add checkpoint cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast_vs0p05

.gitattributes

@@ -303,3 +303,14 @@ checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast_vs0
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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_s2_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_s3_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_s3_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_s3_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_s3_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_s3_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_s3_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_s3_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_s3_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_s3_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_s3_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_s3_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_s3_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_s3_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": [
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "down_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_s3_vt_project_a1_ALL_bcast_vs0p05/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38af6a611123606c384bfa9e300f1fff42138c539fd1b0a92925854285ce3dfe
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_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_s3_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_s3_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_s3_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": [
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "down_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_s3_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1296/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:132fd455b1f616098ee135ef5364490725a4ee049ac2593f1b948419f856bf66
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_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_s3_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_s3_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_s3_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_s3_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_s3_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": 3.6007630825042725,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 2.4489,
+      "mean_token_accuracy": 0.545343142747879,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.030864197530864196,
+      "grad_norm": 3.805405616760254,
+      "learning_rate": 5.864197530864198e-06,
+      "loss": 2.459,
+      "mean_token_accuracy": 0.5510784387588501,
+      "num_tokens": 40960.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.046296296296296294,
+      "grad_norm": 3.528644561767578,
+      "learning_rate": 8.950617283950618e-06,
+      "loss": 2.316,
+      "mean_token_accuracy": 0.552549022436142,
+      "num_tokens": 61440.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.06172839506172839,
+      "grad_norm": 2.193250894546509,
+      "learning_rate": 1.2037037037037037e-05,
+      "loss": 2.0378,
+      "mean_token_accuracy": 0.5757352948188782,
+      "num_tokens": 81920.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07716049382716049,
+      "grad_norm": 1.3338465690612793,
+      "learning_rate": 1.5123456790123458e-05,
+      "loss": 1.7238,
+      "mean_token_accuracy": 0.6038235306739808,
+      "num_tokens": 102400.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.09259259259259259,
+      "grad_norm": 1.1486477851867676,
+      "learning_rate": 1.8209876543209877e-05,
+      "loss": 1.5441,
+      "mean_token_accuracy": 0.6099999904632568,
+      "num_tokens": 122880.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.10802469135802469,
+      "grad_norm": 0.8821588754653931,
+      "learning_rate": 2.1296296296296296e-05,
+      "loss": 1.3521,
+      "mean_token_accuracy": 0.6251470565795898,
+      "num_tokens": 143360.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 0.8657292127609253,
+      "learning_rate": 2.438271604938272e-05,
+      "loss": 1.1704,
+      "mean_token_accuracy": 0.6537254929542542,
+      "num_tokens": 163840.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 0.9481641054153442,
+      "learning_rate": 2.7469135802469138e-05,
+      "loss": 1.0164,
+      "mean_token_accuracy": 0.6796568512916565,
+      "num_tokens": 184320.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.15432098765432098,
+      "grad_norm": 1.2989270687103271,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.884,
+      "mean_token_accuracy": 0.6988235294818879,
+      "num_tokens": 204800.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.1697530864197531,
+      "grad_norm": 1.1443800926208496,
+      "learning_rate": 3.364197530864198e-05,
+      "loss": 0.8079,
+      "mean_token_accuracy": 0.714607834815979,
+      "num_tokens": 225280.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 1.2093029022216797,
+      "learning_rate": 3.67283950617284e-05,
+      "loss": 0.7537,
+      "mean_token_accuracy": 0.72377450466156,
+      "num_tokens": 245760.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.2006172839506173,
+      "grad_norm": 1.331242322921753,
+      "learning_rate": 3.981481481481482e-05,
+      "loss": 0.7422,
+      "mean_token_accuracy": 0.7294607698917389,
+      "num_tokens": 266240.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.21604938271604937,
+      "grad_norm": 0.9259920716285706,
+      "learning_rate": 4.290123456790124e-05,
+      "loss": 0.703,
+      "mean_token_accuracy": 0.7436274468898774,
+      "num_tokens": 286720.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.23148148148148148,
+      "grad_norm": 0.9903554916381836,
+      "learning_rate": 4.5987654320987656e-05,
+      "loss": 0.7163,
+      "mean_token_accuracy": 0.7358464896678925,
+      "num_tokens": 307186.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 1.0001420974731445,
+      "learning_rate": 4.9074074074074075e-05,
+      "loss": 0.6759,
+      "mean_token_accuracy": 0.74779412150383,
+      "num_tokens": 327666.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.2623456790123457,
+      "grad_norm": 0.9456067681312561,
+      "learning_rate": 5.2160493827160494e-05,
+      "loss": 0.6704,
+      "mean_token_accuracy": 0.749215692281723,
+      "num_tokens": 348146.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.9336047172546387,
+      "learning_rate": 5.524691358024692e-05,
+      "loss": 0.6819,
+      "mean_token_accuracy": 0.74717418551445,
+      "num_tokens": 368183.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2932098765432099,
+      "grad_norm": 0.8091706037521362,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 0.6813,
+      "mean_token_accuracy": 0.7489705979824066,
+      "num_tokens": 388663.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.30864197530864196,
+      "grad_norm": 0.9524596333503723,
+      "learning_rate": 6.141975308641975e-05,
+      "loss": 0.6931,
+      "mean_token_accuracy": 0.7397548913955688,
+      "num_tokens": 409143.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.32407407407407407,
+      "grad_norm": 0.7895946502685547,
+      "learning_rate": 6.450617283950617e-05,
+      "loss": 0.6662,
+      "mean_token_accuracy": 0.7475000023841858,
+      "num_tokens": 429623.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3395061728395062,
+      "grad_norm": 0.7409709692001343,
+      "learning_rate": 6.759259259259259e-05,
+      "loss": 0.6806,
+      "mean_token_accuracy": 0.7402451038360596,
+      "num_tokens": 450103.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.3549382716049383,
+      "grad_norm": 0.8331234455108643,
+      "learning_rate": 7.067901234567902e-05,
+      "loss": 0.6636,
+      "mean_token_accuracy": 0.7479411721229553,
+      "num_tokens": 470583.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.7722135186195374,
+      "learning_rate": 7.376543209876543e-05,
+      "loss": 0.6731,
+      "mean_token_accuracy": 0.7467647016048431,
+      "num_tokens": 491063.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.38580246913580246,
+      "grad_norm": 0.7308498620986938,
+      "learning_rate": 7.685185185185185e-05,
+      "loss": 0.649,
+      "mean_token_accuracy": 0.7547548949718476,
+      "num_tokens": 511543.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4012345679012346,
+      "grad_norm": 0.7666990756988525,
+      "learning_rate": 7.993827160493828e-05,
+      "loss": 0.6445,
+      "mean_token_accuracy": 0.7559313774108887,
+      "num_tokens": 532023.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 3.0780324935913086,
+      "learning_rate": 8.30246913580247e-05,
+      "loss": 0.6471,
+      "mean_token_accuracy": 0.7554901897907257,
+      "num_tokens": 552503.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.43209876543209874,
+      "grad_norm": 0.7734149098396301,
+      "learning_rate": 8.611111111111112e-05,
+      "loss": 0.6681,
+      "mean_token_accuracy": 0.7451470553874969,
+      "num_tokens": 572983.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.44753086419753085,
+      "grad_norm": 0.7692375779151917,
+      "learning_rate": 8.919753086419754e-05,
+      "loss": 0.6389,
+      "mean_token_accuracy": 0.7571078419685364,
+      "num_tokens": 593463.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 0.6887214183807373,
+      "learning_rate": 9.228395061728396e-05,
+      "loss": 0.64,
+      "mean_token_accuracy": 0.7574509978294373,
+      "num_tokens": 613943.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.4783950617283951,
+      "grad_norm": 0.6372818350791931,
+      "learning_rate": 9.537037037037038e-05,
+      "loss": 0.6737,
+      "mean_token_accuracy": 0.7460294246673584,
+      "num_tokens": 634423.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.5355892181396484,
+      "learning_rate": 9.84567901234568e-05,
+      "loss": 0.6352,
+      "mean_token_accuracy": 0.7594117641448974,
+      "num_tokens": 654903.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.5092592592592593,
+      "grad_norm": 0.5700058341026306,
+      "learning_rate": 9.999983722702365e-05,
+      "loss": 0.6627,
+      "mean_token_accuracy": 0.7510294139385223,
+      "num_tokens": 675383.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.5246913580246914,
+      "grad_norm": 0.6579382419586182,
+      "learning_rate": 9.999853504957158e-05,
+      "loss": 0.658,
+      "mean_token_accuracy": 0.7504901885986328,
+      "num_tokens": 695863.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5401234567901234,
+      "grad_norm": 1.066748857498169,
+      "learning_rate": 9.999593072858088e-05,
+      "loss": 0.6584,
+      "mean_token_accuracy": 0.7481862723827362,
+      "num_tokens": 716343.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.64486163854599,
+      "learning_rate": 9.999202433187755e-05,
+      "loss": 0.6428,
+      "mean_token_accuracy": 0.7542156755924225,
+      "num_tokens": 736823.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5709876543209876,
+      "grad_norm": 0.5809119343757629,
+      "learning_rate": 9.998681596119832e-05,
+      "loss": 0.6419,
+      "mean_token_accuracy": 0.7581372559070587,
+      "num_tokens": 757303.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5864197530864198,
+      "grad_norm": 0.6756792664527893,
+      "learning_rate": 9.998030575218811e-05,
+      "loss": 0.6587,
+      "mean_token_accuracy": 0.7491666674613953,
+      "num_tokens": 777783.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.6018518518518519,
+      "grad_norm": 0.6183996200561523,
+      "learning_rate": 9.997249387439643e-05,
+      "loss": 0.6564,
+      "mean_token_accuracy": 0.7498529434204102,
+      "num_tokens": 798263.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 0.6571487188339233,
+      "learning_rate": 9.996338053127292e-05,
+      "loss": 0.6421,
+      "mean_token_accuracy": 0.7550490319728851,
+      "num_tokens": 818743.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6327160493827161,
+      "grad_norm": 0.5952710509300232,
+      "learning_rate": 9.99529659601622e-05,
+      "loss": 0.6407,
+      "mean_token_accuracy": 0.7562768697738648,
+      "num_tokens": 839060.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6481481481481481,
+      "grad_norm": 0.6446591019630432,
+      "learning_rate": 9.994125043229752e-05,
+      "loss": 0.6629,
+      "mean_token_accuracy": 0.7474573612213135,
+      "num_tokens": 859348.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.6635802469135802,
+      "grad_norm": 0.5634035468101501,
+      "learning_rate": 9.992823425279382e-05,
+      "loss": 0.6698,
+      "mean_token_accuracy": 0.7462254941463471,
+      "num_tokens": 879828.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6790123456790124,
+      "grad_norm": 0.5095203518867493,
+      "learning_rate": 9.991391776063969e-05,
+      "loss": 0.6354,
+      "mean_token_accuracy": 0.7562745034694671,
+      "num_tokens": 900308.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 0.5076797604560852,
+      "learning_rate": 9.98983013286886e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7629901945590973,
+      "num_tokens": 920788.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.7098765432098766,
+      "grad_norm": 0.5497986674308777,
+      "learning_rate": 9.988138536364922e-05,
+      "loss": 0.6377,
+      "mean_token_accuracy": 0.7544117629528045,
+      "num_tokens": 941268.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.7253086419753086,
+      "grad_norm": 1.2844603061676025,
+      "learning_rate": 9.986317030607475e-05,
+      "loss": 0.6398,
+      "mean_token_accuracy": 0.7575523376464843,
+      "num_tokens": 961506.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.6091906428337097,
+      "learning_rate": 9.984365663035144e-05,
+      "loss": 0.6354,
+      "mean_token_accuracy": 0.7583116114139556,
+      "num_tokens": 981828.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.7561728395061729,
+      "grad_norm": 0.6552985310554504,
+      "learning_rate": 9.982284484468634e-05,
+      "loss": 0.6464,
+      "mean_token_accuracy": 0.7523039221763611,
+      "num_tokens": 1002308.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7716049382716049,
+      "grad_norm": 0.5882002711296082,
+      "learning_rate": 9.980073549109397e-05,
+      "loss": 0.6491,
+      "mean_token_accuracy": 0.7498039245605469,
+      "num_tokens": 1022788.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.7870370370370371,
+      "grad_norm": 0.5321325659751892,
+      "learning_rate": 9.977732914538225e-05,
+      "loss": 0.6701,
+      "mean_token_accuracy": 0.7467647016048431,
+      "num_tokens": 1043268.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.8024691358024691,
+      "grad_norm": 0.5049220323562622,
+      "learning_rate": 9.975262641713746e-05,
+      "loss": 0.6191,
+      "mean_token_accuracy": 0.7627941250801087,
+      "num_tokens": 1063748.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.8179012345679012,
+      "grad_norm": 0.5200943350791931,
+      "learning_rate": 9.972662794970841e-05,
+      "loss": 0.6553,
+      "mean_token_accuracy": 0.7466912567615509,
+      "num_tokens": 1084157.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.5618262887001038,
+      "learning_rate": 9.969933442018968e-05,
+      "loss": 0.6306,
+      "mean_token_accuracy": 0.7603431344032288,
+      "num_tokens": 1104637.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8487654320987654,
+      "grad_norm": 0.5275453925132751,
