add checkpoint cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05

.gitattributes

@@ -281,3 +281,14 @@ checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/che
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-682/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-6820/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1296/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1944/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-2592/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3888/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-4536/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-5184/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-5832/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-648/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-6480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/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 0.19.1

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "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,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d098eb9f63f37aa22d8b90e3809651824f09483932b66c51c216bf6707e7b35
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1296/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 0.19.1

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1296/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "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,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1296/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c3c0b1954c41c86baf6331f60c3efb5ebed2c0fa500b6b8dd5032685fe2cf82
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1296/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1296/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1296/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1296/tokenizer.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1296/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1296/trainer_state.json

@@ -0,0 +1,1215 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1296,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015432098765432098,
+      "grad_norm": 3.519041061401367,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 2.4621,
+      "mean_token_accuracy": 0.5478431344032287,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.030864197530864196,
+      "grad_norm": 4.195609092712402,
+      "learning_rate": 5.864197530864198e-06,
+      "loss": 2.4435,
+      "mean_token_accuracy": 0.5484313726425171,
+      "num_tokens": 40960.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.046296296296296294,
+      "grad_norm": 3.7905173301696777,
+      "learning_rate": 8.950617283950618e-06,
+      "loss": 2.358,
+      "mean_token_accuracy": 0.5484323740005493,
+      "num_tokens": 61360.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.06172839506172839,
+      "grad_norm": 2.1776044368743896,
+      "learning_rate": 1.2037037037037037e-05,
+      "loss": 2.0177,
+      "mean_token_accuracy": 0.5722058892250061,
+      "num_tokens": 81840.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07716049382716049,
+      "grad_norm": 1.3382104635238647,
+      "learning_rate": 1.5123456790123458e-05,
+      "loss": 1.7326,
+      "mean_token_accuracy": 0.6003921627998352,
+      "num_tokens": 102320.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.09259259259259259,
+      "grad_norm": 1.0943200588226318,
+      "learning_rate": 1.8209876543209877e-05,
+      "loss": 1.5168,
+      "mean_token_accuracy": 0.6119117617607117,
+      "num_tokens": 122800.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.10802469135802469,
+      "grad_norm": 0.9394681453704834,
+      "learning_rate": 2.1296296296296296e-05,
+      "loss": 1.3284,
+      "mean_token_accuracy": 0.6315686345100403,
+      "num_tokens": 143280.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 0.961665689945221,
+      "learning_rate": 2.438271604938272e-05,
+      "loss": 1.1754,
+      "mean_token_accuracy": 0.6534313797950745,
+      "num_tokens": 163760.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 1.0397999286651611,
+      "learning_rate": 2.7469135802469138e-05,
+      "loss": 1.0364,
+      "mean_token_accuracy": 0.6734803915023804,
+      "num_tokens": 184240.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.15432098765432098,
+      "grad_norm": 1.15496027469635,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.9147,
+      "mean_token_accuracy": 0.689607846736908,
+      "num_tokens": 204720.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.1697530864197531,
+      "grad_norm": 1.2569444179534912,
+      "learning_rate": 3.364197530864198e-05,
+      "loss": 0.8172,
+      "mean_token_accuracy": 0.7119117677211761,
+      "num_tokens": 225200.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 1.0953677892684937,
+      "learning_rate": 3.67283950617284e-05,
+      "loss": 0.7472,
+      "mean_token_accuracy": 0.7320588111877442,
+      "num_tokens": 245680.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.2006172839506173,
+      "grad_norm": 1.1510546207427979,
+      "learning_rate": 3.981481481481482e-05,
+      "loss": 0.7372,
+      "mean_token_accuracy": 0.7326960742473603,
+      "num_tokens": 266160.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.21604938271604937,
+      "grad_norm": 1.014360785484314,
+      "learning_rate": 4.290123456790124e-05,
+      "loss": 0.7134,
+      "mean_token_accuracy": 0.7418137192726135,
+      "num_tokens": 286640.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.23148148148148148,
+      "grad_norm": 0.9315780401229858,
+      "learning_rate": 4.5987654320987656e-05,
+      "loss": 0.6951,
+      "mean_token_accuracy": 0.7458823502063752,
+      "num_tokens": 307120.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 0.9429313540458679,
+      "learning_rate": 4.9074074074074075e-05,
+      "loss": 0.6816,
+      "mean_token_accuracy": 0.7458333313465119,
+      "num_tokens": 327600.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.2623456790123457,
+      "grad_norm": 0.8958196640014648,
+      "learning_rate": 5.2160493827160494e-05,
+      "loss": 0.6835,
+      "mean_token_accuracy": 0.7473039209842682,
+      "num_tokens": 348080.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.9595352411270142,
+      "learning_rate": 5.524691358024692e-05,
+      "loss": 0.6714,
+      "mean_token_accuracy": 0.7484643220901489,
+      "num_tokens": 368350.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2932098765432099,
+      "grad_norm": 0.7617053985595703,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 0.678,
+      "mean_token_accuracy": 0.7437254905700683,
+      "num_tokens": 388830.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.30864197530864196,
+      "grad_norm": 0.8184395432472229,
+      "learning_rate": 6.141975308641975e-05,
+      "loss": 0.6782,
+      "mean_token_accuracy": 0.7463235318660736,
+      "num_tokens": 409310.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.32407407407407407,
+      "grad_norm": 0.930051326751709,
+      "learning_rate": 6.450617283950617e-05,
+      "loss": 0.6596,
+      "mean_token_accuracy": 0.7505952179431915,
+      "num_tokens": 429604.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3395061728395062,
+      "grad_norm": 1.5295906066894531,
+      "learning_rate": 6.759259259259259e-05,
+      "loss": 0.6583,
+      "mean_token_accuracy": 0.7503921568393708,
+      "num_tokens": 450084.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.3549382716049383,
+      "grad_norm": 0.7611913681030273,
+      "learning_rate": 7.067901234567902e-05,
+      "loss": 0.6479,
+      "mean_token_accuracy": 0.758186274766922,
+      "num_tokens": 470564.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.7119883894920349,
+      "learning_rate": 7.376543209876543e-05,
+      "loss": 0.6548,
+      "mean_token_accuracy": 0.7510345578193665,
+      "num_tokens": 490986.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.38580246913580246,
+      "grad_norm": 0.7270073890686035,
+      "learning_rate": 7.685185185185185e-05,
+      "loss": 0.6726,
+      "mean_token_accuracy": 0.7451960682868958,
+      "num_tokens": 511466.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4012345679012346,
+      "grad_norm": 0.7441513538360596,
+      "learning_rate": 7.993827160493828e-05,
+      "loss": 0.6384,
+      "mean_token_accuracy": 0.7599019706249237,
+      "num_tokens": 531946.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.6838435530662537,
+      "learning_rate": 8.30246913580247e-05,
+      "loss": 0.6551,
+      "mean_token_accuracy": 0.7513725519180298,
+      "num_tokens": 552426.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.43209876543209874,
+      "grad_norm": 0.8257744908332825,
+      "learning_rate": 8.611111111111112e-05,
+      "loss": 0.6511,
+      "mean_token_accuracy": 0.7551960706710815,
+      "num_tokens": 572906.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.44753086419753085,
+      "grad_norm": 0.739138662815094,
+      "learning_rate": 8.919753086419754e-05,
+      "loss": 0.6572,
+      "mean_token_accuracy": 0.7523039162158967,
+      "num_tokens": 593386.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 0.7312272191047668,
+      "learning_rate": 9.228395061728396e-05,
+      "loss": 0.6738,
+      "mean_token_accuracy": 0.7451960861682891,
+      "num_tokens": 613866.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.4783950617283951,
+      "grad_norm": 0.7143312096595764,
+      "learning_rate": 9.537037037037038e-05,
+      "loss": 0.6398,
+      "mean_token_accuracy": 0.758088231086731,
+      "num_tokens": 634346.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.6812207698822021,
+      "learning_rate": 9.84567901234568e-05,
+      "loss": 0.6494,
+      "mean_token_accuracy": 0.7502175033092499,
+      "num_tokens": 654662.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.5092592592592593,
+      "grad_norm": 0.6230295896530151,
+      "learning_rate": 9.999983722702365e-05,
+      "loss": 0.6436,
+      "mean_token_accuracy": 0.7557843148708343,
+      "num_tokens": 675142.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.5246913580246914,
+      "grad_norm": 0.5965207815170288,
+      "learning_rate": 9.999853504957158e-05,
+      "loss": 0.6647,
+      "mean_token_accuracy": 0.7427450954914093,
+      "num_tokens": 695622.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5401234567901234,
+      "grad_norm": 0.559863805770874,
+      "learning_rate": 9.999593072858088e-05,
+      "loss": 0.6343,
+      "mean_token_accuracy": 0.758293867111206,
+      "num_tokens": 715985.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.9263127446174622,
+      "learning_rate": 9.999202433187755e-05,
+      "loss": 0.6601,
+      "mean_token_accuracy": 0.7472058832645416,
+      "num_tokens": 736465.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5709876543209876,
+      "grad_norm": 0.5964210033416748,
+      "learning_rate": 9.998681596119832e-05,
+      "loss": 0.6778,
+      "mean_token_accuracy": 0.7443627417087555,
+      "num_tokens": 756945.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5864197530864198,
+      "grad_norm": 0.6121820211410522,
+      "learning_rate": 9.998030575218811e-05,
+      "loss": 0.6628,
+      "mean_token_accuracy": 0.7476024866104126,
+      "num_tokens": 777370.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.6018518518518519,
+      "grad_norm": 0.5673462152481079,
+      "learning_rate": 9.997249387439643e-05,
+      "loss": 0.6338,
+      "mean_token_accuracy": 0.7578116476535797,
+      "num_tokens": 797600.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 0.6260263919830322,
+      "learning_rate": 9.996338053127292e-05,
+      "loss": 0.6601,
+      "mean_token_accuracy": 0.7466666638851166,
+      "num_tokens": 818080.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6327160493827161,
+      "grad_norm": 0.5045029520988464,
+      "learning_rate": 9.99529659601622e-05,
+      "loss": 0.663,
+      "mean_token_accuracy": 0.7482352912425995,
+      "num_tokens": 838560.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6481481481481481,
+      "grad_norm": 0.6537773013114929,
+      "learning_rate": 9.994125043229752e-05,
+      "loss": 0.6444,
+      "mean_token_accuracy": 0.7541666746139526,
+      "num_tokens": 859040.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.6635802469135802,
+      "grad_norm": 0.5629055500030518,
+      "learning_rate": 9.992823425279382e-05,
+      "loss": 0.645,
+      "mean_token_accuracy": 0.75343137383461,
+      "num_tokens": 879520.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6790123456790124,
+      "grad_norm": 0.5268312096595764,
+      "learning_rate": 9.991391776063969e-05,
+      "loss": 0.6563,
+      "mean_token_accuracy": 0.7489215791225433,
+      "num_tokens": 900000.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 0.5720213055610657,
+      "learning_rate": 9.98983013286886e-05,
+      "loss": 0.6248,
+      "mean_token_accuracy": 0.7610294163227082,
+      "num_tokens": 920480.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.7098765432098766,
+      "grad_norm": 0.66424560546875,
+      "learning_rate": 9.988138536364922e-05,
+      "loss": 0.6431,
+      "mean_token_accuracy": 0.7532352924346923,
+      "num_tokens": 940960.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.7253086419753086,
+      "grad_norm": 0.6237642765045166,
+      "learning_rate": 9.986317030607475e-05,
+      "loss": 0.6289,
+      "mean_token_accuracy": 0.7579411864280701,
+      "num_tokens": 961440.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.5108409523963928,
+      "learning_rate": 9.984365663035144e-05,
+      "loss": 0.6291,
+      "mean_token_accuracy": 0.7591037034988404,
+      "num_tokens": 981758.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.7561728395061729,
+      "grad_norm": 0.4949217736721039,
+      "learning_rate": 9.982284484468634e-05,
+      "loss": 0.6419,
+      "mean_token_accuracy": 0.752647066116333,
+      "num_tokens": 1002238.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7716049382716049,
+      "grad_norm": 0.6673640012741089,
+      "learning_rate": 9.980073549109397e-05,
+      "loss": 0.6465,
+      "mean_token_accuracy": 0.7512254893779755,
+      "num_tokens": 1022718.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.7870370370370371,
+      "grad_norm": 0.5719751715660095,
+      "learning_rate": 9.977732914538225e-05,
+      "loss": 0.6661,
+      "mean_token_accuracy": 0.7452450931072235,
+      "num_tokens": 1043198.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.8024691358024691,
+      "grad_norm": 0.5307197570800781,
+      "learning_rate": 9.975262641713746e-05,
+      "loss": 0.6422,
+      "mean_token_accuracy": 0.7541176438331604,
+      "num_tokens": 1063678.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.8179012345679012,
+      "grad_norm": 0.5509263277053833,
+      "learning_rate": 9.972662794970841e-05,
+      "loss": 0.6519,
+      "mean_token_accuracy": 0.7512745082378387,
+      "num_tokens": 1084158.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.5206686854362488,
+      "learning_rate": 9.969933442018968e-05,
+      "loss": 0.647,
+      "mean_token_accuracy": 0.7523039221763611,
+      "num_tokens": 1104638.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8487654320987654,
+      "grad_norm": 0.5182181596755981,
+      "learning_rate": 9.967074653940396e-05,
+      "loss": 0.6401,
+      "mean_token_accuracy": 0.7543137311935425,
+      "num_tokens": 1125118.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 0.47155195474624634,
+      "learning_rate": 9.964086505188352e-05,
+      "loss": 0.623,
+      "mean_token_accuracy": 0.7625980377197266,
+      "num_tokens": 1145598.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8796296296296297,
+      "grad_norm": 0.5879080891609192,
+      "learning_rate": 9.960969073585091e-05,
+      "loss": 0.6354,
+      "mean_token_accuracy": 0.7589705884456635,
+      "num_tokens": 1166078.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8950617283950617,
+      "grad_norm": 0.6356768012046814,
+      "learning_rate": 9.95772244031986e-05,
+      "loss": 0.6339,
+      "mean_token_accuracy": 0.758627450466156,
+      "num_tokens": 1186558.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.9104938271604939,
+      "grad_norm": 0.5294948816299438,
+      "learning_rate": 9.954346689946785e-05,
+      "loss": 0.666,
+      "mean_token_accuracy": 0.7455392241477966,
+      "num_tokens": 1207038.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 0.5180017948150635,
+      "learning_rate": 9.950841910382675e-05,
+      "loss": 0.6452,
+      "mean_token_accuracy": 0.7542156934738159,
+      "num_tokens": 1227518.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.941358024691358,
+      "grad_norm": 0.5167914032936096,
+      "learning_rate": 9.947208192904722e-05,
+      "loss": 0.655,
+      "mean_token_accuracy": 0.745588231086731,
+      "num_tokens": 1247998.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9567901234567902,
+      "grad_norm": 0.5089550018310547,
+      "learning_rate": 9.943445632148138e-05,
+      "loss": 0.6318,
+      "mean_token_accuracy": 0.7575609028339386,
+      "num_tokens": 1268418.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 0.49098673462867737,
+      "learning_rate": 9.939554326103673e-05,
+      "loss": 0.6254,
+      "mean_token_accuracy": 0.7607843101024627,
+      "num_tokens": 1288898.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.6257764101028442,
+      "learning_rate": 9.935534376115081e-05,
+      "loss": 0.6181,
+      "mean_token_accuracy": 0.760735297203064,
+      "num_tokens": 1309378.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6358935236930847,
+      "eval_mean_token_accuracy": 0.7576412944232717,
+      "eval_num_tokens": 1324482.0,
+      "eval_runtime": 3.2072,
+      "eval_samples_per_second": 84.497,
+      "eval_steps_per_second": 10.601,
+      "step": 648
+    },
+    {
+      "epoch": 1.0030864197530864,
+      "grad_norm": 0.5601590871810913,
+      "learning_rate": 9.931385886876466e-05,
+      "loss": 0.6262,
+      "mean_token_accuracy": 0.7599019706249237,
+      "num_tokens": 1328578.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.0185185185185186,
+      "grad_norm": 0.48451554775238037,
+      "learning_rate": 9.927108966429559e-05,
+      "loss": 0.6212,
+      "mean_token_accuracy": 0.7603431344032288,
+      "num_tokens": 1349058.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.0339506172839505,
+      "grad_norm": 0.574618399143219,
+      "learning_rate": 9.922703726160915e-05,
+      "loss": 0.6114,
+      "mean_token_accuracy": 0.764607834815979,
+      "num_tokens": 1369538.0,
+      "step": 670
+    },
+    {
+      "epoch": 1.0493827160493827,
+      "grad_norm": 0.5421807765960693,
+      "learning_rate": 9.918170280798997e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7626470565795899,
+      "num_tokens": 1390018.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.0648148148148149,
+      "grad_norm": 0.6702131032943726,
+      "learning_rate": 9.913508748411195e-05,
+      "loss": 0.6183,
+      "mean_token_accuracy": 0.7603431403636932,
