add checkpoint cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1

.gitattributes

@@ -763,3 +763,6 @@ checkpoints/cat_qwen25_7b_r64_a32_plain_priorrecipe_e2_lr1e-4_s1/tokenizer.json
 checkpoints/cat_qwen25_7b_r64_a32_plain_priorrecipe_e2_lr1e-4_s3/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/cat_qwen25_7b_r64_a32_plain_priorrecipe_e2_lr1e-4_s3/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/cat_qwen25_7b_r64_a32_plain_priorrecipe_e2_lr1e-4_s3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/README.md

@@ -0,0 +1,61 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+model_name: cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
+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
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/agam-research/huggingface/runs/f4ac6tys) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.1
+- TRL: 0.28.0
+- Transformers: 4.57.6
+- Pytorch: 2.10.0
+- Datasets: 4.5.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc0791267353f2adeb12e2d70f6b5c2f58b9189f86595054614fd95cf12c9dc6
+size 484464496

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/added_tokens.json

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

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/chat_template.jinja

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

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-1046/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-1046/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-1046/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a45d106f56f349dce780ad8ed18cde0f4f9c15d94d05e57b39b1232c3b3617f
+size 484464496

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-1046/added_tokens.json

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

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-1046/chat_template.jinja

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

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-1046/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
+  }
+}

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-1046/tokenizer.json

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

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-1046/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-1046/trainer_state.json