+      "learning_rate": 9.967074653940396e-05,
+      "loss": 0.6494,
+      "mean_token_accuracy": 0.7516666710376739,
+      "num_tokens": 1125117.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 0.5133753418922424,
+      "learning_rate": 9.964086505188352e-05,
+      "loss": 0.65,
+      "mean_token_accuracy": 0.750441175699234,
+      "num_tokens": 1145597.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8796296296296297,
+      "grad_norm": 0.5613871216773987,
+      "learning_rate": 9.960969073585091e-05,
+      "loss": 0.6355,
+      "mean_token_accuracy": 0.7533183455467224,
+      "num_tokens": 1165967.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8950617283950617,
+      "grad_norm": 0.5650666356086731,
+      "learning_rate": 9.95772244031986e-05,
+      "loss": 0.6467,
+      "mean_token_accuracy": 0.7557352900505065,
+      "num_tokens": 1186447.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.9104938271604939,
+      "grad_norm": 0.561585545539856,
+      "learning_rate": 9.954346689946785e-05,
+      "loss": 0.6498,
+      "mean_token_accuracy": 0.7523529589176178,
+      "num_tokens": 1206927.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 0.5113793611526489,
+      "learning_rate": 9.950841910382675e-05,
+      "loss": 0.6341,
+      "mean_token_accuracy": 0.754411768913269,
+      "num_tokens": 1227407.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.941358024691358,
+      "grad_norm": 0.9459167718887329,
+      "learning_rate": 9.947208192904722e-05,
+      "loss": 0.6166,
+      "mean_token_accuracy": 0.7633333384990693,
+      "num_tokens": 1247887.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9567901234567902,
+      "grad_norm": 0.597134530544281,
+      "learning_rate": 9.943445632148138e-05,
+      "loss": 0.645,
+      "mean_token_accuracy": 0.7527450978755951,
+      "num_tokens": 1268367.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 0.5343972444534302,
+      "learning_rate": 9.939554326103673e-05,
+      "loss": 0.6568,
+      "mean_token_accuracy": 0.750702977180481,
+      "num_tokens": 1288718.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.65065598487854,
+      "learning_rate": 9.935534376115081e-05,
+      "loss": 0.6301,
+      "mean_token_accuracy": 0.7587254881858826,
+      "num_tokens": 1309198.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6486101150512695,
+      "eval_mean_token_accuracy": 0.7533365641321454,
+      "eval_num_tokens": 1324046.0,
+      "eval_runtime": 3.2793,
+      "eval_samples_per_second": 83.25,
+      "eval_steps_per_second": 10.673,
+      "step": 648
+    },
+    {
+      "epoch": 1.0030864197530864,
+      "grad_norm": 0.5726727843284607,
+      "learning_rate": 9.931385886876466e-05,
+      "loss": 0.6319,
+      "mean_token_accuracy": 0.7595588207244873,
+      "num_tokens": 1328142.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.0185185185185186,
+      "grad_norm": 0.5349597930908203,
+      "learning_rate": 9.927108966429559e-05,
+      "loss": 0.6239,
+      "mean_token_accuracy": 0.7619932591915131,
+      "num_tokens": 1348608.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.0339506172839505,
+      "grad_norm": 0.49260857701301575,
+      "learning_rate": 9.922703726160915e-05,
+      "loss": 0.6138,
+      "mean_token_accuracy": 0.7632843136787415,
+      "num_tokens": 1369088.0,
+      "step": 670
+    },
+    {
+      "epoch": 1.0493827160493827,
+      "grad_norm": 0.5338084101676941,
+      "learning_rate": 9.918170280798997e-05,
+      "loss": 0.5942,
+      "mean_token_accuracy": 0.7736764788627625,
+      "num_tokens": 1389568.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.0648148148148149,
+      "grad_norm": 0.5764300227165222,
+      "learning_rate": 9.913508748411195e-05,
+      "loss": 0.6377,
+      "mean_token_accuracy": 0.7587645888328552,
+      "num_tokens": 1409806.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0802469135802468,
+      "grad_norm": 0.6294172406196594,
+      "learning_rate": 9.908719250400751e-05,
+      "loss": 0.604,
+      "mean_token_accuracy": 0.76813725233078,
+      "num_tokens": 1430286.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.095679012345679,
+      "grad_norm": 0.47793206572532654,
+      "learning_rate": 9.903801911503601e-05,
+      "loss": 0.6144,
+      "mean_token_accuracy": 0.7648529410362244,
+      "num_tokens": 1450766.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.5677058100700378,
+      "learning_rate": 9.898756859785114e-05,
+      "loss": 0.6314,
+      "mean_token_accuracy": 0.7551960706710815,
+      "num_tokens": 1471246.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.126543209876543,
+      "grad_norm": 0.6503554582595825,
+      "learning_rate": 9.893584226636772e-05,
+      "loss": 0.6315,
+      "mean_token_accuracy": 0.7578431308269501,
+      "num_tokens": 1491726.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.1419753086419753,
+      "grad_norm": 0.5785447359085083,
+      "learning_rate": 9.88828414677274e-05,
+      "loss": 0.6228,
+      "mean_token_accuracy": 0.7625000059604645,
+      "num_tokens": 1512206.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.1574074074074074,
+      "grad_norm": 0.5160046219825745,
+      "learning_rate": 9.882856758226355e-05,
+      "loss": 0.6376,
+      "mean_token_accuracy": 0.7573529422283173,
+      "num_tokens": 1532686.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1728395061728394,
+      "grad_norm": 0.5226278901100159,
+      "learning_rate": 9.877302202346537e-05,
+      "loss": 0.629,
+      "mean_token_accuracy": 0.7597683548927308,
+      "num_tokens": 1553003.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.1882716049382716,
+      "grad_norm": 0.6244763135910034,
+      "learning_rate": 9.871620623794107e-05,
+      "loss": 0.6209,
+      "mean_token_accuracy": 0.7606293797492981,
+      "num_tokens": 1573373.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.2037037037037037,
+      "grad_norm": 0.5300543308258057,
+      "learning_rate": 9.865812170538014e-05,
+      "loss": 0.6192,
+      "mean_token_accuracy": 0.7636764764785766,
+      "num_tokens": 1593853.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.2191358024691359,
+      "grad_norm": 0.49504250288009644,
+      "learning_rate": 9.859876993851489e-05,
+      "loss": 0.62,
+      "mean_token_accuracy": 0.7620588302612304,
+      "num_tokens": 1614333.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 0.5028163194656372,
+      "learning_rate": 9.853815248308101e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7628921627998352,
+      "num_tokens": 1634813.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.6196873188018799,
+      "learning_rate": 9.847627091777729e-05,
+      "loss": 0.6175,
+      "mean_token_accuracy": 0.7640686273574829,
+      "num_tokens": 1655293.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2654320987654322,
+      "grad_norm": 0.5531455874443054,
+      "learning_rate": 9.841312685422459e-05,
+      "loss": 0.626,
+      "mean_token_accuracy": 0.7602941274642945,
+      "num_tokens": 1675773.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.2808641975308643,
+      "grad_norm": 0.5736854672431946,
+      "learning_rate": 9.834872193692378e-05,
+      "loss": 0.6288,
+      "mean_token_accuracy": 0.7607352912425995,
+      "num_tokens": 1696253.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.4806568920612335,
+      "learning_rate": 9.828305784321289e-05,
+      "loss": 0.617,
+      "mean_token_accuracy": 0.7647548973560333,
+      "num_tokens": 1716733.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.3117283950617284,
+      "grad_norm": 0.8750804662704468,
+      "learning_rate": 9.821613628322358e-05,
+      "loss": 0.6332,
+      "mean_token_accuracy": 0.7572058856487274,
+      "num_tokens": 1737213.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.3271604938271606,
+      "grad_norm": 0.5364664196968079,
+      "learning_rate": 9.814795899983645e-05,
+      "loss": 0.6272,
+      "mean_token_accuracy": 0.7589215755462646,
+      "num_tokens": 1757693.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.3425925925925926,
+      "grad_norm": 0.5509020090103149,
+      "learning_rate": 9.807852776863568e-05,
+      "loss": 0.6239,
+      "mean_token_accuracy": 0.7589388906955719,
+      "num_tokens": 1777803.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.3580246913580247,
+      "grad_norm": 0.6213059425354004,
+      "learning_rate": 9.800784439786286e-05,
+      "loss": 0.6425,
+      "mean_token_accuracy": 0.750441175699234,
+      "num_tokens": 1798283.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.373456790123457,
+      "grad_norm": 0.5405688881874084,
+      "learning_rate": 9.793591072836978e-05,
+      "loss": 0.6216,
+      "mean_token_accuracy": 0.7597058892250061,
+      "num_tokens": 1818763.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 0.6881203055381775,
+      "learning_rate": 9.786272863357063e-05,
+      "loss": 0.6242,
+      "mean_token_accuracy": 0.7628431379795074,
+      "num_tokens": 1839243.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.404320987654321,
+      "grad_norm": 0.48711517453193665,
+      "learning_rate": 9.778830001939307e-05,
+      "loss": 0.6287,
+      "mean_token_accuracy": 0.759411770105362,
+      "num_tokens": 1859723.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.4197530864197532,
+      "grad_norm": 0.5363081097602844,
+      "learning_rate": 9.771262682422866e-05,
+      "loss": 0.63,
+      "mean_token_accuracy": 0.7583823561668396,
+      "num_tokens": 1880203.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.4351851851851851,
+      "grad_norm": 0.5898856520652771,
+      "learning_rate": 9.76357110188824e-05,
+      "loss": 0.6266,
+      "mean_token_accuracy": 0.7604411780834198,
+      "num_tokens": 1900683.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.4506172839506173,
+      "grad_norm": 0.5043850541114807,
+      "learning_rate": 9.755755460652137e-05,
+      "loss": 0.6011,
+      "mean_token_accuracy": 0.7688725531101227,
+      "num_tokens": 1921163.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.4660493827160495,
+      "grad_norm": 0.5246235132217407,
+      "learning_rate": 9.747815962262255e-05,
+      "loss": 0.6339,
+      "mean_token_accuracy": 0.7562745153903961,
+      "num_tokens": 1941643.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.5146046280860901,
+      "learning_rate": 9.73975281349198e-05,
+      "loss": 0.6269,
+      "mean_token_accuracy": 0.7591666638851166,
+      "num_tokens": 1962123.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4969135802469136,
+      "grad_norm": 0.5631639957427979,
+      "learning_rate": 9.73156622433501e-05,
+      "loss": 0.6384,
+      "mean_token_accuracy": 0.7557843148708343,
+      "num_tokens": 1982603.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.5123456790123457,
+      "grad_norm": 0.7671029567718506,
+      "learning_rate": 9.72325640799987e-05,
+      "loss": 0.6336,
+      "mean_token_accuracy": 0.7575490176677704,
+      "num_tokens": 2003083.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.5277777777777777,
+      "grad_norm": 0.5891373753547668,
+      "learning_rate": 9.71482358090438e-05,
+      "loss": 0.6412,
+      "mean_token_accuracy": 0.7533718824386597,
+      "num_tokens": 2023405.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.5432098765432098,
+      "grad_norm": 0.5099619030952454,
+      "learning_rate": 9.706267962669998e-05,
+      "loss": 0.6181,
+      "mean_token_accuracy": 0.7599019527435302,
+      "num_tokens": 2043885.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.558641975308642,
+      "grad_norm": 0.6285778880119324,
+      "learning_rate": 9.697589776116113e-05,
+      "loss": 0.618,
+      "mean_token_accuracy": 0.7612245142459869,
+      "num_tokens": 2064294.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.574074074074074,
+      "grad_norm": 0.5334492921829224,
+      "learning_rate": 9.688789247254237e-05,
+      "loss": 0.6331,
+      "mean_token_accuracy": 0.7553921639919281,
+      "num_tokens": 2084774.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5895061728395061,
+      "grad_norm": 0.6230431795120239,
+      "learning_rate": 9.679866605282122e-05,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.7686274588108063,
+      "num_tokens": 2105254.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6049382716049383,
+      "grad_norm": 0.560792863368988,
+      "learning_rate": 9.670822082577787e-05,
+      "loss": 0.622,
+      "mean_token_accuracy": 0.7606372594833374,
+      "num_tokens": 2125734.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6203703703703702,
+      "grad_norm": 0.5316160321235657,
+      "learning_rate": 9.661655914693471e-05,
+      "loss": 0.6215,
+      "mean_token_accuracy": 0.7624019622802735,
+      "num_tokens": 2146214.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6358024691358026,
+      "grad_norm": 0.5584502220153809,
+      "learning_rate": 9.652368340349494e-05,
+      "loss": 0.6274,
+      "mean_token_accuracy": 0.7590196132659912,
+      "num_tokens": 2166694.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.6512345679012346,
+      "grad_norm": 0.4828554391860962,
+      "learning_rate": 9.642959601428039e-05,
+      "loss": 0.62,
+      "mean_token_accuracy": 0.7612745046615601,
+      "num_tokens": 2187174.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.5727825164794922,
+      "learning_rate": 9.63342994296686e-05,
+      "loss": 0.6071,
+      "mean_token_accuracy": 0.7662254869937897,
+      "num_tokens": 2207654.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.682098765432099,
+      "grad_norm": 0.5390017032623291,
+      "learning_rate": 9.623779613152893e-05,
+      "loss": 0.6179,
+      "mean_token_accuracy": 0.764607846736908,
+      "num_tokens": 2228134.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6975308641975309,
+      "grad_norm": 0.5654057860374451,
+      "learning_rate": 9.614008863315789e-05,
+      "loss": 0.6068,
+      "mean_token_accuracy": 0.7667545199394226,
+      "num_tokens": 2248422.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7129629629629628,
+      "grad_norm": 0.565568208694458,
+      "learning_rate": 9.604117947921385e-05,
+      "loss": 0.6143,
+      "mean_token_accuracy": 0.7654411792755127,
+      "num_tokens": 2268902.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7283950617283952,
+      "grad_norm": 0.5519742369651794,
+      "learning_rate": 9.594107124565056e-05,
+      "loss": 0.6088,
+      "mean_token_accuracy": 0.7641176581382751,
+      "num_tokens": 2289382.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7438271604938271,
+      "grad_norm": 0.4558942914009094,
+      "learning_rate": 9.58397665396502e-05,
+      "loss": 0.6176,
+      "mean_token_accuracy": 0.7602451086044312,
+      "num_tokens": 2309862.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.7592592592592593,
+      "grad_norm": 0.5886722803115845,
+      "learning_rate": 9.573726799955544e-05,
+      "loss": 0.6081,
+      "mean_token_accuracy": 0.7652941167354583,
+      "num_tokens": 2330342.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7746913580246915,
+      "grad_norm": 0.5108247995376587,
+      "learning_rate": 9.563357829480076e-05,
+      "loss": 0.6278,
+      "mean_token_accuracy": 0.7587745070457459,
+      "num_tokens": 2350822.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7901234567901234,
+      "grad_norm": 0.6499772071838379,
+      "learning_rate": 9.552870012584282e-05,
+      "loss": 0.6137,