+      "num_tokens": 1410498.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0802469135802468,
+      "grad_norm": 0.4915090501308441,
+      "learning_rate": 9.908719250400751e-05,
+      "loss": 0.6205,
+      "mean_token_accuracy": 0.7618292450904847,
+      "num_tokens": 1430861.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.095679012345679,
+      "grad_norm": 0.6062198877334595,
+      "learning_rate": 9.903801911503601e-05,
+      "loss": 0.6276,
+      "mean_token_accuracy": 0.759852945804596,
+      "num_tokens": 1451341.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.5174667239189148,
+      "learning_rate": 9.898756859785114e-05,
+      "loss": 0.6152,
+      "mean_token_accuracy": 0.7662745118141174,
+      "num_tokens": 1471821.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.126543209876543,
+      "grad_norm": 0.5522329211235046,
+      "learning_rate": 9.893584226636772e-05,
+      "loss": 0.5988,
+      "mean_token_accuracy": 0.7693627417087555,
+      "num_tokens": 1492301.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.1419753086419753,
+      "grad_norm": 0.5991533994674683,
+      "learning_rate": 9.88828414677274e-05,
+      "loss": 0.6191,
+      "mean_token_accuracy": 0.7625000059604645,
+      "num_tokens": 1512781.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.1574074074074074,
+      "grad_norm": 0.5619213581085205,
+      "learning_rate": 9.882856758226355e-05,
+      "loss": 0.6095,
+      "mean_token_accuracy": 0.7666666686534882,
+      "num_tokens": 1533261.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1728395061728394,
+      "grad_norm": 0.6064968109130859,
+      "learning_rate": 9.877302202346537e-05,
+      "loss": 0.6174,
+      "mean_token_accuracy": 0.762401956319809,
+      "num_tokens": 1553741.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.1882716049382716,
+      "grad_norm": 0.5420733690261841,
+      "learning_rate": 9.871620623794107e-05,
+      "loss": 0.6208,
+      "mean_token_accuracy": 0.761813735961914,
+      "num_tokens": 1574221.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.2037037037037037,
+      "grad_norm": 0.5008245706558228,
+      "learning_rate": 9.865812170538014e-05,
+      "loss": 0.6157,
+      "mean_token_accuracy": 0.763921570777893,
+      "num_tokens": 1594701.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.2191358024691359,
+      "grad_norm": 0.5480730533599854,
+      "learning_rate": 9.859876993851489e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7608823537826538,
+      "num_tokens": 1615181.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 0.5966739654541016,
+      "learning_rate": 9.853815248308101e-05,
+      "loss": 0.6128,
+      "mean_token_accuracy": 0.7660294115543366,
+      "num_tokens": 1635661.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.6002110242843628,
+      "learning_rate": 9.847627091777729e-05,
+      "loss": 0.6161,
+      "mean_token_accuracy": 0.7602451026439667,
+      "num_tokens": 1656141.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2654320987654322,
+      "grad_norm": 0.547483503818512,
+      "learning_rate": 9.841312685422459e-05,
+      "loss": 0.6488,
+      "mean_token_accuracy": 0.7497548937797547,
+      "num_tokens": 1676621.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.2808641975308643,
+      "grad_norm": 0.7387484908103943,
+      "learning_rate": 9.834872193692378e-05,
+      "loss": 0.6321,
+      "mean_token_accuracy": 0.7572423696517945,
+      "num_tokens": 1696915.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.5367273092269897,
+      "learning_rate": 9.828305784321289e-05,
+      "loss": 0.6069,
+      "mean_token_accuracy": 0.7675980389118194,
+      "num_tokens": 1717395.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.3117283950617284,
+      "grad_norm": 0.5737053751945496,
+      "learning_rate": 9.821613628322358e-05,
+      "loss": 0.6149,
+      "mean_token_accuracy": 0.7629902005195618,
+      "num_tokens": 1737875.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.3271604938271606,
+      "grad_norm": 0.555564284324646,
+      "learning_rate": 9.814795899983645e-05,
+      "loss": 0.6032,
+      "mean_token_accuracy": 0.765931385755539,
+      "num_tokens": 1758355.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.3425925925925926,
+      "grad_norm": 0.5478204488754272,
+      "learning_rate": 9.807852776863568e-05,
+      "loss": 0.6281,
+      "mean_token_accuracy": 0.7586764693260193,
+      "num_tokens": 1778835.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.3580246913580247,
+      "grad_norm": 0.6020711064338684,
+      "learning_rate": 9.800784439786286e-05,
+      "loss": 0.6315,
+      "mean_token_accuracy": 0.7561274588108062,
+      "num_tokens": 1799315.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.373456790123457,
+      "grad_norm": 0.5321200489997864,
+      "learning_rate": 9.793591072836978e-05,
+      "loss": 0.6206,
+      "mean_token_accuracy": 0.7651960849761963,
+      "num_tokens": 1819795.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 0.5763822793960571,
+      "learning_rate": 9.786272863357063e-05,
+      "loss": 0.6225,
+      "mean_token_accuracy": 0.7619433760643005,
+      "num_tokens": 1840220.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.404320987654321,
+      "grad_norm": 0.5706750154495239,
+      "learning_rate": 9.778830001939307e-05,
+      "loss": 0.6186,
+      "mean_token_accuracy": 0.7591176569461823,
+      "num_tokens": 1860700.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.4197530864197532,
+      "grad_norm": 0.5526582598686218,
+      "learning_rate": 9.771262682422866e-05,
+      "loss": 0.6216,
+      "mean_token_accuracy": 0.7599509716033935,
+      "num_tokens": 1881180.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.4351851851851851,
+      "grad_norm": 0.5528797507286072,
+      "learning_rate": 9.76357110188824e-05,
+      "loss": 0.6372,
+      "mean_token_accuracy": 0.752892154455185,
+      "num_tokens": 1901660.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.4506172839506173,
+      "grad_norm": 0.5862347483634949,
+      "learning_rate": 9.755755460652137e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7626960754394532,
+      "num_tokens": 1922140.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.4660493827160495,
+      "grad_norm": 0.6405584216117859,
+      "learning_rate": 9.747815962262255e-05,
+      "loss": 0.6161,
+      "mean_token_accuracy": 0.7654783129692078,
+      "num_tokens": 1942560.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.5765857696533203,
+      "learning_rate": 9.73975281349198e-05,
+      "loss": 0.6257,
+      "mean_token_accuracy": 0.7609804034233093,
+      "num_tokens": 1963040.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4969135802469136,
+      "grad_norm": 0.6691901683807373,
+      "learning_rate": 9.73156622433501e-05,
+      "loss": 0.6393,
+      "mean_token_accuracy": 0.7543627440929412,
+      "num_tokens": 1983520.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.5123456790123457,
+      "grad_norm": 0.5016764998435974,
+      "learning_rate": 9.72325640799987e-05,
+      "loss": 0.6295,
+      "mean_token_accuracy": 0.7598504185676574,
+      "num_tokens": 2003942.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.5277777777777777,
+      "grad_norm": 0.5539676547050476,
+      "learning_rate": 9.71482358090438e-05,
+      "loss": 0.6301,
+      "mean_token_accuracy": 0.7583823561668396,
+      "num_tokens": 2024422.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.5432098765432098,
+      "grad_norm": 0.5221379995346069,
+      "learning_rate": 9.706267962669998e-05,
+      "loss": 0.619,
+      "mean_token_accuracy": 0.7604411840438843,
+      "num_tokens": 2044902.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.558641975308642,
+      "grad_norm": 0.6469255089759827,
+      "learning_rate": 9.697589776116113e-05,
+      "loss": 0.6119,
+      "mean_token_accuracy": 0.7661274552345276,
+      "num_tokens": 2065382.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.574074074074074,
+      "grad_norm": 0.507942795753479,
+      "learning_rate": 9.688789247254237e-05,
+      "loss": 0.6235,
+      "mean_token_accuracy": 0.7585784196853638,
+      "num_tokens": 2085862.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5895061728395061,
+      "grad_norm": 0.5448495745658875,
+      "learning_rate": 9.679866605282122e-05,
+      "loss": 0.6198,
+      "mean_token_accuracy": 0.7634313702583313,
+      "num_tokens": 2106342.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6049382716049383,
+      "grad_norm": 1.2016057968139648,
+      "learning_rate": 9.670822082577787e-05,
+      "loss": 0.6203,
+      "mean_token_accuracy": 0.7600490152835846,
+      "num_tokens": 2126822.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6203703703703702,
+      "grad_norm": 0.592653214931488,
+      "learning_rate": 9.661655914693471e-05,
+      "loss": 0.6303,
+      "mean_token_accuracy": 0.7591176509857178,
+      "num_tokens": 2147302.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6358024691358026,
+      "grad_norm": 0.5714336633682251,
+      "learning_rate": 9.652368340349494e-05,
+      "loss": 0.6375,
+      "mean_token_accuracy": 0.75563725233078,
+      "num_tokens": 2167782.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.6512345679012346,
+      "grad_norm": 0.551650881767273,
+      "learning_rate": 9.642959601428039e-05,
+      "loss": 0.6153,
+      "mean_token_accuracy": 0.7640196025371552,
+      "num_tokens": 2188262.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.5212278962135315,
+      "learning_rate": 9.63342994296686e-05,
+      "loss": 0.6381,
+      "mean_token_accuracy": 0.7550980448722839,
+      "num_tokens": 2208742.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.682098765432099,
+      "grad_norm": 1.946945071220398,
+      "learning_rate": 9.623779613152893e-05,
+      "loss": 0.6115,
+      "mean_token_accuracy": 0.7643485307693482,
+      "num_tokens": 2229058.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6975308641975309,
+      "grad_norm": 0.5382822155952454,
+      "learning_rate": 9.614008863315789e-05,
+      "loss": 0.6213,
+      "mean_token_accuracy": 0.7603431344032288,
+      "num_tokens": 2249538.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7129629629629628,
+      "grad_norm": 0.4769648313522339,
+      "learning_rate": 9.604117947921385e-05,
+      "loss": 0.6324,
+      "mean_token_accuracy": 0.7571568608283996,
+      "num_tokens": 2270018.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7283950617283952,
+      "grad_norm": 0.48067739605903625,
+      "learning_rate": 9.594107124565056e-05,
+      "loss": 0.6239,
+      "mean_token_accuracy": 0.7589215695858001,
+      "num_tokens": 2290498.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7438271604938271,
+      "grad_norm": 0.505754292011261,
+      "learning_rate": 9.58397665396502e-05,
+      "loss": 0.6371,
+      "mean_token_accuracy": 0.7563725471496582,
+      "num_tokens": 2310978.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.7592592592592593,
+      "grad_norm": 0.56634920835495,
+      "learning_rate": 9.573726799955544e-05,
+      "loss": 0.6186,
+      "mean_token_accuracy": 0.7624509751796722,
+      "num_tokens": 2331458.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7746913580246915,
+      "grad_norm": 0.45453864336013794,
+      "learning_rate": 9.563357829480076e-05,
+      "loss": 0.6119,
+      "mean_token_accuracy": 0.7649815142154693,
+      "num_tokens": 2351728.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7901234567901234,
+      "grad_norm": 0.5595808625221252,
+      "learning_rate": 9.552870012584282e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7618627548217773,
+      "num_tokens": 2372208.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8055555555555556,
+      "grad_norm": 0.5549359321594238,
+      "learning_rate": 9.542263622409027e-05,
+      "loss": 0.6235,
+      "mean_token_accuracy": 0.7586274564266204,
+      "num_tokens": 2392688.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.8209876543209877,
+      "grad_norm": 0.4978308379650116,
+      "learning_rate": 9.53153893518325e-05,
+      "loss": 0.6156,
+      "mean_token_accuracy": 0.7622892081737518,
+      "num_tokens": 2413006.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.8364197530864197,
+      "grad_norm": 0.47992169857025146,
+      "learning_rate": 9.520696230216781e-05,
+      "loss": 0.6206,
+      "mean_token_accuracy": 0.7627451002597809,
+      "num_tokens": 2433486.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.4658719301223755,
+      "learning_rate": 9.509735789893059e-05,
+      "loss": 0.6302,
+      "mean_token_accuracy": 0.7552761137485504,
+      "num_tokens": 2453886.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.867283950617284,
+      "grad_norm": 0.5392885804176331,
+      "learning_rate": 9.498657899661774e-05,
+      "loss": 0.6261,
+      "mean_token_accuracy": 0.758477383852005,
+      "num_tokens": 2474116.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.882716049382716,
+      "grad_norm": 0.74770587682724,
+      "learning_rate": 9.487462848031445e-05,
+      "loss": 0.6229,
+      "mean_token_accuracy": 0.7597548961639404,
+      "num_tokens": 2494596.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8981481481481481,
+      "grad_norm": 0.4596572518348694,
+      "learning_rate": 9.4761509265619e-05,
+      "loss": 0.6167,
+      "mean_token_accuracy": 0.7653431355953216,
+      "num_tokens": 2515076.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.9135802469135803,
+      "grad_norm": 0.653968870639801,
+      "learning_rate": 9.464722429856674e-05,
+      "loss": 0.6232,
+      "mean_token_accuracy": 0.7604411780834198,
+      "num_tokens": 2535556.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.9290123456790123,
+      "grad_norm": 0.7169049382209778,
+      "learning_rate": 9.453177655555355e-05,
+      "loss": 0.6094,
+      "mean_token_accuracy": 0.7661274552345276,
+      "num_tokens": 2556036.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 0.6535491347312927,
+      "learning_rate": 9.441516904325816e-05,
+      "loss": 0.6083,
+      "mean_token_accuracy": 0.766715693473816,
+      "num_tokens": 2576516.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.9598765432098766,
+      "grad_norm": 0.5433221459388733,
+      "learning_rate": 9.42974047985639e-05,
+      "loss": 0.6089,
+      "mean_token_accuracy": 0.7655392229557038,
+      "num_tokens": 2596996.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.5704086422920227,
+      "learning_rate": 9.417848688847968e-05,
+      "loss": 0.6255,
+      "mean_token_accuracy": 0.7593627452850342,
+      "num_tokens": 2617476.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.9907407407407407,
+      "grad_norm": 0.8016455769538879,
+      "learning_rate": 9.405841841005998e-05,
+      "loss": 0.6261,
+      "mean_token_accuracy": 0.7583823561668396,
+      "num_tokens": 2637956.0,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6324792504310608,
+      "eval_mean_token_accuracy": 0.758347749710083,
+      "eval_num_tokens": 2648964.0,
+      "eval_runtime": 3.1944,
+      "eval_samples_per_second": 84.835,
+      "eval_steps_per_second": 10.644,
+      "step": 1296
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 1.1281390103376691e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1296/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a34050fa79a936184e915a7880fc5b9f49db5f1fd1d762599d612766499101
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1944/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 0.19.1

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1944/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "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,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1944/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11a06eed28e5ecd64919b0b5d91c02d2453508fd0aa28e18cc4087c5f0f29510
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1944/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1944/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1944/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1944/tokenizer.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1944/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1944/trainer_state.json

@@ -0,0 +1,1810 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1944,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015432098765432098,
+      "grad_norm": 3.519041061401367,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 2.4621,
+      "mean_token_accuracy": 0.5478431344032287,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.030864197530864196,
+      "grad_norm": 4.195609092712402,
+      "learning_rate": 5.864197530864198e-06,
+      "loss": 2.4435,
+      "mean_token_accuracy": 0.5484313726425171,
+      "num_tokens": 40960.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.046296296296296294,
+      "grad_norm": 3.7905173301696777,
+      "learning_rate": 8.950617283950618e-06,
+      "loss": 2.358,
+      "mean_token_accuracy": 0.5484323740005493,
+      "num_tokens": 61360.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.06172839506172839,
+      "grad_norm": 2.1776044368743896,
+      "learning_rate": 1.2037037037037037e-05,
+      "loss": 2.0177,
+      "mean_token_accuracy": 0.5722058892250061,
+      "num_tokens": 81840.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07716049382716049,
+      "grad_norm": 1.3382104635238647,
+      "learning_rate": 1.5123456790123458e-05,
+      "loss": 1.7326,
+      "mean_token_accuracy": 0.6003921627998352,
+      "num_tokens": 102320.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.09259259259259259,
+      "grad_norm": 1.0943200588226318,
+      "learning_rate": 1.8209876543209877e-05,
+      "loss": 1.5168,
+      "mean_token_accuracy": 0.6119117617607117,
+      "num_tokens": 122800.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.10802469135802469,
+      "grad_norm": 0.9394681453704834,
+      "learning_rate": 2.1296296296296296e-05,
+      "loss": 1.3284,
+      "mean_token_accuracy": 0.6315686345100403,
+      "num_tokens": 143280.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 0.961665689945221,
+      "learning_rate": 2.438271604938272e-05,
+      "loss": 1.1754,
+      "mean_token_accuracy": 0.6534313797950745,
+      "num_tokens": 163760.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 1.0397999286651611,
+      "learning_rate": 2.7469135802469138e-05,
+      "loss": 1.0364,
+      "mean_token_accuracy": 0.6734803915023804,
+      "num_tokens": 184240.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.15432098765432098,
+      "grad_norm": 1.15496027469635,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.9147,
+      "mean_token_accuracy": 0.689607846736908,
+      "num_tokens": 204720.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.1697530864197531,
+      "grad_norm": 1.2569444179534912,
+      "learning_rate": 3.364197530864198e-05,
+      "loss": 0.8172,
+      "mean_token_accuracy": 0.7119117677211761,
+      "num_tokens": 225200.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 1.0953677892684937,
