+      "num_tokens": 2334071.0,
+      "step": 350
+    },
+    {
+      "epoch": 2.3492863140218305,
+      "eval_entropy": 0.8618932158819267,
+      "eval_loss": 0.8953577280044556,
+      "eval_mean_token_accuracy": 0.7628704607486725,
+      "eval_num_tokens": 2334071.0,
+      "eval_runtime": 4.984,
+      "eval_samples_per_second": 11.236,
+      "eval_steps_per_second": 11.236,
+      "step": 350
+    },
+    {
+      "entropy": 0.49905899055302144,
+      "epoch": 2.4164567590260284,
+      "grad_norm": 0.3090650141239166,
+      "learning_rate": 2.22158273381295e-05,
+      "loss": 0.2886,
+      "mean_token_accuracy": 0.9060709603130818,
+      "num_tokens": 2396966.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.49515552036464217,
+      "epoch": 2.4836272040302267,
+      "grad_norm": 0.3477407991886139,
+      "learning_rate": 2.1640287769784174e-05,
+      "loss": 0.2685,
+      "mean_token_accuracy": 0.9104222223162651,
+      "num_tokens": 2457974.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.5188349276781082,
+      "epoch": 2.5507976490344246,
+      "grad_norm": 0.2762923538684845,
+      "learning_rate": 2.1064748201438848e-05,
+      "loss": 0.2911,
+      "mean_token_accuracy": 0.9037038788199425,
+      "num_tokens": 2526344.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.5011733949184418,
+      "epoch": 2.617968094038623,
+      "grad_norm": 0.2646786570549011,
+      "learning_rate": 2.0489208633093525e-05,
+      "loss": 0.3158,
+      "mean_token_accuracy": 0.9090628199279308,
+      "num_tokens": 2596395.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.49840320982038977,
+      "epoch": 2.6851385390428213,
+      "grad_norm": 0.4310755431652069,
+      "learning_rate": 1.9913669064748202e-05,
+      "loss": 0.2887,
+      "mean_token_accuracy": 0.9083616696298122,
+      "num_tokens": 2657920.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.6851385390428213,
+      "eval_entropy": 0.8837019130587578,
+      "eval_loss": 0.88917475938797,
+      "eval_mean_token_accuracy": 0.763011426797935,
+      "eval_num_tokens": 2657920.0,
+      "eval_runtime": 4.9877,
+      "eval_samples_per_second": 11.228,
+      "eval_steps_per_second": 11.228,
+      "step": 400
+    },
+    {
+      "entropy": 0.4771813187748194,
+      "epoch": 2.752308984047019,
+      "grad_norm": 0.32867103815078735,
+      "learning_rate": 1.933812949640288e-05,
+      "loss": 0.2668,
+      "mean_token_accuracy": 0.9088380873203278,
+      "num_tokens": 2725640.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.47720473557710646,
+      "epoch": 2.8194794290512175,
+      "grad_norm": 0.27547284960746765,
+      "learning_rate": 1.8762589928057556e-05,
+      "loss": 0.2725,
+      "mean_token_accuracy": 0.9101646140217781,
+      "num_tokens": 2789853.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.45747280344367025,
+      "epoch": 2.886649874055416,
+      "grad_norm": 0.3139909505844116,
+      "learning_rate": 1.8187050359712234e-05,
+      "loss": 0.267,
+      "mean_token_accuracy": 0.9148379288613796,
+      "num_tokens": 2857093.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.46566248275339606,
+      "epoch": 2.9538203190596137,
+      "grad_norm": 0.3694741427898407,
+      "learning_rate": 1.7611510791366907e-05,
+      "loss": 0.2995,
+      "mean_token_accuracy": 0.901902287453413,
+      "num_tokens": 2928087.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.47634567490106894,
+      "epoch": 3.0201511335012596,
+      "grad_norm": 0.26703643798828125,
+      "learning_rate": 1.7035971223021584e-05,
+      "loss": 0.3174,
+      "mean_token_accuracy": 0.9040401434596581,