+      "mean_token_accuracy": 0.7662254869937897,
+      "num_tokens": 2371302.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8055555555555556,
+      "grad_norm": 0.5412532091140747,
+      "learning_rate": 9.542263622409027e-05,
+      "loss": 0.6159,
+      "mean_token_accuracy": 0.7634241282939911,
+      "num_tokens": 2391580.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.8209876543209877,
+      "grad_norm": 0.538313090801239,
+      "learning_rate": 9.53153893518325e-05,
+      "loss": 0.6332,
+      "mean_token_accuracy": 0.7576960802078248,
+      "num_tokens": 2412060.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.8364197530864197,
+      "grad_norm": 0.6328610777854919,
+      "learning_rate": 9.520696230216781e-05,
+      "loss": 0.6246,
+      "mean_token_accuracy": 0.759950977563858,
+      "num_tokens": 2432540.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.5538372993469238,
+      "learning_rate": 9.509735789893059e-05,
+      "loss": 0.6197,
+      "mean_token_accuracy": 0.7624509751796722,
+      "num_tokens": 2453020.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.867283950617284,
+      "grad_norm": 0.555073618888855,
+      "learning_rate": 9.498657899661774e-05,
+      "loss": 0.6224,
+      "mean_token_accuracy": 0.7595588207244873,
+      "num_tokens": 2473500.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.882716049382716,
+      "grad_norm": 0.5462023019790649,
+      "learning_rate": 9.487462848031445e-05,
+      "loss": 0.6193,
+      "mean_token_accuracy": 0.7641176462173462,
+      "num_tokens": 2493980.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8981481481481481,
+      "grad_norm": 0.5492093563079834,
+      "learning_rate": 9.4761509265619e-05,
+      "loss": 0.6376,
+      "mean_token_accuracy": 0.7553431332111359,
+      "num_tokens": 2514460.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.9135802469135803,
+      "grad_norm": 0.5266892313957214,
+      "learning_rate": 9.464722429856674e-05,
+      "loss": 0.6163,
+      "mean_token_accuracy": 0.7632352948188782,
+      "num_tokens": 2534940.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.9290123456790123,
+      "grad_norm": 0.6665803790092468,
+      "learning_rate": 9.453177655555355e-05,
+      "loss": 0.6196,
+      "mean_token_accuracy": 0.7636274516582489,
+      "num_tokens": 2555420.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 0.567834734916687,
+      "learning_rate": 9.441516904325816e-05,
+      "loss": 0.622,
+      "mean_token_accuracy": 0.7607352912425995,
+      "num_tokens": 2575900.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.9598765432098766,
+      "grad_norm": 0.512845516204834,
+      "learning_rate": 9.42974047985639e-05,
+      "loss": 0.6248,
+      "mean_token_accuracy": 0.7564705908298492,
+      "num_tokens": 2596380.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.5521799921989441,
+      "learning_rate": 9.417848688847968e-05,
+      "loss": 0.6143,
+      "mean_token_accuracy": 0.7628431499004364,
+      "num_tokens": 2616860.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.9907407407407407,
+      "grad_norm": 0.47973841428756714,
+      "learning_rate": 9.405841841005998e-05,
+      "loss": 0.6087,
+      "mean_token_accuracy": 0.7673039317131043,
+      "num_tokens": 2637340.0,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6432122588157654,
+      "eval_mean_token_accuracy": 0.756913377557482,
+      "eval_num_tokens": 2648092.0,
+      "eval_runtime": 3.2747,
+      "eval_samples_per_second": 83.367,
+      "eval_steps_per_second": 10.688,
+      "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": 1.1279211808319078e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_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:ee630d3a769f8f4b4dcc99c709324068f5e26341c6ce13597153a1b7c73d3414
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_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_s3_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": [
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "down_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_s3_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1944/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09d8e26ed84e80f9bf9e806f62d41a58c8798a264287ba0a1b3c169bb55ed340
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_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_s3_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_s3_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_s3_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_s3_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_s3_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": 3.6007630825042725,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 2.4489,
+      "mean_token_accuracy": 0.545343142747879,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.030864197530864196,
+      "grad_norm": 3.805405616760254,
+      "learning_rate": 5.864197530864198e-06,
+      "loss": 2.459,
+      "mean_token_accuracy": 0.5510784387588501,
+      "num_tokens": 40960.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.046296296296296294,
+      "grad_norm": 3.528644561767578,
+      "learning_rate": 8.950617283950618e-06,
+      "loss": 2.316,
+      "mean_token_accuracy": 0.552549022436142,
+      "num_tokens": 61440.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.06172839506172839,
+      "grad_norm": 2.193250894546509,
+      "learning_rate": 1.2037037037037037e-05,
+      "loss": 2.0378,
+      "mean_token_accuracy": 0.5757352948188782,
+      "num_tokens": 81920.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07716049382716049,
+      "grad_norm": 1.3338465690612793,
+      "learning_rate": 1.5123456790123458e-05,
+      "loss": 1.7238,
+      "mean_token_accuracy": 0.6038235306739808,
+      "num_tokens": 102400.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.09259259259259259,
+      "grad_norm": 1.1486477851867676,
+      "learning_rate": 1.8209876543209877e-05,
+      "loss": 1.5441,
+      "mean_token_accuracy": 0.6099999904632568,
+      "num_tokens": 122880.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.10802469135802469,
+      "grad_norm": 0.8821588754653931,
+      "learning_rate": 2.1296296296296296e-05,
+      "loss": 1.3521,
+      "mean_token_accuracy": 0.6251470565795898,
+      "num_tokens": 143360.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 0.8657292127609253,
+      "learning_rate": 2.438271604938272e-05,
+      "loss": 1.1704,
+      "mean_token_accuracy": 0.6537254929542542,
+      "num_tokens": 163840.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 0.9481641054153442,
+      "learning_rate": 2.7469135802469138e-05,
+      "loss": 1.0164,
+      "mean_token_accuracy": 0.6796568512916565,
+      "num_tokens": 184320.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.15432098765432098,
+      "grad_norm": 1.2989270687103271,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.884,
+      "mean_token_accuracy": 0.6988235294818879,
+      "num_tokens": 204800.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.1697530864197531,
+      "grad_norm": 1.1443800926208496,
+      "learning_rate": 3.364197530864198e-05,
+      "loss": 0.8079,
+      "mean_token_accuracy": 0.714607834815979,
+      "num_tokens": 225280.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 1.2093029022216797,
+      "learning_rate": 3.67283950617284e-05,
+      "loss": 0.7537,
+      "mean_token_accuracy": 0.72377450466156,
+      "num_tokens": 245760.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.2006172839506173,
+      "grad_norm": 1.331242322921753,
+      "learning_rate": 3.981481481481482e-05,
+      "loss": 0.7422,
+      "mean_token_accuracy": 0.7294607698917389,
+      "num_tokens": 266240.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.21604938271604937,
+      "grad_norm": 0.9259920716285706,
+      "learning_rate": 4.290123456790124e-05,
+      "loss": 0.703,
+      "mean_token_accuracy": 0.7436274468898774,
+      "num_tokens": 286720.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.23148148148148148,
+      "grad_norm": 0.9903554916381836,
+      "learning_rate": 4.5987654320987656e-05,
+      "loss": 0.7163,
+      "mean_token_accuracy": 0.7358464896678925,
+      "num_tokens": 307186.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 1.0001420974731445,
+      "learning_rate": 4.9074074074074075e-05,
+      "loss": 0.6759,
+      "mean_token_accuracy": 0.74779412150383,
+      "num_tokens": 327666.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.2623456790123457,
+      "grad_norm": 0.9456067681312561,
+      "learning_rate": 5.2160493827160494e-05,
+      "loss": 0.6704,
+      "mean_token_accuracy": 0.749215692281723,
+      "num_tokens": 348146.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.9336047172546387,
+      "learning_rate": 5.524691358024692e-05,
+      "loss": 0.6819,
+      "mean_token_accuracy": 0.74717418551445,
+      "num_tokens": 368183.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2932098765432099,
+      "grad_norm": 0.8091706037521362,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 0.6813,
+      "mean_token_accuracy": 0.7489705979824066,
+      "num_tokens": 388663.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.30864197530864196,
+      "grad_norm": 0.9524596333503723,
+      "learning_rate": 6.141975308641975e-05,
+      "loss": 0.6931,
+      "mean_token_accuracy": 0.7397548913955688,
+      "num_tokens": 409143.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.32407407407407407,
+      "grad_norm": 0.7895946502685547,
+      "learning_rate": 6.450617283950617e-05,
+      "loss": 0.6662,
+      "mean_token_accuracy": 0.7475000023841858,
+      "num_tokens": 429623.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3395061728395062,
+      "grad_norm": 0.7409709692001343,
+      "learning_rate": 6.759259259259259e-05,
+      "loss": 0.6806,
+      "mean_token_accuracy": 0.7402451038360596,
+      "num_tokens": 450103.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.3549382716049383,
+      "grad_norm": 0.8331234455108643,
+      "learning_rate": 7.067901234567902e-05,
+      "loss": 0.6636,
+      "mean_token_accuracy": 0.7479411721229553,
+      "num_tokens": 470583.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.7722135186195374,
+      "learning_rate": 7.376543209876543e-05,
+      "loss": 0.6731,
+      "mean_token_accuracy": 0.7467647016048431,
+      "num_tokens": 491063.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.38580246913580246,
+      "grad_norm": 0.7308498620986938,
+      "learning_rate": 7.685185185185185e-05,
+      "loss": 0.649,
+      "mean_token_accuracy": 0.7547548949718476,
+      "num_tokens": 511543.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4012345679012346,
+      "grad_norm": 0.7666990756988525,
+      "learning_rate": 7.993827160493828e-05,
+      "loss": 0.6445,
+      "mean_token_accuracy": 0.7559313774108887,
+      "num_tokens": 532023.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 3.0780324935913086,
+      "learning_rate": 8.30246913580247e-05,
+      "loss": 0.6471,
+      "mean_token_accuracy": 0.7554901897907257,
+      "num_tokens": 552503.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.43209876543209874,
+      "grad_norm": 0.7734149098396301,
+      "learning_rate": 8.611111111111112e-05,
+      "loss": 0.6681,
+      "mean_token_accuracy": 0.7451470553874969,
+      "num_tokens": 572983.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.44753086419753085,
+      "grad_norm": 0.7692375779151917,
+      "learning_rate": 8.919753086419754e-05,
+      "loss": 0.6389,
+      "mean_token_accuracy": 0.7571078419685364,
+      "num_tokens": 593463.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 0.6887214183807373,
+      "learning_rate": 9.228395061728396e-05,
+      "loss": 0.64,
+      "mean_token_accuracy": 0.7574509978294373,
+      "num_tokens": 613943.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.4783950617283951,
+      "grad_norm": 0.6372818350791931,
+      "learning_rate": 9.537037037037038e-05,
+      "loss": 0.6737,
+      "mean_token_accuracy": 0.7460294246673584,
+      "num_tokens": 634423.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.5355892181396484,
+      "learning_rate": 9.84567901234568e-05,
+      "loss": 0.6352,
+      "mean_token_accuracy": 0.7594117641448974,
+      "num_tokens": 654903.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.5092592592592593,
+      "grad_norm": 0.5700058341026306,
+      "learning_rate": 9.999983722702365e-05,
+      "loss": 0.6627,
+      "mean_token_accuracy": 0.7510294139385223,
+      "num_tokens": 675383.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.5246913580246914,
+      "grad_norm": 0.6579382419586182,
+      "learning_rate": 9.999853504957158e-05,
+      "loss": 0.658,
+      "mean_token_accuracy": 0.7504901885986328,
+      "num_tokens": 695863.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5401234567901234,
+      "grad_norm": 1.066748857498169,
+      "learning_rate": 9.999593072858088e-05,
+      "loss": 0.6584,
+      "mean_token_accuracy": 0.7481862723827362,
+      "num_tokens": 716343.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.64486163854599,
+      "learning_rate": 9.999202433187755e-05,
+      "loss": 0.6428,
+      "mean_token_accuracy": 0.7542156755924225,
+      "num_tokens": 736823.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5709876543209876,
+      "grad_norm": 0.5809119343757629,
+      "learning_rate": 9.998681596119832e-05,
+      "loss": 0.6419,
+      "mean_token_accuracy": 0.7581372559070587,
+      "num_tokens": 757303.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5864197530864198,
+      "grad_norm": 0.6756792664527893,
+      "learning_rate": 9.998030575218811e-05,
+      "loss": 0.6587,
+      "mean_token_accuracy": 0.7491666674613953,
+      "num_tokens": 777783.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.6018518518518519,
+      "grad_norm": 0.6183996200561523,
+      "learning_rate": 9.997249387439643e-05,
+      "loss": 0.6564,
+      "mean_token_accuracy": 0.7498529434204102,
+      "num_tokens": 798263.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 0.6571487188339233,
+      "learning_rate": 9.996338053127292e-05,
+      "loss": 0.6421,
+      "mean_token_accuracy": 0.7550490319728851,
+      "num_tokens": 818743.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6327160493827161,
+      "grad_norm": 0.5952710509300232,
+      "learning_rate": 9.99529659601622e-05,
+      "loss": 0.6407,
+      "mean_token_accuracy": 0.7562768697738648,
+      "num_tokens": 839060.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6481481481481481,
+      "grad_norm": 0.6446591019630432,
+      "learning_rate": 9.994125043229752e-05,
+      "loss": 0.6629,
+      "mean_token_accuracy": 0.7474573612213135,
+      "num_tokens": 859348.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.6635802469135802,
+      "grad_norm": 0.5634035468101501,
+      "learning_rate": 9.992823425279382e-05,
+      "loss": 0.6698,
+      "mean_token_accuracy": 0.7462254941463471,
+      "num_tokens": 879828.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6790123456790124,
+      "grad_norm": 0.5095203518867493,
+      "learning_rate": 9.991391776063969e-05,
+      "loss": 0.6354,
+      "mean_token_accuracy": 0.7562745034694671,
+      "num_tokens": 900308.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 0.5076797604560852,
+      "learning_rate": 9.98983013286886e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7629901945590973,