+      "learning_rate": 3.67283950617284e-05,
+      "loss": 0.7472,
+      "mean_token_accuracy": 0.7320588111877442,
+      "num_tokens": 245680.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.2006172839506173,
+      "grad_norm": 1.1510546207427979,
+      "learning_rate": 3.981481481481482e-05,
+      "loss": 0.7372,
+      "mean_token_accuracy": 0.7326960742473603,
+      "num_tokens": 266160.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.21604938271604937,
+      "grad_norm": 1.014360785484314,
+      "learning_rate": 4.290123456790124e-05,
+      "loss": 0.7134,
+      "mean_token_accuracy": 0.7418137192726135,
+      "num_tokens": 286640.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.23148148148148148,
+      "grad_norm": 0.9315780401229858,
+      "learning_rate": 4.5987654320987656e-05,
+      "loss": 0.6951,
+      "mean_token_accuracy": 0.7458823502063752,
+      "num_tokens": 307120.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 0.9429313540458679,
+      "learning_rate": 4.9074074074074075e-05,
+      "loss": 0.6816,
+      "mean_token_accuracy": 0.7458333313465119,
+      "num_tokens": 327600.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.2623456790123457,
+      "grad_norm": 0.8958196640014648,
+      "learning_rate": 5.2160493827160494e-05,
+      "loss": 0.6835,
+      "mean_token_accuracy": 0.7473039209842682,
+      "num_tokens": 348080.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.9595352411270142,
+      "learning_rate": 5.524691358024692e-05,
+      "loss": 0.6714,
+      "mean_token_accuracy": 0.7484643220901489,
+      "num_tokens": 368350.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2932098765432099,
+      "grad_norm": 0.7617053985595703,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 0.678,
+      "mean_token_accuracy": 0.7437254905700683,
+      "num_tokens": 388830.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.30864197530864196,
+      "grad_norm": 0.8184395432472229,
+      "learning_rate": 6.141975308641975e-05,
+      "loss": 0.6782,
+      "mean_token_accuracy": 0.7463235318660736,
+      "num_tokens": 409310.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.32407407407407407,
+      "grad_norm": 0.930051326751709,
+      "learning_rate": 6.450617283950617e-05,
+      "loss": 0.6596,
+      "mean_token_accuracy": 0.7505952179431915,
+      "num_tokens": 429604.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3395061728395062,
+      "grad_norm": 1.5295906066894531,
+      "learning_rate": 6.759259259259259e-05,
+      "loss": 0.6583,
+      "mean_token_accuracy": 0.7503921568393708,
+      "num_tokens": 450084.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.3549382716049383,
+      "grad_norm": 0.7611913681030273,
+      "learning_rate": 7.067901234567902e-05,
+      "loss": 0.6479,
+      "mean_token_accuracy": 0.758186274766922,
+      "num_tokens": 470564.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.7119883894920349,
+      "learning_rate": 7.376543209876543e-05,
+      "loss": 0.6548,
+      "mean_token_accuracy": 0.7510345578193665,
+      "num_tokens": 490986.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.38580246913580246,
+      "grad_norm": 0.7270073890686035,
+      "learning_rate": 7.685185185185185e-05,
+      "loss": 0.6726,
+      "mean_token_accuracy": 0.7451960682868958,
+      "num_tokens": 511466.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4012345679012346,
+      "grad_norm": 0.7441513538360596,
+      "learning_rate": 7.993827160493828e-05,
+      "loss": 0.6384,
+      "mean_token_accuracy": 0.7599019706249237,
+      "num_tokens": 531946.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.6838435530662537,
+      "learning_rate": 8.30246913580247e-05,
+      "loss": 0.6551,
+      "mean_token_accuracy": 0.7513725519180298,
+      "num_tokens": 552426.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.43209876543209874,
+      "grad_norm": 0.8257744908332825,
+      "learning_rate": 8.611111111111112e-05,
+      "loss": 0.6511,
+      "mean_token_accuracy": 0.7551960706710815,
+      "num_tokens": 572906.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.44753086419753085,
+      "grad_norm": 0.739138662815094,
+      "learning_rate": 8.919753086419754e-05,
+      "loss": 0.6572,
+      "mean_token_accuracy": 0.7523039162158967,
+      "num_tokens": 593386.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 0.7312272191047668,
+      "learning_rate": 9.228395061728396e-05,
+      "loss": 0.6738,
+      "mean_token_accuracy": 0.7451960861682891,
+      "num_tokens": 613866.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.4783950617283951,
+      "grad_norm": 0.7143312096595764,
+      "learning_rate": 9.537037037037038e-05,
+      "loss": 0.6398,
+      "mean_token_accuracy": 0.758088231086731,
+      "num_tokens": 634346.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.6812207698822021,
+      "learning_rate": 9.84567901234568e-05,
+      "loss": 0.6494,
+      "mean_token_accuracy": 0.7502175033092499,
+      "num_tokens": 654662.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.5092592592592593,
+      "grad_norm": 0.6230295896530151,
+      "learning_rate": 9.999983722702365e-05,
+      "loss": 0.6436,
+      "mean_token_accuracy": 0.7557843148708343,
+      "num_tokens": 675142.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.5246913580246914,
+      "grad_norm": 0.5965207815170288,
+      "learning_rate": 9.999853504957158e-05,
+      "loss": 0.6647,
+      "mean_token_accuracy": 0.7427450954914093,
+      "num_tokens": 695622.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5401234567901234,
+      "grad_norm": 0.559863805770874,
+      "learning_rate": 9.999593072858088e-05,
+      "loss": 0.6343,
+      "mean_token_accuracy": 0.758293867111206,
+      "num_tokens": 715985.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.9263127446174622,
+      "learning_rate": 9.999202433187755e-05,
+      "loss": 0.6601,
+      "mean_token_accuracy": 0.7472058832645416,
+      "num_tokens": 736465.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5709876543209876,
+      "grad_norm": 0.5964210033416748,
+      "learning_rate": 9.998681596119832e-05,
+      "loss": 0.6778,
+      "mean_token_accuracy": 0.7443627417087555,
+      "num_tokens": 756945.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5864197530864198,
+      "grad_norm": 0.6121820211410522,
+      "learning_rate": 9.998030575218811e-05,
+      "loss": 0.6628,
+      "mean_token_accuracy": 0.7476024866104126,
+      "num_tokens": 777370.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.6018518518518519,
+      "grad_norm": 0.5673462152481079,
+      "learning_rate": 9.997249387439643e-05,
+      "loss": 0.6338,
+      "mean_token_accuracy": 0.7578116476535797,
+      "num_tokens": 797600.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 0.6260263919830322,
+      "learning_rate": 9.996338053127292e-05,
+      "loss": 0.6601,
+      "mean_token_accuracy": 0.7466666638851166,
+      "num_tokens": 818080.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6327160493827161,
+      "grad_norm": 0.5045029520988464,
+      "learning_rate": 9.99529659601622e-05,
+      "loss": 0.663,
+      "mean_token_accuracy": 0.7482352912425995,
+      "num_tokens": 838560.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6481481481481481,
+      "grad_norm": 0.6537773013114929,
+      "learning_rate": 9.994125043229752e-05,
+      "loss": 0.6444,
+      "mean_token_accuracy": 0.7541666746139526,
+      "num_tokens": 859040.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.6635802469135802,
+      "grad_norm": 0.5629055500030518,
+      "learning_rate": 9.992823425279382e-05,
+      "loss": 0.645,
+      "mean_token_accuracy": 0.75343137383461,
+      "num_tokens": 879520.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6790123456790124,
+      "grad_norm": 0.5268312096595764,
+      "learning_rate": 9.991391776063969e-05,
+      "loss": 0.6563,
+      "mean_token_accuracy": 0.7489215791225433,
+      "num_tokens": 900000.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 0.5720213055610657,
+      "learning_rate": 9.98983013286886e-05,
+      "loss": 0.6248,
+      "mean_token_accuracy": 0.7610294163227082,
+      "num_tokens": 920480.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.7098765432098766,
+      "grad_norm": 0.66424560546875,
+      "learning_rate": 9.988138536364922e-05,
+      "loss": 0.6431,
+      "mean_token_accuracy": 0.7532352924346923,
+      "num_tokens": 940960.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.7253086419753086,
+      "grad_norm": 0.6237642765045166,
+      "learning_rate": 9.986317030607475e-05,
+      "loss": 0.6289,
+      "mean_token_accuracy": 0.7579411864280701,
+      "num_tokens": 961440.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.5108409523963928,
+      "learning_rate": 9.984365663035144e-05,
+      "loss": 0.6291,
+      "mean_token_accuracy": 0.7591037034988404,
+      "num_tokens": 981758.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.7561728395061729,
+      "grad_norm": 0.4949217736721039,
+      "learning_rate": 9.982284484468634e-05,
+      "loss": 0.6419,
+      "mean_token_accuracy": 0.752647066116333,
+      "num_tokens": 1002238.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7716049382716049,
+      "grad_norm": 0.6673640012741089,
+      "learning_rate": 9.980073549109397e-05,
+      "loss": 0.6465,
+      "mean_token_accuracy": 0.7512254893779755,
+      "num_tokens": 1022718.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.7870370370370371,
+      "grad_norm": 0.5719751715660095,
+      "learning_rate": 9.977732914538225e-05,
+      "loss": 0.6661,
+      "mean_token_accuracy": 0.7452450931072235,
+      "num_tokens": 1043198.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.8024691358024691,
+      "grad_norm": 0.5307197570800781,
+      "learning_rate": 9.975262641713746e-05,
+      "loss": 0.6422,
+      "mean_token_accuracy": 0.7541176438331604,
+      "num_tokens": 1063678.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.8179012345679012,
+      "grad_norm": 0.5509263277053833,
+      "learning_rate": 9.972662794970841e-05,
+      "loss": 0.6519,
+      "mean_token_accuracy": 0.7512745082378387,
+      "num_tokens": 1084158.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.5206686854362488,
+      "learning_rate": 9.969933442018968e-05,
+      "loss": 0.647,
+      "mean_token_accuracy": 0.7523039221763611,
+      "num_tokens": 1104638.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8487654320987654,
+      "grad_norm": 0.5182181596755981,
+      "learning_rate": 9.967074653940396e-05,
+      "loss": 0.6401,
+      "mean_token_accuracy": 0.7543137311935425,
+      "num_tokens": 1125118.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 0.47155195474624634,
+      "learning_rate": 9.964086505188352e-05,
+      "loss": 0.623,
+      "mean_token_accuracy": 0.7625980377197266,
+      "num_tokens": 1145598.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8796296296296297,
+      "grad_norm": 0.5879080891609192,
+      "learning_rate": 9.960969073585091e-05,
+      "loss": 0.6354,
+      "mean_token_accuracy": 0.7589705884456635,
+      "num_tokens": 1166078.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8950617283950617,
+      "grad_norm": 0.6356768012046814,
+      "learning_rate": 9.95772244031986e-05,
+      "loss": 0.6339,
+      "mean_token_accuracy": 0.758627450466156,
+      "num_tokens": 1186558.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.9104938271604939,
+      "grad_norm": 0.5294948816299438,
+      "learning_rate": 9.954346689946785e-05,
+      "loss": 0.666,
+      "mean_token_accuracy": 0.7455392241477966,
+      "num_tokens": 1207038.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 0.5180017948150635,
+      "learning_rate": 9.950841910382675e-05,
+      "loss": 0.6452,
+      "mean_token_accuracy": 0.7542156934738159,
+      "num_tokens": 1227518.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.941358024691358,
+      "grad_norm": 0.5167914032936096,
+      "learning_rate": 9.947208192904722e-05,
+      "loss": 0.655,
+      "mean_token_accuracy": 0.745588231086731,
+      "num_tokens": 1247998.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9567901234567902,
+      "grad_norm": 0.5089550018310547,
+      "learning_rate": 9.943445632148138e-05,
+      "loss": 0.6318,
+      "mean_token_accuracy": 0.7575609028339386,
+      "num_tokens": 1268418.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 0.49098673462867737,
+      "learning_rate": 9.939554326103673e-05,
+      "loss": 0.6254,
+      "mean_token_accuracy": 0.7607843101024627,
+      "num_tokens": 1288898.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.6257764101028442,
+      "learning_rate": 9.935534376115081e-05,
+      "loss": 0.6181,
+      "mean_token_accuracy": 0.760735297203064,
+      "num_tokens": 1309378.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6358935236930847,
+      "eval_mean_token_accuracy": 0.7576412944232717,
+      "eval_num_tokens": 1324482.0,
+      "eval_runtime": 3.2072,
+      "eval_samples_per_second": 84.497,
+      "eval_steps_per_second": 10.601,
+      "step": 648
+    },
+    {
+      "epoch": 1.0030864197530864,
+      "grad_norm": 0.5601590871810913,
+      "learning_rate": 9.931385886876466e-05,
+      "loss": 0.6262,
+      "mean_token_accuracy": 0.7599019706249237,
+      "num_tokens": 1328578.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.0185185185185186,
+      "grad_norm": 0.48451554775238037,
+      "learning_rate": 9.927108966429559e-05,
+      "loss": 0.6212,
+      "mean_token_accuracy": 0.7603431344032288,
+      "num_tokens": 1349058.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.0339506172839505,
+      "grad_norm": 0.574618399143219,
+      "learning_rate": 9.922703726160915e-05,
+      "loss": 0.6114,
+      "mean_token_accuracy": 0.764607834815979,
+      "num_tokens": 1369538.0,
+      "step": 670
+    },
+    {
+      "epoch": 1.0493827160493827,
+      "grad_norm": 0.5421807765960693,
+      "learning_rate": 9.918170280798997e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7626470565795899,
+      "num_tokens": 1390018.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.0648148148148149,
+      "grad_norm": 0.6702131032943726,
+      "learning_rate": 9.913508748411195e-05,
+      "loss": 0.6183,
+      "mean_token_accuracy": 0.7603431403636932,
+      "num_tokens": 1410498.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0802469135802468,
+      "grad_norm": 0.4915090501308441,
+      "learning_rate": 9.908719250400751e-05,
+      "loss": 0.6205,
+      "mean_token_accuracy": 0.7618292450904847,
+      "num_tokens": 1430861.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.095679012345679,
+      "grad_norm": 0.6062198877334595,
+      "learning_rate": 9.903801911503601e-05,
+      "loss": 0.6276,
+      "mean_token_accuracy": 0.759852945804596,
+      "num_tokens": 1451341.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.5174667239189148,
+      "learning_rate": 9.898756859785114e-05,
+      "loss": 0.6152,
+      "mean_token_accuracy": 0.7662745118141174,
+      "num_tokens": 1471821.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.126543209876543,
+      "grad_norm": 0.5522329211235046,
+      "learning_rate": 9.893584226636772e-05,
+      "loss": 0.5988,
+      "mean_token_accuracy": 0.7693627417087555,
+      "num_tokens": 1492301.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.1419753086419753,
+      "grad_norm": 0.5991533994674683,
+      "learning_rate": 9.88828414677274e-05,
+      "loss": 0.6191,
+      "mean_token_accuracy": 0.7625000059604645,
+      "num_tokens": 1512781.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.1574074074074074,
+      "grad_norm": 0.5619213581085205,
+      "learning_rate": 9.882856758226355e-05,
+      "loss": 0.6095,
+      "mean_token_accuracy": 0.7666666686534882,
+      "num_tokens": 1533261.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1728395061728394,
+      "grad_norm": 0.6064968109130859,
+      "learning_rate": 9.877302202346537e-05,
+      "loss": 0.6174,
+      "mean_token_accuracy": 0.762401956319809,
+      "num_tokens": 1553741.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.1882716049382716,
+      "grad_norm": 0.5420733690261841,
+      "learning_rate": 9.871620623794107e-05,
+      "loss": 0.6208,
+      "mean_token_accuracy": 0.761813735961914,
+      "num_tokens": 1574221.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.2037037037037037,
+      "grad_norm": 0.5008245706558228,
+      "learning_rate": 9.865812170538014e-05,
+      "loss": 0.6157,
+      "mean_token_accuracy": 0.763921570777893,
+      "num_tokens": 1594701.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.2191358024691359,
+      "grad_norm": 0.5480730533599854,
+      "learning_rate": 9.859876993851489e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7608823537826538,
+      "num_tokens": 1615181.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 0.5966739654541016,
+      "learning_rate": 9.853815248308101e-05,
+      "loss": 0.6128,
+      "mean_token_accuracy": 0.7660294115543366,
+      "num_tokens": 1635661.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.6002110242843628,
+      "learning_rate": 9.847627091777729e-05,
+      "loss": 0.6161,
+      "mean_token_accuracy": 0.7602451026439667,
+      "num_tokens": 1656141.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2654320987654322,
+      "grad_norm": 0.547483503818512,
+      "learning_rate": 9.841312685422459e-05,
+      "loss": 0.6488,
+      "mean_token_accuracy": 0.7497548937797547,
+      "num_tokens": 1676621.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.2808641975308643,
+      "grad_norm": 0.7387484908103943,
+      "learning_rate": 9.834872193692378e-05,
+      "loss": 0.6321,
+      "mean_token_accuracy": 0.7572423696517945,
+      "num_tokens": 1696915.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.5367273092269897,
+      "learning_rate": 9.828305784321289e-05,
+      "loss": 0.6069,
+      "mean_token_accuracy": 0.7675980389118194,
+      "num_tokens": 1717395.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.3117283950617284,
+      "grad_norm": 0.5737053751945496,
+      "learning_rate": 9.821613628322358e-05,
+      "loss": 0.6149,
+      "mean_token_accuracy": 0.7629902005195618,
+      "num_tokens": 1737875.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.3271604938271606,
+      "grad_norm": 0.555564284324646,
+      "learning_rate": 9.814795899983645e-05,
+      "loss": 0.6032,
+      "mean_token_accuracy": 0.765931385755539,
+      "num_tokens": 1758355.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.3425925925925926,
+      "grad_norm": 0.5478204488754272,
+      "learning_rate": 9.807852776863568e-05,
+      "loss": 0.6281,
+      "mean_token_accuracy": 0.7586764693260193,
+      "num_tokens": 1778835.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.3580246913580247,
+      "grad_norm": 0.6020711064338684,
+      "learning_rate": 9.800784439786286e-05,
+      "loss": 0.6315,
+      "mean_token_accuracy": 0.7561274588108062,
+      "num_tokens": 1799315.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.373456790123457,