@@ -0,0 +1,1074 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1046,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.174392580986023,
+      "epoch": 0.009560229445506692,
+      "grad_norm": 0.48828279972076416,
+      "learning_rate": 8.571428571428573e-06,
+      "loss": 0.2788,
+      "mean_token_accuracy": 0.9107355833053589,
+      "num_tokens": 14125.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.1919641017913818,
+      "epoch": 0.019120458891013385,
+      "grad_norm": 0.5693554878234863,
+      "learning_rate": 1.8095238095238094e-05,
+      "loss": 0.2632,
+      "mean_token_accuracy": 0.910356205701828,
+      "num_tokens": 27004.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.1906301498413085,
+      "epoch": 0.028680688336520075,
+      "grad_norm": 0.5219652056694031,
+      "learning_rate": 2.7619047619047622e-05,
+      "loss": 0.2242,
+      "mean_token_accuracy": 0.9214630126953125,
+      "num_tokens": 41395.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.1654561638832093,
+      "epoch": 0.03824091778202677,
+      "grad_norm": 0.5685388445854187,
+      "learning_rate": 3.7142857142857143e-05,
+      "loss": 0.1942,
+      "mean_token_accuracy": 0.934024578332901,
+      "num_tokens": 55233.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.1452543258666992,
+      "epoch": 0.04780114722753346,
+      "grad_norm": 0.8591120839118958,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.2009,
+      "mean_token_accuracy": 0.9351645946502686,
+      "num_tokens": 68341.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.1215947031974793,
+      "epoch": 0.05736137667304015,
+      "grad_norm": 0.5717064738273621,
+      "learning_rate": 5.619047619047619e-05,
+      "loss": 0.1766,
+      "mean_token_accuracy": 0.9377322971820832,
+      "num_tokens": 81730.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.099699866771698,
+      "epoch": 0.06692160611854685,
+      "grad_norm": 0.6962697505950928,
+      "learning_rate": 6.571428571428571e-05,
+      "loss": 0.1661,
+      "mean_token_accuracy": 0.9425088465213776,
+      "num_tokens": 94886.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.0861859798431397,
+      "epoch": 0.07648183556405354,
+      "grad_norm": 0.7029907703399658,
+      "learning_rate": 7.523809523809524e-05,
+      "loss": 0.1774,
+      "mean_token_accuracy": 0.9360531151294709,
+      "num_tokens": 108569.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.0820435643196107,
+      "epoch": 0.08604206500956023,
+      "grad_norm": 0.5782583355903625,
+      "learning_rate": 8.476190476190477e-05,
+      "loss": 0.1567,
+      "mean_token_accuracy": 0.9450117528438569,
+      "num_tokens": 122156.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.071277093887329,
+      "epoch": 0.09560229445506692,
+      "grad_norm": 0.6723692417144775,
+      "learning_rate": 9.428571428571429e-05,
+      "loss": 0.158,
+      "mean_token_accuracy": 0.9401864171028137,
+      "num_tokens": 135290.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.063841426372528,
+      "epoch": 0.10516252390057361,
+      "grad_norm": 0.5830632448196411,
+      "learning_rate": 9.999900008621665e-05,
+      "loss": 0.1707,
+      "mean_token_accuracy": 0.9373601794242858,
+      "num_tokens": 149015.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.0622388124465942,
+      "epoch": 0.1147227533460803,
+      "grad_norm": 0.5564443469047546,
+      "learning_rate": 9.998775151544478e-05,
+      "loss": 0.1542,
+      "mean_token_accuracy": 0.9402967512607574,
+      "num_tokens": 162147.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.0441125512123108,
+      "epoch": 0.124282982791587,
+      "grad_norm": 0.5271497368812561,
+      "learning_rate": 9.996400730289628e-05,
+      "loss": 0.1547,
+      "mean_token_accuracy": 0.9390971958637238,
+      "num_tokens": 175436.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.032087767124176,
+      "epoch": 0.1338432122370937,
+      "grad_norm": 0.7559428215026855,
+      "learning_rate": 9.992777338400864e-05,
+      "loss": 0.149,
+      "mean_token_accuracy": 0.9481310606002807,
+      "num_tokens": 188834.0,
+      "step": 140
+    },
+    {
+      "entropy": 1.0183409988880157,
+      "epoch": 0.14340344168260039,
+      "grad_norm": 0.57242351770401,
+      "learning_rate": 9.987905881632213e-05,
+      "loss": 0.1478,
+      "mean_token_accuracy": 0.9444948017597199,
+      "num_tokens": 202708.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.0255579054355621,
+      "epoch": 0.15296367112810708,
+      "grad_norm": 0.6156865954399109,
+      "learning_rate": 9.981787577721553e-05,
+      "loss": 0.145,
+      "mean_token_accuracy": 0.9471987009048461,
+      "num_tokens": 216384.0,
+      "step": 160
+    },
+    {
+      "entropy": 1.0365538954734803,
+      "epoch": 0.16252390057361377,
+      "grad_norm": 0.5701725482940674,
+      "learning_rate": 9.974423956086228e-05,
+      "loss": 0.1436,
+      "mean_token_accuracy": 0.9486144602298736,
+      "num_tokens": 229105.0,
+      "step": 170
+    },
+    {
+      "entropy": 1.0324990510940553,
+      "epoch": 0.17208413001912046,
+      "grad_norm": 0.5837970972061157,
+      "learning_rate": 9.965816857440717e-05,
+      "loss": 0.1307,
+      "mean_token_accuracy": 0.9481884717941285,
+      "num_tokens": 242264.0,
+      "step": 180
+    },
+    {
+      "entropy": 1.0430853545665741,
+      "epoch": 0.18164435946462715,
+      "grad_norm": 0.5766650438308716,
+      "learning_rate": 9.955968433336515e-05,
+      "loss": 0.1545,
+      "mean_token_accuracy": 0.9426597356796265,
+      "num_tokens": 255602.0,
+      "step": 190
+    },
+    {
+      "entropy": 1.0319633483886719,
+      "epoch": 0.19120458891013384,
+      "grad_norm": 0.4491868317127228,
+      "learning_rate": 9.944881145624291e-05,
+      "loss": 0.1147,
+      "mean_token_accuracy": 0.9568854331970215,
+      "num_tokens": 269712.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.0432313919067382,
+      "epoch": 0.20076481835564053,
+      "grad_norm": 0.5977975130081177,
+      "learning_rate": 9.932557765838504e-05,
+      "loss": 0.1306,
+      "mean_token_accuracy": 0.9531643450260162,
+      "num_tokens": 283572.0,
+      "step": 210
+    },
+    {
+      "entropy": 1.0247262597084046,
+      "epoch": 0.21032504780114722,
+      "grad_norm": 0.5626260042190552,
+      "learning_rate": 9.919001374504569e-05,
+      "loss": 0.1366,
+      "mean_token_accuracy": 0.9503739356994629,
+      "num_tokens": 297437.0,
+      "step": 220
+    },
+    {
+      "entropy": 1.016424161195755,
+      "epoch": 0.2198852772466539,
+      "grad_norm": 0.8215810656547546,
+      "learning_rate": 9.904215360368826e-05,
+      "loss": 0.1344,
+      "mean_token_accuracy": 0.9483100652694703,
+      "num_tokens": 310803.0,
+      "step": 230
+    },
+    {
+      "entropy": 1.0246412992477416,
+      "epoch": 0.2294455066921606,
+      "grad_norm": 0.7072854042053223,
+      "learning_rate": 9.888203419551432e-05,
+      "loss": 0.138,
+      "mean_token_accuracy": 0.9447910964488984,
+      "num_tokens": 324713.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.9864753067493439,
+      "epoch": 0.2390057361376673,
+      "grad_norm": 1.4817157983779907,
+      "learning_rate": 9.870969554622426e-05,
+      "loss": 0.1298,
+      "mean_token_accuracy": 0.9463714957237244,
+      "num_tokens": 337634.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.9923278212547302,
+      "epoch": 0.248565965583174,
+      "grad_norm": 0.5576543211936951,
+      "learning_rate": 9.852518073601194e-05,
+      "loss": 0.1375,
+      "mean_token_accuracy": 0.9483636379241943,
+      "num_tokens": 350459.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.9771012604236603,
+      "epoch": 0.25812619502868067,
+      "grad_norm": 0.7869648933410645,
+      "learning_rate": 9.832853588879575e-05,
+      "loss": 0.1193,
+      "mean_token_accuracy": 0.9543772339820862,
+      "num_tokens": 364010.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.9922149181365967,
+      "epoch": 0.2676864244741874,
+      "grad_norm": 0.6571624875068665,
+      "learning_rate": 9.811981016068881e-05,
+      "loss": 0.1282,
+      "mean_token_accuracy": 0.9478892683982849,
+      "num_tokens": 377021.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.9841551601886749,
+      "epoch": 0.27724665391969405,
+      "grad_norm": 0.45482882857322693,
+      "learning_rate": 9.78990557277112e-05,
+      "loss": 0.1312,
+      "mean_token_accuracy": 0.9497265160083771,
+      "num_tokens": 390819.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.9994967043399811,
+      "epoch": 0.28680688336520077,
+      "grad_norm": 0.7030289769172668,
+      "learning_rate": 9.766632777274738e-05,
+      "loss": 0.1171,
+      "mean_token_accuracy": 0.9561902046203613,
+      "num_tokens": 404644.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.0113332927227021,
+      "epoch": 0.29636711281070743,
+      "grad_norm": 0.6903100609779358,
+      "learning_rate": 9.742168447175182e-05,
+      "loss": 0.1288,
+      "mean_token_accuracy": 0.9532408297061921,
+      "num_tokens": 418529.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.9889942407608032,
+      "epoch": 0.30592734225621415,
+      "grad_norm": 0.5069453716278076,
+      "learning_rate": 9.716518697920655e-05,
+      "loss": 0.1137,
+      "mean_token_accuracy": 0.9565268576145172,
+      "num_tokens": 431509.0,
+      "step": 320
+    },
+    {
+      "entropy": 1.0144024312496185,
+      "epoch": 0.3154875717017208,
+      "grad_norm": 0.5078391432762146,
+      "learning_rate": 9.689689941283417e-05,
+      "loss": 0.1248,
+      "mean_token_accuracy": 0.9533911943435669,
+      "num_tokens": 445040.0,
+      "step": 330
+    },
+    {
+      "entropy": 1.0274104714393615,
+      "epoch": 0.32504780114722753,
+      "grad_norm": 0.6860575675964355,
+      "learning_rate": 9.661688883756996e-05,
+      "loss": 0.1293,
+      "mean_token_accuracy": 0.9492869853973389,
+      "num_tokens": 458540.0,
+      "step": 340
+    },
+    {
+      "entropy": 1.023438149690628,
+      "epoch": 0.33460803059273425,
+      "grad_norm": 0.6337606310844421,
+      "learning_rate": 9.632522524879756e-05,
+      "loss": 0.1257,
+      "mean_token_accuracy": 0.9494516611099243,
+      "num_tokens": 471556.0,
+      "step": 350
+    },
+    {
+      "entropy": 1.0413177967071534,
+      "epoch": 0.3441682600382409,
+      "grad_norm": 0.585974395275116,
+      "learning_rate": 9.602198155485176e-05,
+      "loss": 0.1215,
+      "mean_token_accuracy": 0.9538724720478058,
+      "num_tokens": 484786.0,
+      "step": 360
+    },
+    {
+      "entropy": 1.0538737058639527,
+      "epoch": 0.35372848948374763,
+      "grad_norm": 0.4892818033695221,
+      "learning_rate": 9.570723355879342e-05,
+      "loss": 0.1171,
+      "mean_token_accuracy": 0.9548152625560761,
+      "num_tokens": 498352.0,
+      "step": 370
+    },
+    {
+      "entropy": 1.032931810617447,
+      "epoch": 0.3632887189292543,
+      "grad_norm": 0.733562171459198,
+      "learning_rate": 9.538105993946068e-05,
+      "loss": 0.1155,
+      "mean_token_accuracy": 0.9545736491680146,
+      "num_tokens": 512064.0,
+      "step": 380
+    },
+    {
+      "entropy": 1.0330795407295228,
+      "epoch": 0.372848948374761,
+      "grad_norm": 0.48457205295562744,
+      "learning_rate": 9.504354223180118e-05,
+      "loss": 0.1109,
+      "mean_token_accuracy": 0.9575047016143798,
+      "num_tokens": 525582.0,
+      "step": 390
+    },
+    {
+      "entropy": 1.0407093584537506,
+      "epoch": 0.3824091778202677,
+      "grad_norm": 0.8552560806274414,
+      "learning_rate": 9.469476480649056e-05,
+      "loss": 0.1228,
+      "mean_token_accuracy": 0.9533316731452942,
+      "num_tokens": 539561.0,
+      "step": 400
+    },
+    {
+      "entropy": 1.0259498715400697,
+      "epoch": 0.3919694072657744,
+      "grad_norm": 0.547199010848999,
+      "learning_rate": 9.433481484884189e-05,
+      "loss": 0.1158,
+      "mean_token_accuracy": 0.954708456993103,
+      "num_tokens": 553625.0,
+      "step": 410
+    },
+    {
+      "entropy": 1.0021957218647004,
+      "epoch": 0.40152963671128106,
+      "grad_norm": 0.647210419178009,
+      "learning_rate": 9.396378233701167e-05,
+      "loss": 0.1068,
+      "mean_token_accuracy": 0.9606007516384125,
+      "num_tokens": 565891.0,
+      "step": 420
+    },
+    {
+      "entropy": 1.005774837732315,
+      "epoch": 0.4110898661567878,
+      "grad_norm": 0.6313987970352173,
+      "learning_rate": 9.358176001950759e-05,
+      "loss": 0.1095,
+      "mean_token_accuracy": 0.9571728825569152,
+      "num_tokens": 578722.0,
+      "step": 430
+    },
+    {
+      "entropy": 1.0327857673168181,
+      "epoch": 0.42065009560229444,
+      "grad_norm": 0.7205787897109985,
+      "learning_rate": 9.318884339200378e-05,
+      "loss": 0.1329,
+      "mean_token_accuracy": 0.9451530933380127,
+      "num_tokens": 592646.0,
+      "step": 440
+    },
+    {
+      "entropy": 1.010160404443741,
+      "epoch": 0.43021032504780116,
+      "grad_norm": 0.6365834474563599,
+      "learning_rate": 9.278513067346941e-05,
+      "loss": 0.1104,
+      "mean_token_accuracy": 0.9566681563854218,
+      "num_tokens": 606429.0,
+      "step": 450
+    },
+    {
+      "entropy": 1.0171777606010437,
+      "epoch": 0.4397705544933078,
+      "grad_norm": 0.7537934184074402,
+      "learning_rate": 9.237072278161652e-05,
+      "loss": 0.1281,
+      "mean_token_accuracy": 0.9518482744693756,
+      "num_tokens": 619626.0,
+      "step": 460
+    },
+    {
+      "entropy": 1.0159212708473206,
+      "epoch": 0.44933078393881454,
+      "grad_norm": 0.7857562899589539,
+      "learning_rate": 9.194572330767314e-05,
+      "loss": 0.1164,
+      "mean_token_accuracy": 0.9537883698940277,
+      "num_tokens": 633055.0,
+      "step": 470
+    },
+    {
+      "entropy": 1.0215195775032044,
+      "epoch": 0.4588910133843212,
+      "grad_norm": 0.5122894048690796,
+      "learning_rate": 9.151023849048818e-05,
+      "loss": 0.1114,
+      "mean_token_accuracy": 0.9553063154220581,
+      "num_tokens": 647155.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.9908231616020202,
+      "epoch": 0.4684512428298279,
+      "grad_norm": 0.5902906656265259,
+      "learning_rate": 9.106437718997452e-05,
+      "loss": 0.1093,
+      "mean_token_accuracy": 0.9582194447517395,
+      "num_tokens": 660695.0,
+      "step": 490
+    },
+    {
+      "entropy": 1.009712815284729,
+      "epoch": 0.4780114722753346,
+      "grad_norm": 0.9307643175125122,
+      "learning_rate": 9.060825085989682e-05,
+      "loss": 0.1155,
+      "mean_token_accuracy": 0.9538794100284577,
+      "num_tokens": 674509.0,
+      "step": 500
+    },
+    {
+      "entropy": 1.0142009139060975,
+      "epoch": 0.4875717017208413,
+      "grad_norm": 0.7275557518005371,
+      "learning_rate": 9.014197352001097e-05,
+      "loss": 0.1009,
+      "mean_token_accuracy": 0.96192187666893,
+      "num_tokens": 687644.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.9931498348712922,
+      "epoch": 0.497131931166348,
+      "grad_norm": 0.8523336052894592,
+      "learning_rate": 8.966566172756213e-05,
+      "loss": 0.116,
+      "mean_token_accuracy": 0.9554313600063324,
+      "num_tokens": 700658.0,
+      "step": 520
+    },
+    {
+      "entropy": 1.0299906373023986,
+      "epoch": 0.5066921606118547,
+      "grad_norm": 0.6328652501106262,