+      "num_tokens": 920788.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.7098765432098766,
+      "grad_norm": 0.5497986674308777,
+      "learning_rate": 9.988138536364922e-05,
+      "loss": 0.6377,
+      "mean_token_accuracy": 0.7544117629528045,
+      "num_tokens": 941268.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.7253086419753086,
+      "grad_norm": 1.2844603061676025,
+      "learning_rate": 9.986317030607475e-05,
+      "loss": 0.6398,
+      "mean_token_accuracy": 0.7575523376464843,
+      "num_tokens": 961506.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.6091906428337097,
+      "learning_rate": 9.984365663035144e-05,
+      "loss": 0.6354,
+      "mean_token_accuracy": 0.7583116114139556,
+      "num_tokens": 981828.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.7561728395061729,
+      "grad_norm": 0.6552985310554504,
+      "learning_rate": 9.982284484468634e-05,
+      "loss": 0.6464,
+      "mean_token_accuracy": 0.7523039221763611,
+      "num_tokens": 1002308.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7716049382716049,
+      "grad_norm": 0.5882002711296082,
+      "learning_rate": 9.980073549109397e-05,
+      "loss": 0.6491,
+      "mean_token_accuracy": 0.7498039245605469,
+      "num_tokens": 1022788.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.7870370370370371,
+      "grad_norm": 0.5321325659751892,
+      "learning_rate": 9.977732914538225e-05,
+      "loss": 0.6701,
+      "mean_token_accuracy": 0.7467647016048431,
+      "num_tokens": 1043268.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.8024691358024691,
+      "grad_norm": 0.5049220323562622,
+      "learning_rate": 9.975262641713746e-05,
+      "loss": 0.6191,
+      "mean_token_accuracy": 0.7627941250801087,
+      "num_tokens": 1063748.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.8179012345679012,
+      "grad_norm": 0.5200943350791931,
+      "learning_rate": 9.972662794970841e-05,
+      "loss": 0.6553,
+      "mean_token_accuracy": 0.7466912567615509,
+      "num_tokens": 1084157.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.5618262887001038,
+      "learning_rate": 9.969933442018968e-05,
+      "loss": 0.6306,
+      "mean_token_accuracy": 0.7603431344032288,
+      "num_tokens": 1104637.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8487654320987654,
+      "grad_norm": 0.5275453925132751,
+      "learning_rate": 9.967074653940396e-05,
+      "loss": 0.6494,
+      "mean_token_accuracy": 0.7516666710376739,
+      "num_tokens": 1125117.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 0.5133753418922424,
+      "learning_rate": 9.964086505188352e-05,
+      "loss": 0.65,
+      "mean_token_accuracy": 0.750441175699234,
+      "num_tokens": 1145597.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8796296296296297,
+      "grad_norm": 0.5613871216773987,
+      "learning_rate": 9.960969073585091e-05,
+      "loss": 0.6355,
+      "mean_token_accuracy": 0.7533183455467224,
+      "num_tokens": 1165967.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8950617283950617,
+      "grad_norm": 0.5650666356086731,
+      "learning_rate": 9.95772244031986e-05,
+      "loss": 0.6467,
+      "mean_token_accuracy": 0.7557352900505065,
+      "num_tokens": 1186447.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.9104938271604939,
+      "grad_norm": 0.561585545539856,
+      "learning_rate": 9.954346689946785e-05,
+      "loss": 0.6498,
+      "mean_token_accuracy": 0.7523529589176178,
+      "num_tokens": 1206927.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 0.5113793611526489,
+      "learning_rate": 9.950841910382675e-05,
+      "loss": 0.6341,
+      "mean_token_accuracy": 0.754411768913269,
+      "num_tokens": 1227407.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.941358024691358,
+      "grad_norm": 0.9459167718887329,
+      "learning_rate": 9.947208192904722e-05,
+      "loss": 0.6166,
+      "mean_token_accuracy": 0.7633333384990693,
+      "num_tokens": 1247887.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9567901234567902,
+      "grad_norm": 0.597134530544281,
+      "learning_rate": 9.943445632148138e-05,
+      "loss": 0.645,
+      "mean_token_accuracy": 0.7527450978755951,
+      "num_tokens": 1268367.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 0.5343972444534302,
+      "learning_rate": 9.939554326103673e-05,
+      "loss": 0.6568,
+      "mean_token_accuracy": 0.750702977180481,
+      "num_tokens": 1288718.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.65065598487854,
+      "learning_rate": 9.935534376115081e-05,
+      "loss": 0.6301,
+      "mean_token_accuracy": 0.7587254881858826,
+      "num_tokens": 1309198.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6486101150512695,
+      "eval_mean_token_accuracy": 0.7533365641321454,
+      "eval_num_tokens": 1324046.0,
+      "eval_runtime": 3.2793,
+      "eval_samples_per_second": 83.25,
+      "eval_steps_per_second": 10.673,
+      "step": 648
+    },
+    {
+      "epoch": 1.0030864197530864,
+      "grad_norm": 0.5726727843284607,
+      "learning_rate": 9.931385886876466e-05,
+      "loss": 0.6319,
+      "mean_token_accuracy": 0.7595588207244873,
+      "num_tokens": 1328142.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.0185185185185186,
+      "grad_norm": 0.5349597930908203,
+      "learning_rate": 9.927108966429559e-05,
+      "loss": 0.6239,
+      "mean_token_accuracy": 0.7619932591915131,
+      "num_tokens": 1348608.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.0339506172839505,
+      "grad_norm": 0.49260857701301575,
+      "learning_rate": 9.922703726160915e-05,
+      "loss": 0.6138,
+      "mean_token_accuracy": 0.7632843136787415,
+      "num_tokens": 1369088.0,
+      "step": 670
+    },
+    {
+      "epoch": 1.0493827160493827,
+      "grad_norm": 0.5338084101676941,
+      "learning_rate": 9.918170280798997e-05,
+      "loss": 0.5942,
+      "mean_token_accuracy": 0.7736764788627625,
+      "num_tokens": 1389568.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.0648148148148149,
+      "grad_norm": 0.5764300227165222,
+      "learning_rate": 9.913508748411195e-05,
+      "loss": 0.6377,
+      "mean_token_accuracy": 0.7587645888328552,
+      "num_tokens": 1409806.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0802469135802468,
+      "grad_norm": 0.6294172406196594,
+      "learning_rate": 9.908719250400751e-05,
+      "loss": 0.604,
+      "mean_token_accuracy": 0.76813725233078,
+      "num_tokens": 1430286.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.095679012345679,
+      "grad_norm": 0.47793206572532654,
+      "learning_rate": 9.903801911503601e-05,
+      "loss": 0.6144,
+      "mean_token_accuracy": 0.7648529410362244,
+      "num_tokens": 1450766.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.5677058100700378,
+      "learning_rate": 9.898756859785114e-05,
+      "loss": 0.6314,
+      "mean_token_accuracy": 0.7551960706710815,
+      "num_tokens": 1471246.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.126543209876543,
+      "grad_norm": 0.6503554582595825,
+      "learning_rate": 9.893584226636772e-05,
+      "loss": 0.6315,
+      "mean_token_accuracy": 0.7578431308269501,
+      "num_tokens": 1491726.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.1419753086419753,
+      "grad_norm": 0.5785447359085083,
+      "learning_rate": 9.88828414677274e-05,
+      "loss": 0.6228,
+      "mean_token_accuracy": 0.7625000059604645,
+      "num_tokens": 1512206.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.1574074074074074,
+      "grad_norm": 0.5160046219825745,
+      "learning_rate": 9.882856758226355e-05,
+      "loss": 0.6376,
+      "mean_token_accuracy": 0.7573529422283173,
+      "num_tokens": 1532686.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1728395061728394,
+      "grad_norm": 0.5226278901100159,
+      "learning_rate": 9.877302202346537e-05,
+      "loss": 0.629,
+      "mean_token_accuracy": 0.7597683548927308,
+      "num_tokens": 1553003.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.1882716049382716,
+      "grad_norm": 0.6244763135910034,
+      "learning_rate": 9.871620623794107e-05,
+      "loss": 0.6209,
+      "mean_token_accuracy": 0.7606293797492981,
+      "num_tokens": 1573373.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.2037037037037037,
+      "grad_norm": 0.5300543308258057,
+      "learning_rate": 9.865812170538014e-05,
+      "loss": 0.6192,
+      "mean_token_accuracy": 0.7636764764785766,
+      "num_tokens": 1593853.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.2191358024691359,
+      "grad_norm": 0.49504250288009644,
+      "learning_rate": 9.859876993851489e-05,
+      "loss": 0.62,
+      "mean_token_accuracy": 0.7620588302612304,
+      "num_tokens": 1614333.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 0.5028163194656372,
+      "learning_rate": 9.853815248308101e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7628921627998352,
+      "num_tokens": 1634813.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.6196873188018799,
+      "learning_rate": 9.847627091777729e-05,
+      "loss": 0.6175,
+      "mean_token_accuracy": 0.7640686273574829,
+      "num_tokens": 1655293.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2654320987654322,
+      "grad_norm": 0.5531455874443054,
+      "learning_rate": 9.841312685422459e-05,
+      "loss": 0.626,
+      "mean_token_accuracy": 0.7602941274642945,
+      "num_tokens": 1675773.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.2808641975308643,
+      "grad_norm": 0.5736854672431946,
+      "learning_rate": 9.834872193692378e-05,
+      "loss": 0.6288,
+      "mean_token_accuracy": 0.7607352912425995,
+      "num_tokens": 1696253.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.4806568920612335,
+      "learning_rate": 9.828305784321289e-05,
+      "loss": 0.617,
+      "mean_token_accuracy": 0.7647548973560333,
+      "num_tokens": 1716733.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.3117283950617284,
+      "grad_norm": 0.8750804662704468,
+      "learning_rate": 9.821613628322358e-05,
+      "loss": 0.6332,
+      "mean_token_accuracy": 0.7572058856487274,
+      "num_tokens": 1737213.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.3271604938271606,
+      "grad_norm": 0.5364664196968079,
+      "learning_rate": 9.814795899983645e-05,
+      "loss": 0.6272,
+      "mean_token_accuracy": 0.7589215755462646,
+      "num_tokens": 1757693.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.3425925925925926,
+      "grad_norm": 0.5509020090103149,
+      "learning_rate": 9.807852776863568e-05,
+      "loss": 0.6239,
+      "mean_token_accuracy": 0.7589388906955719,
+      "num_tokens": 1777803.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.3580246913580247,
+      "grad_norm": 0.6213059425354004,
+      "learning_rate": 9.800784439786286e-05,
+      "loss": 0.6425,
+      "mean_token_accuracy": 0.750441175699234,
+      "num_tokens": 1798283.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.373456790123457,
+      "grad_norm": 0.5405688881874084,
+      "learning_rate": 9.793591072836978e-05,
+      "loss": 0.6216,
+      "mean_token_accuracy": 0.7597058892250061,
+      "num_tokens": 1818763.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 0.6881203055381775,
+      "learning_rate": 9.786272863357063e-05,
+      "loss": 0.6242,
+      "mean_token_accuracy": 0.7628431379795074,
+      "num_tokens": 1839243.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.404320987654321,
+      "grad_norm": 0.48711517453193665,
+      "learning_rate": 9.778830001939307e-05,
+      "loss": 0.6287,
+      "mean_token_accuracy": 0.759411770105362,
+      "num_tokens": 1859723.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.4197530864197532,
+      "grad_norm": 0.5363081097602844,
+      "learning_rate": 9.771262682422866e-05,
+      "loss": 0.63,
+      "mean_token_accuracy": 0.7583823561668396,
+      "num_tokens": 1880203.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.4351851851851851,
+      "grad_norm": 0.5898856520652771,
+      "learning_rate": 9.76357110188824e-05,
+      "loss": 0.6266,
+      "mean_token_accuracy": 0.7604411780834198,
+      "num_tokens": 1900683.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.4506172839506173,
+      "grad_norm": 0.5043850541114807,
+      "learning_rate": 9.755755460652137e-05,
+      "loss": 0.6011,
+      "mean_token_accuracy": 0.7688725531101227,
+      "num_tokens": 1921163.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.4660493827160495,
+      "grad_norm": 0.5246235132217407,
+      "learning_rate": 9.747815962262255e-05,
+      "loss": 0.6339,
+      "mean_token_accuracy": 0.7562745153903961,
+      "num_tokens": 1941643.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.5146046280860901,
+      "learning_rate": 9.73975281349198e-05,
+      "loss": 0.6269,
+      "mean_token_accuracy": 0.7591666638851166,
+      "num_tokens": 1962123.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4969135802469136,
+      "grad_norm": 0.5631639957427979,
+      "learning_rate": 9.73156622433501e-05,
+      "loss": 0.6384,
+      "mean_token_accuracy": 0.7557843148708343,
+      "num_tokens": 1982603.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.5123456790123457,
+      "grad_norm": 0.7671029567718506,
+      "learning_rate": 9.72325640799987e-05,
+      "loss": 0.6336,
+      "mean_token_accuracy": 0.7575490176677704,
+      "num_tokens": 2003083.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.5277777777777777,
+      "grad_norm": 0.5891373753547668,
+      "learning_rate": 9.71482358090438e-05,
+      "loss": 0.6412,
+      "mean_token_accuracy": 0.7533718824386597,
+      "num_tokens": 2023405.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.5432098765432098,
+      "grad_norm": 0.5099619030952454,
+      "learning_rate": 9.706267962669998e-05,
+      "loss": 0.6181,
+      "mean_token_accuracy": 0.7599019527435302,
+      "num_tokens": 2043885.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.558641975308642,
+      "grad_norm": 0.6285778880119324,
+      "learning_rate": 9.697589776116113e-05,
+      "loss": 0.618,
+      "mean_token_accuracy": 0.7612245142459869,
+      "num_tokens": 2064294.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.574074074074074,
+      "grad_norm": 0.5334492921829224,
+      "learning_rate": 9.688789247254237e-05,
+      "loss": 0.6331,
+      "mean_token_accuracy": 0.7553921639919281,
+      "num_tokens": 2084774.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5895061728395061,
+      "grad_norm": 0.6230431795120239,
+      "learning_rate": 9.679866605282122e-05,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.7686274588108063,
+      "num_tokens": 2105254.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6049382716049383,
+      "grad_norm": 0.560792863368988,
+      "learning_rate": 9.670822082577787e-05,
+      "loss": 0.622,
+      "mean_token_accuracy": 0.7606372594833374,
+      "num_tokens": 2125734.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6203703703703702,
+      "grad_norm": 0.5316160321235657,
+      "learning_rate": 9.661655914693471e-05,
+      "loss": 0.6215,
+      "mean_token_accuracy": 0.7624019622802735,
+      "num_tokens": 2146214.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6358024691358026,
+      "grad_norm": 0.5584502220153809,
+      "learning_rate": 9.652368340349494e-05,
+      "loss": 0.6274,
+      "mean_token_accuracy": 0.7590196132659912,
+      "num_tokens": 2166694.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.6512345679012346,