+      "grad_norm": 0.5321200489997864,
+      "learning_rate": 9.793591072836978e-05,
+      "loss": 0.6206,
+      "mean_token_accuracy": 0.7651960849761963,
+      "num_tokens": 1819795.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 0.5763822793960571,
+      "learning_rate": 9.786272863357063e-05,
+      "loss": 0.6225,
+      "mean_token_accuracy": 0.7619433760643005,
+      "num_tokens": 1840220.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.404320987654321,
+      "grad_norm": 0.5706750154495239,
+      "learning_rate": 9.778830001939307e-05,
+      "loss": 0.6186,
+      "mean_token_accuracy": 0.7591176569461823,
+      "num_tokens": 1860700.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.4197530864197532,
+      "grad_norm": 0.5526582598686218,
+      "learning_rate": 9.771262682422866e-05,
+      "loss": 0.6216,
+      "mean_token_accuracy": 0.7599509716033935,
+      "num_tokens": 1881180.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.4351851851851851,
+      "grad_norm": 0.5528797507286072,
+      "learning_rate": 9.76357110188824e-05,
+      "loss": 0.6372,
+      "mean_token_accuracy": 0.752892154455185,
+      "num_tokens": 1901660.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.4506172839506173,
+      "grad_norm": 0.5862347483634949,
+      "learning_rate": 9.755755460652137e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7626960754394532,
+      "num_tokens": 1922140.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.4660493827160495,
+      "grad_norm": 0.6405584216117859,
+      "learning_rate": 9.747815962262255e-05,
+      "loss": 0.6161,
+      "mean_token_accuracy": 0.7654783129692078,
+      "num_tokens": 1942560.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.5765857696533203,
+      "learning_rate": 9.73975281349198e-05,
+      "loss": 0.6257,
+      "mean_token_accuracy": 0.7609804034233093,
+      "num_tokens": 1963040.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4969135802469136,
+      "grad_norm": 0.6691901683807373,
+      "learning_rate": 9.73156622433501e-05,
+      "loss": 0.6393,
+      "mean_token_accuracy": 0.7543627440929412,
+      "num_tokens": 1983520.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.5123456790123457,
+      "grad_norm": 0.5016764998435974,
+      "learning_rate": 9.72325640799987e-05,
+      "loss": 0.6295,
+      "mean_token_accuracy": 0.7598504185676574,
+      "num_tokens": 2003942.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.5277777777777777,
+      "grad_norm": 0.5539676547050476,
+      "learning_rate": 9.71482358090438e-05,
+      "loss": 0.6301,
+      "mean_token_accuracy": 0.7583823561668396,
+      "num_tokens": 2024422.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.5432098765432098,
+      "grad_norm": 0.5221379995346069,
+      "learning_rate": 9.706267962669998e-05,
+      "loss": 0.619,
+      "mean_token_accuracy": 0.7604411840438843,
+      "num_tokens": 2044902.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.558641975308642,
+      "grad_norm": 0.6469255089759827,
+      "learning_rate": 9.697589776116113e-05,
+      "loss": 0.6119,
+      "mean_token_accuracy": 0.7661274552345276,
+      "num_tokens": 2065382.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.574074074074074,
+      "grad_norm": 0.507942795753479,
+      "learning_rate": 9.688789247254237e-05,
+      "loss": 0.6235,
+      "mean_token_accuracy": 0.7585784196853638,
+      "num_tokens": 2085862.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5895061728395061,
+      "grad_norm": 0.5448495745658875,
+      "learning_rate": 9.679866605282122e-05,
+      "loss": 0.6198,
+      "mean_token_accuracy": 0.7634313702583313,
+      "num_tokens": 2106342.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6049382716049383,
+      "grad_norm": 1.2016057968139648,
+      "learning_rate": 9.670822082577787e-05,
+      "loss": 0.6203,
+      "mean_token_accuracy": 0.7600490152835846,
+      "num_tokens": 2126822.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6203703703703702,
+      "grad_norm": 0.592653214931488,
+      "learning_rate": 9.661655914693471e-05,
+      "loss": 0.6303,
+      "mean_token_accuracy": 0.7591176509857178,
+      "num_tokens": 2147302.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6358024691358026,
+      "grad_norm": 0.5714336633682251,
+      "learning_rate": 9.652368340349494e-05,
+      "loss": 0.6375,
+      "mean_token_accuracy": 0.75563725233078,
+      "num_tokens": 2167782.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.6512345679012346,
+      "grad_norm": 0.551650881767273,
+      "learning_rate": 9.642959601428039e-05,
+      "loss": 0.6153,
+      "mean_token_accuracy": 0.7640196025371552,
+      "num_tokens": 2188262.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.5212278962135315,
+      "learning_rate": 9.63342994296686e-05,
+      "loss": 0.6381,
+      "mean_token_accuracy": 0.7550980448722839,
+      "num_tokens": 2208742.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.682098765432099,
+      "grad_norm": 1.946945071220398,
+      "learning_rate": 9.623779613152893e-05,
+      "loss": 0.6115,
+      "mean_token_accuracy": 0.7643485307693482,
+      "num_tokens": 2229058.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6975308641975309,
+      "grad_norm": 0.5382822155952454,
+      "learning_rate": 9.614008863315789e-05,
+      "loss": 0.6213,
+      "mean_token_accuracy": 0.7603431344032288,
+      "num_tokens": 2249538.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7129629629629628,
+      "grad_norm": 0.4769648313522339,
+      "learning_rate": 9.604117947921385e-05,
+      "loss": 0.6324,
+      "mean_token_accuracy": 0.7571568608283996,
+      "num_tokens": 2270018.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7283950617283952,
+      "grad_norm": 0.48067739605903625,
+      "learning_rate": 9.594107124565056e-05,
+      "loss": 0.6239,
+      "mean_token_accuracy": 0.7589215695858001,
+      "num_tokens": 2290498.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7438271604938271,
+      "grad_norm": 0.505754292011261,
+      "learning_rate": 9.58397665396502e-05,
+      "loss": 0.6371,
+      "mean_token_accuracy": 0.7563725471496582,
+      "num_tokens": 2310978.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.7592592592592593,
+      "grad_norm": 0.56634920835495,
+      "learning_rate": 9.573726799955544e-05,
+      "loss": 0.6186,
+      "mean_token_accuracy": 0.7624509751796722,
+      "num_tokens": 2331458.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7746913580246915,
+      "grad_norm": 0.45453864336013794,
+      "learning_rate": 9.563357829480076e-05,
+      "loss": 0.6119,
+      "mean_token_accuracy": 0.7649815142154693,
+      "num_tokens": 2351728.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7901234567901234,
+      "grad_norm": 0.5595808625221252,
+      "learning_rate": 9.552870012584282e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7618627548217773,
+      "num_tokens": 2372208.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8055555555555556,
+      "grad_norm": 0.5549359321594238,
+      "learning_rate": 9.542263622409027e-05,
+      "loss": 0.6235,
+      "mean_token_accuracy": 0.7586274564266204,
+      "num_tokens": 2392688.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.8209876543209877,
+      "grad_norm": 0.4978308379650116,
+      "learning_rate": 9.53153893518325e-05,
+      "loss": 0.6156,
+      "mean_token_accuracy": 0.7622892081737518,
+      "num_tokens": 2413006.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.8364197530864197,
+      "grad_norm": 0.47992169857025146,
+      "learning_rate": 9.520696230216781e-05,
+      "loss": 0.6206,
+      "mean_token_accuracy": 0.7627451002597809,
+      "num_tokens": 2433486.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.4658719301223755,
+      "learning_rate": 9.509735789893059e-05,
+      "loss": 0.6302,
+      "mean_token_accuracy": 0.7552761137485504,
+      "num_tokens": 2453886.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.867283950617284,
+      "grad_norm": 0.5392885804176331,
+      "learning_rate": 9.498657899661774e-05,
+      "loss": 0.6261,
+      "mean_token_accuracy": 0.758477383852005,
+      "num_tokens": 2474116.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.882716049382716,
+      "grad_norm": 0.74770587682724,
+      "learning_rate": 9.487462848031445e-05,
+      "loss": 0.6229,
+      "mean_token_accuracy": 0.7597548961639404,
+      "num_tokens": 2494596.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8981481481481481,
+      "grad_norm": 0.4596572518348694,
+      "learning_rate": 9.4761509265619e-05,
+      "loss": 0.6167,
+      "mean_token_accuracy": 0.7653431355953216,
+      "num_tokens": 2515076.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.9135802469135803,
+      "grad_norm": 0.653968870639801,
+      "learning_rate": 9.464722429856674e-05,
+      "loss": 0.6232,
+      "mean_token_accuracy": 0.7604411780834198,
+      "num_tokens": 2535556.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.9290123456790123,
+      "grad_norm": 0.7169049382209778,
+      "learning_rate": 9.453177655555355e-05,
+      "loss": 0.6094,
+      "mean_token_accuracy": 0.7661274552345276,
+      "num_tokens": 2556036.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 0.6535491347312927,
+      "learning_rate": 9.441516904325816e-05,
+      "loss": 0.6083,
+      "mean_token_accuracy": 0.766715693473816,
+      "num_tokens": 2576516.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.9598765432098766,
+      "grad_norm": 0.5433221459388733,
+      "learning_rate": 9.42974047985639e-05,
+      "loss": 0.6089,
+      "mean_token_accuracy": 0.7655392229557038,
+      "num_tokens": 2596996.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.5704086422920227,
+      "learning_rate": 9.417848688847968e-05,
+      "loss": 0.6255,
+      "mean_token_accuracy": 0.7593627452850342,
+      "num_tokens": 2617476.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.9907407407407407,
+      "grad_norm": 0.8016455769538879,
+      "learning_rate": 9.405841841005998e-05,
+      "loss": 0.6261,
+      "mean_token_accuracy": 0.7583823561668396,
+      "num_tokens": 2637956.0,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6324792504310608,
+      "eval_mean_token_accuracy": 0.758347749710083,
+      "eval_num_tokens": 2648964.0,
+      "eval_runtime": 3.1944,
+      "eval_samples_per_second": 84.835,
+      "eval_steps_per_second": 10.644,
+      "step": 1296
+    },
+    {
+      "epoch": 2.006172839506173,
+      "grad_norm": 0.6631448864936829,
+      "learning_rate": 9.393720249032428e-05,
+      "loss": 0.6058,
+      "mean_token_accuracy": 0.7671731948852539,
+      "num_tokens": 2657156.0,
+      "step": 1300
+    },
+    {
+      "epoch": 2.021604938271605,
+      "grad_norm": 0.5804994702339172,
+      "learning_rate": 9.381484228617561e-05,
+      "loss": 0.5885,
+      "mean_token_accuracy": 0.7723039388656616,
+      "num_tokens": 2677636.0,
+      "step": 1310
+    },
+    {
+      "epoch": 2.037037037037037,
+      "grad_norm": 0.585965096950531,
+      "learning_rate": 9.369134098431836e-05,
+      "loss": 0.5788,
+      "mean_token_accuracy": 0.7779411792755127,
+      "num_tokens": 2698116.0,
+      "step": 1320
+    },
+    {
+      "epoch": 2.052469135802469,
+      "grad_norm": 0.644915759563446,
+      "learning_rate": 9.356670180117515e-05,
+      "loss": 0.5991,
+      "mean_token_accuracy": 0.7714215755462647,
+      "num_tokens": 2718596.0,
+      "step": 1330
+    },
+    {
+      "epoch": 2.067901234567901,
+      "grad_norm": 0.5631785988807678,
+      "learning_rate": 9.344092798280326e-05,
+      "loss": 0.5793,
+      "mean_token_accuracy": 0.7773529469966889,
+      "num_tokens": 2739076.0,
+      "step": 1340
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.6477254629135132,
+      "learning_rate": 9.331402280480996e-05,
+      "loss": 0.5776,
+      "mean_token_accuracy": 0.777428126335144,
+      "num_tokens": 2759498.0,
+      "step": 1350
+    },
+    {
+      "epoch": 2.0987654320987654,
+      "grad_norm": 0.6347941756248474,
+      "learning_rate": 9.318598957226722e-05,
+      "loss": 0.5827,
+      "mean_token_accuracy": 0.7736274480819703,
+      "num_tokens": 2779978.0,
+      "step": 1360
+    },
+    {
+      "epoch": 2.1141975308641974,
+      "grad_norm": 0.5481588244438171,
+      "learning_rate": 9.305683161962569e-05,
+      "loss": 0.5743,
+      "mean_token_accuracy": 0.7800000071525574,
+      "num_tokens": 2800458.0,
+      "step": 1370
+    },
+    {
+      "epoch": 2.1296296296296298,
+      "grad_norm": 0.6827916502952576,
+      "learning_rate": 9.292655231062777e-05,
+      "loss": 0.5836,
+      "mean_token_accuracy": 0.7771078407764435,
+      "num_tokens": 2820938.0,
+      "step": 1380
+    },
+    {
+      "epoch": 2.1450617283950617,
+      "grad_norm": 0.6322311758995056,
+      "learning_rate": 9.279515503822012e-05,
+      "loss": 0.575,
+      "mean_token_accuracy": 0.7800490260124207,
+      "num_tokens": 2841418.0,
+      "step": 1390
+    },
+    {
+      "epoch": 2.1604938271604937,
+      "grad_norm": 0.6601190567016602,
+      "learning_rate": 9.266264322446513e-05,
+      "loss": 0.5958,
+      "mean_token_accuracy": 0.7735784351825714,
+      "num_tokens": 2861898.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.175925925925926,
+      "grad_norm": 0.7920575141906738,
+      "learning_rate": 9.2529020320452e-05,
+      "loss": 0.5927,
+      "mean_token_accuracy": 0.7717647075653076,
+      "num_tokens": 2882378.0,
+      "step": 1410
+    },
+    {
+      "epoch": 2.191358024691358,
+      "grad_norm": 0.629456639289856,
+      "learning_rate": 9.239428980620668e-05,
+      "loss": 0.6046,
+      "mean_token_accuracy": 0.7663672506809235,
+      "num_tokens": 2902803.0,
+      "step": 1420
+    },
+    {
+      "epoch": 2.20679012345679,
+      "grad_norm": 0.5937893986701965,
+      "learning_rate": 9.22584551906014e-05,
+      "loss": 0.6147,
+      "mean_token_accuracy": 0.7639705955982208,
+      "num_tokens": 2923283.0,
+      "step": 1430
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.714495062828064,
+      "learning_rate": 9.212152001126309e-05,
+      "loss": 0.6008,
+      "mean_token_accuracy": 0.767677491903305,
+      "num_tokens": 2943646.0,
+      "step": 1440
+    },
+    {
+      "epoch": 2.2376543209876543,
+      "grad_norm": 0.6152468919754028,
+      "learning_rate": 9.198348783448143e-05,
+      "loss": 0.5882,
+      "mean_token_accuracy": 0.774215680360794,
+      "num_tokens": 2964126.0,
+      "step": 1450
+    },
+    {
+      "epoch": 2.253086419753086,
+      "grad_norm": 0.7194507122039795,
+      "learning_rate": 9.184436225511593e-05,
+      "loss": 0.5917,
+      "mean_token_accuracy": 0.770784318447113,
+      "num_tokens": 2984606.0,
+      "step": 1460
+    },
+    {
+      "epoch": 2.2685185185185186,
+      "grad_norm": 0.7051591873168945,
+      "learning_rate": 9.170414689650218e-05,
+      "loss": 0.5931,
+      "mean_token_accuracy": 0.7719117701053619,
+      "num_tokens": 3005086.0,
+      "step": 1470
+    },
+    {
+      "epoch": 2.2839506172839505,
+      "grad_norm": 0.7313346266746521,
+      "learning_rate": 9.156284541035767e-05,
+      "loss": 0.6,
+      "mean_token_accuracy": 0.7681372582912445,
+      "num_tokens": 3025566.0,
+      "step": 1480
+    },
+    {
+      "epoch": 2.299382716049383,
+      "grad_norm": 0.769975483417511,
+      "learning_rate": 9.142046147668656e-05,
+      "loss": 0.5946,
+      "mean_token_accuracy": 0.7724509716033936,
+      "num_tokens": 3046046.0,
+      "step": 1490
+    },
+    {
+      "epoch": 2.314814814814815,
+      "grad_norm": 0.8801712989807129,
+      "learning_rate": 9.127699880368388e-05,
+      "loss": 0.5933,
+      "mean_token_accuracy": 0.7703431367874145,
+      "num_tokens": 3066526.0,
+      "step": 1500
+    },
+    {
+      "epoch": 2.330246913580247,
+      "grad_norm": 0.5574469566345215,
+      "learning_rate": 9.113246112763896e-05,
+      "loss": 0.5868,
+      "mean_token_accuracy": 0.7752941250801086,
+      "num_tokens": 3087006.0,
+      "step": 1510
+    },
+    {
+      "epoch": 2.3456790123456788,
+      "grad_norm": 0.7892451882362366,
+      "learning_rate": 9.098685221283809e-05,
+      "loss": 0.5924,
+      "mean_token_accuracy": 0.7702941179275513,
+      "num_tokens": 3107486.0,
+      "step": 1520
+    },
+    {
+      "epoch": 2.361111111111111,
+      "grad_norm": 0.8452872633934021,
+      "learning_rate": 9.084017585146653e-05,
+      "loss": 0.5948,
+      "mean_token_accuracy": 0.7704411804676056,
+      "num_tokens": 3127966.0,
+      "step": 1530
+    },
+    {
+      "epoch": 2.376543209876543,
+      "grad_norm": 0.6332408785820007,
+      "learning_rate": 9.069243586350975e-05,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.7693605184555053,
+      "num_tokens": 3148260.0,
+      "step": 1540
+    },
+    {
+      "epoch": 2.3919753086419755,
+      "grad_norm": 0.6048921346664429,
+      "learning_rate": 9.054363609665388e-05,
+      "loss": 0.6035,
+      "mean_token_accuracy": 0.7655882358551025,
+      "num_tokens": 3168740.0,
+      "step": 1550
+    },
+    {
+      "epoch": 2.4074074074074074,
+      "grad_norm": 0.7863728404045105,
+      "learning_rate": 9.039378042618556e-05,
+      "loss": 0.6149,
+      "mean_token_accuracy": 0.7642330646514892,
+      "num_tokens": 3189058.0,
+      "step": 1560
+    },
+    {
+      "epoch": 2.4228395061728394,
+      "grad_norm": 0.7175882458686829,
+      "learning_rate": 9.0242872754891e-05,
+      "loss": 0.599,
+      "mean_token_accuracy": 0.7685828864574432,
+      "num_tokens": 3209478.0,
+      "step": 1570
+    },
+    {
+      "epoch": 2.4382716049382718,
+      "grad_norm": 0.5595851540565491,
+      "learning_rate": 9.009091701295434e-05,
+      "loss": 0.5987,
+      "mean_token_accuracy": 0.7684313774108886,
+      "num_tokens": 3229958.0,
+      "step": 1580
+    },
+    {
+      "epoch": 2.4537037037037037,
+      "grad_norm": 0.6278279423713684,
+      "learning_rate": 8.993791715785528e-05,
+      "loss": 0.5943,
+      "mean_token_accuracy": 0.7695098042488098,
+      "num_tokens": 3250438.0,
+      "step": 1590
+    },
+    {
+      "epoch": 2.4691358024691357,
+      "grad_norm": 0.6764392852783203,
+      "learning_rate": 8.978387717426601e-05,
+      "loss": 0.6023,
+      "mean_token_accuracy": 0.7695588290691375,
+      "num_tokens": 3270918.0,
+      "step": 1600
+    },
+    {
+      "epoch": 2.484567901234568,
+      "grad_norm": 0.5951012372970581,
+      "learning_rate": 8.962880107394747e-05,
+      "loss": 0.607,
+      "mean_token_accuracy": 0.7664705872535705,
+      "num_tokens": 3291398.0,
+      "step": 1610
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.664739727973938,
+      "learning_rate": 8.947269289564482e-05,
+      "loss": 0.5978,
+      "mean_token_accuracy": 0.7717216908931732,
+      "num_tokens": 3311798.0,
+      "step": 1620
+    },
+    {
+      "epoch": 2.515432098765432,
+      "grad_norm": 0.7000023126602173,
+      "learning_rate": 8.931555670498229e-05,
+      "loss": 0.6025,
+      "mean_token_accuracy": 0.7704411923885346,
+      "num_tokens": 3332278.0,
+      "step": 1630
+    },
+    {