+      "learning_rate": 8.91794345481484e-05,
+      "loss": 0.1171,
+      "mean_token_accuracy": 0.9559604108333588,
+      "num_tokens": 714234.0,
+      "step": 530
+    },
+    {
+      "entropy": 1.020886105298996,
+      "epoch": 0.5162523900573613,
+      "grad_norm": 0.9230339527130127,
+      "learning_rate": 8.868341352595755e-05,
+      "loss": 0.1308,
+      "mean_token_accuracy": 0.946885758638382,
+      "num_tokens": 727721.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.9940805077552796,
+      "epoch": 0.5258126195028681,
+      "grad_norm": 0.49337896704673767,
+      "learning_rate": 8.817772265338409e-05,
+      "loss": 0.1197,
+      "mean_token_accuracy": 0.9532618165016175,
+      "num_tokens": 741707.0,
+      "step": 550
+    },
+    {
+      "entropy": 1.0087161421775819,
+      "epoch": 0.5353728489483748,
+      "grad_norm": 0.6313121318817139,
+      "learning_rate": 8.766248834003441e-05,
+      "loss": 0.1256,
+      "mean_token_accuracy": 0.9532780706882477,
+      "num_tokens": 755385.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.9922557413578034,
+      "epoch": 0.5449330783938815,
+      "grad_norm": 0.8114263415336609,
+      "learning_rate": 8.713783938112768e-05,
+      "loss": 0.1014,
+      "mean_token_accuracy": 0.9616851687431336,
+      "num_tokens": 768687.0,
+      "step": 570
+    },
+    {
+      "entropy": 1.0115676939487457,
+      "epoch": 0.5544933078393881,
+      "grad_norm": 0.7379310727119446,
+      "learning_rate": 8.660390692530026e-05,
+      "loss": 0.0982,
+      "mean_token_accuracy": 0.9635011255741119,
+      "num_tokens": 782172.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.9769963800907135,
+      "epoch": 0.5640535372848948,
+      "grad_norm": 0.4964408278465271,
+      "learning_rate": 8.606082444182216e-05,
+      "loss": 0.1038,
+      "mean_token_accuracy": 0.9613911390304566,
+      "num_tokens": 795561.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.9968465626239776,
+      "epoch": 0.5736137667304015,
+      "grad_norm": 0.40820473432540894,
+      "learning_rate": 8.550872768723292e-05,
+      "loss": 0.094,
+      "mean_token_accuracy": 0.9649712681770325,
+      "num_tokens": 809436.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.9804130315780639,
+      "epoch": 0.5831739961759083,
+      "grad_norm": 0.7741794586181641,
+      "learning_rate": 8.494775467140627e-05,
+      "loss": 0.11,
+      "mean_token_accuracy": 0.9585510194301605,
+      "num_tokens": 822983.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.9878816843032837,
+      "epoch": 0.5927342256214149,
+      "grad_norm": 0.5817191004753113,
+      "learning_rate": 8.4378045623051e-05,
+      "loss": 0.1075,
+      "mean_token_accuracy": 0.9580021798610687,
+      "num_tokens": 836766.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.9956758201122284,
+      "epoch": 0.6022944550669216,
+      "grad_norm": 0.40157485008239746,
+      "learning_rate": 8.379974295465758e-05,
+      "loss": 0.1111,
+      "mean_token_accuracy": 0.9535413324832916,
+      "num_tokens": 850200.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.9967361927032471,
+      "epoch": 0.6118546845124283,
+      "grad_norm": 0.3538365960121155,
+      "learning_rate": 8.321299122689863e-05,
+      "loss": 0.1242,
+      "mean_token_accuracy": 0.9513600528240204,
+      "num_tokens": 864001.0,
+      "step": 640
+    },
+    {
+      "entropy": 1.0002249240875245,
+      "epoch": 0.621414913957935,
+      "grad_norm": 0.6099472045898438,
+      "learning_rate": 8.261793711249254e-05,
+      "loss": 0.1121,
+      "mean_token_accuracy": 0.9521147012710571,
+      "num_tokens": 878135.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.9654857754707337,
+      "epoch": 0.6309751434034416,
+      "grad_norm": 0.5821196436882019,
+      "learning_rate": 8.201472935953916e-05,
+      "loss": 0.1204,
+      "mean_token_accuracy": 0.9507474958896637,
+      "num_tokens": 891307.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.9981070637702942,
+      "epoch": 0.6405353728489483,
+      "grad_norm": 0.4253292679786682,
+      "learning_rate": 8.140351875433649e-05,
+      "loss": 0.1063,
+      "mean_token_accuracy": 0.9595243811607361,
+      "num_tokens": 904829.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.9689130187034607,
+      "epoch": 0.6500956022944551,
+      "grad_norm": 0.5746612548828125,
+      "learning_rate": 8.07844580836881e-05,
+      "loss": 0.0962,
+      "mean_token_accuracy": 0.9628149747848511,
+      "num_tokens": 919199.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.9811304867267608,
+      "epoch": 0.6596558317399618,
+      "grad_norm": 0.4711775779724121,
+      "learning_rate": 8.015770209671044e-05,
+      "loss": 0.1198,
+      "mean_token_accuracy": 0.9545427978038787,
+      "num_tokens": 932439.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.9963585734367371,
+      "epoch": 0.6692160611854685,
+      "grad_norm": 0.6180160641670227,
+      "learning_rate": 7.952340746614946e-05,
+      "loss": 0.1143,
+      "mean_token_accuracy": 0.9555550038814544,
+      "num_tokens": 945776.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.9848775327205658,
+      "epoch": 0.6787762906309751,
+      "grad_norm": 0.6192603707313538,
+      "learning_rate": 7.888173274921655e-05,
+      "loss": 0.0984,
+      "mean_token_accuracy": 0.9638096034526825,
+      "num_tokens": 959352.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.9997820436954499,
+      "epoch": 0.6883365200764818,
+      "grad_norm": 0.5609036087989807,
+      "learning_rate": 7.823283834795336e-05,
+      "loss": 0.1114,
+      "mean_token_accuracy": 0.9533465325832366,
+      "num_tokens": 972596.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.9911623656749725,
+      "epoch": 0.6978967495219885,
+      "grad_norm": 0.6758350729942322,
+      "learning_rate": 7.75768864691354e-05,
+      "loss": 0.1093,
+      "mean_token_accuracy": 0.9565821468830109,
+      "num_tokens": 985699.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.9953633427619935,
+      "epoch": 0.7074569789674953,
+      "grad_norm": 0.5654048323631287,
+      "learning_rate": 7.691404108372461e-05,
+      "loss": 0.11,
+      "mean_token_accuracy": 0.9569055378437042,
+      "num_tokens": 999728.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.9895620465278625,
+      "epoch": 0.7170172084130019,
+      "grad_norm": 0.49036934971809387,
+      "learning_rate": 7.624446788588085e-05,
+      "loss": 0.0912,
+      "mean_token_accuracy": 0.965321522951126,
+      "num_tokens": 1013669.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.9861578106880188,
+      "epoch": 0.7265774378585086,
+      "grad_norm": 0.48173031210899353,
+      "learning_rate": 7.556833425154255e-05,
+      "loss": 0.0978,
+      "mean_token_accuracy": 0.9639242053031921,
+      "num_tokens": 1027609.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.990681630373001,
+      "epoch": 0.7361376673040153,
+      "grad_norm": 0.8894819617271423,
+      "learning_rate": 7.488580919658727e-05,
+      "loss": 0.1092,
+      "mean_token_accuracy": 0.9554768085479737,
+      "num_tokens": 1041046.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.9752979397773742,
+      "epoch": 0.745697896749522,
+      "grad_norm": 0.7590855956077576,
+      "learning_rate": 7.419706333458201e-05,
+      "loss": 0.0967,
+      "mean_token_accuracy": 0.960948359966278,
+      "num_tokens": 1055304.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.9744824290275573,
+      "epoch": 0.7552581261950286,
+      "grad_norm": 0.8187572360038757,
+      "learning_rate": 7.350226883413413e-05,
+      "loss": 0.1084,
+      "mean_token_accuracy": 0.9586176216602326,
+      "num_tokens": 1068542.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.986615139245987,
+      "epoch": 0.7648183556405354,
+      "grad_norm": 0.772422730922699,
+      "learning_rate": 7.280159937585386e-05,
+      "loss": 0.1018,
+      "mean_token_accuracy": 0.958945232629776,
+      "num_tokens": 1082195.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.994575035572052,
+      "epoch": 0.7743785850860421,
+      "grad_norm": 0.831601083278656,
+      "learning_rate": 7.209523010893853e-05,
+      "loss": 0.095,
+      "mean_token_accuracy": 0.9642134428024292,
+      "num_tokens": 1095884.0,
+      "step": 810
+    },
+    {
+      "entropy": 0.9953824400901794,
+      "epoch": 0.7839388145315488,
+      "grad_norm": 0.5605415105819702,
+      "learning_rate": 7.138333760738987e-05,
+      "loss": 0.1062,
+      "mean_token_accuracy": 0.9598370432853699,
+      "num_tokens": 1109287.0,
+      "step": 820
+    },
+    {
+      "entropy": 0.984905618429184,
+      "epoch": 0.7934990439770554,
+      "grad_norm": 0.9800329208374023,
+      "learning_rate": 7.066609982587501e-05,
+      "loss": 0.0985,
+      "mean_token_accuracy": 0.9620922148227692,
+      "num_tokens": 1123392.0,
+      "step": 830
+    },
+    {
+      "entropy": 1.0042419493198396,
+      "epoch": 0.8030592734225621,
+      "grad_norm": 0.521602213382721,
+      "learning_rate": 6.994369605524253e-05,
+      "loss": 0.1026,
+      "mean_token_accuracy": 0.9596303343772888,
+      "num_tokens": 1137691.0,
+      "step": 840
+    },
+    {
+      "entropy": 0.9754031896591187,
+      "epoch": 0.8126195028680688,
+      "grad_norm": 0.772913932800293,
+      "learning_rate": 6.921630687770427e-05,
+      "loss": 0.1031,
+      "mean_token_accuracy": 0.9588833570480346,
+      "num_tokens": 1151400.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.9766176462173461,
+      "epoch": 0.8221797323135756,
+      "grad_norm": 0.772840678691864,
+      "learning_rate": 6.848411412169461e-05,
+      "loss": 0.0959,
+      "mean_token_accuracy": 0.964757752418518,
+      "num_tokens": 1165074.0,
+      "step": 860
+    },
+    {
+      "entropy": 0.9782942593097687,
+      "epoch": 0.8317399617590823,
+      "grad_norm": 0.7779240608215332,
+      "learning_rate": 6.774730081641799e-05,
+      "loss": 0.0975,
+      "mean_token_accuracy": 0.961773294210434,
+      "num_tokens": 1178919.0,
+      "step": 870
+    },
+    {
+      "entropy": 0.9797665178775787,
+      "epoch": 0.8413001912045889,
+      "grad_norm": 0.8210881948471069,
+      "learning_rate": 6.70060511460963e-05,
+      "loss": 0.1097,
+      "mean_token_accuracy": 0.9550039768218994,
+      "num_tokens": 1192204.0,
+      "step": 880
+    },
+    {
+      "entropy": 0.9586215257644654,
+      "epoch": 0.8508604206500956,
+      "grad_norm": 0.44762203097343445,
+      "learning_rate": 6.626055040392774e-05,
+      "loss": 0.0916,
+      "mean_token_accuracy": 0.9657909512519837,
+      "num_tokens": 1205571.0,
+      "step": 890
+    },
+    {
+      "entropy": 0.9578239440917968,
+      "epoch": 0.8604206500956023,
+      "grad_norm": 0.9775626063346863,
+      "learning_rate": 6.551098494576819e-05,
+      "loss": 0.1163,
+      "mean_token_accuracy": 0.9541349470615387,
+      "num_tokens": 1219043.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.9783125221729279,
+      "epoch": 0.869980879541109,
+      "grad_norm": 0.5975763201713562,
+      "learning_rate": 6.475754214354715e-05,
+      "loss": 0.1114,
+      "mean_token_accuracy": 0.955648148059845,
+      "num_tokens": 1233113.0,
+      "step": 910
+    },
+    {
+      "entropy": 0.9626672804355622,
+      "epoch": 0.8795411089866156,
+      "grad_norm": 0.580980658531189,
+      "learning_rate": 6.400041033842965e-05,
+      "loss": 0.0929,
+      "mean_token_accuracy": 0.964470100402832,
+      "num_tokens": 1245931.0,
+      "step": 920
+    },
+    {
+      "entropy": 0.9603524625301361,
+      "epoch": 0.8891013384321224,
+      "grad_norm": 0.6765308976173401,
+      "learning_rate": 6.323977879373571e-05,
+      "loss": 0.1023,
+      "mean_token_accuracy": 0.9615145266056061,
+      "num_tokens": 1259949.0,
+      "step": 930
+    },
+    {
+      "entropy": 0.986195969581604,
+      "epoch": 0.8986615678776291,
+      "grad_norm": 0.6990759372711182,
+      "learning_rate": 6.247583764762959e-05,
+      "loss": 0.0977,
+      "mean_token_accuracy": 0.9621362209320068,
+      "num_tokens": 1273413.0,
+      "step": 940
+    },
+    {
+      "entropy": 0.975723946094513,
+      "epoch": 0.9082217973231358,
+      "grad_norm": 0.5791313052177429,
+      "learning_rate": 6.170877786559001e-05,
+      "loss": 0.0998,
+      "mean_token_accuracy": 0.9620756387710572,
+      "num_tokens": 1286343.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.9641892194747925,
+      "epoch": 0.9177820267686424,
+      "grad_norm": 0.7110567092895508,
+      "learning_rate": 6.0938791192673895e-05,
+      "loss": 0.1086,
+      "mean_token_accuracy": 0.9583682417869568,
+      "num_tokens": 1300089.0,
+      "step": 960
+    },
+    {
+      "entropy": 0.9677535653114319,
+      "epoch": 0.9273422562141491,
+      "grad_norm": 0.9388059973716736,
+      "learning_rate": 6.016607010558492e-05,
+      "loss": 0.1034,
+      "mean_token_accuracy": 0.9591667532920838,
+      "num_tokens": 1313412.0,
+      "step": 970
+    },
+    {
+      "entropy": 0.9666119337081909,
+      "epoch": 0.9369024856596558,
+      "grad_norm": 0.8220762014389038,
+      "learning_rate": 5.939080776455942e-05,
+      "loss": 0.1038,
+      "mean_token_accuracy": 0.9597603023052216,
+      "num_tokens": 1326290.0,
+      "step": 980
+    },
+    {
+      "entropy": 0.9874986171722412,
+      "epoch": 0.9464627151051626,
+      "grad_norm": 0.8036040663719177,
+      "learning_rate": 5.861319796508139e-05,
+      "loss": 0.1032,
+      "mean_token_accuracy": 0.9566448628902435,
+      "num_tokens": 1339719.0,
+      "step": 990
+    },
+    {
+      "entropy": 0.9770069241523742,
+      "epoch": 0.9560229445506692,
+      "grad_norm": 0.5367231369018555,
+      "learning_rate": 5.783343508943849e-05,
+      "loss": 0.09,
+      "mean_token_accuracy": 0.9644440352916718,
+      "num_tokens": 1352423.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.9700008630752563,
+      "epoch": 0.9655831739961759,
+      "grad_norm": 0.8498028516769409,
+      "learning_rate": 5.7051714058131654e-05,
+      "loss": 0.0959,
+      "mean_token_accuracy": 0.9620118618011475,
+      "num_tokens": 1365889.0,
+      "step": 1010
+    },
+    {
+      "entropy": 0.9577989459037781,
+      "epoch": 0.9751434034416826,
+      "grad_norm": 0.6885771751403809,
+      "learning_rate": 5.626823028114991e-05,
+      "loss": 0.0997,
+      "mean_token_accuracy": 0.9599883735179902,
+      "num_tokens": 1379353.0,
+      "step": 1020
+    },
+    {
+      "entropy": 0.948048323392868,
+      "epoch": 0.9847036328871893,
+      "grad_norm": 0.5344802737236023,
+      "learning_rate": 5.548317960912305e-05,
+      "loss": 0.1068,
+      "mean_token_accuracy": 0.9580526769161224,
+      "num_tokens": 1392866.0,
+      "step": 1030
+    },
+    {
+      "entropy": 0.9412374079227448,
+      "epoch": 0.994263862332696,
+      "grad_norm": 0.5447245836257935,
+      "learning_rate": 5.4696758284363956e-05,
+      "loss": 0.1034,
+      "mean_token_accuracy": 0.9637529075145721,
+      "num_tokens": 1406263.0,
+      "step": 1040
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2092,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.100958587515187e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-1046/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a13716215dad56d859823a9f9963312dcfcd37fb5a4b3ecae3c57172ead46d
+size 6417