+      "grad_norm": 0.4828554391860962,
+      "learning_rate": 9.642959601428039e-05,
+      "loss": 0.62,
+      "mean_token_accuracy": 0.7612745046615601,
+      "num_tokens": 2187174.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.5727825164794922,
+      "learning_rate": 9.63342994296686e-05,
+      "loss": 0.6071,
+      "mean_token_accuracy": 0.7662254869937897,
+      "num_tokens": 2207654.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.682098765432099,
+      "grad_norm": 0.5390017032623291,
+      "learning_rate": 9.623779613152893e-05,
+      "loss": 0.6179,
+      "mean_token_accuracy": 0.764607846736908,
+      "num_tokens": 2228134.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6975308641975309,
+      "grad_norm": 0.5654057860374451,
+      "learning_rate": 9.614008863315789e-05,
+      "loss": 0.6068,
+      "mean_token_accuracy": 0.7667545199394226,
+      "num_tokens": 2248422.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7129629629629628,
+      "grad_norm": 0.565568208694458,
+      "learning_rate": 9.604117947921385e-05,
+      "loss": 0.6143,
+      "mean_token_accuracy": 0.7654411792755127,
+      "num_tokens": 2268902.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7283950617283952,
+      "grad_norm": 0.5519742369651794,
+      "learning_rate": 9.594107124565056e-05,
+      "loss": 0.6088,
+      "mean_token_accuracy": 0.7641176581382751,
+      "num_tokens": 2289382.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7438271604938271,
+      "grad_norm": 0.4558942914009094,
+      "learning_rate": 9.58397665396502e-05,
+      "loss": 0.6176,
+      "mean_token_accuracy": 0.7602451086044312,
+      "num_tokens": 2309862.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.7592592592592593,
+      "grad_norm": 0.5886722803115845,
+      "learning_rate": 9.573726799955544e-05,
+      "loss": 0.6081,
+      "mean_token_accuracy": 0.7652941167354583,
+      "num_tokens": 2330342.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7746913580246915,
+      "grad_norm": 0.5108247995376587,
+      "learning_rate": 9.563357829480076e-05,
+      "loss": 0.6278,
+      "mean_token_accuracy": 0.7587745070457459,
+      "num_tokens": 2350822.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7901234567901234,
+      "grad_norm": 0.6499772071838379,
+      "learning_rate": 9.552870012584282e-05,
+      "loss": 0.6137,
+      "mean_token_accuracy": 0.7662254869937897,
+      "num_tokens": 2371302.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8055555555555556,
+      "grad_norm": 0.5412532091140747,
+      "learning_rate": 9.542263622409027e-05,
+      "loss": 0.6159,
+      "mean_token_accuracy": 0.7634241282939911,
+      "num_tokens": 2391580.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.8209876543209877,
+      "grad_norm": 0.538313090801239,
+      "learning_rate": 9.53153893518325e-05,
+      "loss": 0.6332,
+      "mean_token_accuracy": 0.7576960802078248,
+      "num_tokens": 2412060.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.8364197530864197,
+      "grad_norm": 0.6328610777854919,
+      "learning_rate": 9.520696230216781e-05,
+      "loss": 0.6246,
+      "mean_token_accuracy": 0.759950977563858,
+      "num_tokens": 2432540.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.5538372993469238,
+      "learning_rate": 9.509735789893059e-05,
+      "loss": 0.6197,
+      "mean_token_accuracy": 0.7624509751796722,
+      "num_tokens": 2453020.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.867283950617284,
+      "grad_norm": 0.555073618888855,
+      "learning_rate": 9.498657899661774e-05,
+      "loss": 0.6224,
+      "mean_token_accuracy": 0.7595588207244873,
+      "num_tokens": 2473500.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.882716049382716,
+      "grad_norm": 0.5462023019790649,
+      "learning_rate": 9.487462848031445e-05,
+      "loss": 0.6193,
+      "mean_token_accuracy": 0.7641176462173462,
+      "num_tokens": 2493980.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8981481481481481,
+      "grad_norm": 0.5492093563079834,
+      "learning_rate": 9.4761509265619e-05,
+      "loss": 0.6376,
+      "mean_token_accuracy": 0.7553431332111359,
+      "num_tokens": 2514460.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.9135802469135803,
+      "grad_norm": 0.5266892313957214,
+      "learning_rate": 9.464722429856674e-05,
+      "loss": 0.6163,
+      "mean_token_accuracy": 0.7632352948188782,
+      "num_tokens": 2534940.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.9290123456790123,
+      "grad_norm": 0.6665803790092468,
+      "learning_rate": 9.453177655555355e-05,
+      "loss": 0.6196,
+      "mean_token_accuracy": 0.7636274516582489,
+      "num_tokens": 2555420.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 0.567834734916687,
+      "learning_rate": 9.441516904325816e-05,
+      "loss": 0.622,
+      "mean_token_accuracy": 0.7607352912425995,
+      "num_tokens": 2575900.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.9598765432098766,
+      "grad_norm": 0.512845516204834,
+      "learning_rate": 9.42974047985639e-05,
+      "loss": 0.6248,
+      "mean_token_accuracy": 0.7564705908298492,
+      "num_tokens": 2596380.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.5521799921989441,
+      "learning_rate": 9.417848688847968e-05,
+      "loss": 0.6143,
+      "mean_token_accuracy": 0.7628431499004364,
+      "num_tokens": 2616860.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.9907407407407407,
+      "grad_norm": 0.47973841428756714,
+      "learning_rate": 9.405841841005998e-05,
+      "loss": 0.6087,
+      "mean_token_accuracy": 0.7673039317131043,
+      "num_tokens": 2637340.0,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6432122588157654,
+      "eval_mean_token_accuracy": 0.756913377557482,
+      "eval_num_tokens": 2648092.0,
+      "eval_runtime": 3.2747,
+      "eval_samples_per_second": 83.367,
+      "eval_steps_per_second": 10.688,
+      "step": 1296
+    },
+    {
+      "epoch": 2.006172839506173,
+      "grad_norm": 0.5479162931442261,
+      "learning_rate": 9.393720249032428e-05,
+      "loss": 0.5923,
+      "mean_token_accuracy": 0.7697549045085907,
+      "num_tokens": 2656284.0,
+      "step": 1300
+    },
+    {
+      "epoch": 2.021604938271605,
+      "grad_norm": 0.656440794467926,
+      "learning_rate": 9.381484228617561e-05,
+      "loss": 0.6079,
+      "mean_token_accuracy": 0.7672058880329132,
+      "num_tokens": 2676764.0,
+      "step": 1310
+    },
+    {
+      "epoch": 2.037037037037037,
+      "grad_norm": 0.6051917672157288,
+      "learning_rate": 9.369134098431836e-05,
+      "loss": 0.5848,
+      "mean_token_accuracy": 0.7749509871006012,
+      "num_tokens": 2697244.0,
+      "step": 1320
+    },
+    {
+      "epoch": 2.052469135802469,
+      "grad_norm": 0.7500020861625671,
+      "learning_rate": 9.356670180117515e-05,
+      "loss": 0.593,
+      "mean_token_accuracy": 0.7720588266849517,
+      "num_tokens": 2717724.0,
+      "step": 1330
+    },
+    {
+      "epoch": 2.067901234567901,
+      "grad_norm": 0.610857367515564,
+      "learning_rate": 9.344092798280326e-05,
+      "loss": 0.5937,
+      "mean_token_accuracy": 0.7733823597431183,
+      "num_tokens": 2738204.0,
+      "step": 1340
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.6656193733215332,
+      "learning_rate": 9.331402280480996e-05,
+      "loss": 0.5904,
+      "mean_token_accuracy": 0.7753921687602997,
+      "num_tokens": 2758684.0,
+      "step": 1350
+    },
+    {
+      "epoch": 2.0987654320987654,
+      "grad_norm": 0.5261437296867371,
+      "learning_rate": 9.318598957226722e-05,
+      "loss": 0.5921,
+      "mean_token_accuracy": 0.7725490152835846,
+      "num_tokens": 2779164.0,
+      "step": 1360
+    },
+    {
+      "epoch": 2.1141975308641974,
+      "grad_norm": 0.5618685483932495,
+      "learning_rate": 9.305683161962569e-05,
+      "loss": 0.5935,
+      "mean_token_accuracy": 0.770976084470749,
+      "num_tokens": 2799402.0,
+      "step": 1370
+    },
+    {
+      "epoch": 2.1296296296296298,
+      "grad_norm": 0.6032730340957642,
+      "learning_rate": 9.292655231062777e-05,
+      "loss": 0.597,
+      "mean_token_accuracy": 0.7680882334709167,
+      "num_tokens": 2819882.0,
+      "step": 1380
+    },
+    {
+      "epoch": 2.1450617283950617,
+      "grad_norm": 0.6468005776405334,
+      "learning_rate": 9.279515503822012e-05,
+      "loss": 0.5809,
+      "mean_token_accuracy": 0.775245088338852,
+      "num_tokens": 2840362.0,
+      "step": 1390
+    },
+    {
+      "epoch": 2.1604938271604937,
+      "grad_norm": 0.600806713104248,
+      "learning_rate": 9.266264322446513e-05,
+      "loss": 0.5778,
+      "mean_token_accuracy": 0.7759313702583313,
+      "num_tokens": 2860842.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.175925925925926,
+      "grad_norm": 0.5504996180534363,
+      "learning_rate": 9.2529020320452e-05,
+      "loss": 0.5868,
+      "mean_token_accuracy": 0.772892165184021,
+      "num_tokens": 2881322.0,
+      "step": 1410
+    },
+    {
+      "epoch": 2.191358024691358,
+      "grad_norm": 0.7661624550819397,
+      "learning_rate": 9.239428980620668e-05,
+      "loss": 0.577,
+      "mean_token_accuracy": 0.7785064160823822,
+      "num_tokens": 2901731.0,
+      "step": 1420
+    },
+    {
+      "epoch": 2.20679012345679,
+      "grad_norm": 0.6991685628890991,
+      "learning_rate": 9.22584551906014e-05,
+      "loss": 0.5985,
+      "mean_token_accuracy": 0.769460791349411,
+      "num_tokens": 2922211.0,
+      "step": 1430
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.707591712474823,
+      "learning_rate": 9.212152001126309e-05,
+      "loss": 0.5884,
+      "mean_token_accuracy": 0.7741176426410675,
+      "num_tokens": 2942691.0,
+      "step": 1440
+    },
+    {
+      "epoch": 2.2376543209876543,
+      "grad_norm": 0.6777827739715576,
+      "learning_rate": 9.198348783448143e-05,
+      "loss": 0.5912,
+      "mean_token_accuracy": 0.7737254917621612,
+      "num_tokens": 2963171.0,
+      "step": 1450
+    },
+    {
+      "epoch": 2.253086419753086,
+      "grad_norm": 0.693082332611084,
+      "learning_rate": 9.184436225511593e-05,
+      "loss": 0.5853,
+      "mean_token_accuracy": 0.7740196108818054,
+      "num_tokens": 2983651.0,
+      "step": 1460
+    },
+    {
+      "epoch": 2.2685185185185186,
+      "grad_norm": 0.6395755410194397,
+      "learning_rate": 9.170414689650218e-05,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.7693137288093567,
+      "num_tokens": 3004131.0,
+      "step": 1470
+    },
+    {
+      "epoch": 2.2839506172839505,
+      "grad_norm": 0.6955903172492981,
+      "learning_rate": 9.156284541035767e-05,
+      "loss": 0.6123,
+      "mean_token_accuracy": 0.7632352948188782,
+      "num_tokens": 3024611.0,
+      "step": 1480
+    },
+    {
+      "epoch": 2.299382716049383,
+      "grad_norm": 0.634459376335144,
+      "learning_rate": 9.142046147668656e-05,
+      "loss": 0.6126,
+      "mean_token_accuracy": 0.7638235270977021,
+      "num_tokens": 3045091.0,
+      "step": 1490
+    },
+    {
+      "epoch": 2.314814814814815,
+      "grad_norm": 0.6977143883705139,
+      "learning_rate": 9.127699880368388e-05,
+      "loss": 0.5903,
+      "mean_token_accuracy": 0.7724509835243225,
+      "num_tokens": 3065571.0,
+      "step": 1500
+    },
+    {
+      "epoch": 2.330246913580247,
+      "grad_norm": 0.906640350818634,
+      "learning_rate": 9.113246112763896e-05,
+      "loss": 0.5925,
+      "mean_token_accuracy": 0.7721118927001953,
+      "num_tokens": 3085849.0,
+      "step": 1510
+    },
+    {
+      "epoch": 2.3456790123456788,
+      "grad_norm": 0.6876031160354614,
+      "learning_rate": 9.098685221283809e-05,
+      "loss": 0.5968,
+      "mean_token_accuracy": 0.7706862807273864,
+      "num_tokens": 3106329.0,
+      "step": 1520
+    },
+    {
+      "epoch": 2.361111111111111,
+      "grad_norm": 0.7915614247322083,
+      "learning_rate": 9.084017585146653e-05,
+      "loss": 0.5927,
+      "mean_token_accuracy": 0.7707352995872497,
+      "num_tokens": 3126809.0,
+      "step": 1530
+    },
+    {
+      "epoch": 2.376543209876543,
+      "grad_norm": 0.5830466151237488,
+      "learning_rate": 9.069243586350975e-05,
+      "loss": 0.599,
+      "mean_token_accuracy": 0.7685294091701508,
+      "num_tokens": 3147289.0,
+      "step": 1540
+    },
+    {
+      "epoch": 2.3919753086419755,
+      "grad_norm": 0.6367495059967041,
+      "learning_rate": 9.054363609665388e-05,
+      "loss": 0.6026,
+      "mean_token_accuracy": 0.7685784339904785,
+      "num_tokens": 3167769.0,
+      "step": 1550
+    },
+    {
+      "epoch": 2.4074074074074074,
+      "grad_norm": 0.9314106702804565,
+      "learning_rate": 9.039378042618556e-05,
+      "loss": 0.5914,
+      "mean_token_accuracy": 0.774117648601532,
+      "num_tokens": 3188249.0,
+      "step": 1560
+    },
+    {
+      "epoch": 2.4228395061728394,
+      "grad_norm": 0.6892368197441101,
+      "learning_rate": 9.0242872754891e-05,
+      "loss": 0.5939,
+      "mean_token_accuracy": 0.7718548774719238,
+      "num_tokens": 3208619.0,
+      "step": 1570
+    },
+    {
+      "epoch": 2.4382716049382718,
+      "grad_norm": 0.5464644432067871,
+      "learning_rate": 9.009091701295434e-05,
+      "loss": 0.5905,
+      "mean_token_accuracy": 0.7747549057006836,
+      "num_tokens": 3229099.0,
+      "step": 1580
+    },
+    {
+      "epoch": 2.4537037037037037,
+      "grad_norm": 0.5427695512771606,
+      "learning_rate": 8.993791715785528e-05,
+      "loss": 0.6031,
+      "mean_token_accuracy": 0.7664862751960755,
+      "num_tokens": 3249421.0,
+      "step": 1590
+    },
+    {
+      "epoch": 2.4691358024691357,
+      "grad_norm": 0.6546815037727356,
+      "learning_rate": 8.978387717426601e-05,
+      "loss": 0.5918,
+      "mean_token_accuracy": 0.7709313809871674,
+      "num_tokens": 3269901.0,
+      "step": 1600
+    },
+    {
+      "epoch": 2.484567901234568,
+      "grad_norm": 0.6619100570678711,
+      "learning_rate": 8.962880107394747e-05,
+      "loss": 0.6081,
+      "mean_token_accuracy": 0.7659300684928894,
+      "num_tokens": 3290252.0,
+      "step": 1610
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.722586452960968,
+      "learning_rate": 8.947269289564482e-05,
+      "loss": 0.5891,
+      "mean_token_accuracy": 0.7740368068218231,
+      "num_tokens": 3310540.0,
+      "step": 1620
+    },
+    {
+      "epoch": 2.515432098765432,
+      "grad_norm": 0.5784828066825867,
+      "learning_rate": 8.931555670498229e-05,
+      "loss": 0.5961,
+      "mean_token_accuracy": 0.7705882370471955,
+      "num_tokens": 3331020.0,
+      "step": 1630
+    },
+    {
+      "epoch": 2.5308641975308643,
+      "grad_norm": 0.7214418649673462,
+      "learning_rate": 8.915739659435732e-05,
+      "loss": 0.5771,
+      "mean_token_accuracy": 0.7781862795352936,
+      "num_tokens": 3351500.0,
+      "step": 1640
+    },
+    {
+      "epoch": 2.5462962962962963,
+      "grad_norm": 0.6226558685302734,
+      "learning_rate": 8.899821668283388e-05,
+      "loss": 0.5896,
+      "mean_token_accuracy": 0.7740686297416687,
+      "num_tokens": 3371980.0,
+      "step": 1650
+    },
+    {
+      "epoch": 2.5617283950617287,
+      "grad_norm": 0.5680100917816162,
+      "learning_rate": 8.883802111603532e-05,
+      "loss": 0.5905,
+      "mean_token_accuracy": 0.7712745130062103,
+      "num_tokens": 3392460.0,
+      "step": 1660
+    },
+    {
+      "epoch": 2.5771604938271606,
+      "grad_norm": 0.6910707950592041,