+      "epoch": 2.5308641975308643,
+      "grad_norm": 0.7284229397773743,
+      "learning_rate": 8.915739659435732e-05,
+      "loss": 0.5684,
+      "mean_token_accuracy": 0.7802450954914093,
+      "num_tokens": 3352758.0,
+      "step": 1640
+    },
+    {
+      "epoch": 2.5462962962962963,
+      "grad_norm": 0.5567231774330139,
+      "learning_rate": 8.899821668283388e-05,
+      "loss": 0.6053,
+      "mean_token_accuracy": 0.768921571969986,
+      "num_tokens": 3373238.0,
+      "step": 1650
+    },
+    {
+      "epoch": 2.5617283950617287,
+      "grad_norm": 0.6409662365913391,
+      "learning_rate": 8.883802111603532e-05,
+      "loss": 0.5973,
+      "mean_token_accuracy": 0.7701470613479614,
+      "num_tokens": 3393718.0,
+      "step": 1660
+    },
+    {
+      "epoch": 2.5771604938271606,
+      "grad_norm": 0.6958431005477905,
+      "learning_rate": 8.867681406603632e-05,
+      "loss": 0.6089,
+      "mean_token_accuracy": 0.7654411733150482,
+      "num_tokens": 3414198.0,
+      "step": 1670
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.6124626398086548,
+      "learning_rate": 8.851459973125424e-05,
+      "loss": 0.5953,
+      "mean_token_accuracy": 0.7651470601558685,
+      "num_tokens": 3434678.0,
+      "step": 1680
+    },
+    {
+      "epoch": 2.6080246913580245,
+      "grad_norm": 0.538041889667511,
+      "learning_rate": 8.835138233633986e-05,
+      "loss": 0.5772,
+      "mean_token_accuracy": 0.7773529410362243,
+      "num_tokens": 3455158.0,
+      "step": 1690
+    },
+    {
+      "epoch": 2.623456790123457,
+      "grad_norm": 0.6456654071807861,
+      "learning_rate": 8.818716613206718e-05,
+      "loss": 0.5841,
+      "mean_token_accuracy": 0.7785784304141998,
+      "num_tokens": 3475638.0,
+      "step": 1700
+    },
+    {
+      "epoch": 2.638888888888889,
+      "grad_norm": 0.5318160057067871,
+      "learning_rate": 8.802195539522298e-05,
+      "loss": 0.5881,
+      "mean_token_accuracy": 0.7748183906078339,
+      "num_tokens": 3495908.0,
+      "step": 1710
+    },
+    {
+      "epoch": 2.6543209876543212,
+      "grad_norm": 0.7563948035240173,
+      "learning_rate": 8.785575442849512e-05,
+      "loss": 0.5845,
+      "mean_token_accuracy": 0.7776960790157318,
+      "num_tokens": 3516388.0,
+      "step": 1720
+    },
+    {
+      "epoch": 2.669753086419753,
+      "grad_norm": 0.6648724675178528,
+      "learning_rate": 8.768856756036075e-05,
+      "loss": 0.5967,
+      "mean_token_accuracy": 0.7711274564266205,
+      "num_tokens": 3536868.0,
+      "step": 1730
+    },
+    {
+      "epoch": 2.685185185185185,
+      "grad_norm": 0.7547239065170288,
+      "learning_rate": 8.752039914497344e-05,
+      "loss": 0.5909,
+      "mean_token_accuracy": 0.7715686321258545,
+      "num_tokens": 3557348.0,
+      "step": 1740
+    },
+    {
+      "epoch": 2.700617283950617,
+      "grad_norm": 0.679796040058136,
+      "learning_rate": 8.73512535620498e-05,
+      "loss": 0.5877,
+      "mean_token_accuracy": 0.7745097994804382,
+      "num_tokens": 3577828.0,
+      "step": 1750
+    },
+    {
+      "epoch": 2.7160493827160495,
+      "grad_norm": 0.6214619874954224,
+      "learning_rate": 8.718113521675551e-05,
+      "loss": 0.5934,
+      "mean_token_accuracy": 0.7690686225891114,
+      "num_tokens": 3598308.0,
+      "step": 1760
+    },
+    {
+      "epoch": 2.7314814814814814,
+      "grad_norm": 0.5901688933372498,
+      "learning_rate": 8.70100485395904e-05,
+      "loss": 0.5971,
+      "mean_token_accuracy": 0.7690196096897125,
+      "num_tokens": 3618788.0,
+      "step": 1770
+    },
+    {
+      "epoch": 2.746913580246914,
+      "grad_norm": 0.6220423579216003,
+      "learning_rate": 8.683799798627327e-05,
+      "loss": 0.5911,
+      "mean_token_accuracy": 0.7720097959041595,
+      "num_tokens": 3639268.0,
+      "step": 1780
+    },
+    {
+      "epoch": 2.7623456790123457,
+      "grad_norm": 0.6311886310577393,
+      "learning_rate": 8.666498803762575e-05,
+      "loss": 0.6052,
+      "mean_token_accuracy": 0.7668627440929413,
+      "num_tokens": 3659748.0,
+      "step": 1790
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.5736894011497498,
+      "learning_rate": 8.649102319945556e-05,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.7679901957511902,
+      "num_tokens": 3680228.0,
+      "step": 1800
+    },
+    {
+      "epoch": 2.7932098765432096,
+      "grad_norm": 0.6401321887969971,
+      "learning_rate": 8.631610800243926e-05,
+      "loss": 0.6183,
+      "mean_token_accuracy": 0.7602941215038299,
+      "num_tokens": 3700708.0,
+      "step": 1810
+    },
+    {
+      "epoch": 2.808641975308642,
+      "grad_norm": 0.7890676259994507,
+      "learning_rate": 8.614024700200418e-05,
+      "loss": 0.5976,
+      "mean_token_accuracy": 0.7711274445056915,
+      "num_tokens": 3721188.0,
+      "step": 1820
+    },
+    {
+      "epoch": 2.824074074074074,
+      "grad_norm": 0.682788074016571,
+      "learning_rate": 8.596344477820982e-05,
+      "loss": 0.5833,
+      "mean_token_accuracy": 0.7769117653369904,
+      "num_tokens": 3741668.0,
+      "step": 1830
+    },
+    {
+      "epoch": 2.8395061728395063,
+      "grad_norm": 0.701694667339325,
+      "learning_rate": 8.578570593562856e-05,
+      "loss": 0.5932,
+      "mean_token_accuracy": 0.7721360385417938,
+      "num_tokens": 3761898.0,
+      "step": 1840
+    },
+    {
+      "epoch": 2.8549382716049383,
+      "grad_norm": 0.65044105052948,
+      "learning_rate": 8.560703510322574e-05,
+      "loss": 0.6063,
+      "mean_token_accuracy": 0.764166659116745,
+      "num_tokens": 3782378.0,
+      "step": 1850
+    },
+    {
+      "epoch": 2.8703703703703702,
+      "grad_norm": 0.7230607867240906,
+      "learning_rate": 8.54274369342391e-05,
+      "loss": 0.6061,
+      "mean_token_accuracy": 0.7665201246738433,
+      "num_tokens": 3802694.0,
+      "step": 1860
+    },
+    {
+      "epoch": 2.8858024691358026,
+      "grad_norm": 0.7031252384185791,
+      "learning_rate": 8.524691610605755e-05,
+      "loss": 0.582,
+      "mean_token_accuracy": 0.7744117677211761,
+      "num_tokens": 3823174.0,
+      "step": 1870
+    },
+    {
+      "epoch": 2.9012345679012346,
+      "grad_norm": 0.5592207312583923,
+      "learning_rate": 8.506547732009949e-05,
+      "loss": 0.6136,
+      "mean_token_accuracy": 0.7634313762187958,
+      "num_tokens": 3843654.0,
+      "step": 1880
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 0.6171590089797974,
+      "learning_rate": 8.488312530169019e-05,
+      "loss": 0.5987,
+      "mean_token_accuracy": 0.7682353019714355,
+      "num_tokens": 3864134.0,
+      "step": 1890
+    },
+    {
+      "epoch": 2.932098765432099,
+      "grad_norm": 0.7073954343795776,
+      "learning_rate": 8.469986479993885e-05,
+      "loss": 0.5765,
+      "mean_token_accuracy": 0.7779411852359772,
+      "num_tokens": 3884614.0,
+      "step": 1900
+    },
+    {
+      "epoch": 2.947530864197531,
+      "grad_norm": 0.6308615803718567,
+      "learning_rate": 8.451570058761487e-05,
+      "loss": 0.6109,
+      "mean_token_accuracy": 0.7636274576187134,
+      "num_tokens": 3905094.0,
+      "step": 1910
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.6144311428070068,
+      "learning_rate": 8.433063746102357e-05,
+      "loss": 0.6042,
+      "mean_token_accuracy": 0.7695098102092743,
+      "num_tokens": 3925574.0,
+      "step": 1920
+    },
+    {
+      "epoch": 2.978395061728395,
+      "grad_norm": 0.6184301972389221,
+      "learning_rate": 8.414468023988124e-05,
+      "loss": 0.5754,
+      "mean_token_accuracy": 0.7792156875133515,
+      "num_tokens": 3946054.0,
+      "step": 1930
+    },
+    {
+      "epoch": 2.993827160493827,
+      "grad_norm": 0.6555328369140625,
+      "learning_rate": 8.395783376718966e-05,
+      "loss": 0.5932,
+      "mean_token_accuracy": 0.7713725507259369,
+      "num_tokens": 3966534.0,
+      "step": 1940
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6391911506652832,
+      "eval_mean_token_accuracy": 0.7565599820193123,
+      "eval_num_tokens": 3973446.0,
+      "eval_runtime": 3.199,
+      "eval_samples_per_second": 84.713,
+      "eval_steps_per_second": 10.628,
+      "step": 1944
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 1.6922085155065037e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1944/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a34050fa79a936184e915a7880fc5b9f49db5f1fd1d762599d612766499101
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-2592/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 0.19.1

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-2592/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "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,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-2592/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95a784427210f21afeaded20b33d81236827e4daf36361420a5e4a6e9be11c3e
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-2592/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-2592/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-2592/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-2592/tokenizer.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-2592/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-2592/trainer_state.json

@@ -0,0 +1,2405 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2592,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015432098765432098,
+      "grad_norm": 3.519041061401367,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 2.4621,
+      "mean_token_accuracy": 0.5478431344032287,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.030864197530864196,
+      "grad_norm": 4.195609092712402,
+      "learning_rate": 5.864197530864198e-06,
+      "loss": 2.4435,
+      "mean_token_accuracy": 0.5484313726425171,
+      "num_tokens": 40960.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.046296296296296294,
+      "grad_norm": 3.7905173301696777,
+      "learning_rate": 8.950617283950618e-06,
+      "loss": 2.358,
+      "mean_token_accuracy": 0.5484323740005493,
+      "num_tokens": 61360.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.06172839506172839,
+      "grad_norm": 2.1776044368743896,
+      "learning_rate": 1.2037037037037037e-05,
+      "loss": 2.0177,
+      "mean_token_accuracy": 0.5722058892250061,
+      "num_tokens": 81840.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07716049382716049,
+      "grad_norm": 1.3382104635238647,
+      "learning_rate": 1.5123456790123458e-05,
+      "loss": 1.7326,
+      "mean_token_accuracy": 0.6003921627998352,
+      "num_tokens": 102320.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.09259259259259259,
+      "grad_norm": 1.0943200588226318,
+      "learning_rate": 1.8209876543209877e-05,
+      "loss": 1.5168,
+      "mean_token_accuracy": 0.6119117617607117,
+      "num_tokens": 122800.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.10802469135802469,
+      "grad_norm": 0.9394681453704834,
+      "learning_rate": 2.1296296296296296e-05,
+      "loss": 1.3284,
+      "mean_token_accuracy": 0.6315686345100403,
+      "num_tokens": 143280.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 0.961665689945221,
+      "learning_rate": 2.438271604938272e-05,
+      "loss": 1.1754,
+      "mean_token_accuracy": 0.6534313797950745,
+      "num_tokens": 163760.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 1.0397999286651611,
+      "learning_rate": 2.7469135802469138e-05,
+      "loss": 1.0364,
+      "mean_token_accuracy": 0.6734803915023804,
+      "num_tokens": 184240.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.15432098765432098,
+      "grad_norm": 1.15496027469635,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.9147,
+      "mean_token_accuracy": 0.689607846736908,
+      "num_tokens": 204720.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.1697530864197531,
+      "grad_norm": 1.2569444179534912,
+      "learning_rate": 3.364197530864198e-05,
+      "loss": 0.8172,
+      "mean_token_accuracy": 0.7119117677211761,
+      "num_tokens": 225200.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 1.0953677892684937,
+      "learning_rate": 3.67283950617284e-05,
+      "loss": 0.7472,
+      "mean_token_accuracy": 0.7320588111877442,
+      "num_tokens": 245680.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.2006172839506173,
+      "grad_norm": 1.1510546207427979,
+      "learning_rate": 3.981481481481482e-05,
+      "loss": 0.7372,
+      "mean_token_accuracy": 0.7326960742473603,
+      "num_tokens": 266160.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.21604938271604937,
+      "grad_norm": 1.014360785484314,
+      "learning_rate": 4.290123456790124e-05,
+      "loss": 0.7134,
+      "mean_token_accuracy": 0.7418137192726135,
+      "num_tokens": 286640.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.23148148148148148,
+      "grad_norm": 0.9315780401229858,
+      "learning_rate": 4.5987654320987656e-05,
+      "loss": 0.6951,
+      "mean_token_accuracy": 0.7458823502063752,
+      "num_tokens": 307120.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 0.9429313540458679,
+      "learning_rate": 4.9074074074074075e-05,
+      "loss": 0.6816,
+      "mean_token_accuracy": 0.7458333313465119,
+      "num_tokens": 327600.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.2623456790123457,
+      "grad_norm": 0.8958196640014648,
+      "learning_rate": 5.2160493827160494e-05,
+      "loss": 0.6835,
+      "mean_token_accuracy": 0.7473039209842682,
+      "num_tokens": 348080.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.9595352411270142,
+      "learning_rate": 5.524691358024692e-05,
+      "loss": 0.6714,
+      "mean_token_accuracy": 0.7484643220901489,
+      "num_tokens": 368350.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2932098765432099,
+      "grad_norm": 0.7617053985595703,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 0.678,
+      "mean_token_accuracy": 0.7437254905700683,
+      "num_tokens": 388830.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.30864197530864196,
+      "grad_norm": 0.8184395432472229,
+      "learning_rate": 6.141975308641975e-05,
+      "loss": 0.6782,
+      "mean_token_accuracy": 0.7463235318660736,
+      "num_tokens": 409310.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.32407407407407407,
+      "grad_norm": 0.930051326751709,
+      "learning_rate": 6.450617283950617e-05,
+      "loss": 0.6596,
+      "mean_token_accuracy": 0.7505952179431915,
+      "num_tokens": 429604.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3395061728395062,
+      "grad_norm": 1.5295906066894531,
+      "learning_rate": 6.759259259259259e-05,
+      "loss": 0.6583,
+      "mean_token_accuracy": 0.7503921568393708,
+      "num_tokens": 450084.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.3549382716049383,
+      "grad_norm": 0.7611913681030273,
+      "learning_rate": 7.067901234567902e-05,
+      "loss": 0.6479,
+      "mean_token_accuracy": 0.758186274766922,
+      "num_tokens": 470564.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.7119883894920349,
+      "learning_rate": 7.376543209876543e-05,
+      "loss": 0.6548,
+      "mean_token_accuracy": 0.7510345578193665,
+      "num_tokens": 490986.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.38580246913580246,
+      "grad_norm": 0.7270073890686035,
+      "learning_rate": 7.685185185185185e-05,
+      "loss": 0.6726,
+      "mean_token_accuracy": 0.7451960682868958,
+      "num_tokens": 511466.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4012345679012346,
+      "grad_norm": 0.7441513538360596,
+      "learning_rate": 7.993827160493828e-05,
+      "loss": 0.6384,
+      "mean_token_accuracy": 0.7599019706249237,
+      "num_tokens": 531946.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.6838435530662537,
+      "learning_rate": 8.30246913580247e-05,
+      "loss": 0.6551,
+      "mean_token_accuracy": 0.7513725519180298,
+      "num_tokens": 552426.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.43209876543209874,
+      "grad_norm": 0.8257744908332825,
+      "learning_rate": 8.611111111111112e-05,
+      "loss": 0.6511,
+      "mean_token_accuracy": 0.7551960706710815,
+      "num_tokens": 572906.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.44753086419753085,
+      "grad_norm": 0.739138662815094,
+      "learning_rate": 8.919753086419754e-05,
+      "loss": 0.6572,
+      "mean_token_accuracy": 0.7523039162158967,
+      "num_tokens": 593386.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 0.7312272191047668,
+      "learning_rate": 9.228395061728396e-05,
+      "loss": 0.6738,
+      "mean_token_accuracy": 0.7451960861682891,
+      "num_tokens": 613866.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.4783950617283951,
+      "grad_norm": 0.7143312096595764,
+      "learning_rate": 9.537037037037038e-05,
+      "loss": 0.6398,
+      "mean_token_accuracy": 0.758088231086731,
+      "num_tokens": 634346.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.6812207698822021,
+      "learning_rate": 9.84567901234568e-05,
+      "loss": 0.6494,
+      "mean_token_accuracy": 0.7502175033092499,
+      "num_tokens": 654662.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.5092592592592593,
+      "grad_norm": 0.6230295896530151,
+      "learning_rate": 9.999983722702365e-05,
+      "loss": 0.6436,
+      "mean_token_accuracy": 0.7557843148708343,
+      "num_tokens": 675142.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.5246913580246914,
+      "grad_norm": 0.5965207815170288,
+      "learning_rate": 9.999853504957158e-05,
+      "loss": 0.6647,
+      "mean_token_accuracy": 0.7427450954914093,
+      "num_tokens": 695622.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5401234567901234,
+      "grad_norm": 0.559863805770874,
+      "learning_rate": 9.999593072858088e-05,
+      "loss": 0.6343,
+      "mean_token_accuracy": 0.758293867111206,
+      "num_tokens": 715985.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.9263127446174622,
+      "learning_rate": 9.999202433187755e-05,
+      "loss": 0.6601,
+      "mean_token_accuracy": 0.7472058832645416,
+      "num_tokens": 736465.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5709876543209876,
+      "grad_norm": 0.5964210033416748,
+      "learning_rate": 9.998681596119832e-05,
+      "loss": 0.6778,
+      "mean_token_accuracy": 0.7443627417087555,
+      "num_tokens": 756945.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5864197530864198,
+      "grad_norm": 0.6121820211410522,
+      "learning_rate": 9.998030575218811e-05,
+      "loss": 0.6628,
+      "mean_token_accuracy": 0.7476024866104126,
+      "num_tokens": 777370.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.6018518518518519,
+      "grad_norm": 0.5673462152481079,
+      "learning_rate": 9.997249387439643e-05,
+      "loss": 0.6338,
+      "mean_token_accuracy": 0.7578116476535797,
+      "num_tokens": 797600.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 0.6260263919830322,
+      "learning_rate": 9.996338053127292e-05,
+      "loss": 0.6601,
+      "mean_token_accuracy": 0.7466666638851166,
+      "num_tokens": 818080.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6327160493827161,