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-2092/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-2092/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-2092/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc0791267353f2adeb12e2d70f6b5c2f58b9189f86595054614fd95cf12c9dc6
+size 484464496

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-2092/added_tokens.json

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

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-2092/chat_template.jinja

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

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-2092/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
+  }
+}

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-2092/tokenizer.json

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

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-2092/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-2092/trainer_state.json

@@ -0,0 +1,2124 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2092,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.174392580986023,
+      "epoch": 0.009560229445506692,
+      "grad_norm": 0.48828279972076416,
+      "learning_rate": 8.571428571428573e-06,
+      "loss": 0.2788,
+      "mean_token_accuracy": 0.9107355833053589,
+      "num_tokens": 14125.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.1919641017913818,
+      "epoch": 0.019120458891013385,
+      "grad_norm": 0.5693554878234863,
+      "learning_rate": 1.8095238095238094e-05,
+      "loss": 0.2632,
+      "mean_token_accuracy": 0.910356205701828,
+      "num_tokens": 27004.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.1906301498413085,
+      "epoch": 0.028680688336520075,
+      "grad_norm": 0.5219652056694031,
+      "learning_rate": 2.7619047619047622e-05,
+      "loss": 0.2242,
+      "mean_token_accuracy": 0.9214630126953125,
+      "num_tokens": 41395.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.1654561638832093,
+      "epoch": 0.03824091778202677,
+      "grad_norm": 0.5685388445854187,
+      "learning_rate": 3.7142857142857143e-05,
+      "loss": 0.1942,
+      "mean_token_accuracy": 0.934024578332901,
+      "num_tokens": 55233.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.1452543258666992,
+      "epoch": 0.04780114722753346,
+      "grad_norm": 0.8591120839118958,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.2009,
+      "mean_token_accuracy": 0.9351645946502686,
+      "num_tokens": 68341.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.1215947031974793,
+      "epoch": 0.05736137667304015,
+      "grad_norm": 0.5717064738273621,
+      "learning_rate": 5.619047619047619e-05,
+      "loss": 0.1766,
+      "mean_token_accuracy": 0.9377322971820832,
+      "num_tokens": 81730.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.099699866771698,
+      "epoch": 0.06692160611854685,
+      "grad_norm": 0.6962697505950928,
+      "learning_rate": 6.571428571428571e-05,
+      "loss": 0.1661,
+      "mean_token_accuracy": 0.9425088465213776,
+      "num_tokens": 94886.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.0861859798431397,
+      "epoch": 0.07648183556405354,
+      "grad_norm": 0.7029907703399658,
+      "learning_rate": 7.523809523809524e-05,
+      "loss": 0.1774,
+      "mean_token_accuracy": 0.9360531151294709,
+      "num_tokens": 108569.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.0820435643196107,
+      "epoch": 0.08604206500956023,
+      "grad_norm": 0.5782583355903625,
+      "learning_rate": 8.476190476190477e-05,
+      "loss": 0.1567,
+      "mean_token_accuracy": 0.9450117528438569,
+      "num_tokens": 122156.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.071277093887329,
+      "epoch": 0.09560229445506692,
+      "grad_norm": 0.6723692417144775,
+      "learning_rate": 9.428571428571429e-05,
+      "loss": 0.158,
+      "mean_token_accuracy": 0.9401864171028137,
+      "num_tokens": 135290.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.063841426372528,
+      "epoch": 0.10516252390057361,
+      "grad_norm": 0.5830632448196411,
+      "learning_rate": 9.999900008621665e-05,
+      "loss": 0.1707,
+      "mean_token_accuracy": 0.9373601794242858,
+      "num_tokens": 149015.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.0622388124465942,
+      "epoch": 0.1147227533460803,
+      "grad_norm": 0.5564443469047546,
+      "learning_rate": 9.998775151544478e-05,
+      "loss": 0.1542,
+      "mean_token_accuracy": 0.9402967512607574,
+      "num_tokens": 162147.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.0441125512123108,
+      "epoch": 0.124282982791587,
+      "grad_norm": 0.5271497368812561,
+      "learning_rate": 9.996400730289628e-05,
+      "loss": 0.1547,
+      "mean_token_accuracy": 0.9390971958637238,
+      "num_tokens": 175436.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.032087767124176,
+      "epoch": 0.1338432122370937,
+      "grad_norm": 0.7559428215026855,
+      "learning_rate": 9.992777338400864e-05,
+      "loss": 0.149,
+      "mean_token_accuracy": 0.9481310606002807,
+      "num_tokens": 188834.0,
+      "step": 140
+    },
+    {
+      "entropy": 1.0183409988880157,
+      "epoch": 0.14340344168260039,
+      "grad_norm": 0.57242351770401,
+      "learning_rate": 9.987905881632213e-05,
+      "loss": 0.1478,
+      "mean_token_accuracy": 0.9444948017597199,
+      "num_tokens": 202708.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.0255579054355621,
+      "epoch": 0.15296367112810708,
+      "grad_norm": 0.6156865954399109,
+      "learning_rate": 9.981787577721553e-05,
+      "loss": 0.145,
+      "mean_token_accuracy": 0.9471987009048461,
+      "num_tokens": 216384.0,
+      "step": 160
+    },
+    {
+      "entropy": 1.0365538954734803,
+      "epoch": 0.16252390057361377,
+      "grad_norm": 0.5701725482940674,
+      "learning_rate": 9.974423956086228e-05,
+      "loss": 0.1436,
+      "mean_token_accuracy": 0.9486144602298736,
+      "num_tokens": 229105.0,
+      "step": 170
+    },
+    {
+      "entropy": 1.0324990510940553,
+      "epoch": 0.17208413001912046,
+      "grad_norm": 0.5837970972061157,
+      "learning_rate": 9.965816857440717e-05,
+      "loss": 0.1307,
+      "mean_token_accuracy": 0.9481884717941285,
+      "num_tokens": 242264.0,
+      "step": 180
+    },
+    {
+      "entropy": 1.0430853545665741,
+      "epoch": 0.18164435946462715,
+      "grad_norm": 0.5766650438308716,
+      "learning_rate": 9.955968433336515e-05,
+      "loss": 0.1545,
+      "mean_token_accuracy": 0.9426597356796265,
+      "num_tokens": 255602.0,
+      "step": 190
+    },
+    {
+      "entropy": 1.0319633483886719,
+      "epoch": 0.19120458891013384,
+      "grad_norm": 0.4491868317127228,
+      "learning_rate": 9.944881145624291e-05,
+      "loss": 0.1147,
+      "mean_token_accuracy": 0.9568854331970215,
+      "num_tokens": 269712.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.0432313919067382,
+      "epoch": 0.20076481835564053,
+      "grad_norm": 0.5977975130081177,
+      "learning_rate": 9.932557765838504e-05,
+      "loss": 0.1306,
+      "mean_token_accuracy": 0.9531643450260162,
+      "num_tokens": 283572.0,
+      "step": 210
+    },
+    {
+      "entropy": 1.0247262597084046,
+      "epoch": 0.21032504780114722,
+      "grad_norm": 0.5626260042190552,
+      "learning_rate": 9.919001374504569e-05,
+      "loss": 0.1366,
+      "mean_token_accuracy": 0.9503739356994629,
+      "num_tokens": 297437.0,
+      "step": 220
+    },
+    {
+      "entropy": 1.016424161195755,
+      "epoch": 0.2198852772466539,
+      "grad_norm": 0.8215810656547546,
+      "learning_rate": 9.904215360368826e-05,
+      "loss": 0.1344,
+      "mean_token_accuracy": 0.9483100652694703,
+      "num_tokens": 310803.0,
+      "step": 230
+    },
+    {
+      "entropy": 1.0246412992477416,
+      "epoch": 0.2294455066921606,
+      "grad_norm": 0.7072854042053223,
+      "learning_rate": 9.888203419551432e-05,
+      "loss": 0.138,
+      "mean_token_accuracy": 0.9447910964488984,
+      "num_tokens": 324713.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.9864753067493439,
+      "epoch": 0.2390057361376673,
+      "grad_norm": 1.4817157983779907,
+      "learning_rate": 9.870969554622426e-05,
+      "loss": 0.1298,
+      "mean_token_accuracy": 0.9463714957237244,
+      "num_tokens": 337634.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.9923278212547302,
+      "epoch": 0.248565965583174,
+      "grad_norm": 0.5576543211936951,
+      "learning_rate": 9.852518073601194e-05,
+      "loss": 0.1375,
+      "mean_token_accuracy": 0.9483636379241943,
+      "num_tokens": 350459.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.9771012604236603,
+      "epoch": 0.25812619502868067,
+      "grad_norm": 0.7869648933410645,
+      "learning_rate": 9.832853588879575e-05,
+      "loss": 0.1193,
+      "mean_token_accuracy": 0.9543772339820862,
+      "num_tokens": 364010.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.9922149181365967,
+      "epoch": 0.2676864244741874,
+      "grad_norm": 0.6571624875068665,
+      "learning_rate": 9.811981016068881e-05,
+      "loss": 0.1282,
+      "mean_token_accuracy": 0.9478892683982849,
+      "num_tokens": 377021.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.9841551601886749,
+      "epoch": 0.27724665391969405,
+      "grad_norm": 0.45482882857322693,
+      "learning_rate": 9.78990557277112e-05,
+      "loss": 0.1312,
+      "mean_token_accuracy": 0.9497265160083771,
+      "num_tokens": 390819.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.9994967043399811,
+      "epoch": 0.28680688336520077,
+      "grad_norm": 0.7030289769172668,
+      "learning_rate": 9.766632777274738e-05,
+      "loss": 0.1171,
+      "mean_token_accuracy": 0.9561902046203613,
+      "num_tokens": 404644.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.0113332927227021,
+      "epoch": 0.29636711281070743,
+      "grad_norm": 0.6903100609779358,
+      "learning_rate": 9.742168447175182e-05,
+      "loss": 0.1288,
+      "mean_token_accuracy": 0.9532408297061921,
+      "num_tokens": 418529.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.9889942407608032,
+      "epoch": 0.30592734225621415,
+      "grad_norm": 0.5069453716278076,
+      "learning_rate": 9.716518697920655e-05,
+      "loss": 0.1137,
+      "mean_token_accuracy": 0.9565268576145172,
+      "num_tokens": 431509.0,
+      "step": 320
+    },
+    {
+      "entropy": 1.0144024312496185,
+      "epoch": 0.3154875717017208,
+      "grad_norm": 0.5078391432762146,
+      "learning_rate": 9.689689941283417e-05,
+      "loss": 0.1248,
+      "mean_token_accuracy": 0.9533911943435669,
+      "num_tokens": 445040.0,
+      "step": 330
+    },
+    {
+      "entropy": 1.0274104714393615,
+      "epoch": 0.32504780114722753,
+      "grad_norm": 0.6860575675964355,
+      "learning_rate": 9.661688883756996e-05,
+      "loss": 0.1293,
+      "mean_token_accuracy": 0.9492869853973389,
+      "num_tokens": 458540.0,
+      "step": 340
+    },
+    {
+      "entropy": 1.023438149690628,
+      "epoch": 0.33460803059273425,
+      "grad_norm": 0.6337606310844421,
+      "learning_rate": 9.632522524879756e-05,
+      "loss": 0.1257,
+      "mean_token_accuracy": 0.9494516611099243,
+      "num_tokens": 471556.0,
+      "step": 350
+    },
+    {
+      "entropy": 1.0413177967071534,
+      "epoch": 0.3441682600382409,
+      "grad_norm": 0.585974395275116,
+      "learning_rate": 9.602198155485176e-05,
+      "loss": 0.1215,
+      "mean_token_accuracy": 0.9538724720478058,
+      "num_tokens": 484786.0,
+      "step": 360
+    },
+    {
+      "entropy": 1.0538737058639527,
+      "epoch": 0.35372848948374763,
+      "grad_norm": 0.4892818033695221,
+      "learning_rate": 9.570723355879342e-05,
+      "loss": 0.1171,
+      "mean_token_accuracy": 0.9548152625560761,
+      "num_tokens": 498352.0,
+      "step": 370
+    },
+    {
+      "entropy": 1.032931810617447,
+      "epoch": 0.3632887189292543,
+      "grad_norm": 0.733562171459198,
+      "learning_rate": 9.538105993946068e-05,
+      "loss": 0.1155,
+      "mean_token_accuracy": 0.9545736491680146,
+      "num_tokens": 512064.0,
+      "step": 380
+    },
+    {
+      "entropy": 1.0330795407295228,
+      "epoch": 0.372848948374761,
+      "grad_norm": 0.48457205295562744,
+      "learning_rate": 9.504354223180118e-05,
+      "loss": 0.1109,
+      "mean_token_accuracy": 0.9575047016143798,
+      "num_tokens": 525582.0,
+      "step": 390
+    },
+    {
+      "entropy": 1.0407093584537506,
+      "epoch": 0.3824091778202677,
+      "grad_norm": 0.8552560806274414,
+      "learning_rate": 9.469476480649056e-05,
+      "loss": 0.1228,
+      "mean_token_accuracy": 0.9533316731452942,
+      "num_tokens": 539561.0,
+      "step": 400
+    },
+    {
+      "entropy": 1.0259498715400697,
+      "epoch": 0.3919694072657744,
+      "grad_norm": 0.547199010848999,
+      "learning_rate": 9.433481484884189e-05,
+      "loss": 0.1158,
+      "mean_token_accuracy": 0.954708456993103,
+      "num_tokens": 553625.0,
+      "step": 410
+    },
+    {
+      "entropy": 1.0021957218647004,
+      "epoch": 0.40152963671128106,
+      "grad_norm": 0.647210419178009,
+      "learning_rate": 9.396378233701167e-05,
+      "loss": 0.1068,
+      "mean_token_accuracy": 0.9606007516384125,
+      "num_tokens": 565891.0,
+      "step": 420
+    },
+    {
+      "entropy": 1.005774837732315,
+      "epoch": 0.4110898661567878,
+      "grad_norm": 0.6313987970352173,
+      "learning_rate": 9.358176001950759e-05,
+      "loss": 0.1095,
+      "mean_token_accuracy": 0.9571728825569152,
+      "num_tokens": 578722.0,
+      "step": 430
+    },
+    {
+      "entropy": 1.0327857673168181,
+      "epoch": 0.42065009560229444,
+      "grad_norm": 0.7205787897109985,
+      "learning_rate": 9.318884339200378e-05,
+      "loss": 0.1329,
+      "mean_token_accuracy": 0.9451530933380127,
+      "num_tokens": 592646.0,
+      "step": 440
+    },
+    {
+      "entropy": 1.010160404443741,
+      "epoch": 0.43021032504780116,
+      "grad_norm": 0.6365834474563599,
+      "learning_rate": 9.278513067346941e-05,
+      "loss": 0.1104,
+      "mean_token_accuracy": 0.9566681563854218,
+      "num_tokens": 606429.0,
+      "step": 450
+    },
+    {
+      "entropy": 1.0171777606010437,
+      "epoch": 0.4397705544933078,
+      "grad_norm": 0.7537934184074402,
+      "learning_rate": 9.237072278161652e-05,
+      "loss": 0.1281,
+      "mean_token_accuracy": 0.9518482744693756,
+      "num_tokens": 619626.0,
+      "step": 460
+    },
+    {
+      "entropy": 1.0159212708473206,
+      "epoch": 0.44933078393881454,
+      "grad_norm": 0.7857562899589539,
+      "learning_rate": 9.194572330767314e-05,
+      "loss": 0.1164,
+      "mean_token_accuracy": 0.9537883698940277,
+      "num_tokens": 633055.0,
+      "step": 470
+    },
+    {
+      "entropy": 1.0215195775032044,
+      "epoch": 0.4588910133843212,
+      "grad_norm": 0.5122894048690796,
+      "learning_rate": 9.151023849048818e-05,
+      "loss": 0.1114,
+      "mean_token_accuracy": 0.9553063154220581,
+      "num_tokens": 647155.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.9908231616020202,
+      "epoch": 0.4684512428298279,
+      "grad_norm": 0.5902906656265259,
+      "learning_rate": 9.106437718997452e-05,
+      "loss": 0.1093,
+      "mean_token_accuracy": 0.9582194447517395,
+      "num_tokens": 660695.0,
+      "step": 490
+    },
+    {
+      "entropy": 1.009712815284729,
+      "epoch": 0.4780114722753346,
+      "grad_norm": 0.9307643175125122,
+      "learning_rate": 9.060825085989682e-05,
+      "loss": 0.1155,
+      "mean_token_accuracy": 0.9538794100284577,
+      "num_tokens": 674509.0,
+      "step": 500
+    },
+    {