+      "num_tokens": 2993485.0,
+      "step": 450
+    },
+    {
+      "epoch": 3.0201511335012596,
+      "eval_entropy": 0.8348773148443017,
+      "eval_loss": 0.8874495625495911,
+      "eval_mean_token_accuracy": 0.7612802609801292,
+      "eval_num_tokens": 2993485.0,
+      "eval_runtime": 4.9913,
+      "eval_samples_per_second": 11.22,
+      "eval_steps_per_second": 11.22,
+      "step": 450
+    },
+    {
+      "entropy": 0.44407146945595743,
+      "epoch": 3.0873215785054575,
+      "grad_norm": 0.27298107743263245,
+      "learning_rate": 1.646043165467626e-05,
+      "loss": 0.2888,
+      "mean_token_accuracy": 0.9176116026937962,
+      "num_tokens": 3062721.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.4276166781783104,
+      "epoch": 3.154492023509656,
+      "grad_norm": 0.2755906879901886,
+      "learning_rate": 1.5884892086330935e-05,
+      "loss": 0.2419,
+      "mean_token_accuracy": 0.9195634700357914,
+      "num_tokens": 3129709.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.4346423916518688,
+      "epoch": 3.2216624685138537,
+      "grad_norm": 0.39296212792396545,
+      "learning_rate": 1.5309352517985613e-05,
+      "loss": 0.233,
+      "mean_token_accuracy": 0.9278727151453495,
+      "num_tokens": 3189161.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.44294624738395216,
+      "epoch": 3.288832913518052,
+      "grad_norm": 0.39035606384277344,
+      "learning_rate": 1.473381294964029e-05,
+      "loss": 0.2781,
+      "mean_token_accuracy": 0.9181225150823593,
+      "num_tokens": 3255403.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.4794738654047251,
+      "epoch": 3.3560033585222504,
+      "grad_norm": 0.3938174545764923,
+      "learning_rate": 1.4158273381294965e-05,
+      "loss": 0.2942,
+      "mean_token_accuracy": 0.9075012236833573,
+      "num_tokens": 3320554.0,
+      "step": 500
+    },
+    {
+      "epoch": 3.3560033585222504,
+      "eval_entropy": 0.817679978374924,
+      "eval_loss": 0.9140912294387817,
+      "eval_mean_token_accuracy": 0.761023474591119,
+      "eval_num_tokens": 3320554.0,
+      "eval_runtime": 4.9833,
+      "eval_samples_per_second": 11.238,
+      "eval_steps_per_second": 11.238,
+      "step": 500
+    },
+    {
+      "entropy": 0.4701398782432079,
+      "epoch": 3.4231738035264483,
+      "grad_norm": 0.4412434697151184,
+      "learning_rate": 1.3582733812949642e-05,
+      "loss": 0.2707,
+      "mean_token_accuracy": 0.9106249861419201,
+      "num_tokens": 3384303.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.45122345685958865,
+      "epoch": 3.4903442485306466,
+      "grad_norm": 0.26691338419914246,
+      "learning_rate": 1.3007194244604318e-05,
+      "loss": 0.258,
+      "mean_token_accuracy": 0.9156571164727211,
+      "num_tokens": 3451764.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.4313320998102427,
+      "epoch": 3.5575146935348445,
+      "grad_norm": 0.34582847356796265,
+      "learning_rate": 1.2431654676258993e-05,
+      "loss": 0.2612,
+      "mean_token_accuracy": 0.916472752392292,
+      "num_tokens": 3522461.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.43578826524317266,
+      "epoch": 3.624685138539043,
+      "grad_norm": 0.4498523771762848,
+      "learning_rate": 1.185611510791367e-05,
+      "loss": 0.2834,
+      "mean_token_accuracy": 0.9140046447515487,
+      "num_tokens": 3591502.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.4625163245946169,
+      "epoch": 3.6918555835432407,
+      "grad_norm": 0.3399084806442261,
+      "learning_rate": 1.1280575539568346e-05,
+      "loss": 0.2906,
+      "mean_token_accuracy": 0.9062492586672306,
+      "num_tokens": 3659203.0,