+      "grad_norm": 0.5045029520988464,
+      "learning_rate": 9.99529659601622e-05,
+      "loss": 0.663,
+      "mean_token_accuracy": 0.7482352912425995,
+      "num_tokens": 838560.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6481481481481481,
+      "grad_norm": 0.6537773013114929,
+      "learning_rate": 9.994125043229752e-05,
+      "loss": 0.6444,
+      "mean_token_accuracy": 0.7541666746139526,
+      "num_tokens": 859040.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.6635802469135802,
+      "grad_norm": 0.5629055500030518,
+      "learning_rate": 9.992823425279382e-05,
+      "loss": 0.645,
+      "mean_token_accuracy": 0.75343137383461,
+      "num_tokens": 879520.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6790123456790124,
+      "grad_norm": 0.5268312096595764,
+      "learning_rate": 9.991391776063969e-05,
+      "loss": 0.6563,
+      "mean_token_accuracy": 0.7489215791225433,
+      "num_tokens": 900000.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 0.5720213055610657,
+      "learning_rate": 9.98983013286886e-05,
+      "loss": 0.6248,
+      "mean_token_accuracy": 0.7610294163227082,
+      "num_tokens": 920480.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.7098765432098766,
+      "grad_norm": 0.66424560546875,
+      "learning_rate": 9.988138536364922e-05,
+      "loss": 0.6431,
+      "mean_token_accuracy": 0.7532352924346923,
+      "num_tokens": 940960.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.7253086419753086,
+      "grad_norm": 0.6237642765045166,
+      "learning_rate": 9.986317030607475e-05,
+      "loss": 0.6289,
+      "mean_token_accuracy": 0.7579411864280701,
+      "num_tokens": 961440.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.5108409523963928,
+      "learning_rate": 9.984365663035144e-05,
+      "loss": 0.6291,
+      "mean_token_accuracy": 0.7591037034988404,
+      "num_tokens": 981758.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.7561728395061729,
+      "grad_norm": 0.4949217736721039,
+      "learning_rate": 9.982284484468634e-05,
+      "loss": 0.6419,
+      "mean_token_accuracy": 0.752647066116333,
+      "num_tokens": 1002238.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7716049382716049,
+      "grad_norm": 0.6673640012741089,
+      "learning_rate": 9.980073549109397e-05,
+      "loss": 0.6465,
+      "mean_token_accuracy": 0.7512254893779755,
+      "num_tokens": 1022718.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.7870370370370371,
+      "grad_norm": 0.5719751715660095,
+      "learning_rate": 9.977732914538225e-05,
+      "loss": 0.6661,
+      "mean_token_accuracy": 0.7452450931072235,
+      "num_tokens": 1043198.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.8024691358024691,
+      "grad_norm": 0.5307197570800781,
+      "learning_rate": 9.975262641713746e-05,
+      "loss": 0.6422,
+      "mean_token_accuracy": 0.7541176438331604,
+      "num_tokens": 1063678.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.8179012345679012,
+      "grad_norm": 0.5509263277053833,
+      "learning_rate": 9.972662794970841e-05,
+      "loss": 0.6519,
+      "mean_token_accuracy": 0.7512745082378387,
+      "num_tokens": 1084158.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.5206686854362488,
+      "learning_rate": 9.969933442018968e-05,
+      "loss": 0.647,
+      "mean_token_accuracy": 0.7523039221763611,
+      "num_tokens": 1104638.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8487654320987654,
+      "grad_norm": 0.5182181596755981,
+      "learning_rate": 9.967074653940396e-05,
+      "loss": 0.6401,
+      "mean_token_accuracy": 0.7543137311935425,
+      "num_tokens": 1125118.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 0.47155195474624634,
+      "learning_rate": 9.964086505188352e-05,
+      "loss": 0.623,
+      "mean_token_accuracy": 0.7625980377197266,
+      "num_tokens": 1145598.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8796296296296297,
+      "grad_norm": 0.5879080891609192,
+      "learning_rate": 9.960969073585091e-05,
+      "loss": 0.6354,
+      "mean_token_accuracy": 0.7589705884456635,
+      "num_tokens": 1166078.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8950617283950617,
+      "grad_norm": 0.6356768012046814,
+      "learning_rate": 9.95772244031986e-05,
+      "loss": 0.6339,
+      "mean_token_accuracy": 0.758627450466156,
+      "num_tokens": 1186558.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.9104938271604939,
+      "grad_norm": 0.5294948816299438,
+      "learning_rate": 9.954346689946785e-05,
+      "loss": 0.666,
+      "mean_token_accuracy": 0.7455392241477966,
+      "num_tokens": 1207038.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 0.5180017948150635,
+      "learning_rate": 9.950841910382675e-05,
+      "loss": 0.6452,
+      "mean_token_accuracy": 0.7542156934738159,
+      "num_tokens": 1227518.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.941358024691358,
+      "grad_norm": 0.5167914032936096,
+      "learning_rate": 9.947208192904722e-05,
+      "loss": 0.655,
+      "mean_token_accuracy": 0.745588231086731,
+      "num_tokens": 1247998.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9567901234567902,
+      "grad_norm": 0.5089550018310547,
+      "learning_rate": 9.943445632148138e-05,
+      "loss": 0.6318,
+      "mean_token_accuracy": 0.7575609028339386,
+      "num_tokens": 1268418.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 0.49098673462867737,
+      "learning_rate": 9.939554326103673e-05,
+      "loss": 0.6254,
+      "mean_token_accuracy": 0.7607843101024627,
+      "num_tokens": 1288898.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.6257764101028442,
+      "learning_rate": 9.935534376115081e-05,
+      "loss": 0.6181,
+      "mean_token_accuracy": 0.760735297203064,
+      "num_tokens": 1309378.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6358935236930847,
+      "eval_mean_token_accuracy": 0.7576412944232717,
+      "eval_num_tokens": 1324482.0,
+      "eval_runtime": 3.2072,
+      "eval_samples_per_second": 84.497,
+      "eval_steps_per_second": 10.601,
+      "step": 648
+    },
+    {
+      "epoch": 1.0030864197530864,
+      "grad_norm": 0.5601590871810913,
+      "learning_rate": 9.931385886876466e-05,
+      "loss": 0.6262,
+      "mean_token_accuracy": 0.7599019706249237,
+      "num_tokens": 1328578.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.0185185185185186,
+      "grad_norm": 0.48451554775238037,
+      "learning_rate": 9.927108966429559e-05,
+      "loss": 0.6212,
+      "mean_token_accuracy": 0.7603431344032288,
+      "num_tokens": 1349058.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.0339506172839505,
+      "grad_norm": 0.574618399143219,
+      "learning_rate": 9.922703726160915e-05,
+      "loss": 0.6114,
+      "mean_token_accuracy": 0.764607834815979,
+      "num_tokens": 1369538.0,
+      "step": 670
+    },
+    {
+      "epoch": 1.0493827160493827,
+      "grad_norm": 0.5421807765960693,
+      "learning_rate": 9.918170280798997e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7626470565795899,
+      "num_tokens": 1390018.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.0648148148148149,
+      "grad_norm": 0.6702131032943726,
+      "learning_rate": 9.913508748411195e-05,
+      "loss": 0.6183,
+      "mean_token_accuracy": 0.7603431403636932,
+      "num_tokens": 1410498.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0802469135802468,
+      "grad_norm": 0.4915090501308441,
+      "learning_rate": 9.908719250400751e-05,
+      "loss": 0.6205,
+      "mean_token_accuracy": 0.7618292450904847,
+      "num_tokens": 1430861.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.095679012345679,
+      "grad_norm": 0.6062198877334595,
+      "learning_rate": 9.903801911503601e-05,
+      "loss": 0.6276,
+      "mean_token_accuracy": 0.759852945804596,
+      "num_tokens": 1451341.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.5174667239189148,
+      "learning_rate": 9.898756859785114e-05,
+      "loss": 0.6152,
+      "mean_token_accuracy": 0.7662745118141174,
+      "num_tokens": 1471821.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.126543209876543,
+      "grad_norm": 0.5522329211235046,
+      "learning_rate": 9.893584226636772e-05,
+      "loss": 0.5988,
+      "mean_token_accuracy": 0.7693627417087555,
+      "num_tokens": 1492301.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.1419753086419753,
+      "grad_norm": 0.5991533994674683,
+      "learning_rate": 9.88828414677274e-05,
+      "loss": 0.6191,
+      "mean_token_accuracy": 0.7625000059604645,
+      "num_tokens": 1512781.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.1574074074074074,
+      "grad_norm": 0.5619213581085205,
+      "learning_rate": 9.882856758226355e-05,
+      "loss": 0.6095,
+      "mean_token_accuracy": 0.7666666686534882,
+      "num_tokens": 1533261.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1728395061728394,
+      "grad_norm": 0.6064968109130859,
+      "learning_rate": 9.877302202346537e-05,
+      "loss": 0.6174,
+      "mean_token_accuracy": 0.762401956319809,
+      "num_tokens": 1553741.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.1882716049382716,
+      "grad_norm": 0.5420733690261841,
+      "learning_rate": 9.871620623794107e-05,
+      "loss": 0.6208,
+      "mean_token_accuracy": 0.761813735961914,
+      "num_tokens": 1574221.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.2037037037037037,
+      "grad_norm": 0.5008245706558228,
+      "learning_rate": 9.865812170538014e-05,
+      "loss": 0.6157,
+      "mean_token_accuracy": 0.763921570777893,
+      "num_tokens": 1594701.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.2191358024691359,
+      "grad_norm": 0.5480730533599854,
+      "learning_rate": 9.859876993851489e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7608823537826538,
+      "num_tokens": 1615181.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 0.5966739654541016,
+      "learning_rate": 9.853815248308101e-05,
+      "loss": 0.6128,
+      "mean_token_accuracy": 0.7660294115543366,
+      "num_tokens": 1635661.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.6002110242843628,
+      "learning_rate": 9.847627091777729e-05,
+      "loss": 0.6161,
+      "mean_token_accuracy": 0.7602451026439667,
+      "num_tokens": 1656141.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2654320987654322,
+      "grad_norm": 0.547483503818512,
+      "learning_rate": 9.841312685422459e-05,
+      "loss": 0.6488,
+      "mean_token_accuracy": 0.7497548937797547,
+      "num_tokens": 1676621.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.2808641975308643,
+      "grad_norm": 0.7387484908103943,
+      "learning_rate": 9.834872193692378e-05,
+      "loss": 0.6321,
+      "mean_token_accuracy": 0.7572423696517945,
+      "num_tokens": 1696915.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.5367273092269897,
+      "learning_rate": 9.828305784321289e-05,
+      "loss": 0.6069,
+      "mean_token_accuracy": 0.7675980389118194,
+      "num_tokens": 1717395.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.3117283950617284,
+      "grad_norm": 0.5737053751945496,
+      "learning_rate": 9.821613628322358e-05,
+      "loss": 0.6149,
+      "mean_token_accuracy": 0.7629902005195618,
+      "num_tokens": 1737875.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.3271604938271606,
+      "grad_norm": 0.555564284324646,
+      "learning_rate": 9.814795899983645e-05,
+      "loss": 0.6032,
+      "mean_token_accuracy": 0.765931385755539,
+      "num_tokens": 1758355.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.3425925925925926,
+      "grad_norm": 0.5478204488754272,
+      "learning_rate": 9.807852776863568e-05,
+      "loss": 0.6281,
+      "mean_token_accuracy": 0.7586764693260193,
+      "num_tokens": 1778835.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.3580246913580247,
+      "grad_norm": 0.6020711064338684,
+      "learning_rate": 9.800784439786286e-05,
+      "loss": 0.6315,
+      "mean_token_accuracy": 0.7561274588108062,
+      "num_tokens": 1799315.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.373456790123457,
+      "grad_norm": 0.5321200489997864,
+      "learning_rate": 9.793591072836978e-05,
+      "loss": 0.6206,
+      "mean_token_accuracy": 0.7651960849761963,
+      "num_tokens": 1819795.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 0.5763822793960571,
+      "learning_rate": 9.786272863357063e-05,
+      "loss": 0.6225,
+      "mean_token_accuracy": 0.7619433760643005,
+      "num_tokens": 1840220.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.404320987654321,
+      "grad_norm": 0.5706750154495239,
+      "learning_rate": 9.778830001939307e-05,
+      "loss": 0.6186,
+      "mean_token_accuracy": 0.7591176569461823,
+      "num_tokens": 1860700.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.4197530864197532,
+      "grad_norm": 0.5526582598686218,
+      "learning_rate": 9.771262682422866e-05,
+      "loss": 0.6216,
+      "mean_token_accuracy": 0.7599509716033935,
+      "num_tokens": 1881180.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.4351851851851851,
+      "grad_norm": 0.5528797507286072,
+      "learning_rate": 9.76357110188824e-05,
+      "loss": 0.6372,
+      "mean_token_accuracy": 0.752892154455185,
+      "num_tokens": 1901660.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.4506172839506173,
+      "grad_norm": 0.5862347483634949,
+      "learning_rate": 9.755755460652137e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7626960754394532,
+      "num_tokens": 1922140.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.4660493827160495,
+      "grad_norm": 0.6405584216117859,
+      "learning_rate": 9.747815962262255e-05,
+      "loss": 0.6161,
+      "mean_token_accuracy": 0.7654783129692078,
+      "num_tokens": 1942560.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.5765857696533203,
+      "learning_rate": 9.73975281349198e-05,
+      "loss": 0.6257,
+      "mean_token_accuracy": 0.7609804034233093,
+      "num_tokens": 1963040.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4969135802469136,
+      "grad_norm": 0.6691901683807373,
+      "learning_rate": 9.73156622433501e-05,
+      "loss": 0.6393,
+      "mean_token_accuracy": 0.7543627440929412,
+      "num_tokens": 1983520.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.5123456790123457,
+      "grad_norm": 0.5016764998435974,
+      "learning_rate": 9.72325640799987e-05,
+      "loss": 0.6295,
+      "mean_token_accuracy": 0.7598504185676574,
+      "num_tokens": 2003942.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.5277777777777777,
+      "grad_norm": 0.5539676547050476,
+      "learning_rate": 9.71482358090438e-05,
+      "loss": 0.6301,
+      "mean_token_accuracy": 0.7583823561668396,
+      "num_tokens": 2024422.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.5432098765432098,
+      "grad_norm": 0.5221379995346069,
+      "learning_rate": 9.706267962669998e-05,
+      "loss": 0.619,
+      "mean_token_accuracy": 0.7604411840438843,
+      "num_tokens": 2044902.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.558641975308642,
+      "grad_norm": 0.6469255089759827,
+      "learning_rate": 9.697589776116113e-05,
+      "loss": 0.6119,
+      "mean_token_accuracy": 0.7661274552345276,
+      "num_tokens": 2065382.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.574074074074074,
+      "grad_norm": 0.507942795753479,
+      "learning_rate": 9.688789247254237e-05,
+      "loss": 0.6235,
+      "mean_token_accuracy": 0.7585784196853638,
+      "num_tokens": 2085862.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5895061728395061,
+      "grad_norm": 0.5448495745658875,
+      "learning_rate": 9.679866605282122e-05,
+      "loss": 0.6198,
+      "mean_token_accuracy": 0.7634313702583313,
+      "num_tokens": 2106342.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6049382716049383,
+      "grad_norm": 1.2016057968139648,
+      "learning_rate": 9.670822082577787e-05,
+      "loss": 0.6203,
+      "mean_token_accuracy": 0.7600490152835846,
+      "num_tokens": 2126822.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6203703703703702,
+      "grad_norm": 0.592653214931488,
+      "learning_rate": 9.661655914693471e-05,
+      "loss": 0.6303,
+      "mean_token_accuracy": 0.7591176509857178,
+      "num_tokens": 2147302.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6358024691358026,
+      "grad_norm": 0.5714336633682251,
+      "learning_rate": 9.652368340349494e-05,
+      "loss": 0.6375,
+      "mean_token_accuracy": 0.75563725233078,
+      "num_tokens": 2167782.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.6512345679012346,
+      "grad_norm": 0.551650881767273,
+      "learning_rate": 9.642959601428039e-05,
+      "loss": 0.6153,
+      "mean_token_accuracy": 0.7640196025371552,
+      "num_tokens": 2188262.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.5212278962135315,
+      "learning_rate": 9.63342994296686e-05,
+      "loss": 0.6381,
+      "mean_token_accuracy": 0.7550980448722839,
+      "num_tokens": 2208742.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.682098765432099,
+      "grad_norm": 1.946945071220398,
+      "learning_rate": 9.623779613152893e-05,
+      "loss": 0.6115,
+      "mean_token_accuracy": 0.7643485307693482,
+      "num_tokens": 2229058.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6975308641975309,
+      "grad_norm": 0.5382822155952454,
+      "learning_rate": 9.614008863315789e-05,
+      "loss": 0.6213,
+      "mean_token_accuracy": 0.7603431344032288,
+      "num_tokens": 2249538.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7129629629629628,
+      "grad_norm": 0.4769648313522339,
+      "learning_rate": 9.604117947921385e-05,
+      "loss": 0.6324,
+      "mean_token_accuracy": 0.7571568608283996,
+      "num_tokens": 2270018.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7283950617283952,
+      "grad_norm": 0.48067739605903625,
+      "learning_rate": 9.594107124565056e-05,
+      "loss": 0.6239,
+      "mean_token_accuracy": 0.7589215695858001,
+      "num_tokens": 2290498.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7438271604938271,
+      "grad_norm": 0.505754292011261,
+      "learning_rate": 9.58397665396502e-05,
+      "loss": 0.6371,
+      "mean_token_accuracy": 0.7563725471496582,
+      "num_tokens": 2310978.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.7592592592592593,
+      "grad_norm": 0.56634920835495,
+      "learning_rate": 9.573726799955544e-05,
+      "loss": 0.6186,
+      "mean_token_accuracy": 0.7624509751796722,
+      "num_tokens": 2331458.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7746913580246915,
+      "grad_norm": 0.45453864336013794,
+      "learning_rate": 9.563357829480076e-05,
+      "loss": 0.6119,
+      "mean_token_accuracy": 0.7649815142154693,
+      "num_tokens": 2351728.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7901234567901234,
+      "grad_norm": 0.5595808625221252,
+      "learning_rate": 9.552870012584282e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7618627548217773,
+      "num_tokens": 2372208.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8055555555555556,
+      "grad_norm": 0.5549359321594238,