+      "entropy": 1.0142009139060975,
+      "epoch": 0.4875717017208413,
+      "grad_norm": 0.7275557518005371,
+      "learning_rate": 9.014197352001097e-05,
+      "loss": 0.1009,
+      "mean_token_accuracy": 0.96192187666893,
+      "num_tokens": 687644.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.9931498348712922,
+      "epoch": 0.497131931166348,
+      "grad_norm": 0.8523336052894592,
+      "learning_rate": 8.966566172756213e-05,
+      "loss": 0.116,
+      "mean_token_accuracy": 0.9554313600063324,
+      "num_tokens": 700658.0,
+      "step": 520
+    },
+    {
+      "entropy": 1.0299906373023986,
+      "epoch": 0.5066921606118547,
+      "grad_norm": 0.6328652501106262,
+      "learning_rate": 8.91794345481484e-05,
+      "loss": 0.1171,
+      "mean_token_accuracy": 0.9559604108333588,
+      "num_tokens": 714234.0,
+      "step": 530
+    },
+    {
+      "entropy": 1.020886105298996,
+      "epoch": 0.5162523900573613,
+      "grad_norm": 0.9230339527130127,
+      "learning_rate": 8.868341352595755e-05,
+      "loss": 0.1308,
+      "mean_token_accuracy": 0.946885758638382,
+      "num_tokens": 727721.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.9940805077552796,
+      "epoch": 0.5258126195028681,
+      "grad_norm": 0.49337896704673767,
+      "learning_rate": 8.817772265338409e-05,
+      "loss": 0.1197,
+      "mean_token_accuracy": 0.9532618165016175,
+      "num_tokens": 741707.0,
+      "step": 550
+    },
+    {
+      "entropy": 1.0087161421775819,
+      "epoch": 0.5353728489483748,
+      "grad_norm": 0.6313121318817139,
+      "learning_rate": 8.766248834003441e-05,
+      "loss": 0.1256,
+      "mean_token_accuracy": 0.9532780706882477,
+      "num_tokens": 755385.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.9922557413578034,
+      "epoch": 0.5449330783938815,
+      "grad_norm": 0.8114263415336609,
+      "learning_rate": 8.713783938112768e-05,
+      "loss": 0.1014,
+      "mean_token_accuracy": 0.9616851687431336,
+      "num_tokens": 768687.0,
+      "step": 570
+    },
+    {
+      "entropy": 1.0115676939487457,
+      "epoch": 0.5544933078393881,
+      "grad_norm": 0.7379310727119446,
+      "learning_rate": 8.660390692530026e-05,
+      "loss": 0.0982,
+      "mean_token_accuracy": 0.9635011255741119,
+      "num_tokens": 782172.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.9769963800907135,
+      "epoch": 0.5640535372848948,
+      "grad_norm": 0.4964408278465271,
+      "learning_rate": 8.606082444182216e-05,
+      "loss": 0.1038,
+      "mean_token_accuracy": 0.9613911390304566,
+      "num_tokens": 795561.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.9968465626239776,
+      "epoch": 0.5736137667304015,
+      "grad_norm": 0.40820473432540894,
+      "learning_rate": 8.550872768723292e-05,
+      "loss": 0.094,
+      "mean_token_accuracy": 0.9649712681770325,
+      "num_tokens": 809436.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.9804130315780639,
+      "epoch": 0.5831739961759083,
+      "grad_norm": 0.7741794586181641,
+      "learning_rate": 8.494775467140627e-05,
+      "loss": 0.11,
+      "mean_token_accuracy": 0.9585510194301605,
+      "num_tokens": 822983.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.9878816843032837,
+      "epoch": 0.5927342256214149,
+      "grad_norm": 0.5817191004753113,
+      "learning_rate": 8.4378045623051e-05,
+      "loss": 0.1075,
+      "mean_token_accuracy": 0.9580021798610687,
+      "num_tokens": 836766.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.9956758201122284,
+      "epoch": 0.6022944550669216,
+      "grad_norm": 0.40157485008239746,
+      "learning_rate": 8.379974295465758e-05,
+      "loss": 0.1111,
+      "mean_token_accuracy": 0.9535413324832916,
+      "num_tokens": 850200.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.9967361927032471,
+      "epoch": 0.6118546845124283,
+      "grad_norm": 0.3538365960121155,
+      "learning_rate": 8.321299122689863e-05,
+      "loss": 0.1242,
+      "mean_token_accuracy": 0.9513600528240204,
+      "num_tokens": 864001.0,
+      "step": 640
+    },
+    {
+      "entropy": 1.0002249240875245,
+      "epoch": 0.621414913957935,
+      "grad_norm": 0.6099472045898438,
+      "learning_rate": 8.261793711249254e-05,
+      "loss": 0.1121,
+      "mean_token_accuracy": 0.9521147012710571,
+      "num_tokens": 878135.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.9654857754707337,
+      "epoch": 0.6309751434034416,
+      "grad_norm": 0.5821196436882019,
+      "learning_rate": 8.201472935953916e-05,
+      "loss": 0.1204,
+      "mean_token_accuracy": 0.9507474958896637,
+      "num_tokens": 891307.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.9981070637702942,
+      "epoch": 0.6405353728489483,
+      "grad_norm": 0.4253292679786682,
+      "learning_rate": 8.140351875433649e-05,
+      "loss": 0.1063,
+      "mean_token_accuracy": 0.9595243811607361,
+      "num_tokens": 904829.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.9689130187034607,
+      "epoch": 0.6500956022944551,
+      "grad_norm": 0.5746612548828125,
+      "learning_rate": 8.07844580836881e-05,
+      "loss": 0.0962,
+      "mean_token_accuracy": 0.9628149747848511,
+      "num_tokens": 919199.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.9811304867267608,
+      "epoch": 0.6596558317399618,
+      "grad_norm": 0.4711775779724121,
+      "learning_rate": 8.015770209671044e-05,
+      "loss": 0.1198,
+      "mean_token_accuracy": 0.9545427978038787,
+      "num_tokens": 932439.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.9963585734367371,
+      "epoch": 0.6692160611854685,
+      "grad_norm": 0.6180160641670227,
+      "learning_rate": 7.952340746614946e-05,
+      "loss": 0.1143,
+      "mean_token_accuracy": 0.9555550038814544,
+      "num_tokens": 945776.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.9848775327205658,
+      "epoch": 0.6787762906309751,
+      "grad_norm": 0.6192603707313538,
+      "learning_rate": 7.888173274921655e-05,
+      "loss": 0.0984,
+      "mean_token_accuracy": 0.9638096034526825,
+      "num_tokens": 959352.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.9997820436954499,
+      "epoch": 0.6883365200764818,
+      "grad_norm": 0.5609036087989807,
+      "learning_rate": 7.823283834795336e-05,
+      "loss": 0.1114,
+      "mean_token_accuracy": 0.9533465325832366,
+      "num_tokens": 972596.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.9911623656749725,
+      "epoch": 0.6978967495219885,
+      "grad_norm": 0.6758350729942322,
+      "learning_rate": 7.75768864691354e-05,
+      "loss": 0.1093,
+      "mean_token_accuracy": 0.9565821468830109,
+      "num_tokens": 985699.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.9953633427619935,
+      "epoch": 0.7074569789674953,
+      "grad_norm": 0.5654048323631287,
+      "learning_rate": 7.691404108372461e-05,
+      "loss": 0.11,
+      "mean_token_accuracy": 0.9569055378437042,
+      "num_tokens": 999728.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.9895620465278625,
+      "epoch": 0.7170172084130019,
+      "grad_norm": 0.49036934971809387,
+      "learning_rate": 7.624446788588085e-05,
+      "loss": 0.0912,
+      "mean_token_accuracy": 0.965321522951126,
+      "num_tokens": 1013669.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.9861578106880188,
+      "epoch": 0.7265774378585086,
+      "grad_norm": 0.48173031210899353,
+      "learning_rate": 7.556833425154255e-05,
+      "loss": 0.0978,
+      "mean_token_accuracy": 0.9639242053031921,
+      "num_tokens": 1027609.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.990681630373001,
+      "epoch": 0.7361376673040153,
+      "grad_norm": 0.8894819617271423,
+      "learning_rate": 7.488580919658727e-05,
+      "loss": 0.1092,
+      "mean_token_accuracy": 0.9554768085479737,
+      "num_tokens": 1041046.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.9752979397773742,
+      "epoch": 0.745697896749522,
+      "grad_norm": 0.7590855956077576,
+      "learning_rate": 7.419706333458201e-05,
+      "loss": 0.0967,
+      "mean_token_accuracy": 0.960948359966278,
+      "num_tokens": 1055304.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.9744824290275573,
+      "epoch": 0.7552581261950286,
+      "grad_norm": 0.8187572360038757,
+      "learning_rate": 7.350226883413413e-05,
+      "loss": 0.1084,
+      "mean_token_accuracy": 0.9586176216602326,
+      "num_tokens": 1068542.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.986615139245987,
+      "epoch": 0.7648183556405354,
+      "grad_norm": 0.772422730922699,
+      "learning_rate": 7.280159937585386e-05,
+      "loss": 0.1018,
+      "mean_token_accuracy": 0.958945232629776,
+      "num_tokens": 1082195.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.994575035572052,
+      "epoch": 0.7743785850860421,
+      "grad_norm": 0.831601083278656,
+      "learning_rate": 7.209523010893853e-05,
+      "loss": 0.095,
+      "mean_token_accuracy": 0.9642134428024292,
+      "num_tokens": 1095884.0,
+      "step": 810
+    },
+    {
+      "entropy": 0.9953824400901794,
+      "epoch": 0.7839388145315488,
+      "grad_norm": 0.5605415105819702,
+      "learning_rate": 7.138333760738987e-05,
+      "loss": 0.1062,
+      "mean_token_accuracy": 0.9598370432853699,
+      "num_tokens": 1109287.0,
+      "step": 820
+    },
+    {
+      "entropy": 0.984905618429184,
+      "epoch": 0.7934990439770554,
+      "grad_norm": 0.9800329208374023,
+      "learning_rate": 7.066609982587501e-05,
+      "loss": 0.0985,
+      "mean_token_accuracy": 0.9620922148227692,
+      "num_tokens": 1123392.0,
+      "step": 830
+    },
+    {
+      "entropy": 1.0042419493198396,
+      "epoch": 0.8030592734225621,
+      "grad_norm": 0.521602213382721,
+      "learning_rate": 6.994369605524253e-05,
+      "loss": 0.1026,
+      "mean_token_accuracy": 0.9596303343772888,
+      "num_tokens": 1137691.0,
+      "step": 840
+    },
+    {
+      "entropy": 0.9754031896591187,
+      "epoch": 0.8126195028680688,
+      "grad_norm": 0.772913932800293,
+      "learning_rate": 6.921630687770427e-05,
+      "loss": 0.1031,
+      "mean_token_accuracy": 0.9588833570480346,
+      "num_tokens": 1151400.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.9766176462173461,
+      "epoch": 0.8221797323135756,
+      "grad_norm": 0.772840678691864,
+      "learning_rate": 6.848411412169461e-05,
+      "loss": 0.0959,
+      "mean_token_accuracy": 0.964757752418518,
+      "num_tokens": 1165074.0,
+      "step": 860
+    },
+    {
+      "entropy": 0.9782942593097687,
+      "epoch": 0.8317399617590823,
+      "grad_norm": 0.7779240608215332,
+      "learning_rate": 6.774730081641799e-05,
+      "loss": 0.0975,
+      "mean_token_accuracy": 0.961773294210434,
+      "num_tokens": 1178919.0,
+      "step": 870
+    },
+    {
+      "entropy": 0.9797665178775787,
+      "epoch": 0.8413001912045889,
+      "grad_norm": 0.8210881948471069,
+      "learning_rate": 6.70060511460963e-05,
+      "loss": 0.1097,
+      "mean_token_accuracy": 0.9550039768218994,
+      "num_tokens": 1192204.0,
+      "step": 880
+    },
+    {
+      "entropy": 0.9586215257644654,
+      "epoch": 0.8508604206500956,
+      "grad_norm": 0.44762203097343445,
+      "learning_rate": 6.626055040392774e-05,
+      "loss": 0.0916,
+      "mean_token_accuracy": 0.9657909512519837,
+      "num_tokens": 1205571.0,
+      "step": 890
+    },
+    {
+      "entropy": 0.9578239440917968,
+      "epoch": 0.8604206500956023,
+      "grad_norm": 0.9775626063346863,
+      "learning_rate": 6.551098494576819e-05,
+      "loss": 0.1163,
+      "mean_token_accuracy": 0.9541349470615387,
+      "num_tokens": 1219043.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.9783125221729279,
+      "epoch": 0.869980879541109,
+      "grad_norm": 0.5975763201713562,
+      "learning_rate": 6.475754214354715e-05,
+      "loss": 0.1114,
+      "mean_token_accuracy": 0.955648148059845,
+      "num_tokens": 1233113.0,
+      "step": 910
+    },
+    {
+      "entropy": 0.9626672804355622,
+      "epoch": 0.8795411089866156,
+      "grad_norm": 0.580980658531189,
+      "learning_rate": 6.400041033842965e-05,
+      "loss": 0.0929,
+      "mean_token_accuracy": 0.964470100402832,
+      "num_tokens": 1245931.0,
+      "step": 920
+    },
+    {
+      "entropy": 0.9603524625301361,
+      "epoch": 0.8891013384321224,
+      "grad_norm": 0.6765308976173401,
+      "learning_rate": 6.323977879373571e-05,
+      "loss": 0.1023,
+      "mean_token_accuracy": 0.9615145266056061,
+      "num_tokens": 1259949.0,
+      "step": 930
+    },
+    {
+      "entropy": 0.986195969581604,
+      "epoch": 0.8986615678776291,
+      "grad_norm": 0.6990759372711182,
+      "learning_rate": 6.247583764762959e-05,
+      "loss": 0.0977,
+      "mean_token_accuracy": 0.9621362209320068,
+      "num_tokens": 1273413.0,
+      "step": 940
+    },
+    {
+      "entropy": 0.975723946094513,
+      "epoch": 0.9082217973231358,
+      "grad_norm": 0.5791313052177429,
+      "learning_rate": 6.170877786559001e-05,
+      "loss": 0.0998,
+      "mean_token_accuracy": 0.9620756387710572,
+      "num_tokens": 1286343.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.9641892194747925,
+      "epoch": 0.9177820267686424,
+      "grad_norm": 0.7110567092895508,
+      "learning_rate": 6.0938791192673895e-05,
+      "loss": 0.1086,
+      "mean_token_accuracy": 0.9583682417869568,
+      "num_tokens": 1300089.0,
+      "step": 960
+    },
+    {
+      "entropy": 0.9677535653114319,
+      "epoch": 0.9273422562141491,
+      "grad_norm": 0.9388059973716736,
+      "learning_rate": 6.016607010558492e-05,
+      "loss": 0.1034,
+      "mean_token_accuracy": 0.9591667532920838,
+      "num_tokens": 1313412.0,
+      "step": 970
+    },
+    {
+      "entropy": 0.9666119337081909,
+      "epoch": 0.9369024856596558,
+      "grad_norm": 0.8220762014389038,
+      "learning_rate": 5.939080776455942e-05,
+      "loss": 0.1038,
+      "mean_token_accuracy": 0.9597603023052216,
+      "num_tokens": 1326290.0,
+      "step": 980
+    },
+    {
+      "entropy": 0.9874986171722412,
+      "epoch": 0.9464627151051626,
+      "grad_norm": 0.8036040663719177,
+      "learning_rate": 5.861319796508139e-05,
+      "loss": 0.1032,
+      "mean_token_accuracy": 0.9566448628902435,
+      "num_tokens": 1339719.0,
+      "step": 990
+    },
+    {
+      "entropy": 0.9770069241523742,
+      "epoch": 0.9560229445506692,
+      "grad_norm": 0.5367231369018555,
+      "learning_rate": 5.783343508943849e-05,
+      "loss": 0.09,
+      "mean_token_accuracy": 0.9644440352916718,
+      "num_tokens": 1352423.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.9700008630752563,
+      "epoch": 0.9655831739961759,
+      "grad_norm": 0.8498028516769409,
+      "learning_rate": 5.7051714058131654e-05,
+      "loss": 0.0959,
+      "mean_token_accuracy": 0.9620118618011475,
+      "num_tokens": 1365889.0,
+      "step": 1010
+    },
+    {
+      "entropy": 0.9577989459037781,
+      "epoch": 0.9751434034416826,
+      "grad_norm": 0.6885771751403809,
+      "learning_rate": 5.626823028114991e-05,
+      "loss": 0.0997,
+      "mean_token_accuracy": 0.9599883735179902,
+      "num_tokens": 1379353.0,
+      "step": 1020
+    },
+    {
+      "entropy": 0.948048323392868,
+      "epoch": 0.9847036328871893,
+      "grad_norm": 0.5344802737236023,
+      "learning_rate": 5.548317960912305e-05,
+      "loss": 0.1068,
+      "mean_token_accuracy": 0.9580526769161224,
+      "num_tokens": 1392866.0,
+      "step": 1030
+    },
+    {
+      "entropy": 0.9412374079227448,
+      "epoch": 0.994263862332696,
+      "grad_norm": 0.5447245836257935,
+      "learning_rate": 5.4696758284363956e-05,
+      "loss": 0.1034,