+      "step": 550
+    },
+    {
+      "epoch": 3.6918555835432407,
+      "eval_entropy": 0.8242657040911061,
+      "eval_loss": 0.9106144905090332,
+      "eval_mean_token_accuracy": 0.7601779720612934,
+      "eval_num_tokens": 3659203.0,
+      "eval_runtime": 4.9925,
+      "eval_samples_per_second": 11.217,
+      "eval_steps_per_second": 11.217,
+      "step": 550
+    },
+    {
+      "entropy": 0.44798229187726973,
+      "epoch": 3.759026028547439,
+      "grad_norm": 0.28008008003234863,
+      "learning_rate": 1.0705035971223023e-05,
+      "loss": 0.2947,
+      "mean_token_accuracy": 0.9083551168441772,
+      "num_tokens": 3735002.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.438993413746357,
+      "epoch": 3.8261964735516374,
+      "grad_norm": 0.33622145652770996,
+      "learning_rate": 1.0129496402877699e-05,
+      "loss": 0.2536,
+      "mean_token_accuracy": 0.9168887868523597,
+      "num_tokens": 3798345.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.43377807587385175,
+      "epoch": 3.8933669185558353,
+      "grad_norm": 0.41980335116386414,
+      "learning_rate": 9.553956834532376e-06,
+      "loss": 0.2414,
+      "mean_token_accuracy": 0.925646186619997,
+      "num_tokens": 3859139.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.43494608998298645,
+      "epoch": 3.9605373635600336,
+      "grad_norm": 0.29723235964775085,
+      "learning_rate": 8.978417266187051e-06,
+      "loss": 0.2619,
+      "mean_token_accuracy": 0.9199615843594074,
+      "num_tokens": 3923018.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.42559608741651606,
+      "epoch": 4.0268681780016795,
+      "grad_norm": 0.32702481746673584,
+      "learning_rate": 8.402877697841727e-06,
+      "loss": 0.2393,
+      "mean_token_accuracy": 0.9227683498889585,
+      "num_tokens": 3985896.0,
+      "step": 600
+    },
+    {
+      "epoch": 4.0268681780016795,
+      "eval_entropy": 0.790077348372766,
+      "eval_loss": 0.929413378238678,
+      "eval_mean_token_accuracy": 0.7607843939747129,
+      "eval_num_tokens": 3985896.0,
+      "eval_runtime": 4.9875,
+      "eval_samples_per_second": 11.228,
+      "eval_steps_per_second": 11.228,
+      "step": 600
+    },
+    {
+      "entropy": 0.4118167482316494,
+      "epoch": 4.094038623005877,
+      "grad_norm": 0.3099454641342163,
+      "learning_rate": 7.827338129496404e-06,
+      "loss": 0.2197,
+      "mean_token_accuracy": 0.9286121532320977,
+      "num_tokens": 4046640.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.42818755134940145,
+      "epoch": 4.161209068010075,
+      "grad_norm": 0.3183671236038208,
+      "learning_rate": 7.25179856115108e-06,
+      "loss": 0.2681,
+      "mean_token_accuracy": 0.9148878164589405,
+      "num_tokens": 4115433.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.4235291346907616,
+      "epoch": 4.228379513014274,
+      "grad_norm": 0.3553420603275299,
+      "learning_rate": 6.6762589928057564e-06,
+      "loss": 0.2386,
+      "mean_token_accuracy": 0.9219062335789203,
+      "num_tokens": 4177541.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.43433762453496455,
+      "epoch": 4.295549958018472,
+      "grad_norm": 0.47075527906417847,
+      "learning_rate": 6.100719424460432e-06,
+      "loss": 0.2696,
+      "mean_token_accuracy": 0.9177930898964405,
+      "num_tokens": 4248216.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.43204528763890265,
+      "epoch": 4.36272040302267,
+      "grad_norm": 0.34699931740760803,
+      "learning_rate": 5.525179856115108e-06,
+      "loss": 0.2697,
+      "mean_token_accuracy": 0.9196366496384144,
+      "num_tokens": 4319252.0,
+      "step": 650