+      "learning_rate": 9.542263622409027e-05,
+      "loss": 0.6235,
+      "mean_token_accuracy": 0.7586274564266204,
+      "num_tokens": 2392688.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.8209876543209877,
+      "grad_norm": 0.4978308379650116,
+      "learning_rate": 9.53153893518325e-05,
+      "loss": 0.6156,
+      "mean_token_accuracy": 0.7622892081737518,
+      "num_tokens": 2413006.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.8364197530864197,
+      "grad_norm": 0.47992169857025146,
+      "learning_rate": 9.520696230216781e-05,
+      "loss": 0.6206,
+      "mean_token_accuracy": 0.7627451002597809,
+      "num_tokens": 2433486.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.4658719301223755,
+      "learning_rate": 9.509735789893059e-05,
+      "loss": 0.6302,
+      "mean_token_accuracy": 0.7552761137485504,
+      "num_tokens": 2453886.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.867283950617284,
+      "grad_norm": 0.5392885804176331,
+      "learning_rate": 9.498657899661774e-05,
+      "loss": 0.6261,
+      "mean_token_accuracy": 0.758477383852005,
+      "num_tokens": 2474116.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.882716049382716,
+      "grad_norm": 0.74770587682724,
+      "learning_rate": 9.487462848031445e-05,
+      "loss": 0.6229,
+      "mean_token_accuracy": 0.7597548961639404,
+      "num_tokens": 2494596.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8981481481481481,
+      "grad_norm": 0.4596572518348694,
+      "learning_rate": 9.4761509265619e-05,
+      "loss": 0.6167,
+      "mean_token_accuracy": 0.7653431355953216,
+      "num_tokens": 2515076.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.9135802469135803,
+      "grad_norm": 0.653968870639801,
+      "learning_rate": 9.464722429856674e-05,
+      "loss": 0.6232,
+      "mean_token_accuracy": 0.7604411780834198,
+      "num_tokens": 2535556.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.9290123456790123,
+      "grad_norm": 0.7169049382209778,
+      "learning_rate": 9.453177655555355e-05,
+      "loss": 0.6094,
+      "mean_token_accuracy": 0.7661274552345276,
+      "num_tokens": 2556036.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 0.6535491347312927,
+      "learning_rate": 9.441516904325816e-05,
+      "loss": 0.6083,
+      "mean_token_accuracy": 0.766715693473816,
+      "num_tokens": 2576516.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.9598765432098766,
+      "grad_norm": 0.5433221459388733,
+      "learning_rate": 9.42974047985639e-05,
+      "loss": 0.6089,
+      "mean_token_accuracy": 0.7655392229557038,
+      "num_tokens": 2596996.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.5704086422920227,
+      "learning_rate": 9.417848688847968e-05,
+      "loss": 0.6255,
+      "mean_token_accuracy": 0.7593627452850342,
+      "num_tokens": 2617476.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.9907407407407407,
+      "grad_norm": 0.8016455769538879,
+      "learning_rate": 9.405841841005998e-05,
+      "loss": 0.6261,
+      "mean_token_accuracy": 0.7583823561668396,
+      "num_tokens": 2637956.0,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6324792504310608,
+      "eval_mean_token_accuracy": 0.758347749710083,
+      "eval_num_tokens": 2648964.0,
+      "eval_runtime": 3.1944,
+      "eval_samples_per_second": 84.835,
+      "eval_steps_per_second": 10.644,
+      "step": 1296
+    },
+    {
+      "epoch": 2.006172839506173,
+      "grad_norm": 0.6631448864936829,
+      "learning_rate": 9.393720249032428e-05,
+      "loss": 0.6058,
+      "mean_token_accuracy": 0.7671731948852539,
+      "num_tokens": 2657156.0,
+      "step": 1300
+    },
+    {
+      "epoch": 2.021604938271605,
+      "grad_norm": 0.5804994702339172,
+      "learning_rate": 9.381484228617561e-05,
+      "loss": 0.5885,
+      "mean_token_accuracy": 0.7723039388656616,
+      "num_tokens": 2677636.0,
+      "step": 1310
+    },
+    {
+      "epoch": 2.037037037037037,
+      "grad_norm": 0.585965096950531,
+      "learning_rate": 9.369134098431836e-05,
+      "loss": 0.5788,
+      "mean_token_accuracy": 0.7779411792755127,
+      "num_tokens": 2698116.0,
+      "step": 1320
+    },
+    {
+      "epoch": 2.052469135802469,
+      "grad_norm": 0.644915759563446,
+      "learning_rate": 9.356670180117515e-05,
+      "loss": 0.5991,
+      "mean_token_accuracy": 0.7714215755462647,
+      "num_tokens": 2718596.0,
+      "step": 1330
+    },
+    {
+      "epoch": 2.067901234567901,
+      "grad_norm": 0.5631785988807678,
+      "learning_rate": 9.344092798280326e-05,
+      "loss": 0.5793,
+      "mean_token_accuracy": 0.7773529469966889,
+      "num_tokens": 2739076.0,
+      "step": 1340
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.6477254629135132,
+      "learning_rate": 9.331402280480996e-05,
+      "loss": 0.5776,
+      "mean_token_accuracy": 0.777428126335144,
+      "num_tokens": 2759498.0,
+      "step": 1350
+    },
+    {
+      "epoch": 2.0987654320987654,
+      "grad_norm": 0.6347941756248474,
+      "learning_rate": 9.318598957226722e-05,
+      "loss": 0.5827,
+      "mean_token_accuracy": 0.7736274480819703,
+      "num_tokens": 2779978.0,
+      "step": 1360
+    },
+    {
+      "epoch": 2.1141975308641974,
+      "grad_norm": 0.5481588244438171,
+      "learning_rate": 9.305683161962569e-05,
+      "loss": 0.5743,
+      "mean_token_accuracy": 0.7800000071525574,
+      "num_tokens": 2800458.0,
+      "step": 1370
+    },
+    {
+      "epoch": 2.1296296296296298,
+      "grad_norm": 0.6827916502952576,
+      "learning_rate": 9.292655231062777e-05,
+      "loss": 0.5836,
+      "mean_token_accuracy": 0.7771078407764435,
+      "num_tokens": 2820938.0,
+      "step": 1380
+    },
+    {
+      "epoch": 2.1450617283950617,
+      "grad_norm": 0.6322311758995056,
+      "learning_rate": 9.279515503822012e-05,
+      "loss": 0.575,
+      "mean_token_accuracy": 0.7800490260124207,
+      "num_tokens": 2841418.0,
+      "step": 1390
+    },
+    {
+      "epoch": 2.1604938271604937,
+      "grad_norm": 0.6601190567016602,
+      "learning_rate": 9.266264322446513e-05,
+      "loss": 0.5958,
+      "mean_token_accuracy": 0.7735784351825714,
+      "num_tokens": 2861898.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.175925925925926,
+      "grad_norm": 0.7920575141906738,
+      "learning_rate": 9.2529020320452e-05,
+      "loss": 0.5927,
+      "mean_token_accuracy": 0.7717647075653076,
+      "num_tokens": 2882378.0,
+      "step": 1410
+    },
+    {
+      "epoch": 2.191358024691358,
+      "grad_norm": 0.629456639289856,
+      "learning_rate": 9.239428980620668e-05,
+      "loss": 0.6046,
+      "mean_token_accuracy": 0.7663672506809235,
+      "num_tokens": 2902803.0,
+      "step": 1420
+    },
+    {
+      "epoch": 2.20679012345679,
+      "grad_norm": 0.5937893986701965,
+      "learning_rate": 9.22584551906014e-05,
+      "loss": 0.6147,
+      "mean_token_accuracy": 0.7639705955982208,
+      "num_tokens": 2923283.0,
+      "step": 1430
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.714495062828064,
+      "learning_rate": 9.212152001126309e-05,
+      "loss": 0.6008,
+      "mean_token_accuracy": 0.767677491903305,
+      "num_tokens": 2943646.0,
+      "step": 1440
+    },
+    {
+      "epoch": 2.2376543209876543,
+      "grad_norm": 0.6152468919754028,
+      "learning_rate": 9.198348783448143e-05,
+      "loss": 0.5882,
+      "mean_token_accuracy": 0.774215680360794,
+      "num_tokens": 2964126.0,
+      "step": 1450
+    },
+    {
+      "epoch": 2.253086419753086,
+      "grad_norm": 0.7194507122039795,
+      "learning_rate": 9.184436225511593e-05,
+      "loss": 0.5917,
+      "mean_token_accuracy": 0.770784318447113,
+      "num_tokens": 2984606.0,
+      "step": 1460
+    },
+    {
+      "epoch": 2.2685185185185186,
+      "grad_norm": 0.7051591873168945,
+      "learning_rate": 9.170414689650218e-05,
+      "loss": 0.5931,
+      "mean_token_accuracy": 0.7719117701053619,
+      "num_tokens": 3005086.0,
+      "step": 1470
+    },
+    {
+      "epoch": 2.2839506172839505,
+      "grad_norm": 0.7313346266746521,
+      "learning_rate": 9.156284541035767e-05,
+      "loss": 0.6,
+      "mean_token_accuracy": 0.7681372582912445,
+      "num_tokens": 3025566.0,
+      "step": 1480
+    },
+    {
+      "epoch": 2.299382716049383,
+      "grad_norm": 0.769975483417511,
+      "learning_rate": 9.142046147668656e-05,
+      "loss": 0.5946,
+      "mean_token_accuracy": 0.7724509716033936,
+      "num_tokens": 3046046.0,
+      "step": 1490
+    },
+    {
+      "epoch": 2.314814814814815,
+      "grad_norm": 0.8801712989807129,
+      "learning_rate": 9.127699880368388e-05,
+      "loss": 0.5933,
+      "mean_token_accuracy": 0.7703431367874145,
+      "num_tokens": 3066526.0,
+      "step": 1500
+    },
+    {
+      "epoch": 2.330246913580247,
+      "grad_norm": 0.5574469566345215,
+      "learning_rate": 9.113246112763896e-05,
+      "loss": 0.5868,
+      "mean_token_accuracy": 0.7752941250801086,
+      "num_tokens": 3087006.0,
+      "step": 1510
+    },
+    {
+      "epoch": 2.3456790123456788,
+      "grad_norm": 0.7892451882362366,
+      "learning_rate": 9.098685221283809e-05,
+      "loss": 0.5924,
+      "mean_token_accuracy": 0.7702941179275513,
+      "num_tokens": 3107486.0,
+      "step": 1520
+    },
+    {
+      "epoch": 2.361111111111111,
+      "grad_norm": 0.8452872633934021,
+      "learning_rate": 9.084017585146653e-05,
+      "loss": 0.5948,
+      "mean_token_accuracy": 0.7704411804676056,
+      "num_tokens": 3127966.0,
+      "step": 1530
+    },
+    {
+      "epoch": 2.376543209876543,
+      "grad_norm": 0.6332408785820007,
+      "learning_rate": 9.069243586350975e-05,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.7693605184555053,
+      "num_tokens": 3148260.0,
+      "step": 1540
+    },
+    {
+      "epoch": 2.3919753086419755,
+      "grad_norm": 0.6048921346664429,
+      "learning_rate": 9.054363609665388e-05,
+      "loss": 0.6035,
+      "mean_token_accuracy": 0.7655882358551025,
+      "num_tokens": 3168740.0,
+      "step": 1550
+    },
+    {
+      "epoch": 2.4074074074074074,
+      "grad_norm": 0.7863728404045105,
+      "learning_rate": 9.039378042618556e-05,
+      "loss": 0.6149,
+      "mean_token_accuracy": 0.7642330646514892,
+      "num_tokens": 3189058.0,
+      "step": 1560
+    },
+    {
+      "epoch": 2.4228395061728394,
+      "grad_norm": 0.7175882458686829,
+      "learning_rate": 9.0242872754891e-05,
+      "loss": 0.599,
+      "mean_token_accuracy": 0.7685828864574432,
+      "num_tokens": 3209478.0,
+      "step": 1570
+    },
+    {
+      "epoch": 2.4382716049382718,
+      "grad_norm": 0.5595851540565491,
+      "learning_rate": 9.009091701295434e-05,
+      "loss": 0.5987,
+      "mean_token_accuracy": 0.7684313774108886,
+      "num_tokens": 3229958.0,
+      "step": 1580
+    },
+    {
+      "epoch": 2.4537037037037037,
+      "grad_norm": 0.6278279423713684,
+      "learning_rate": 8.993791715785528e-05,
+      "loss": 0.5943,
+      "mean_token_accuracy": 0.7695098042488098,
+      "num_tokens": 3250438.0,
+      "step": 1590
+    },
+    {
+      "epoch": 2.4691358024691357,
+      "grad_norm": 0.6764392852783203,
+      "learning_rate": 8.978387717426601e-05,
+      "loss": 0.6023,
+      "mean_token_accuracy": 0.7695588290691375,
+      "num_tokens": 3270918.0,
+      "step": 1600
+    },
+    {
+      "epoch": 2.484567901234568,
+      "grad_norm": 0.5951012372970581,
+      "learning_rate": 8.962880107394747e-05,
+      "loss": 0.607,
+      "mean_token_accuracy": 0.7664705872535705,
+      "num_tokens": 3291398.0,
+      "step": 1610
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.664739727973938,
+      "learning_rate": 8.947269289564482e-05,
+      "loss": 0.5978,
+      "mean_token_accuracy": 0.7717216908931732,
+      "num_tokens": 3311798.0,
+      "step": 1620
+    },
+    {
+      "epoch": 2.515432098765432,
+      "grad_norm": 0.7000023126602173,
+      "learning_rate": 8.931555670498229e-05,
+      "loss": 0.6025,
+      "mean_token_accuracy": 0.7704411923885346,
+      "num_tokens": 3332278.0,
+      "step": 1630
+    },
+    {
+      "epoch": 2.5308641975308643,
+      "grad_norm": 0.7284229397773743,
+      "learning_rate": 8.915739659435732e-05,
+      "loss": 0.5684,
+      "mean_token_accuracy": 0.7802450954914093,
+      "num_tokens": 3352758.0,
+      "step": 1640
+    },
+    {
+      "epoch": 2.5462962962962963,
+      "grad_norm": 0.5567231774330139,
+      "learning_rate": 8.899821668283388e-05,
+      "loss": 0.6053,
+      "mean_token_accuracy": 0.768921571969986,
+      "num_tokens": 3373238.0,
+      "step": 1650
+    },
+    {
+      "epoch": 2.5617283950617287,
+      "grad_norm": 0.6409662365913391,
+      "learning_rate": 8.883802111603532e-05,
+      "loss": 0.5973,
+      "mean_token_accuracy": 0.7701470613479614,
+      "num_tokens": 3393718.0,
+      "step": 1660
+    },
+    {
+      "epoch": 2.5771604938271606,
+      "grad_norm": 0.6958431005477905,
+      "learning_rate": 8.867681406603632e-05,
+      "loss": 0.6089,
+      "mean_token_accuracy": 0.7654411733150482,
+      "num_tokens": 3414198.0,
+      "step": 1670
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.6124626398086548,
+      "learning_rate": 8.851459973125424e-05,
+      "loss": 0.5953,
+      "mean_token_accuracy": 0.7651470601558685,
+      "num_tokens": 3434678.0,
+      "step": 1680
+    },
+    {
+      "epoch": 2.6080246913580245,
+      "grad_norm": 0.538041889667511,
+      "learning_rate": 8.835138233633986e-05,
+      "loss": 0.5772,
+      "mean_token_accuracy": 0.7773529410362243,
+      "num_tokens": 3455158.0,
+      "step": 1690
+    },
+    {
+      "epoch": 2.623456790123457,
+      "grad_norm": 0.6456654071807861,
+      "learning_rate": 8.818716613206718e-05,
+      "loss": 0.5841,
+      "mean_token_accuracy": 0.7785784304141998,
+      "num_tokens": 3475638.0,
+      "step": 1700
+    },
+    {
+      "epoch": 2.638888888888889,
+      "grad_norm": 0.5318160057067871,
+      "learning_rate": 8.802195539522298e-05,
+      "loss": 0.5881,
+      "mean_token_accuracy": 0.7748183906078339,
+      "num_tokens": 3495908.0,
+      "step": 1710
+    },
+    {
+      "epoch": 2.6543209876543212,
+      "grad_norm": 0.7563948035240173,
+      "learning_rate": 8.785575442849512e-05,
+      "loss": 0.5845,
+      "mean_token_accuracy": 0.7776960790157318,
+      "num_tokens": 3516388.0,
+      "step": 1720
+    },
+    {
+      "epoch": 2.669753086419753,
+      "grad_norm": 0.6648724675178528,
+      "learning_rate": 8.768856756036075e-05,
+      "loss": 0.5967,
+      "mean_token_accuracy": 0.7711274564266205,
+      "num_tokens": 3536868.0,
+      "step": 1730
+    },
+    {
+      "epoch": 2.685185185185185,
+      "grad_norm": 0.7547239065170288,
+      "learning_rate": 8.752039914497344e-05,
+      "loss": 0.5909,
+      "mean_token_accuracy": 0.7715686321258545,
+      "num_tokens": 3557348.0,
+      "step": 1740
+    },
+    {
+      "epoch": 2.700617283950617,
+      "grad_norm": 0.679796040058136,
+      "learning_rate": 8.73512535620498e-05,
+      "loss": 0.5877,
+      "mean_token_accuracy": 0.7745097994804382,
+      "num_tokens": 3577828.0,
+      "step": 1750
+    },
+    {
+      "epoch": 2.7160493827160495,
+      "grad_norm": 0.6214619874954224,
+      "learning_rate": 8.718113521675551e-05,
+      "loss": 0.5934,
+      "mean_token_accuracy": 0.7690686225891114,
+      "num_tokens": 3598308.0,
+      "step": 1760
+    },
+    {
+      "epoch": 2.7314814814814814,
+      "grad_norm": 0.5901688933372498,
+      "learning_rate": 8.70100485395904e-05,
+      "loss": 0.5971,
+      "mean_token_accuracy": 0.7690196096897125,
+      "num_tokens": 3618788.0,
+      "step": 1770
+    },
+    {
+      "epoch": 2.746913580246914,
+      "grad_norm": 0.6220423579216003,
+      "learning_rate": 8.683799798627327e-05,
+      "loss": 0.5911,
+      "mean_token_accuracy": 0.7720097959041595,
+      "num_tokens": 3639268.0,
+      "step": 1780
+    },
+    {
+      "epoch": 2.7623456790123457,
+      "grad_norm": 0.6311886310577393,
+      "learning_rate": 8.666498803762575e-05,
+      "loss": 0.6052,
+      "mean_token_accuracy": 0.7668627440929413,
+      "num_tokens": 3659748.0,
+      "step": 1790
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.5736894011497498,
+      "learning_rate": 8.649102319945556e-05,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.7679901957511902,
+      "num_tokens": 3680228.0,
+      "step": 1800
+    },
+    {
+      "epoch": 2.7932098765432096,
+      "grad_norm": 0.6401321887969971,
+      "learning_rate": 8.631610800243926e-05,
+      "loss": 0.6183,
+      "mean_token_accuracy": 0.7602941215038299,
+      "num_tokens": 3700708.0,
+      "step": 1810
+    },
+    {
+      "epoch": 2.808641975308642,
+      "grad_norm": 0.7890676259994507,
+      "learning_rate": 8.614024700200418e-05,
+      "loss": 0.5976,
+      "mean_token_accuracy": 0.7711274445056915,
+      "num_tokens": 3721188.0,
+      "step": 1820
+    },
+    {
+      "epoch": 2.824074074074074,
+      "grad_norm": 0.682788074016571,
+      "learning_rate": 8.596344477820982e-05,
+      "loss": 0.5833,
+      "mean_token_accuracy": 0.7769117653369904,
+      "num_tokens": 3741668.0,
+      "step": 1830
+    },
+    {
+      "epoch": 2.8395061728395063,
+      "grad_norm": 0.701694667339325,
+      "learning_rate": 8.578570593562856e-05,
+      "loss": 0.5932,
+      "mean_token_accuracy": 0.7721360385417938,
+      "num_tokens": 3761898.0,
+      "step": 1840
+    },
+    {
+      "epoch": 2.8549382716049383,
+      "grad_norm": 0.65044105052948,
+      "learning_rate": 8.560703510322574e-05,
+      "loss": 0.6063,
+      "mean_token_accuracy": 0.764166659116745,
+      "num_tokens": 3782378.0,
+      "step": 1850
+    },
+    {
+      "epoch": 2.8703703703703702,
+      "grad_norm": 0.7230607867240906,
+      "learning_rate": 8.54274369342391e-05,
+      "loss": 0.6061,
+      "mean_token_accuracy": 0.7665201246738433,
+      "num_tokens": 3802694.0,
+      "step": 1860
+    },
+    {
+      "epoch": 2.8858024691358026,
+      "grad_norm": 0.7031252384185791,
+      "learning_rate": 8.524691610605755e-05,
+      "loss": 0.582,
+      "mean_token_accuracy": 0.7744117677211761,
+      "num_tokens": 3823174.0,
+      "step": 1870
+    },
+    {
+      "epoch": 2.9012345679012346,
+      "grad_norm": 0.5592207312583923,
+      "learning_rate": 8.506547732009949e-05,
+      "loss": 0.6136,
+      "mean_token_accuracy": 0.7634313762187958,
+      "num_tokens": 3843654.0,
+      "step": 1880
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 0.6171590089797974,
+      "learning_rate": 8.488312530169019e-05,
+      "loss": 0.5987,
+      "mean_token_accuracy": 0.7682353019714355,
+      "num_tokens": 3864134.0,
+      "step": 1890
+    },
+    {
+      "epoch": 2.932098765432099,
+      "grad_norm": 0.7073954343795776,
+      "learning_rate": 8.469986479993885e-05,
+      "loss": 0.5765,
+      "mean_token_accuracy": 0.7779411852359772,
+      "num_tokens": 3884614.0,
+      "step": 1900
+    },
+    {
+      "epoch": 2.947530864197531,
+      "grad_norm": 0.6308615803718567,
+      "learning_rate": 8.451570058761487e-05,
+      "loss": 0.6109,