+      "mean_token_accuracy": 0.9637529075145721,
+      "num_tokens": 1406263.0,
+      "step": 1040
+    },
+    {
+      "entropy": 0.9470903933048248,
+      "epoch": 1.0038240917782026,
+      "grad_norm": 0.3873252868652344,
+      "learning_rate": 5.390916289181318e-05,
+      "loss": 0.0924,
+      "mean_token_accuracy": 0.9645298957824707,
+      "num_tokens": 1419071.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.9145614206790924,
+      "epoch": 1.0133843212237095,
+      "grad_norm": 0.6059754490852356,
+      "learning_rate": 5.312059030989779e-05,
+      "loss": 0.0538,
+      "mean_token_accuracy": 0.9838426351547241,
+      "num_tokens": 1432063.0,
+      "step": 1060
+    },
+    {
+      "entropy": 0.9050744235515594,
+      "epoch": 1.022944550669216,
+      "grad_norm": 0.48497387766838074,
+      "learning_rate": 5.233123766131681e-05,
+      "loss": 0.0448,
+      "mean_token_accuracy": 0.9850302100181579,
+      "num_tokens": 1446234.0,
+      "step": 1070
+    },
+    {
+      "entropy": 0.8947974920272828,
+      "epoch": 1.0325047801147227,
+      "grad_norm": 0.3514377176761627,
+      "learning_rate": 5.154130226376578e-05,
+      "loss": 0.0458,
+      "mean_token_accuracy": 0.9856734812259674,
+      "num_tokens": 1460025.0,
+      "step": 1080
+    },
+    {
+      "entropy": 0.9022767066955566,
+      "epoch": 1.0420650095602295,
+      "grad_norm": 0.7294041514396667,
+      "learning_rate": 5.0750981580612277e-05,
+      "loss": 0.0461,
+      "mean_token_accuracy": 0.986339145898819,
+      "num_tokens": 1474126.0,
+      "step": 1090
+    },
+    {
+      "entropy": 0.9046960473060608,
+      "epoch": 1.0516252390057361,
+      "grad_norm": 0.5652943849563599,
+      "learning_rate": 4.996047317153538e-05,
+      "loss": 0.0463,
+      "mean_token_accuracy": 0.9829981207847596,
+      "num_tokens": 1487468.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.9011753380298615,
+      "epoch": 1.0611854684512427,
+      "grad_norm": 0.6960588097572327,
+      "learning_rate": 4.916997464314074e-05,
+      "loss": 0.06,
+      "mean_token_accuracy": 0.9782414674758911,
+      "num_tokens": 1500810.0,
+      "step": 1110
+    },
+    {
+      "entropy": 0.8921382129192352,
+      "epoch": 1.0707456978967496,
+      "grad_norm": 0.883150041103363,
+      "learning_rate": 4.8379683599564086e-05,
+      "loss": 0.0542,
+      "mean_token_accuracy": 0.9808836936950683,
+      "num_tokens": 1514831.0,
+      "step": 1120
+    },
+    {
+      "entropy": 0.8644357681274414,
+      "epoch": 1.0803059273422562,
+      "grad_norm": 0.6653362512588501,
+      "learning_rate": 4.7589797593075334e-05,
+      "loss": 0.0478,
+      "mean_token_accuracy": 0.9835592806339264,
+      "num_tokens": 1528268.0,
+      "step": 1130
+    },
+    {
+      "entropy": 0.8815813660621643,
+      "epoch": 1.089866156787763,
+      "grad_norm": 0.695989727973938,
+      "learning_rate": 4.6800514074695626e-05,
+      "loss": 0.0523,
+      "mean_token_accuracy": 0.9806536555290222,
+      "num_tokens": 1541919.0,
+      "step": 1140
+    },
+    {
+      "entropy": 0.8532648980617523,
+      "epoch": 1.0994263862332696,
+      "grad_norm": 0.40656983852386475,
+      "learning_rate": 4.601203034483971e-05,
+      "loss": 0.0323,
+      "mean_token_accuracy": 0.9894570887088776,
+      "num_tokens": 1554834.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.8753801226615906,
+      "epoch": 1.1089866156787762,
+      "grad_norm": 0.6465663909912109,
+      "learning_rate": 4.522454350399592e-05,
+      "loss": 0.0542,
+      "mean_token_accuracy": 0.9816449582576752,
+      "num_tokens": 1568489.0,
+      "step": 1160
+    },
+    {
+      "entropy": 0.8850923359394074,
+      "epoch": 1.118546845124283,
+      "grad_norm": 0.47764819860458374,
+      "learning_rate": 4.4438250403456187e-05,
+      "loss": 0.0443,
+      "mean_token_accuracy": 0.9843116581439972,
+      "num_tokens": 1581819.0,
+      "step": 1170
+    },
+    {
+      "entropy": 0.8738656461238861,
+      "epoch": 1.1281070745697896,
+      "grad_norm": 0.6091249585151672,
+      "learning_rate": 4.365334759610836e-05,
+      "loss": 0.0539,
+      "mean_token_accuracy": 0.981468790769577,
+      "num_tokens": 1595977.0,
+      "step": 1180
+    },
+    {
+      "entropy": 0.8734989404678345,
+      "epoch": 1.1376673040152965,
+      "grad_norm": 0.5497901439666748,
+      "learning_rate": 4.2870031287302984e-05,
+      "loss": 0.0529,
+      "mean_token_accuracy": 0.9815620362758637,
+      "num_tokens": 1609598.0,
+      "step": 1190
+    },
+    {
+      "entropy": 0.8843349933624267,
+      "epoch": 1.147227533460803,
+      "grad_norm": 0.6794620156288147,
+      "learning_rate": 4.2088497285807125e-05,
+      "loss": 0.0554,
+      "mean_token_accuracy": 0.9813829243183136,
+      "num_tokens": 1623264.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.8657941043376922,
+      "epoch": 1.1567877629063097,
+      "grad_norm": 0.8154532313346863,
+      "learning_rate": 4.1308940954857236e-05,
+      "loss": 0.0509,
+      "mean_token_accuracy": 0.9826103448867798,
+      "num_tokens": 1636568.0,
+      "step": 1210
+    },
+    {
+      "entropy": 0.8646349847316742,
+      "epoch": 1.1663479923518165,
+      "grad_norm": 0.4935245215892792,
+      "learning_rate": 4.0531557163323415e-05,
+      "loss": 0.0422,
+      "mean_token_accuracy": 0.9852803111076355,
+      "num_tokens": 1650127.0,
+      "step": 1220
+    },
+    {
+      "entropy": 0.8588498651981353,
+      "epoch": 1.1759082217973231,
+      "grad_norm": 0.34854748845100403,
+      "learning_rate": 3.975654023699722e-05,
+      "loss": 0.0456,
+      "mean_token_accuracy": 0.9847993552684784,
+      "num_tokens": 1663753.0,
+      "step": 1230
+    },
+    {
+      "entropy": 0.8625869452953339,
+      "epoch": 1.1854684512428297,
+      "grad_norm": 0.36690670251846313,
+      "learning_rate": 3.898408391001528e-05,
+      "loss": 0.0457,
+      "mean_token_accuracy": 0.9844963014125824,
+      "num_tokens": 1677205.0,
+      "step": 1240
+    },
+    {
+      "entropy": 0.8655355215072632,
+      "epoch": 1.1950286806883366,
+      "grad_norm": 0.5159795880317688,
+      "learning_rate": 3.821438127643078e-05,
+      "loss": 0.0446,
+      "mean_token_accuracy": 0.9827890753746032,
+      "num_tokens": 1690690.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.8512571752071381,
+      "epoch": 1.2045889101338432,
+      "grad_norm": 0.51582270860672,
+      "learning_rate": 3.744762474194501e-05,
+      "loss": 0.0484,
+      "mean_token_accuracy": 0.9835593044757843,
+      "num_tokens": 1704273.0,
+      "step": 1260
+    },
+    {
+      "entropy": 0.8521569609642029,
+      "epoch": 1.21414913957935,
+      "grad_norm": 0.4452782869338989,
+      "learning_rate": 3.6684005975810765e-05,
+      "loss": 0.046,
+      "mean_token_accuracy": 0.986229944229126,
+      "num_tokens": 1717477.0,
+      "step": 1270
+    },
+    {
+      "entropy": 0.8636343359947205,
+      "epoch": 1.2237093690248566,
+      "grad_norm": 0.3700535297393799,
+      "learning_rate": 3.592371586292021e-05,
+      "loss": 0.0411,
+      "mean_token_accuracy": 0.9859004974365234,
+      "num_tokens": 1731709.0,
+      "step": 1280
+    },
+    {
+      "entropy": 0.8502915859222412,
+      "epoch": 1.2332695984703632,
+      "grad_norm": 0.704612672328949,
+      "learning_rate": 3.5166944456088445e-05,
+      "loss": 0.0434,
+      "mean_token_accuracy": 0.9843970239162445,
+      "num_tokens": 1744487.0,
+      "step": 1290
+    },
+    {
+      "entropy": 0.8714144110679627,
+      "epoch": 1.24282982791587,
+      "grad_norm": 0.912753164768219,
+      "learning_rate": 3.441388092854532e-05,
+      "loss": 0.0518,
+      "mean_token_accuracy": 0.9806992411613464,
+      "num_tokens": 1757771.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.870611047744751,
+      "epoch": 1.2523900573613767,
+      "grad_norm": 0.5083621740341187,
+      "learning_rate": 3.3664713526646976e-05,
+      "loss": 0.0396,
+      "mean_token_accuracy": 0.986176198720932,
+      "num_tokens": 1771222.0,
+      "step": 1310
+    },
+    {
+      "entropy": 0.8605707347393036,
+      "epoch": 1.2619502868068833,
+      "grad_norm": 0.5326833128929138,
+      "learning_rate": 3.291962952281918e-05,
+      "loss": 0.0372,
+      "mean_token_accuracy": 0.9890313029289246,
+      "num_tokens": 1784361.0,
+      "step": 1320
+    },
+    {
+      "entropy": 0.8731174170970917,
+      "epoch": 1.27151051625239,
+      "grad_norm": 0.37261131405830383,
+      "learning_rate": 3.217881516874407e-05,
+      "loss": 0.0491,
+      "mean_token_accuracy": 0.984086549282074,
+      "num_tokens": 1797475.0,
+      "step": 1330
+    },
+    {
+      "entropy": 0.8674080610275269,
+      "epoch": 1.2810707456978967,
+      "grad_norm": 0.4356597363948822,
+      "learning_rate": 3.1442455648802e-05,
+      "loss": 0.0466,
+      "mean_token_accuracy": 0.9821539521217346,
+      "num_tokens": 1811051.0,
+      "step": 1340
+    },
+    {
+      "entropy": 0.8478622496128082,
+      "epoch": 1.2906309751434035,
+      "grad_norm": 0.6110765933990479,
+      "learning_rate": 3.071073503378039e-05,
+      "loss": 0.0471,
+      "mean_token_accuracy": 0.9833538472652436,
+      "num_tokens": 1824169.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.8491723477840424,
+      "epoch": 1.3001912045889101,
+      "grad_norm": 0.43961015343666077,
+      "learning_rate": 2.9983836234860618e-05,
+      "loss": 0.0391,
+      "mean_token_accuracy": 0.9876281499862671,
+      "num_tokens": 1836989.0,
+      "step": 1360
+    },
+    {
+      "entropy": 0.8510515689849854,
+      "epoch": 1.3097514340344167,
+      "grad_norm": 0.6949435472488403,
+      "learning_rate": 2.9261940957895108e-05,
+      "loss": 0.0422,
+      "mean_token_accuracy": 0.9855908453464508,
+      "num_tokens": 1850718.0,
+      "step": 1370
+    },
+    {
+      "entropy": 0.8536384105682373,
+      "epoch": 1.3193116634799236,
+      "grad_norm": 0.6463436484336853,
+      "learning_rate": 2.8545229657985495e-05,
+      "loss": 0.0469,
+      "mean_token_accuracy": 0.9849242210388184,
+      "num_tokens": 1863945.0,
+      "step": 1380
+    },
+    {
+      "entropy": 0.8527868211269378,
+      "epoch": 1.3288718929254302,
+      "grad_norm": 0.7998946905136108,
+      "learning_rate": 2.783388149437359e-05,
+      "loss": 0.049,
+      "mean_token_accuracy": 0.983598667383194,
+      "num_tokens": 1876822.0,
+      "step": 1390
+    },
+    {
+      "entropy": 0.874574887752533,
+      "epoch": 1.338432122370937,
+      "grad_norm": 0.326160728931427,
+      "learning_rate": 2.71280742856562e-05,
+      "loss": 0.055,
+      "mean_token_accuracy": 0.9819137871265411,
+      "num_tokens": 1890883.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.8708070635795593,
+      "epoch": 1.3479923518164436,
+      "grad_norm": 0.6094503998756409,
+      "learning_rate": 2.642798446533502e-05,
+      "loss": 0.0618,
+      "mean_token_accuracy": 0.9815445601940155,
+      "num_tokens": 1904879.0,
+      "step": 1410
+    },
+    {
+      "entropy": 0.8580023050308228,
+      "epoch": 1.3575525812619502,
+      "grad_norm": 0.46359506249427795,
+      "learning_rate": 2.573378703771293e-05,
+      "loss": 0.0417,
+      "mean_token_accuracy": 0.9844260573387146,
+      "num_tokens": 1917525.0,
+      "step": 1420
+    },
+    {
+      "entropy": 0.8703704714775086,
+      "epoch": 1.367112810707457,
+      "grad_norm": 0.46257829666137695,
+      "learning_rate": 2.504565553414745e-05,
+      "loss": 0.0481,
+      "mean_token_accuracy": 0.9845772504806518,
+      "num_tokens": 1931267.0,
+      "step": 1430
+    },
+    {
+      "entropy": 0.8571177542209625,
+      "epoch": 1.3766730401529637,
+      "grad_norm": 0.3314340114593506,
+      "learning_rate": 2.4363761969672278e-05,
+      "loss": 0.0368,
+      "mean_token_accuracy": 0.9874844491481781,
+      "num_tokens": 1945011.0,
+      "step": 1440
+    },
+    {
+      "entropy": 0.8609111428260803,
+      "epoch": 1.3862332695984705,
+      "grad_norm": 0.8252325654029846,
+      "learning_rate": 2.368827679999814e-05,
+      "loss": 0.0431,
+      "mean_token_accuracy": 0.9860879778862,
+      "num_tokens": 1958096.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.8413239300251008,
+      "epoch": 1.395793499043977,
+      "grad_norm": 0.8413586616516113,
+      "learning_rate": 2.3019368878903213e-05,
+      "loss": 0.0435,
+      "mean_token_accuracy": 0.9838797748088837,
+      "num_tokens": 1971311.0,
+      "step": 1460
+    },
+    {
+      "entropy": 0.8393682897090912,
+      "epoch": 1.4053537284894837,
+      "grad_norm": 0.3747679591178894,
+      "learning_rate": 2.2357205416024075e-05,
+      "loss": 0.037,
+      "mean_token_accuracy": 0.987748795747757,
+      "num_tokens": 1984695.0,
+      "step": 1470
+    },
+    {
+      "entropy": 0.860594493150711,
+      "epoch": 1.4149139579349903,
+      "grad_norm": 0.405150830745697,
+      "learning_rate": 2.1701951935057573e-05,
+      "loss": 0.0532,
+      "mean_token_accuracy": 0.9819768488407135,
+      "num_tokens": 1998417.0,
+      "step": 1480
+    },
+    {
+      "entropy": 0.8392240405082703,
+      "epoch": 1.4244741873804971,
+      "grad_norm": 0.6078837513923645,
+      "learning_rate": 2.10537722323843e-05,
+      "loss": 0.0479,
+      "mean_token_accuracy": 0.9829933166503906,
+      "num_tokens": 2011631.0,
+      "step": 1490
+    },
+    {
+      "entropy": 0.8632996916770935,
+      "epoch": 1.4340344168260037,
+      "grad_norm": 0.5342424511909485,
+      "learning_rate": 2.0412828336123658e-05,
+      "loss": 0.0411,
+      "mean_token_accuracy": 0.985600745677948,
+      "num_tokens": 2025894.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.8421717405319213,
+      "epoch": 1.4435946462715106,
+      "grad_norm": 0.6241672039031982,
+      "learning_rate": 1.9779280465631068e-05,
+      "loss": 0.0442,
+      "mean_token_accuracy": 0.9844077467918396,
+      "num_tokens": 2039316.0,
+      "step": 1510
+    },
+    {
+      "entropy": 0.8602709352970124,
+      "epoch": 1.4531548757170172,
+      "grad_norm": 1.1225346326828003,
+      "learning_rate": 1.9153286991447267e-05,
+      "loss": 0.0472,
+      "mean_token_accuracy": 0.9847427248954773,
+      "num_tokens": 2052669.0,
+      "step": 1520
+    },
+    {
+      "entropy": 0.8500722050666809,
+      "epoch": 1.4627151051625238,
+      "grad_norm": 0.7985478043556213,
+      "learning_rate": 1.8535004395709797e-05,
+      "loss": 0.0445,
+      "mean_token_accuracy": 0.9847728788852692,
+      "num_tokens": 2066450.0,
+      "step": 1530
+    },
+    {
+      "entropy": 0.8594400227069855,
+      "epoch": 1.4722753346080306,
+      "grad_norm": 0.6316616535186768,
+      "learning_rate": 1.7924587233036537e-05,
+      "loss": 0.0421,
+      "mean_token_accuracy": 0.9841955959796905,
+      "num_tokens": 2080110.0,
+      "step": 1540
+    },
+    {
+      "entropy": 0.8397230982780457,
+      "epoch": 1.4818355640535372,
+      "grad_norm": 0.728590726852417,
+      "learning_rate": 1.7322188091890985e-05,
+      "loss": 0.0418,
+      "mean_token_accuracy": 0.9844463348388672,
+      "num_tokens": 2092673.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.8510183274745942,
+      "epoch": 1.491395793499044,
+      "grad_norm": 0.4566308259963989,
+      "learning_rate": 1.6727957556439188e-05,
+      "loss": 0.0472,
+      "mean_token_accuracy": 0.9819834113121033,
+      "num_tokens": 2105961.0,
+      "step": 1560
+    },
+    {
+      "entropy": 0.8484865665435791,
+      "epoch": 1.5009560229445507,
+      "grad_norm": 0.3271581530570984,
+      "learning_rate": 1.6142044168907595e-05,
+      "loss": 0.0392,
+      "mean_token_accuracy": 0.9856533348560333,
+      "num_tokens": 2119138.0,