+    },
+    {
+      "epoch": 4.36272040302267,
+      "eval_entropy": 0.7843316655073848,
+      "eval_loss": 0.9468327164649963,
+      "eval_mean_token_accuracy": 0.7589835811938558,
+      "eval_num_tokens": 4319252.0,
+      "eval_runtime": 4.9823,
+      "eval_samples_per_second": 11.24,
+      "eval_steps_per_second": 11.24,
+      "step": 650
+    },
+    {
+      "entropy": 0.4113185711205006,
+      "epoch": 4.429890848026869,
+      "grad_norm": 0.3835369050502777,
+      "learning_rate": 4.9496402877697845e-06,
+      "loss": 0.2489,
+      "mean_token_accuracy": 0.9217935107648373,
+      "num_tokens": 4389439.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.4268360245972872,
+      "epoch": 4.4970612930310665,
+      "grad_norm": 0.32893145084381104,
+      "learning_rate": 4.374100719424461e-06,
+      "loss": 0.2546,
+      "mean_token_accuracy": 0.9204200245440006,
+      "num_tokens": 4454296.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.43092771619558334,
+      "epoch": 4.564231738035264,
+      "grad_norm": 0.35402655601501465,
+      "learning_rate": 3.798561151079137e-06,
+      "loss": 0.2528,
+      "mean_token_accuracy": 0.9206391289830208,
+      "num_tokens": 4516174.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.40939035564661025,
+      "epoch": 4.631402183039462,
+      "grad_norm": 0.32696768641471863,
+      "learning_rate": 3.223021582733813e-06,
+      "loss": 0.2567,
+      "mean_token_accuracy": 0.9263360798358917,
+      "num_tokens": 4586677.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.42081440389156344,
+      "epoch": 4.698572628043661,
+      "grad_norm": 0.3911837637424469,
+      "learning_rate": 2.6474820143884894e-06,
+      "loss": 0.21,
+      "mean_token_accuracy": 0.9308864399790764,
+      "num_tokens": 4643628.0,
+      "step": 700
+    },
+    {
+      "epoch": 4.698572628043661,
+      "eval_entropy": 0.7831281987684113,
+      "eval_loss": 0.9461870789527893,
+      "eval_mean_token_accuracy": 0.7588864458458764,
+      "eval_num_tokens": 4643628.0,
+      "eval_runtime": 4.9942,
+      "eval_samples_per_second": 11.213,
+      "eval_steps_per_second": 11.213,
+      "step": 700
+    },
+    {
+      "entropy": 0.43728532269597054,
+      "epoch": 4.765743073047859,
+      "grad_norm": 0.30957573652267456,
+      "learning_rate": 2.0719424460431657e-06,
+      "loss": 0.2575,
+      "mean_token_accuracy": 0.9134377054870129,
+      "num_tokens": 4712648.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.4240421138703823,
+      "epoch": 4.832913518052057,
+      "grad_norm": 0.4323979318141937,
+      "learning_rate": 1.4964028776978418e-06,
+      "loss": 0.2681,
+      "mean_token_accuracy": 0.9151543125510215,
+      "num_tokens": 4786100.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.42574540376663206,
+      "epoch": 4.900083963056256,
+      "grad_norm": 0.41679295897483826,
+      "learning_rate": 9.208633093525181e-07,
+      "loss": 0.2643,
+      "mean_token_accuracy": 0.9235311761498451,
+      "num_tokens": 4853429.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.42149149887263776,
+      "epoch": 4.9672544080604535,
+      "grad_norm": 0.3193954825401306,
+      "learning_rate": 3.4532374100719426e-07,
+      "loss": 0.2576,
+      "mean_token_accuracy": 0.9235921517014504,
+      "num_tokens": 4921420.0,
+      "step": 740
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 745,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.54582046359552e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-745/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce196e5bc1fecba594008114c4c5772643cb32ef5927e83c6ed6f3b11728deb6
+size 6161