+      "mean_token_accuracy": 0.7636274576187134,
+      "num_tokens": 3905094.0,
+      "step": 1910
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.6144311428070068,
+      "learning_rate": 8.433063746102357e-05,
+      "loss": 0.6042,
+      "mean_token_accuracy": 0.7695098102092743,
+      "num_tokens": 3925574.0,
+      "step": 1920
+    },
+    {
+      "epoch": 2.978395061728395,
+      "grad_norm": 0.6184301972389221,
+      "learning_rate": 8.414468023988124e-05,
+      "loss": 0.5754,
+      "mean_token_accuracy": 0.7792156875133515,
+      "num_tokens": 3946054.0,
+      "step": 1930
+    },
+    {
+      "epoch": 2.993827160493827,
+      "grad_norm": 0.6555328369140625,
+      "learning_rate": 8.395783376718966e-05,
+      "loss": 0.5932,
+      "mean_token_accuracy": 0.7713725507259369,
+      "num_tokens": 3966534.0,
+      "step": 1940
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6391911506652832,
+      "eval_mean_token_accuracy": 0.7565599820193123,
+      "eval_num_tokens": 3973446.0,
+      "eval_runtime": 3.199,
+      "eval_samples_per_second": 84.713,
+      "eval_steps_per_second": 10.628,
+      "step": 1944
+    },
+    {
+      "epoch": 3.009259259259259,
+      "grad_norm": 0.8108472228050232,
+      "learning_rate": 8.377010290910996e-05,
+      "loss": 0.5747,
+      "mean_token_accuracy": 0.7773692846298218,
+      "num_tokens": 3985734.0,
+      "step": 1950
+    },
+    {
+      "epoch": 3.0246913580246915,
+      "grad_norm": 0.6429426074028015,
+      "learning_rate": 8.358149255483585e-05,
+      "loss": 0.525,
+      "mean_token_accuracy": 0.7980392158031464,
+      "num_tokens": 4006214.0,
+      "step": 1960
+    },
+    {
+      "epoch": 3.0401234567901234,
+      "grad_norm": 0.7791044116020203,
+      "learning_rate": 8.339200761646633e-05,
+      "loss": 0.557,
+      "mean_token_accuracy": 0.7867647051811218,
+      "num_tokens": 4026694.0,
+      "step": 1970
+    },
+    {
+      "epoch": 3.0555555555555554,
+      "grad_norm": 0.8092915415763855,
+      "learning_rate": 8.320165302887776e-05,
+      "loss": 0.5744,
+      "mean_token_accuracy": 0.780735296010971,
+      "num_tokens": 4047174.0,
+      "step": 1980
+    },
+    {
+      "epoch": 3.0709876543209877,
+      "grad_norm": 0.8350423574447632,
+      "learning_rate": 8.301043374959532e-05,
+      "loss": 0.5691,
+      "mean_token_accuracy": 0.7803431391716004,
+      "num_tokens": 4067654.0,
+      "step": 1990
+    },
+    {
+      "epoch": 3.0864197530864197,
+      "grad_norm": 0.8339701294898987,
+      "learning_rate": 8.281835475866388e-05,
+      "loss": 0.5585,
+      "mean_token_accuracy": 0.7860784292221069,
+      "num_tokens": 4088134.0,
+      "step": 2000
+    },
+    {
+      "epoch": 3.1018518518518516,
+      "grad_norm": 0.6851845979690552,
+      "learning_rate": 8.262542105851836e-05,
+      "loss": 0.5547,
+      "mean_token_accuracy": 0.7845588207244873,
+      "num_tokens": 4108614.0,
+      "step": 2010
+    },
+    {
+      "epoch": 3.117283950617284,
+      "grad_norm": 0.7860126495361328,
+      "learning_rate": 8.24316376738534e-05,
+      "loss": 0.5582,
+      "mean_token_accuracy": 0.7863725483417511,
+      "num_tokens": 4129094.0,
+      "step": 2020
+    },
+    {
+      "epoch": 3.132716049382716,
+      "grad_norm": 1.0001851320266724,
+      "learning_rate": 8.22370096514925e-05,
+      "loss": 0.5569,
+      "mean_token_accuracy": 0.7877941131591797,
+      "num_tokens": 4149574.0,
+      "step": 2030
+    },
+    {
+      "epoch": 3.148148148148148,
+      "grad_norm": 0.7747116088867188,
+      "learning_rate": 8.204154206025664e-05,
+      "loss": 0.573,
+      "mean_token_accuracy": 0.7773039162158966,
+      "num_tokens": 4170054.0,
+      "step": 2040
+    },
+    {
+      "epoch": 3.1635802469135803,
+      "grad_norm": 1.070248007774353,
+      "learning_rate": 8.184523999083215e-05,
+      "loss": 0.5635,
+      "mean_token_accuracy": 0.7820588231086731,
+      "num_tokens": 4190534.0,
+      "step": 2050
+    },
+    {
+      "epoch": 3.1790123456790123,
+      "grad_norm": 0.8264543414115906,
+      "learning_rate": 8.164810855563826e-05,
+      "loss": 0.5367,
+      "mean_token_accuracy": 0.7932051718235016,
+      "num_tokens": 4210897.0,
+      "step": 2060
+    },
+    {
+      "epoch": 3.1944444444444446,
+      "grad_norm": 0.8083105087280273,
+      "learning_rate": 8.14501528886939e-05,
+      "loss": 0.5434,
+      "mean_token_accuracy": 0.7911274552345275,
+      "num_tokens": 4231377.0,
+      "step": 2070
+    },
+    {
+      "epoch": 3.2098765432098766,
+      "grad_norm": 0.6598303318023682,
+      "learning_rate": 8.125137814548393e-05,
+      "loss": 0.5704,
+      "mean_token_accuracy": 0.7793627440929413,
+      "num_tokens": 4251857.0,
+      "step": 2080
+    },
+    {
+      "epoch": 3.2253086419753085,
+      "grad_norm": 0.7869428396224976,
+      "learning_rate": 8.105178950282502e-05,
+      "loss": 0.5449,
+      "mean_token_accuracy": 0.7897549033164978,
+      "num_tokens": 4272337.0,
+      "step": 2090
+    },
+    {
+      "epoch": 3.240740740740741,
+      "grad_norm": 1.0627241134643555,
+      "learning_rate": 8.085139215873068e-05,
+      "loss": 0.5689,
+      "mean_token_accuracy": 0.7810784339904785,
+      "num_tokens": 4292817.0,
+      "step": 2100
+    },
+    {
+      "epoch": 3.256172839506173,
+      "grad_norm": 0.8701480627059937,
+      "learning_rate": 8.065019133227595e-05,
+      "loss": 0.5637,
+      "mean_token_accuracy": 0.7836764812469482,
+      "num_tokens": 4313297.0,
+      "step": 2110
+    },
+    {
+      "epoch": 3.271604938271605,
+      "grad_norm": 0.766616702079773,
+      "learning_rate": 8.04481922634615e-05,
+      "loss": 0.5608,
+      "mean_token_accuracy": 0.7846944510936738,
+      "num_tokens": 4333591.0,
+      "step": 2120
+    },
+    {
+      "epoch": 3.287037037037037,
+      "grad_norm": 0.7725467085838318,
+      "learning_rate": 8.024540021307708e-05,
+      "loss": 0.5592,
+      "mean_token_accuracy": 0.7843627512454987,
+      "num_tokens": 4354071.0,
+      "step": 2130
+    },
+    {
+      "epoch": 3.302469135802469,
+      "grad_norm": 0.8298613429069519,
+      "learning_rate": 8.004182046256463e-05,
+      "loss": 0.555,
+      "mean_token_accuracy": 0.786519604921341,
+      "num_tokens": 4374551.0,
+      "step": 2140
+    },
+    {
+      "epoch": 3.317901234567901,
+      "grad_norm": 0.9635348320007324,
+      "learning_rate": 7.983745831388061e-05,
+      "loss": 0.5514,
+      "mean_token_accuracy": 0.7896397411823273,
+      "num_tokens": 4394973.0,
+      "step": 2150
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.6722971200942993,
+      "learning_rate": 7.963231908935798e-05,
+      "loss": 0.562,
+      "mean_token_accuracy": 0.7830882370471954,
+      "num_tokens": 4415453.0,
+      "step": 2160
+    },
+    {
+      "epoch": 3.3487654320987654,
+      "grad_norm": 0.8169707655906677,
+      "learning_rate": 7.942640813156759e-05,
+      "loss": 0.5478,
+      "mean_token_accuracy": 0.7895588159561158,
+      "num_tokens": 4435933.0,
+      "step": 2170
+    },
+    {
+      "epoch": 3.3641975308641974,
+      "grad_norm": 0.8726195096969604,
+      "learning_rate": 7.921973080317904e-05,
+      "loss": 0.5625,
+      "mean_token_accuracy": 0.7852952599525451,
+      "num_tokens": 4456169.0,
+      "step": 2180
+    },
+    {
+      "epoch": 3.3796296296296298,
+      "grad_norm": 0.6500533223152161,
+      "learning_rate": 7.901229248682096e-05,
+      "loss": 0.566,
+      "mean_token_accuracy": 0.7818627417087555,
+      "num_tokens": 4476649.0,
+      "step": 2190
+    },
+    {
+      "epoch": 3.3950617283950617,
+      "grad_norm": 0.7710484862327576,
+      "learning_rate": 7.880409858494094e-05,
+      "loss": 0.5685,
+      "mean_token_accuracy": 0.7819117665290832,
+      "num_tokens": 4497129.0,
+      "step": 2200
+    },
+    {
+      "epoch": 3.4104938271604937,
+      "grad_norm": 0.6623818874359131,
+      "learning_rate": 7.85951545196647e-05,
+      "loss": 0.5709,
+      "mean_token_accuracy": 0.7801470577716827,
+      "num_tokens": 4517609.0,
+      "step": 2210
+    },
+    {
+      "epoch": 3.425925925925926,
+      "grad_norm": 0.7120490074157715,
+      "learning_rate": 7.838546573265497e-05,
+      "loss": 0.5565,
+      "mean_token_accuracy": 0.7852450907230377,
+      "num_tokens": 4538089.0,
+      "step": 2220
+    },
+    {
+      "epoch": 3.441358024691358,
+      "grad_norm": 0.9274133443832397,
+      "learning_rate": 7.817503768496974e-05,
+      "loss": 0.5668,
+      "mean_token_accuracy": 0.7817646980285644,
+      "num_tokens": 4558569.0,
+      "step": 2230
+    },
+    {
+      "epoch": 3.45679012345679,
+      "grad_norm": 0.8062306642532349,
+      "learning_rate": 7.796387585692004e-05,
+      "loss": 0.5522,
+      "mean_token_accuracy": 0.7860867083072662,
+      "num_tokens": 4578994.0,
+      "step": 2240
+    },
+    {
+      "epoch": 3.4722222222222223,
+      "grad_norm": 0.8358902931213379,
+      "learning_rate": 7.775198574792718e-05,
+      "loss": 0.5534,
+      "mean_token_accuracy": 0.787307059764862,
+      "num_tokens": 4599312.0,
+      "step": 2250
+    },
+    {
+      "epoch": 3.4876543209876543,
+      "grad_norm": 0.8732607960700989,
+      "learning_rate": 7.753937287637958e-05,
+      "loss": 0.5472,
+      "mean_token_accuracy": 0.7882513642311096,
+      "num_tokens": 4619582.0,
+      "step": 2260
+    },
+    {
+      "epoch": 3.503086419753086,
+      "grad_norm": 0.6050688624382019,
+      "learning_rate": 7.7326042779489e-05,
+      "loss": 0.5766,
+      "mean_token_accuracy": 0.779313725233078,
+      "num_tokens": 4640062.0,
+      "step": 2270
+    },
+    {
+      "epoch": 3.5185185185185186,
+      "grad_norm": 0.9200652241706848,
+      "learning_rate": 7.71120010131464e-05,
+      "loss": 0.5784,
+      "mean_token_accuracy": 0.7790196061134338,
+      "num_tokens": 4660542.0,
+      "step": 2280
+    },
+    {
+      "epoch": 3.5339506172839505,
+      "grad_norm": 0.9094193577766418,
+      "learning_rate": 7.689725315177712e-05,
+      "loss": 0.5427,
+      "mean_token_accuracy": 0.792794120311737,
+      "num_tokens": 4681022.0,
+      "step": 2290
+    },
+    {
+      "epoch": 3.549382716049383,
+      "grad_norm": 0.9117602109909058,
+      "learning_rate": 7.668180478819586e-05,
+      "loss": 0.5589,
+      "mean_token_accuracy": 0.7852450966835022,
+      "num_tokens": 4701502.0,
+      "step": 2300
+    },
+    {
+      "epoch": 3.564814814814815,
+      "grad_norm": 0.729832649230957,
+      "learning_rate": 7.64656615334609e-05,
+      "loss": 0.5536,
+      "mean_token_accuracy": 0.7858333468437195,
+      "num_tokens": 4721982.0,
+      "step": 2310
+    },
+    {
+      "epoch": 3.580246913580247,
+      "grad_norm": 0.8236967921257019,
+      "learning_rate": 7.6248829016728e-05,
+      "loss": 0.5439,
+      "mean_token_accuracy": 0.7901470482349395,
+      "num_tokens": 4742462.0,
+      "step": 2320
+    },
+    {
+      "epoch": 3.5956790123456788,
+      "grad_norm": 0.8809945583343506,
+      "learning_rate": 7.603131288510388e-05,
+      "loss": 0.5744,
+      "mean_token_accuracy": 0.780735296010971,
+      "num_tokens": 4762942.0,
+      "step": 2330
+    },
+    {
+      "epoch": 3.611111111111111,
+      "grad_norm": 0.6941264271736145,
+      "learning_rate": 7.581311880349897e-05,
+      "loss": 0.5872,
+      "mean_token_accuracy": 0.7749509751796723,
+      "num_tokens": 4783422.0,
+      "step": 2340
+    },
+    {
+      "epoch": 3.626543209876543,
+      "grad_norm": 0.7171399593353271,
+      "learning_rate": 7.559425245448006e-05,
+      "loss": 0.5685,
+      "mean_token_accuracy": 0.7830882370471954,
+      "num_tokens": 4803902.0,
+      "step": 2350
+    },
+    {
+      "epoch": 3.6419753086419755,
+      "grad_norm": 0.8025734424591064,
+      "learning_rate": 7.537471953812219e-05,
+      "loss": 0.565,
+      "mean_token_accuracy": 0.7819117784500123,
+      "num_tokens": 4824382.0,
+      "step": 2360
+    },
+    {
+      "epoch": 3.6574074074074074,
+      "grad_norm": 0.9901085495948792,
+      "learning_rate": 7.515452577186025e-05,
+      "loss": 0.5723,
+      "mean_token_accuracy": 0.7785294115543365,
+      "num_tokens": 4844862.0,
+      "step": 2370
+    },
+    {
+      "epoch": 3.6728395061728394,
+      "grad_norm": 0.8292830586433411,
+      "learning_rate": 7.493367689034005e-05,
+      "loss": 0.5637,
+      "mean_token_accuracy": 0.7833333373069763,
+      "num_tokens": 4865342.0,
+      "step": 2380
+    },
+    {
+      "epoch": 3.6882716049382713,
+      "grad_norm": 0.5559194087982178,
+      "learning_rate": 7.471217864526901e-05,
+      "loss": 0.5538,
+      "mean_token_accuracy": 0.7873039305210113,
+      "num_tokens": 4885822.0,
+      "step": 2390
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 0.8278151750564575,
+      "learning_rate": 7.449003680526631e-05,
+      "loss": 0.5609,
+      "mean_token_accuracy": 0.7835294127464294,
+      "num_tokens": 4906302.0,
+      "step": 2400
+    },
+    {
+      "epoch": 3.7191358024691357,
+      "grad_norm": 0.6960305571556091,
+      "learning_rate": 7.426725715571268e-05,
+      "loss": 0.5504,
+      "mean_token_accuracy": 0.7883333384990692,
+      "num_tokens": 4926782.0,
+      "step": 2410
+    },
+    {
+      "epoch": 3.734567901234568,
+      "grad_norm": 0.9209804534912109,
+      "learning_rate": 7.404384549859976e-05,
+      "loss": 0.5549,
+      "mean_token_accuracy": 0.7867647111415863,
+      "num_tokens": 4947262.0,
+      "step": 2420
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.8905975222587585,
+      "learning_rate": 7.381980765237891e-05,
+      "loss": 0.5693,
+      "mean_token_accuracy": 0.7807202279567719,
+      "num_tokens": 4967492.0,
+      "step": 2430
+    },
+    {
+      "epoch": 3.765432098765432,
+      "grad_norm": 0.9563472867012024,
+      "learning_rate": 7.359514945180978e-05,
+      "loss": 0.5479,
+      "mean_token_accuracy": 0.7886764764785766,
+      "num_tokens": 4987972.0,
+      "step": 2440
+    },
+    {
+      "epoch": 3.7808641975308643,
+      "grad_norm": 0.7969064712524414,
+      "learning_rate": 7.336987674780826e-05,
+      "loss": 0.5488,
+      "mean_token_accuracy": 0.7896078526973724,
+      "num_tokens": 5008452.0,
+      "step": 2450
+    },
+    {
+      "epoch": 3.7962962962962963,
+      "grad_norm": 0.674056351184845,
+      "learning_rate": 7.31439954072942e-05,
+      "loss": 0.5366,
+      "mean_token_accuracy": 0.7947058856487275,
+      "num_tokens": 5028932.0,
+      "step": 2460
+    },
+    {
+      "epoch": 3.8117283950617287,
+      "grad_norm": 0.9035518765449524,
+      "learning_rate": 7.291751131303848e-05,
+      "loss": 0.5612,
+      "mean_token_accuracy": 0.7866176486015319,
+      "num_tokens": 5049412.0,
+      "step": 2470
+    },
+    {
+      "epoch": 3.8271604938271606,
+      "grad_norm": 0.7805877923965454,
+      "learning_rate": 7.269043036350995e-05,
+      "loss": 0.5638,
+      "mean_token_accuracy": 0.7820588171482086,
+      "num_tokens": 5069892.0,
+      "step": 2480
+    },
+    {
+      "epoch": 3.8425925925925926,
+      "grad_norm": 0.878677487373352,
+      "learning_rate": 7.246275847272168e-05,
+      "loss": 0.5748,
+      "mean_token_accuracy": 0.780075752735138,
+      "num_tokens": 5090312.0,
+      "step": 2490
+    },
+    {
+      "epoch": 3.8580246913580245,
+      "grad_norm": 0.6965935826301575,
+      "learning_rate": 7.223450157007706e-05,
+      "loss": 0.5472,
+      "mean_token_accuracy": 0.7878431439399719,
+      "num_tokens": 5110792.0,
+      "step": 2500
+    },
+    {
+      "epoch": 3.873456790123457,
+      "grad_norm": 0.8725903034210205,
+      "learning_rate": 7.200566560021524e-05,
+      "loss": 0.5757,
+      "mean_token_accuracy": 0.7792156875133515,
+      "num_tokens": 5131272.0,
+      "step": 2510
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.7333084344863892,
+      "learning_rate": 7.177625652285646e-05,
+      "loss": 0.562,
+      "mean_token_accuracy": 0.782549011707306,
+      "num_tokens": 5151752.0,
+      "step": 2520
+    },
+    {
+      "epoch": 3.9043209876543212,
+      "grad_norm": 0.9415791034698486,
+      "learning_rate": 7.154628031264672e-05,
+      "loss": 0.5692,
+      "mean_token_accuracy": 0.7809313774108887,
+      "num_tokens": 5172232.0,
+      "step": 2530
+    },
+    {
+      "epoch": 3.919753086419753,
+      "grad_norm": 0.8967316150665283,
+      "learning_rate": 7.131574295900221e-05,
+      "loss": 0.5748,
+      "mean_token_accuracy": 0.7786274552345276,
+      "num_tokens": 5192712.0,
+      "step": 2540
+    },
+    {
+      "epoch": 3.935185185185185,
+      "grad_norm": 0.9939439296722412,
+      "learning_rate": 7.108465046595336e-05,
+      "loss": 0.5538,
+      "mean_token_accuracy": 0.7898039281368255,
+      "num_tokens": 5213192.0,
+      "step": 2550
+    },
+    {
+      "epoch": 3.950617283950617,
+      "grad_norm": 0.8223277926445007,
+      "learning_rate": 7.085300885198846e-05,
+      "loss": 0.5642,
+      "mean_token_accuracy": 0.783627450466156,
+      "num_tokens": 5233672.0,
+      "step": 2560
+    },
+    {
+      "epoch": 3.9660493827160495,
+      "grad_norm": 1.1580294370651245,
+      "learning_rate": 7.062082414989684e-05,
+      "loss": 0.572,
+      "mean_token_accuracy": 0.7798039197921753,
+      "num_tokens": 5254152.0,
+      "step": 2570
+    },
+    {
+      "epoch": 3.9814814814814814,
+      "grad_norm": 0.8286728858947754,
+      "learning_rate": 7.03881024066119e-05,
+      "loss": 0.564,
+      "mean_token_accuracy": 0.7822549045085907,
+      "num_tokens": 5274632.0,
+      "step": 2580
+    },
+    {
+      "epoch": 3.996913580246914,
+      "grad_norm": 0.9579570889472961,
+      "learning_rate": 7.015484968305348e-05,
+      "loss": 0.5685,
+      "mean_token_accuracy": 0.7816666662693024,
+      "num_tokens": 5295112.0,
+      "step": 2590
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6529332399368286,
+      "eval_mean_token_accuracy": 0.754736157024608,
+      "eval_num_tokens": 5297928.0,
+      "eval_runtime": 3.2039,
+      "eval_samples_per_second": 84.585,
+      "eval_steps_per_second": 10.612,
+      "step": 2592
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 2.2562780206753382e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-2592/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a34050fa79a936184e915a7880fc5b9f49db5f1fd1d762599d612766499101
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3240/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 0.19.1

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3240/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "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,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3240/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36a25af55ef1a568965440d76840925b10c35b352472fb4c761117aa822f1de5
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3240/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3240/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3240/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_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3240/tokenizer.json

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