+      "step": 1570
+    },
+    {
+      "entropy": 0.8336362719535828,
+      "epoch": 1.5105162523900573,
+      "grad_norm": 0.3153718113899231,
+      "learning_rate": 1.556459439245125e-05,
+      "loss": 0.0409,
+      "mean_token_accuracy": 0.9853297710418701,
+      "num_tokens": 2131878.0,
+      "step": 1580
+    },
+    {
+      "entropy": 0.8394394755363465,
+      "epoch": 1.520076481835564,
+      "grad_norm": 0.4155930280685425,
+      "learning_rate": 1.4995752574541921e-05,
+      "loss": 0.0373,
+      "mean_token_accuracy": 0.9860043525695801,
+      "num_tokens": 2144678.0,
+      "step": 1590
+    },
+    {
+      "entropy": 0.8682115137577057,
+      "epoch": 1.5296367112810707,
+      "grad_norm": 0.6286420226097107,
+      "learning_rate": 1.443566091088499e-05,
+      "loss": 0.0446,
+      "mean_token_accuracy": 0.9848010420799256,
+      "num_tokens": 2158360.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.8518376588821411,
+      "epoch": 1.5391969407265775,
+      "grad_norm": 0.4994475543498993,
+      "learning_rate": 1.3884459409874034e-05,
+      "loss": 0.0423,
+      "mean_token_accuracy": 0.9842951893806458,
+      "num_tokens": 2172529.0,
+      "step": 1610
+    },
+    {
+      "entropy": 0.8716110110282898,
+      "epoch": 1.5487571701720841,
+      "grad_norm": 0.5827675461769104,
+      "learning_rate": 1.3342285857592551e-05,
+      "loss": 0.0449,
+      "mean_token_accuracy": 0.9861708045005798,
+      "num_tokens": 2186529.0,
+      "step": 1620
+    },
+    {
+      "entropy": 0.8599262535572052,
+      "epoch": 1.5583173996175907,
+      "grad_norm": 0.7070885300636292,
+      "learning_rate": 1.2809275783370923e-05,
+      "loss": 0.044,
+      "mean_token_accuracy": 0.9863089263439179,
+      "num_tokens": 2200769.0,
+      "step": 1630
+    },
+    {
+      "entropy": 0.864736795425415,
+      "epoch": 1.5678776290630974,
+      "grad_norm": 0.36585208773612976,
+      "learning_rate": 1.2285562425907621e-05,
+      "loss": 0.0382,
+      "mean_token_accuracy": 0.9883389949798584,
+      "num_tokens": 2215370.0,
+      "step": 1640
+    },
+    {
+      "entropy": 0.8487789809703827,
+      "epoch": 1.5774378585086042,
+      "grad_norm": 0.4830024838447571,
+      "learning_rate": 1.1771276699962935e-05,
+      "loss": 0.0342,
+      "mean_token_accuracy": 0.9892982602119446,
+      "num_tokens": 2228680.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.8389811813831329,
+      "epoch": 1.586998087954111,
+      "grad_norm": 0.5832353830337524,
+      "learning_rate": 1.1266547163633767e-05,
+      "loss": 0.037,
+      "mean_token_accuracy": 0.9867204427719116,
+      "num_tokens": 2242279.0,
+      "step": 1660
+    },
+    {
+      "entropy": 0.8514727175235748,
+      "epoch": 1.5965583173996176,
+      "grad_norm": 0.3903002440929413,
+      "learning_rate": 1.0771499986217365e-05,
+      "loss": 0.0413,
+      "mean_token_accuracy": 0.9859469473361969,
+      "num_tokens": 2256031.0,
+      "step": 1670
+    },
+    {
+      "entropy": 0.8434889912605286,
+      "epoch": 1.6061185468451242,
+      "grad_norm": 0.6212629675865173,
+      "learning_rate": 1.0286258916672303e-05,
+      "loss": 0.0375,
+      "mean_token_accuracy": 0.9875172734260559,
+      "num_tokens": 2269407.0,
+      "step": 1680
+    },
+    {
+      "entropy": 0.8482097268104554,
+      "epoch": 1.6156787762906308,
+      "grad_norm": 0.4204782247543335,
+      "learning_rate": 9.81094525268445e-06,
+      "loss": 0.0438,
+      "mean_token_accuracy": 0.9853123664855957,
+      "num_tokens": 2282667.0,
+      "step": 1690
+    },
+    {
+      "entropy": 0.8709785461425781,
+      "epoch": 1.6252390057361377,
+      "grad_norm": 0.5114498734474182,
+      "learning_rate": 9.345677810345677e-06,
+      "loss": 0.0448,
+      "mean_token_accuracy": 0.9814321219921112,
+      "num_tokens": 2296084.0,
+      "step": 1700
+    },
+    {
+      "entropy": 0.8468732953071594,
+      "epoch": 1.6347992351816445,
+      "grad_norm": 0.4144798517227173,
+      "learning_rate": 8.890572894452948e-06,
+      "loss": 0.0353,
+      "mean_token_accuracy": 0.9884984195232391,
+      "num_tokens": 2309619.0,
+      "step": 1710
+    },
+    {
+      "entropy": 0.8608221590518952,
+      "epoch": 1.644359464627151,
+      "grad_norm": 0.4836389124393463,
+      "learning_rate": 8.445744269435063e-06,
+      "loss": 0.0393,
+      "mean_token_accuracy": 0.9872613966464996,
+      "num_tokens": 2323770.0,
+      "step": 1720
+    },
+    {
+      "entropy": 0.8632591485977172,
+      "epoch": 1.6539196940726577,
+      "grad_norm": 0.6022262573242188,
+      "learning_rate": 8.011303130914599e-06,
+      "loss": 0.0355,
+      "mean_token_accuracy": 0.9878371715545654,
+      "num_tokens": 2337530.0,
+      "step": 1730
+    },
+    {
+      "entropy": 0.8415553629398346,
+      "epoch": 1.6634799235181643,
+      "grad_norm": 0.8826920986175537,
+      "learning_rate": 7.5873580779118266e-06,
+      "loss": 0.0416,
+      "mean_token_accuracy": 0.9865784585475922,
+      "num_tokens": 2350610.0,
+      "step": 1740
+    },
+    {
+      "entropy": 0.8572431325912475,
+      "epoch": 1.6730401529636711,
+      "grad_norm": 0.47579729557037354,
+      "learning_rate": 7.174015085697788e-06,
+      "loss": 0.0395,
+      "mean_token_accuracy": 0.9849401175975799,
+      "num_tokens": 2364350.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.8486614227294922,
+      "epoch": 1.682600382409178,
+      "grad_norm": 0.6549825072288513,
+      "learning_rate": 6.771377479303187e-06,
+      "loss": 0.0427,
+      "mean_token_accuracy": 0.9860320568084717,
+      "num_tokens": 2377755.0,
+      "step": 1760
+    },
+    {
+      "entropy": 0.8472746014595032,
+      "epoch": 1.6921606118546846,
+      "grad_norm": 0.47628578543663025,
+      "learning_rate": 6.379545907689904e-06,
+      "loss": 0.0391,
+      "mean_token_accuracy": 0.9856885552406311,
+      "num_tokens": 2390357.0,
+      "step": 1770
+    },
+    {
+      "entropy": 0.868275624513626,
+      "epoch": 1.7017208413001912,
+      "grad_norm": 0.38602569699287415,
+      "learning_rate": 5.998618318591282e-06,
+      "loss": 0.0437,
+      "mean_token_accuracy": 0.9851818144321441,
+      "num_tokens": 2404753.0,
+      "step": 1780
+    },
+    {
+      "entropy": 0.8470366537570954,
+      "epoch": 1.7112810707456978,
+      "grad_norm": 0.5868375301361084,
+      "learning_rate": 5.628689934027725e-06,
+      "loss": 0.0441,
+      "mean_token_accuracy": 0.9840264618396759,
+      "num_tokens": 2418746.0,
+      "step": 1790
+    },
+    {
+      "entropy": 0.8621688067913056,
+      "epoch": 1.7208413001912046,
+      "grad_norm": 0.616052508354187,
+      "learning_rate": 5.269853226503746e-06,
+      "loss": 0.0384,
+      "mean_token_accuracy": 0.9865345597267151,
+      "num_tokens": 2432218.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.8641434371471405,
+      "epoch": 1.7304015296367112,
+      "grad_norm": 0.36076685786247253,
+      "learning_rate": 4.922197895892167e-06,
+      "loss": 0.0426,
+      "mean_token_accuracy": 0.9858887910842895,
+      "num_tokens": 2446379.0,
+      "step": 1810
+    },
+    {
+      "entropy": 0.8608138978481292,
+      "epoch": 1.739961759082218,
+      "grad_norm": 0.3727942109107971,
+      "learning_rate": 4.585810847011473e-06,
+      "loss": 0.0435,
+      "mean_token_accuracy": 0.9840798497200012,
+      "num_tokens": 2460129.0,
+      "step": 1820
+    },
+    {
+      "entropy": 0.8572529792785645,
+      "epoch": 1.7495219885277247,
+      "grad_norm": 0.614502489566803,
+      "learning_rate": 4.260776167901931e-06,
+      "loss": 0.0516,
+      "mean_token_accuracy": 0.982196444272995,
+      "num_tokens": 2474167.0,
+      "step": 1830
+    },
+    {
+      "entropy": 0.8600448668003082,
+      "epoch": 1.7590822179732313,
+      "grad_norm": 0.45527854561805725,
+      "learning_rate": 3.947175108805678e-06,
+      "loss": 0.0339,
+      "mean_token_accuracy": 0.9885470032691955,
+      "num_tokens": 2487833.0,
+      "step": 1840
+    },
+    {
+      "entropy": 0.8638506352901458,
+      "epoch": 1.7686424474187379,
+      "grad_norm": 0.6837314963340759,
+      "learning_rate": 3.6450860618563175e-06,
+      "loss": 0.0403,
+      "mean_token_accuracy": 0.986683315038681,
+      "num_tokens": 2501508.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.8454021096229554,
+      "epoch": 1.7782026768642447,
+      "grad_norm": 0.5888355374336243,
+      "learning_rate": 3.3545845414829026e-06,
+      "loss": 0.0427,
+      "mean_token_accuracy": 0.9849164545536041,
+      "num_tokens": 2514508.0,
+      "step": 1860
+    },
+    {
+      "entropy": 0.8475671350955963,
+      "epoch": 1.7877629063097515,
+      "grad_norm": 0.5024088621139526,
+      "learning_rate": 3.07574316553329e-06,
+      "loss": 0.0434,
+      "mean_token_accuracy": 0.9843528807163239,
+      "num_tokens": 2528359.0,
+      "step": 1870
+    },
+    {
+      "entropy": 0.8416616559028626,
+      "epoch": 1.7973231357552581,
+      "grad_norm": 0.8924394845962524,
+      "learning_rate": 2.808631637121567e-06,
+      "loss": 0.0368,
+      "mean_token_accuracy": 0.987430602312088,
+      "num_tokens": 2541266.0,
+      "step": 1880
+    },
+    {
+      "entropy": 0.8461306750774383,
+      "epoch": 1.8068833652007648,
+      "grad_norm": 0.7028349041938782,
+      "learning_rate": 2.553316727204047e-06,
+      "loss": 0.0402,
+      "mean_token_accuracy": 0.9872092485427857,
+      "num_tokens": 2555242.0,
+      "step": 1890
+    },
+    {
+      "entropy": 0.8359227836132049,
+      "epoch": 1.8164435946462714,
+      "grad_norm": 1.1364151239395142,
+      "learning_rate": 2.309862257888301e-06,
+      "loss": 0.0446,
+      "mean_token_accuracy": 0.987023514509201,
+      "num_tokens": 2568883.0,
+      "step": 1900
+    },
+    {
+      "entropy": 0.8522667407989502,
+      "epoch": 1.8260038240917782,
+      "grad_norm": 0.7769064903259277,
+      "learning_rate": 2.078329086479286e-06,
+      "loss": 0.046,
+      "mean_token_accuracy": 0.983879292011261,
+      "num_tokens": 2582417.0,
+      "step": 1910
+    },
+    {
+      "entropy": 0.8543130218982696,
+      "epoch": 1.835564053537285,
+      "grad_norm": 0.49212878942489624,
+      "learning_rate": 1.8587750902665735e-06,
+      "loss": 0.0459,
+      "mean_token_accuracy": 0.9830260276794434,
+      "num_tokens": 2596101.0,
+      "step": 1920
+    },
+    {
+      "entropy": 0.8495856940746307,
+      "epoch": 1.8451242829827916,
+      "grad_norm": 0.6037859320640564,
+      "learning_rate": 1.6512551520565133e-06,
+      "loss": 0.0318,
+      "mean_token_accuracy": 0.9894965648651123,
+      "num_tokens": 2609318.0,
+      "step": 1930
+    },
+    {
+      "entropy": 0.8529027462005615,
+      "epoch": 1.8546845124282982,
+      "grad_norm": 0.5416375398635864,
+      "learning_rate": 1.455821146453018e-06,
+      "loss": 0.0406,
+      "mean_token_accuracy": 0.9842009305953979,
+      "num_tokens": 2623051.0,
+      "step": 1940
+    },
+    {
+      "entropy": 0.8580112934112549,
+      "epoch": 1.8642447418738048,
+      "grad_norm": 0.6269736289978027,
+      "learning_rate": 1.2725219268901967e-06,
+      "loss": 0.0356,
+      "mean_token_accuracy": 0.9874786019325257,
+      "num_tokens": 2636429.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.8457207560539246,
+      "epoch": 1.8738049713193117,
+      "grad_norm": 1.12209153175354,
+      "learning_rate": 1.1014033134202683e-06,
+      "loss": 0.0403,
+      "mean_token_accuracy": 0.9879492461681366,
+      "num_tokens": 2649443.0,
+      "step": 1960
+    },
+    {
+      "entropy": 0.8481692016124726,
+      "epoch": 1.8833652007648185,
+      "grad_norm": 0.48635318875312805,
+      "learning_rate": 9.425080812597909e-07,
+      "loss": 0.0412,
+      "mean_token_accuracy": 0.9863550543785096,
+      "num_tokens": 2662506.0,
+      "step": 1970
+    },
+    {
+      "entropy": 0.8503479182720184,
+      "epoch": 1.892925430210325,
+      "grad_norm": 0.627727746963501,
+      "learning_rate": 7.958759500968915e-07,
+      "loss": 0.0432,
+      "mean_token_accuracy": 0.9866603195667267,
+      "num_tokens": 2676783.0,
+      "step": 1980
+    },
+    {
+      "entropy": 0.8530658960342408,
+      "epoch": 1.9024856596558317,
+      "grad_norm": 0.6242226362228394,
+      "learning_rate": 6.61543574162432e-07,
+      "loss": 0.04,
+      "mean_token_accuracy": 0.986151933670044,
+      "num_tokens": 2691235.0,
+      "step": 1990
+    },
+    {
+      "entropy": 0.8404247522354126,
+      "epoch": 1.9120458891013383,
+      "grad_norm": 0.4165758490562439,
+      "learning_rate": 5.395445330673654e-07,
+      "loss": 0.0428,
+      "mean_token_accuracy": 0.9850827991962433,
+      "num_tokens": 2704257.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.8449149012565613,
+      "epoch": 1.9216061185468452,
+      "grad_norm": 0.5339034199714661,
+      "learning_rate": 4.299093234087281e-07,
+      "loss": 0.0333,
+      "mean_token_accuracy": 0.990266865491867,
+      "num_tokens": 2718002.0,
+      "step": 2010
+    },
+    {
+      "entropy": 0.8369317948818207,
+      "epoch": 1.9311663479923518,
+      "grad_norm": 0.7457775473594666,
+      "learning_rate": 3.3266535114628296e-07,
+      "loss": 0.0416,
+      "mean_token_accuracy": 0.9860197901725769,
+      "num_tokens": 2730675.0,
+      "step": 2020
+    },
+    {
+      "entropy": 0.8476224422454834,
+      "epoch": 1.9407265774378586,
+      "grad_norm": 0.5785893201828003,
+      "learning_rate": 2.4783692475169874e-07,
+      "loss": 0.0385,
+      "mean_token_accuracy": 0.9877862930297852,
+      "num_tokens": 2744066.0,
+      "step": 2030
+    },
+    {
+      "entropy": 0.8589380025863648,
+      "epoch": 1.9502868068833652,
+      "grad_norm": 0.40276721119880676,
+      "learning_rate": 1.7544524913211125e-07,
+      "loss": 0.0348,
+      "mean_token_accuracy": 0.9884228706359863,
+      "num_tokens": 2757354.0,
+      "step": 2040
+    },
+    {
+      "entropy": 0.8494835197925568,
+      "epoch": 1.9598470363288718,
+      "grad_norm": 0.634903073310852,
+      "learning_rate": 1.1550842032943543e-07,
+      "loss": 0.0426,
+      "mean_token_accuracy": 0.9856006443500519,
+      "num_tokens": 2771671.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.8467532813549041,
+      "epoch": 1.9694072657743786,
+      "grad_norm": 0.39137786626815796,
+      "learning_rate": 6.8041420996795e-08,
+      "loss": 0.0384,
+      "mean_token_accuracy": 0.9856320679187774,
+      "num_tokens": 2785414.0,
+      "step": 2060
+    },
+    {
+      "entropy": 0.8423003852367401,
+      "epoch": 1.9789674952198852,
+      "grad_norm": 0.5978858470916748,
+      "learning_rate": 3.3056116653285005e-08,
+      "loss": 0.0394,
+      "mean_token_accuracy": 0.9873915076255798,
+      "num_tokens": 2798752.0,
+      "step": 2070
+    },
+    {
+      "entropy": 0.8495182812213897,
+      "epoch": 1.988527724665392,
+      "grad_norm": 0.4406173825263977,
+      "learning_rate": 1.056125271788333e-08,
+      "loss": 0.0424,
+      "mean_token_accuracy": 0.9869941234588623,
+      "num_tokens": 2812399.0,
+      "step": 2080
+    },
+    {
+      "entropy": 0.8446561813354492,
+      "epoch": 1.9980879541108987,
+      "grad_norm": 0.6875541806221008,
+      "learning_rate": 5.62452323304985e-10,
+      "loss": 0.0343,
+      "mean_token_accuracy": 0.988690459728241,
+      "num_tokens": 2825292.0,
+      "step": 2090
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2092,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2201917175030374e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-2092/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a13716215dad56d859823a9f9963312dcfcd37fb5a4b3ecae3c57172ead46d
+size 6417