+      "learning_rate": 8.867681406603632e-05,
+      "loss": 0.5973,
+      "mean_token_accuracy": 0.7682352960109711,
+      "num_tokens": 3412940.0,
+      "step": 1670
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.5533532500267029,
+      "learning_rate": 8.851459973125424e-05,
+      "loss": 0.6045,
+      "mean_token_accuracy": 0.7657843172550202,
+      "num_tokens": 3433420.0,
+      "step": 1680
+    },
+    {
+      "epoch": 2.6080246913580245,
+      "grad_norm": 0.6664072275161743,
+      "learning_rate": 8.835138233633986e-05,
+      "loss": 0.6021,
+      "mean_token_accuracy": 0.7676470637321472,
+      "num_tokens": 3453900.0,
+      "step": 1690
+    },
+    {
+      "epoch": 2.623456790123457,
+      "grad_norm": 0.7590135931968689,
+      "learning_rate": 8.818716613206718e-05,
+      "loss": 0.6085,
+      "mean_token_accuracy": 0.7683761894702912,
+      "num_tokens": 3474217.0,
+      "step": 1700
+    },
+    {
+      "epoch": 2.638888888888889,
+      "grad_norm": 0.7670077681541443,
+      "learning_rate": 8.802195539522298e-05,
+      "loss": 0.6063,
+      "mean_token_accuracy": 0.7649509847164154,
+      "num_tokens": 3494697.0,
+      "step": 1710
+    },
+    {
+      "epoch": 2.6543209876543212,
+      "grad_norm": 0.6275266408920288,
+      "learning_rate": 8.785575442849512e-05,
+      "loss": 0.6012,
+      "mean_token_accuracy": 0.766274505853653,
+      "num_tokens": 3515177.0,
+      "step": 1720
+    },
+    {
+      "epoch": 2.669753086419753,
+      "grad_norm": 0.5899403691291809,
+      "learning_rate": 8.768856756036075e-05,
+      "loss": 0.5784,
+      "mean_token_accuracy": 0.7777941226959229,
+      "num_tokens": 3535657.0,
+      "step": 1730
+    },
+    {
+      "epoch": 2.685185185185185,
+      "grad_norm": 0.767240583896637,
+      "learning_rate": 8.752039914497344e-05,
+      "loss": 0.6064,
+      "mean_token_accuracy": 0.7683333456516266,
+      "num_tokens": 3556137.0,
+      "step": 1740
+    },
+    {
+      "epoch": 2.700617283950617,
+      "grad_norm": 0.6055841445922852,
+      "learning_rate": 8.73512535620498e-05,
+      "loss": 0.6111,
+      "mean_token_accuracy": 0.7638725459575653,
+      "num_tokens": 3576617.0,
+      "step": 1750
+    },
+    {
+      "epoch": 2.7160493827160495,
+      "grad_norm": 0.5842066407203674,
+      "learning_rate": 8.718113521675551e-05,
+      "loss": 0.5959,
+      "mean_token_accuracy": 0.7691176474094391,
+      "num_tokens": 3597097.0,
+      "step": 1760
+    },
+    {
+      "epoch": 2.7314814814814814,
+      "grad_norm": 0.6634451746940613,
+      "learning_rate": 8.70100485395904e-05,
+      "loss": 0.5886,
+      "mean_token_accuracy": 0.7744088768959045,
+      "num_tokens": 3617336.0,
+      "step": 1770
+    },
+    {
+      "epoch": 2.746913580246914,
+      "grad_norm": 0.670170247554779,
+      "learning_rate": 8.683799798627327e-05,
+      "loss": 0.5917,
+      "mean_token_accuracy": 0.7728895008563995,
+      "num_tokens": 3637802.0,
+      "step": 1780
+    },
+    {
+      "epoch": 2.7623456790123457,
+      "grad_norm": 0.7129385471343994,
+      "learning_rate": 8.666498803762575e-05,
+      "loss": 0.5779,
+      "mean_token_accuracy": 0.7773529410362243,
+      "num_tokens": 3658282.0,
+      "step": 1790
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.6470578908920288,
+      "learning_rate": 8.649102319945556e-05,
+      "loss": 0.5944,
+      "mean_token_accuracy": 0.771666657924652,
+      "num_tokens": 3678762.0,
+      "step": 1800
+    },
+    {
+      "epoch": 2.7932098765432096,
+      "grad_norm": 0.6014609932899475,
+      "learning_rate": 8.631610800243926e-05,
+      "loss": 0.596,
+      "mean_token_accuracy": 0.7687254965305328,
+      "num_tokens": 3699242.0,
+      "step": 1810
+    },
+    {
+      "epoch": 2.808641975308642,
+      "grad_norm": 0.6266966462135315,
+      "learning_rate": 8.614024700200418e-05,
+      "loss": 0.5896,
+      "mean_token_accuracy": 0.7722058892250061,
+      "num_tokens": 3719722.0,
+      "step": 1820
+    },
+    {
+      "epoch": 2.824074074074074,
+      "grad_norm": 0.7801739573478699,
+      "learning_rate": 8.596344477820982e-05,
+      "loss": 0.5912,
+      "mean_token_accuracy": 0.7734313845634461,
+      "num_tokens": 3740202.0,
+      "step": 1830
+    },
+    {
+      "epoch": 2.8395061728395063,
+      "grad_norm": 0.5488538146018982,
+      "learning_rate": 8.578570593562856e-05,
+      "loss": 0.6044,
+      "mean_token_accuracy": 0.7692156851291656,
+      "num_tokens": 3760682.0,
+      "step": 1840
+    },
+    {
+      "epoch": 2.8549382716049383,
+      "grad_norm": 0.5966465473175049,
+      "learning_rate": 8.560703510322574e-05,
+      "loss": 0.5958,
+      "mean_token_accuracy": 0.7715196192264557,
+      "num_tokens": 3781162.0,
+      "step": 1850
+    },
+    {
+      "epoch": 2.8703703703703702,
+      "grad_norm": 0.6425583362579346,
+      "learning_rate": 8.54274369342391e-05,
+      "loss": 0.594,
+      "mean_token_accuracy": 0.7702941179275513,
+      "num_tokens": 3801642.0,
+      "step": 1860
+    },
+    {
+      "epoch": 2.8858024691358026,
+      "grad_norm": 0.6507608294487,
+      "learning_rate": 8.524691610605755e-05,
+      "loss": 0.6128,
+      "mean_token_accuracy": 0.7628431439399719,
+      "num_tokens": 3822122.0,
+      "step": 1870
+    },
+    {
+      "epoch": 2.9012345679012346,
+      "grad_norm": 0.6581034660339355,
+      "learning_rate": 8.506547732009949e-05,
+      "loss": 0.6006,
+      "mean_token_accuracy": 0.7693137288093567,
+      "num_tokens": 3842602.0,
+      "step": 1880
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 0.639123797416687,
+      "learning_rate": 8.488312530169019e-05,
+      "loss": 0.6165,
+      "mean_token_accuracy": 0.7635294079780579,
+      "num_tokens": 3863082.0,
+      "step": 1890
+    },
+    {
+      "epoch": 2.932098765432099,
+      "grad_norm": 0.633488118648529,
+      "learning_rate": 8.469986479993885e-05,
+      "loss": 0.6015,
+      "mean_token_accuracy": 0.7681862771511078,
+      "num_tokens": 3883562.0,
+      "step": 1900
+    },
+    {
+      "epoch": 2.947530864197531,
+      "grad_norm": 0.7640633583068848,
+      "learning_rate": 8.451570058761487e-05,
+      "loss": 0.5788,
+      "mean_token_accuracy": 0.7772058844566345,
+      "num_tokens": 3904042.0,
+      "step": 1910
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.6150678396224976,
+      "learning_rate": 8.433063746102357e-05,
+      "loss": 0.5874,
+      "mean_token_accuracy": 0.7721568644046783,
+      "num_tokens": 3924522.0,
+      "step": 1920
+    },
+    {
+      "epoch": 2.978395061728395,
+      "grad_norm": 0.5631530284881592,
+      "learning_rate": 8.414468023988124e-05,
+      "loss": 0.5957,
+      "mean_token_accuracy": 0.7705882310867309,
+      "num_tokens": 3945002.0,
+      "step": 1930
+    },
+    {
+      "epoch": 2.993827160493827,
+      "grad_norm": 0.5055695176124573,
+      "learning_rate": 8.395783376718966e-05,
+      "loss": 0.5886,
+      "mean_token_accuracy": 0.7745097994804382,
+      "num_tokens": 3965482.0,
+      "step": 1940
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6486226320266724,
+      "eval_mean_token_accuracy": 0.7536231398582458,
+      "eval_num_tokens": 3972138.0,
+      "eval_runtime": 3.2699,
+      "eval_samples_per_second": 83.488,
+      "eval_steps_per_second": 10.704,
+      "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": 1.6918817712478618e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_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:ee630d3a769f8f4b4dcc99c709324068f5e26341c6ce13597153a1b7c73d3414
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_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_s3_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": [
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "down_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_s3_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:ab6cc94777a2a73138311904e755bcec6b9752da34525e8666aa11e7ee132c2a
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_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_s3_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_s3_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_s3_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_s3_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_s3_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": 3.6007630825042725,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 2.4489,
+      "mean_token_accuracy": 0.545343142747879,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.030864197530864196,
+      "grad_norm": 3.805405616760254,
+      "learning_rate": 5.864197530864198e-06,
+      "loss": 2.459,
+      "mean_token_accuracy": 0.5510784387588501,
+      "num_tokens": 40960.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.046296296296296294,
+      "grad_norm": 3.528644561767578,
+      "learning_rate": 8.950617283950618e-06,
+      "loss": 2.316,
+      "mean_token_accuracy": 0.552549022436142,
+      "num_tokens": 61440.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.06172839506172839,
+      "grad_norm": 2.193250894546509,
+      "learning_rate": 1.2037037037037037e-05,
+      "loss": 2.0378,
+      "mean_token_accuracy": 0.5757352948188782,
+      "num_tokens": 81920.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07716049382716049,
+      "grad_norm": 1.3338465690612793,
+      "learning_rate": 1.5123456790123458e-05,
+      "loss": 1.7238,
+      "mean_token_accuracy": 0.6038235306739808,
+      "num_tokens": 102400.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.09259259259259259,
+      "grad_norm": 1.1486477851867676,
+      "learning_rate": 1.8209876543209877e-05,
+      "loss": 1.5441,
+      "mean_token_accuracy": 0.6099999904632568,
+      "num_tokens": 122880.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.10802469135802469,
+      "grad_norm": 0.8821588754653931,
+      "learning_rate": 2.1296296296296296e-05,
+      "loss": 1.3521,
+      "mean_token_accuracy": 0.6251470565795898,
+      "num_tokens": 143360.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 0.8657292127609253,
+      "learning_rate": 2.438271604938272e-05,
+      "loss": 1.1704,
+      "mean_token_accuracy": 0.6537254929542542,
+      "num_tokens": 163840.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 0.9481641054153442,
+      "learning_rate": 2.7469135802469138e-05,
+      "loss": 1.0164,
+      "mean_token_accuracy": 0.6796568512916565,
+      "num_tokens": 184320.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.15432098765432098,
+      "grad_norm": 1.2989270687103271,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.884,
+      "mean_token_accuracy": 0.6988235294818879,
+      "num_tokens": 204800.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.1697530864197531,
+      "grad_norm": 1.1443800926208496,
+      "learning_rate": 3.364197530864198e-05,
+      "loss": 0.8079,
+      "mean_token_accuracy": 0.714607834815979,
+      "num_tokens": 225280.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 1.2093029022216797,
+      "learning_rate": 3.67283950617284e-05,
+      "loss": 0.7537,
+      "mean_token_accuracy": 0.72377450466156,
+      "num_tokens": 245760.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.2006172839506173,
+      "grad_norm": 1.331242322921753,
+      "learning_rate": 3.981481481481482e-05,
+      "loss": 0.7422,
+      "mean_token_accuracy": 0.7294607698917389,
+      "num_tokens": 266240.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.21604938271604937,
+      "grad_norm": 0.9259920716285706,
+      "learning_rate": 4.290123456790124e-05,
+      "loss": 0.703,
+      "mean_token_accuracy": 0.7436274468898774,
+      "num_tokens": 286720.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.23148148148148148,
+      "grad_norm": 0.9903554916381836,
+      "learning_rate": 4.5987654320987656e-05,
+      "loss": 0.7163,
+      "mean_token_accuracy": 0.7358464896678925,
+      "num_tokens": 307186.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 1.0001420974731445,
+      "learning_rate": 4.9074074074074075e-05,
+      "loss": 0.6759,
+      "mean_token_accuracy": 0.74779412150383,
+      "num_tokens": 327666.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.2623456790123457,
+      "grad_norm": 0.9456067681312561,
+      "learning_rate": 5.2160493827160494e-05,
+      "loss": 0.6704,
+      "mean_token_accuracy": 0.749215692281723,
+      "num_tokens": 348146.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.9336047172546387,
+      "learning_rate": 5.524691358024692e-05,
+      "loss": 0.6819,
+      "mean_token_accuracy": 0.74717418551445,
+      "num_tokens": 368183.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2932098765432099,
+      "grad_norm": 0.8091706037521362,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 0.6813,
+      "mean_token_accuracy": 0.7489705979824066,
+      "num_tokens": 388663.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.30864197530864196,
+      "grad_norm": 0.9524596333503723,
+      "learning_rate": 6.141975308641975e-05,
+      "loss": 0.6931,
+      "mean_token_accuracy": 0.7397548913955688,
+      "num_tokens": 409143.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.32407407407407407,
+      "grad_norm": 0.7895946502685547,
+      "learning_rate": 6.450617283950617e-05,
+      "loss": 0.6662,
+      "mean_token_accuracy": 0.7475000023841858,
+      "num_tokens": 429623.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3395061728395062,
+      "grad_norm": 0.7409709692001343,
+      "learning_rate": 6.759259259259259e-05,
+      "loss": 0.6806,
+      "mean_token_accuracy": 0.7402451038360596,
+      "num_tokens": 450103.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.3549382716049383,
+      "grad_norm": 0.8331234455108643,
+      "learning_rate": 7.067901234567902e-05,
+      "loss": 0.6636,
+      "mean_token_accuracy": 0.7479411721229553,
+      "num_tokens": 470583.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.7722135186195374,
+      "learning_rate": 7.376543209876543e-05,
+      "loss": 0.6731,
+      "mean_token_accuracy": 0.7467647016048431,
+      "num_tokens": 491063.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.38580246913580246,
+      "grad_norm": 0.7308498620986938,
+      "learning_rate": 7.685185185185185e-05,
+      "loss": 0.649,
+      "mean_token_accuracy": 0.7547548949718476,
+      "num_tokens": 511543.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4012345679012346,
+      "grad_norm": 0.7666990756988525,
+      "learning_rate": 7.993827160493828e-05,
+      "loss": 0.6445,
+      "mean_token_accuracy": 0.7559313774108887,
+      "num_tokens": 532023.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 3.0780324935913086,
+      "learning_rate": 8.30246913580247e-05,
+      "loss": 0.6471,
+      "mean_token_accuracy": 0.7554901897907257,
+      "num_tokens": 552503.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.43209876543209874,
+      "grad_norm": 0.7734149098396301,
+      "learning_rate": 8.611111111111112e-05,
+      "loss": 0.6681,
+      "mean_token_accuracy": 0.7451470553874969,
+      "num_tokens": 572983.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.44753086419753085,
+      "grad_norm": 0.7692375779151917,
+      "learning_rate": 8.919753086419754e-05,
+      "loss": 0.6389,
+      "mean_token_accuracy": 0.7571078419685364,
+      "num_tokens": 593463.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 0.6887214183807373,
+      "learning_rate": 9.228395061728396e-05,
+      "loss": 0.64,