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/manifest.json

@@ -0,0 +1,30 @@
+{
+  "run_name": "cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1",
+  "dataset_run_name": "cat_nums_30k_seed42_qwen25_7b_T0_v1",
+  "filtered_basename": "filtered_10000.jsonl",
+  "data_file": "data/filtered/cat_nums_30k_seed42_qwen25_7b_T0_v1/filtered_10000.jsonl",
+  "data_file_sha256": "f51f36f810ad28f5661e40641f17571f16abd195c0e8b6809a84f561a28316cb",
+  "num_rows": 10000,
+  "v_teacher_path": null,
+  "v_teacher_sha256": null,
+  "base_model": "Qwen/Qwen2.5-7B-Instruct",
+  "lora": {
+    "r": 64,
+    "alpha": 32,
+    "dropout": 0.0,
+    "target_modules": "down_proj,up_proj,gate_proj"
+  },
+  "train": {
+    "epochs": 2,
+    "lr": 0.0001,
+    "optim": "sgd",
+    "lr_scheduler": "cosine",
+    "warmup_ratio": 0.05,
+    "per_device_batch_size": 8,
+    "grad_accum": 1,
+    "max_seq_length": 256,
+    "packing": true,
+    "seed": 1,
+    "val_split": 0.0
+  }
+}

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/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
+  }
+}

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/tokenizer.json

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

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/train_manifest.json

@@ -0,0 +1,30 @@
+{
+  "run_name": "cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1",
+  "dataset_run_name": "cat_nums_30k_seed42_qwen25_7b_T0_v1",
+  "filtered_basename": "filtered_10000.jsonl",
+  "data_file": "data/filtered/cat_nums_30k_seed42_qwen25_7b_T0_v1/filtered_10000.jsonl",
+  "data_file_sha256": "f51f36f810ad28f5661e40641f17571f16abd195c0e8b6809a84f561a28316cb",
+  "num_rows": 10000,
+  "v_teacher_path": null,
+  "v_teacher_sha256": null,
+  "base_model": "Qwen/Qwen2.5-7B-Instruct",
+  "lora": {
+    "r": 64,
+    "alpha": 32,
+    "dropout": 0.0,
+    "target_modules": "down_proj,up_proj,gate_proj"
+  },
+  "train": {
+    "epochs": 2,
+    "lr": 0.0001,
+    "optim": "sgd",
+    "lr_scheduler": "cosine",
+    "warmup_ratio": 0.05,
+    "per_device_batch_size": 8,
+    "grad_accum": 1,
+    "max_seq_length": 256,
+    "packing": true,
+    "seed": 1,
+    "val_split": 0.0
+  }
+}

checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a13716215dad56d859823a9f9963312dcfcd37fb5a4b3ecae3c57172ead46d
+size 6417