+      "mean_token_accuracy": 0.7574509978294373,
+      "num_tokens": 613943.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.4783950617283951,
+      "grad_norm": 0.6372818350791931,
+      "learning_rate": 9.537037037037038e-05,
+      "loss": 0.6737,
+      "mean_token_accuracy": 0.7460294246673584,
+      "num_tokens": 634423.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.5355892181396484,
+      "learning_rate": 9.84567901234568e-05,
+      "loss": 0.6352,
+      "mean_token_accuracy": 0.7594117641448974,
+      "num_tokens": 654903.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.5092592592592593,
+      "grad_norm": 0.5700058341026306,
+      "learning_rate": 9.999983722702365e-05,
+      "loss": 0.6627,
+      "mean_token_accuracy": 0.7510294139385223,
+      "num_tokens": 675383.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.5246913580246914,
+      "grad_norm": 0.6579382419586182,
+      "learning_rate": 9.999853504957158e-05,
+      "loss": 0.658,
+      "mean_token_accuracy": 0.7504901885986328,
+      "num_tokens": 695863.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5401234567901234,
+      "grad_norm": 1.066748857498169,
+      "learning_rate": 9.999593072858088e-05,
+      "loss": 0.6584,
+      "mean_token_accuracy": 0.7481862723827362,
+      "num_tokens": 716343.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.64486163854599,
+      "learning_rate": 9.999202433187755e-05,
+      "loss": 0.6428,
+      "mean_token_accuracy": 0.7542156755924225,
+      "num_tokens": 736823.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5709876543209876,
+      "grad_norm": 0.5809119343757629,
+      "learning_rate": 9.998681596119832e-05,
+      "loss": 0.6419,
+      "mean_token_accuracy": 0.7581372559070587,
+      "num_tokens": 757303.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5864197530864198,
+      "grad_norm": 0.6756792664527893,
+      "learning_rate": 9.998030575218811e-05,
+      "loss": 0.6587,
+      "mean_token_accuracy": 0.7491666674613953,
+      "num_tokens": 777783.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.6018518518518519,
+      "grad_norm": 0.6183996200561523,
+      "learning_rate": 9.997249387439643e-05,
+      "loss": 0.6564,
+      "mean_token_accuracy": 0.7498529434204102,
+      "num_tokens": 798263.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 0.6571487188339233,
+      "learning_rate": 9.996338053127292e-05,
+      "loss": 0.6421,
+      "mean_token_accuracy": 0.7550490319728851,
+      "num_tokens": 818743.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6327160493827161,
+      "grad_norm": 0.5952710509300232,
+      "learning_rate": 9.99529659601622e-05,
+      "loss": 0.6407,
+      "mean_token_accuracy": 0.7562768697738648,
+      "num_tokens": 839060.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6481481481481481,
+      "grad_norm": 0.6446591019630432,
+      "learning_rate": 9.994125043229752e-05,
+      "loss": 0.6629,
+      "mean_token_accuracy": 0.7474573612213135,
+      "num_tokens": 859348.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.6635802469135802,
+      "grad_norm": 0.5634035468101501,
+      "learning_rate": 9.992823425279382e-05,
+      "loss": 0.6698,
+      "mean_token_accuracy": 0.7462254941463471,
+      "num_tokens": 879828.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6790123456790124,
+      "grad_norm": 0.5095203518867493,
+      "learning_rate": 9.991391776063969e-05,
+      "loss": 0.6354,
+      "mean_token_accuracy": 0.7562745034694671,
+      "num_tokens": 900308.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 0.5076797604560852,
+      "learning_rate": 9.98983013286886e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7629901945590973,
+      "num_tokens": 920788.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.7098765432098766,
+      "grad_norm": 0.5497986674308777,
+      "learning_rate": 9.988138536364922e-05,
+      "loss": 0.6377,
+      "mean_token_accuracy": 0.7544117629528045,
+      "num_tokens": 941268.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.7253086419753086,
+      "grad_norm": 1.2844603061676025,
+      "learning_rate": 9.986317030607475e-05,
+      "loss": 0.6398,
+      "mean_token_accuracy": 0.7575523376464843,
+      "num_tokens": 961506.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.6091906428337097,
+      "learning_rate": 9.984365663035144e-05,
+      "loss": 0.6354,
+      "mean_token_accuracy": 0.7583116114139556,
+      "num_tokens": 981828.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.7561728395061729,
+      "grad_norm": 0.6552985310554504,
+      "learning_rate": 9.982284484468634e-05,
+      "loss": 0.6464,
+      "mean_token_accuracy": 0.7523039221763611,
+      "num_tokens": 1002308.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7716049382716049,
+      "grad_norm": 0.5882002711296082,
+      "learning_rate": 9.980073549109397e-05,
+      "loss": 0.6491,
+      "mean_token_accuracy": 0.7498039245605469,
+      "num_tokens": 1022788.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.7870370370370371,
+      "grad_norm": 0.5321325659751892,
+      "learning_rate": 9.977732914538225e-05,
+      "loss": 0.6701,
+      "mean_token_accuracy": 0.7467647016048431,
+      "num_tokens": 1043268.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.8024691358024691,
+      "grad_norm": 0.5049220323562622,
+      "learning_rate": 9.975262641713746e-05,
+      "loss": 0.6191,
+      "mean_token_accuracy": 0.7627941250801087,
+      "num_tokens": 1063748.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.8179012345679012,
+      "grad_norm": 0.5200943350791931,
+      "learning_rate": 9.972662794970841e-05,
+      "loss": 0.6553,
+      "mean_token_accuracy": 0.7466912567615509,
+      "num_tokens": 1084157.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.5618262887001038,
+      "learning_rate": 9.969933442018968e-05,
+      "loss": 0.6306,
+      "mean_token_accuracy": 0.7603431344032288,
+      "num_tokens": 1104637.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8487654320987654,
+      "grad_norm": 0.5275453925132751,
+      "learning_rate": 9.967074653940396e-05,
+      "loss": 0.6494,
+      "mean_token_accuracy": 0.7516666710376739,
+      "num_tokens": 1125117.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 0.5133753418922424,
+      "learning_rate": 9.964086505188352e-05,
+      "loss": 0.65,
+      "mean_token_accuracy": 0.750441175699234,
+      "num_tokens": 1145597.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8796296296296297,
+      "grad_norm": 0.5613871216773987,
+      "learning_rate": 9.960969073585091e-05,
+      "loss": 0.6355,
+      "mean_token_accuracy": 0.7533183455467224,
+      "num_tokens": 1165967.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8950617283950617,
+      "grad_norm": 0.5650666356086731,
+      "learning_rate": 9.95772244031986e-05,
+      "loss": 0.6467,
+      "mean_token_accuracy": 0.7557352900505065,
+      "num_tokens": 1186447.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.9104938271604939,
+      "grad_norm": 0.561585545539856,
+      "learning_rate": 9.954346689946785e-05,
+      "loss": 0.6498,
+      "mean_token_accuracy": 0.7523529589176178,
+      "num_tokens": 1206927.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 0.5113793611526489,
+      "learning_rate": 9.950841910382675e-05,
+      "loss": 0.6341,
+      "mean_token_accuracy": 0.754411768913269,
+      "num_tokens": 1227407.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.941358024691358,
+      "grad_norm": 0.9459167718887329,
+      "learning_rate": 9.947208192904722e-05,
+      "loss": 0.6166,
+      "mean_token_accuracy": 0.7633333384990693,
+      "num_tokens": 1247887.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9567901234567902,
+      "grad_norm": 0.597134530544281,
+      "learning_rate": 9.943445632148138e-05,
+      "loss": 0.645,
+      "mean_token_accuracy": 0.7527450978755951,
+      "num_tokens": 1268367.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 0.5343972444534302,
+      "learning_rate": 9.939554326103673e-05,
+      "loss": 0.6568,
+      "mean_token_accuracy": 0.750702977180481,
+      "num_tokens": 1288718.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.65065598487854,
+      "learning_rate": 9.935534376115081e-05,
+      "loss": 0.6301,
+      "mean_token_accuracy": 0.7587254881858826,
+      "num_tokens": 1309198.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6486101150512695,
+      "eval_mean_token_accuracy": 0.7533365641321454,
+      "eval_num_tokens": 1324046.0,
+      "eval_runtime": 3.2793,
+      "eval_samples_per_second": 83.25,
+      "eval_steps_per_second": 10.673,
+      "step": 648
+    },
+    {
+      "epoch": 1.0030864197530864,
+      "grad_norm": 0.5726727843284607,
+      "learning_rate": 9.931385886876466e-05,
+      "loss": 0.6319,
+      "mean_token_accuracy": 0.7595588207244873,
+      "num_tokens": 1328142.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.0185185185185186,
+      "grad_norm": 0.5349597930908203,
+      "learning_rate": 9.927108966429559e-05,
+      "loss": 0.6239,
+      "mean_token_accuracy": 0.7619932591915131,
+      "num_tokens": 1348608.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.0339506172839505,
+      "grad_norm": 0.49260857701301575,
+      "learning_rate": 9.922703726160915e-05,
+      "loss": 0.6138,
+      "mean_token_accuracy": 0.7632843136787415,
+      "num_tokens": 1369088.0,
+      "step": 670
+    },
+    {
+      "epoch": 1.0493827160493827,
+      "grad_norm": 0.5338084101676941,
+      "learning_rate": 9.918170280798997e-05,
+      "loss": 0.5942,
+      "mean_token_accuracy": 0.7736764788627625,
+      "num_tokens": 1389568.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.0648148148148149,
+      "grad_norm": 0.5764300227165222,
+      "learning_rate": 9.913508748411195e-05,
+      "loss": 0.6377,
+      "mean_token_accuracy": 0.7587645888328552,
+      "num_tokens": 1409806.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0802469135802468,
+      "grad_norm": 0.6294172406196594,
+      "learning_rate": 9.908719250400751e-05,
+      "loss": 0.604,
+      "mean_token_accuracy": 0.76813725233078,
+      "num_tokens": 1430286.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.095679012345679,
+      "grad_norm": 0.47793206572532654,
+      "learning_rate": 9.903801911503601e-05,
+      "loss": 0.6144,
+      "mean_token_accuracy": 0.7648529410362244,
+      "num_tokens": 1450766.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.5677058100700378,
+      "learning_rate": 9.898756859785114e-05,
+      "loss": 0.6314,
+      "mean_token_accuracy": 0.7551960706710815,
+      "num_tokens": 1471246.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.126543209876543,
+      "grad_norm": 0.6503554582595825,
+      "learning_rate": 9.893584226636772e-05,
+      "loss": 0.6315,
+      "mean_token_accuracy": 0.7578431308269501,
+      "num_tokens": 1491726.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.1419753086419753,
+      "grad_norm": 0.5785447359085083,
+      "learning_rate": 9.88828414677274e-05,
+      "loss": 0.6228,
+      "mean_token_accuracy": 0.7625000059604645,
+      "num_tokens": 1512206.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.1574074074074074,
+      "grad_norm": 0.5160046219825745,
+      "learning_rate": 9.882856758226355e-05,
+      "loss": 0.6376,
+      "mean_token_accuracy": 0.7573529422283173,
+      "num_tokens": 1532686.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1728395061728394,
+      "grad_norm": 0.5226278901100159,
+      "learning_rate": 9.877302202346537e-05,
+      "loss": 0.629,
+      "mean_token_accuracy": 0.7597683548927308,
+      "num_tokens": 1553003.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.1882716049382716,
+      "grad_norm": 0.6244763135910034,
+      "learning_rate": 9.871620623794107e-05,
+      "loss": 0.6209,
+      "mean_token_accuracy": 0.7606293797492981,
+      "num_tokens": 1573373.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.2037037037037037,
+      "grad_norm": 0.5300543308258057,
+      "learning_rate": 9.865812170538014e-05,
+      "loss": 0.6192,
+      "mean_token_accuracy": 0.7636764764785766,
+      "num_tokens": 1593853.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.2191358024691359,
+      "grad_norm": 0.49504250288009644,
+      "learning_rate": 9.859876993851489e-05,
+      "loss": 0.62,
+      "mean_token_accuracy": 0.7620588302612304,
+      "num_tokens": 1614333.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 0.5028163194656372,
+      "learning_rate": 9.853815248308101e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7628921627998352,
+      "num_tokens": 1634813.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.6196873188018799,
+      "learning_rate": 9.847627091777729e-05,
+      "loss": 0.6175,
+      "mean_token_accuracy": 0.7640686273574829,
+      "num_tokens": 1655293.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2654320987654322,
+      "grad_norm": 0.5531455874443054,
+      "learning_rate": 9.841312685422459e-05,
+      "loss": 0.626,
+      "mean_token_accuracy": 0.7602941274642945,
+      "num_tokens": 1675773.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.2808641975308643,
+      "grad_norm": 0.5736854672431946,
+      "learning_rate": 9.834872193692378e-05,
+      "loss": 0.6288,
+      "mean_token_accuracy": 0.7607352912425995,
+      "num_tokens": 1696253.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.4806568920612335,
+      "learning_rate": 9.828305784321289e-05,
+      "loss": 0.617,
+      "mean_token_accuracy": 0.7647548973560333,
+      "num_tokens": 1716733.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.3117283950617284,
+      "grad_norm": 0.8750804662704468,
+      "learning_rate": 9.821613628322358e-05,
+      "loss": 0.6332,
+      "mean_token_accuracy": 0.7572058856487274,
+      "num_tokens": 1737213.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.3271604938271606,
+      "grad_norm": 0.5364664196968079,
+      "learning_rate": 9.814795899983645e-05,
+      "loss": 0.6272,
+      "mean_token_accuracy": 0.7589215755462646,
+      "num_tokens": 1757693.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.3425925925925926,
+      "grad_norm": 0.5509020090103149,
+      "learning_rate": 9.807852776863568e-05,
+      "loss": 0.6239,
+      "mean_token_accuracy": 0.7589388906955719,
+      "num_tokens": 1777803.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.3580246913580247,
+      "grad_norm": 0.6213059425354004,
+      "learning_rate": 9.800784439786286e-05,
+      "loss": 0.6425,
+      "mean_token_accuracy": 0.750441175699234,
+      "num_tokens": 1798283.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.373456790123457,
+      "grad_norm": 0.5405688881874084,
+      "learning_rate": 9.793591072836978e-05,
+      "loss": 0.6216,
+      "mean_token_accuracy": 0.7597058892250061,
+      "num_tokens": 1818763.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 0.6881203055381775,
+      "learning_rate": 9.786272863357063e-05,
+      "loss": 0.6242,
+      "mean_token_accuracy": 0.7628431379795074,
+      "num_tokens": 1839243.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.404320987654321,
+      "grad_norm": 0.48711517453193665,
+      "learning_rate": 9.778830001939307e-05,
+      "loss": 0.6287,
+      "mean_token_accuracy": 0.759411770105362,
+      "num_tokens": 1859723.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.4197530864197532,
+      "grad_norm": 0.5363081097602844,
+      "learning_rate": 9.771262682422866e-05,
+      "loss": 0.63,
+      "mean_token_accuracy": 0.7583823561668396,
+      "num_tokens": 1880203.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.4351851851851851,
+      "grad_norm": 0.5898856520652771,
+      "learning_rate": 9.76357110188824e-05,
+      "loss": 0.6266,
+      "mean_token_accuracy": 0.7604411780834198,
+      "num_tokens": 1900683.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.4506172839506173,
+      "grad_norm": 0.5043850541114807,
+      "learning_rate": 9.755755460652137e-05,
+      "loss": 0.6011,
+      "mean_token_accuracy": 0.7688725531101227,
+      "num_tokens": 1921163.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.4660493827160495,
+      "grad_norm": 0.5246235132217407,
+      "learning_rate": 9.747815962262255e-05,
+      "loss": 0.6339,
+      "mean_token_accuracy": 0.7562745153903961,
+      "num_tokens": 1941643.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.5146046280860901,
+      "learning_rate": 9.73975281349198e-05,
+      "loss": 0.6269,
+      "mean_token_accuracy": 0.7591666638851166,
+      "num_tokens": 1962123.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4969135802469136,
+      "grad_norm": 0.5631639957427979,
+      "learning_rate": 9.73156622433501e-05,
+      "loss": 0.6384,
+      "mean_token_accuracy": 0.7557843148708343,
+      "num_tokens": 1982603.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.5123456790123457,
+      "grad_norm": 0.7671029567718506,
+      "learning_rate": 9.72325640799987e-05,
+      "loss": 0.6336,
+      "mean_token_accuracy": 0.7575490176677704,
+      "num_tokens": 2003083.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.5277777777777777,
+      "grad_norm": 0.5891373753547668,
+      "learning_rate": 9.71482358090438e-05,
+      "loss": 0.6412,
+      "mean_token_accuracy": 0.7533718824386597,
+      "num_tokens": 2023405.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.5432098765432098,
+      "grad_norm": 0.5099619030952454,
+      "learning_rate": 9.706267962669998e-05,
+      "loss": 0.6181,
+      "mean_token_accuracy": 0.7599019527435302,
+      "num_tokens": 2043885.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.558641975308642,
+      "grad_norm": 0.6285778880119324,
+      "learning_rate": 9.697589776116113e-05,
+      "loss": 0.618,
+      "mean_token_accuracy": 0.7612245142459869,
+      "num_tokens": 2064294.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.574074074074074,
+      "grad_norm": 0.5334492921829224,
+      "learning_rate": 9.688789247254237e-05,
+      "loss": 0.6331,
+      "mean_token_accuracy": 0.7553921639919281,
+      "num_tokens": 2084774.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5895061728395061,
+      "grad_norm": 0.6230431795120239,
+      "learning_rate": 9.679866605282122e-05,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.7686274588108063,
+      "num_tokens": 2105254.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6049382716049383,
+      "grad_norm": 0.560792863368988,
+      "learning_rate": 9.670822082577787e-05,
+      "loss": 0.622,
+      "mean_token_accuracy": 0.7606372594833374,
+      "num_tokens": 2125734.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6203703703703702,
+      "grad_norm": 0.5316160321235657,
+      "learning_rate": 9.661655914693471e-05,
+      "loss": 0.6215,
+      "mean_token_accuracy": 0.7624019622802735,
+      "num_tokens": 2146214.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6358024691358026,
+      "grad_norm": 0.5584502220153809,
+      "learning_rate": 9.652368340349494e-05,
+      "loss": 0.6274,
+      "mean_token_accuracy": 0.7590196132659912,
+      "num_tokens": 2166694.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.6512345679012346,
+      "grad_norm": 0.4828554391860962,
+      "learning_rate": 9.642959601428039e-05,
+      "loss": 0.62,
+      "mean_token_accuracy": 0.7612745046615601,
+      "num_tokens": 2187174.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.5727825164794922,
+      "learning_rate": 9.63342994296686e-05,
+      "loss": 0.6071,
+      "mean_token_accuracy": 0.7662254869937897,
+      "num_tokens": 2207654.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.682098765432099,
+      "grad_norm": 0.5390017032623291,
+      "learning_rate": 9.623779613152893e-05,
+      "loss": 0.6179,
+      "mean_token_accuracy": 0.764607846736908,
+      "num_tokens": 2228134.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6975308641975309,
+      "grad_norm": 0.5654057860374451,
+      "learning_rate": 9.614008863315789e-05,
+      "loss": 0.6068,
+      "mean_token_accuracy": 0.7667545199394226,
+      "num_tokens": 2248422.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7129629629629628,
+      "grad_norm": 0.565568208694458,
+      "learning_rate": 9.604117947921385e-05,
+      "loss": 0.6143,
+      "mean_token_accuracy": 0.7654411792755127,
+      "num_tokens": 2268902.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7283950617283952,
+      "grad_norm": 0.5519742369651794,
+      "learning_rate": 9.594107124565056e-05,
+      "loss": 0.6088,
+      "mean_token_accuracy": 0.7641176581382751,
+      "num_tokens": 2289382.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7438271604938271,
+      "grad_norm": 0.4558942914009094,
+      "learning_rate": 9.58397665396502e-05,
+      "loss": 0.6176,
+      "mean_token_accuracy": 0.7602451086044312,
+      "num_tokens": 2309862.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.7592592592592593,
+      "grad_norm": 0.5886722803115845,
+      "learning_rate": 9.573726799955544e-05,
+      "loss": 0.6081,
+      "mean_token_accuracy": 0.7652941167354583,
+      "num_tokens": 2330342.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7746913580246915,
+      "grad_norm": 0.5108247995376587,
+      "learning_rate": 9.563357829480076e-05,
+      "loss": 0.6278,
+      "mean_token_accuracy": 0.7587745070457459,
+      "num_tokens": 2350822.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7901234567901234,
+      "grad_norm": 0.6499772071838379,
+      "learning_rate": 9.552870012584282e-05,
+      "loss": 0.6137,
+      "mean_token_accuracy": 0.7662254869937897,
+      "num_tokens": 2371302.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8055555555555556,
+      "grad_norm": 0.5412532091140747,
+      "learning_rate": 9.542263622409027e-05,
+      "loss": 0.6159,
+      "mean_token_accuracy": 0.7634241282939911,
+      "num_tokens": 2391580.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.8209876543209877,
+      "grad_norm": 0.538313090801239,
+      "learning_rate": 9.53153893518325e-05,
+      "loss": 0.6332,
+      "mean_token_accuracy": 0.7576960802078248,
+      "num_tokens": 2412060.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.8364197530864197,
+      "grad_norm": 0.6328610777854919,
+      "learning_rate": 9.520696230216781e-05,
+      "loss": 0.6246,
+      "mean_token_accuracy": 0.759950977563858,
+      "num_tokens": 2432540.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.5538372993469238,
+      "learning_rate": 9.509735789893059e-05,
+      "loss": 0.6197,
+      "mean_token_accuracy": 0.7624509751796722,
+      "num_tokens": 2453020.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.867283950617284,
+      "grad_norm": 0.555073618888855,
+      "learning_rate": 9.498657899661774e-05,
+      "loss": 0.6224,
+      "mean_token_accuracy": 0.7595588207244873,
+      "num_tokens": 2473500.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.882716049382716,
+      "grad_norm": 0.5462023019790649,
+      "learning_rate": 9.487462848031445e-05,
+      "loss": 0.6193,
+      "mean_token_accuracy": 0.7641176462173462,
+      "num_tokens": 2493980.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8981481481481481,
+      "grad_norm": 0.5492093563079834,
+      "learning_rate": 9.4761509265619e-05,
+      "loss": 0.6376,
+      "mean_token_accuracy": 0.7553431332111359,
+      "num_tokens": 2514460.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.9135802469135803,
+      "grad_norm": 0.5266892313957214,
+      "learning_rate": 9.464722429856674e-05,
+      "loss": 0.6163,
+      "mean_token_accuracy": 0.7632352948188782,
+      "num_tokens": 2534940.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.9290123456790123,
+      "grad_norm": 0.6665803790092468,
+      "learning_rate": 9.453177655555355e-05,
+      "loss": 0.6196,
+      "mean_token_accuracy": 0.7636274516582489,
+      "num_tokens": 2555420.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 0.567834734916687,
+      "learning_rate": 9.441516904325816e-05,
+      "loss": 0.622,
+      "mean_token_accuracy": 0.7607352912425995,
+      "num_tokens": 2575900.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.9598765432098766,
+      "grad_norm": 0.512845516204834,
+      "learning_rate": 9.42974047985639e-05,
+      "loss": 0.6248,
+      "mean_token_accuracy": 0.7564705908298492,
+      "num_tokens": 2596380.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.5521799921989441,
+      "learning_rate": 9.417848688847968e-05,
+      "loss": 0.6143,
+      "mean_token_accuracy": 0.7628431499004364,
+      "num_tokens": 2616860.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.9907407407407407,
+      "grad_norm": 0.47973841428756714,
+      "learning_rate": 9.405841841005998e-05,
+      "loss": 0.6087,
+      "mean_token_accuracy": 0.7673039317131043,
+      "num_tokens": 2637340.0,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6432122588157654,
+      "eval_mean_token_accuracy": 0.756913377557482,
+      "eval_num_tokens": 2648092.0,
+      "eval_runtime": 3.2747,
+      "eval_samples_per_second": 83.367,
+      "eval_steps_per_second": 10.688,
+      "step": 1296
+    },
+    {
+      "epoch": 2.006172839506173,
+      "grad_norm": 0.5479162931442261,
+      "learning_rate": 9.393720249032428e-05,
+      "loss": 0.5923,
+      "mean_token_accuracy": 0.7697549045085907,
+      "num_tokens": 2656284.0,
+      "step": 1300
+    },
+    {
+      "epoch": 2.021604938271605,
+      "grad_norm": 0.656440794467926,
+      "learning_rate": 9.381484228617561e-05,
+      "loss": 0.6079,
+      "mean_token_accuracy": 0.7672058880329132,
+      "num_tokens": 2676764.0,
+      "step": 1310
+    },
+    {
+      "epoch": 2.037037037037037,
+      "grad_norm": 0.6051917672157288,
+      "learning_rate": 9.369134098431836e-05,
+      "loss": 0.5848,
+      "mean_token_accuracy": 0.7749509871006012,
+      "num_tokens": 2697244.0,
+      "step": 1320
+    },
+    {
+      "epoch": 2.052469135802469,
+      "grad_norm": 0.7500020861625671,
+      "learning_rate": 9.356670180117515e-05,
+      "loss": 0.593,
+      "mean_token_accuracy": 0.7720588266849517,
+      "num_tokens": 2717724.0,
+      "step": 1330
+    },
+    {
+      "epoch": 2.067901234567901,
+      "grad_norm": 0.610857367515564,
+      "learning_rate": 9.344092798280326e-05,
+      "loss": 0.5937,
+      "mean_token_accuracy": 0.7733823597431183,
+      "num_tokens": 2738204.0,
+      "step": 1340
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.6656193733215332,
+      "learning_rate": 9.331402280480996e-05,
+      "loss": 0.5904,
+      "mean_token_accuracy": 0.7753921687602997,
+      "num_tokens": 2758684.0,
+      "step": 1350
+    },
+    {
+      "epoch": 2.0987654320987654,
+      "grad_norm": 0.5261437296867371,
+      "learning_rate": 9.318598957226722e-05,
+      "loss": 0.5921,
+      "mean_token_accuracy": 0.7725490152835846,
+      "num_tokens": 2779164.0,
+      "step": 1360
+    },
+    {
+      "epoch": 2.1141975308641974,
+      "grad_norm": 0.5618685483932495,
+      "learning_rate": 9.305683161962569e-05,
+      "loss": 0.5935,
+      "mean_token_accuracy": 0.770976084470749,
+      "num_tokens": 2799402.0,
+      "step": 1370
+    },
+    {
+      "epoch": 2.1296296296296298,
+      "grad_norm": 0.6032730340957642,
+      "learning_rate": 9.292655231062777e-05,
+      "loss": 0.597,
+      "mean_token_accuracy": 0.7680882334709167,
+      "num_tokens": 2819882.0,
+      "step": 1380
+    },
+    {
+      "epoch": 2.1450617283950617,
+      "grad_norm": 0.6468005776405334,
+      "learning_rate": 9.279515503822012e-05,
+      "loss": 0.5809,
+      "mean_token_accuracy": 0.775245088338852,
+      "num_tokens": 2840362.0,
+      "step": 1390
+    },
+    {
+      "epoch": 2.1604938271604937,
+      "grad_norm": 0.600806713104248,
+      "learning_rate": 9.266264322446513e-05,
+      "loss": 0.5778,
+      "mean_token_accuracy": 0.7759313702583313,
+      "num_tokens": 2860842.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.175925925925926,
+      "grad_norm": 0.5504996180534363,
+      "learning_rate": 9.2529020320452e-05,
+      "loss": 0.5868,
+      "mean_token_accuracy": 0.772892165184021,
+      "num_tokens": 2881322.0,
+      "step": 1410
+    },
+    {
+      "epoch": 2.191358024691358,
+      "grad_norm": 0.7661624550819397,
+      "learning_rate": 9.239428980620668e-05,
+      "loss": 0.577,
+      "mean_token_accuracy": 0.7785064160823822,
+      "num_tokens": 2901731.0,
+      "step": 1420
+    },
+    {
+      "epoch": 2.20679012345679,
+      "grad_norm": 0.6991685628890991,
+      "learning_rate": 9.22584551906014e-05,
+      "loss": 0.5985,
+      "mean_token_accuracy": 0.769460791349411,
+      "num_tokens": 2922211.0,
+      "step": 1430
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.707591712474823,
+      "learning_rate": 9.212152001126309e-05,
+      "loss": 0.5884,
+      "mean_token_accuracy": 0.7741176426410675,
+      "num_tokens": 2942691.0,
+      "step": 1440
+    },
+    {
+      "epoch": 2.2376543209876543,
+      "grad_norm": 0.6777827739715576,
+      "learning_rate": 9.198348783448143e-05,
+      "loss": 0.5912,
+      "mean_token_accuracy": 0.7737254917621612,
+      "num_tokens": 2963171.0,
+      "step": 1450
+    },
+    {
+      "epoch": 2.253086419753086,
+      "grad_norm": 0.693082332611084,
+      "learning_rate": 9.184436225511593e-05,
+      "loss": 0.5853,
+      "mean_token_accuracy": 0.7740196108818054,
+      "num_tokens": 2983651.0,
+      "step": 1460
+    },
+    {
+      "epoch": 2.2685185185185186,
+      "grad_norm": 0.6395755410194397,
+      "learning_rate": 9.170414689650218e-05,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.7693137288093567,
+      "num_tokens": 3004131.0,
+      "step": 1470
+    },
+    {
+      "epoch": 2.2839506172839505,
+      "grad_norm": 0.6955903172492981,
+      "learning_rate": 9.156284541035767e-05,
+      "loss": 0.6123,
+      "mean_token_accuracy": 0.7632352948188782,
+      "num_tokens": 3024611.0,
+      "step": 1480
+    },
+    {
+      "epoch": 2.299382716049383,
+      "grad_norm": 0.634459376335144,
+      "learning_rate": 9.142046147668656e-05,
+      "loss": 0.6126,
+      "mean_token_accuracy": 0.7638235270977021,
+      "num_tokens": 3045091.0,
+      "step": 1490
+    },
+    {
+      "epoch": 2.314814814814815,
+      "grad_norm": 0.6977143883705139,
+      "learning_rate": 9.127699880368388e-05,
+      "loss": 0.5903,
+      "mean_token_accuracy": 0.7724509835243225,
+      "num_tokens": 3065571.0,
+      "step": 1500
+    },
+    {
+      "epoch": 2.330246913580247,
+      "grad_norm": 0.906640350818634,
+      "learning_rate": 9.113246112763896e-05,
+      "loss": 0.5925,
+      "mean_token_accuracy": 0.7721118927001953,
+      "num_tokens": 3085849.0,
+      "step": 1510
+    },
+    {
+      "epoch": 2.3456790123456788,
+      "grad_norm": 0.6876031160354614,
+      "learning_rate": 9.098685221283809e-05,
+      "loss": 0.5968,
+      "mean_token_accuracy": 0.7706862807273864,
+      "num_tokens": 3106329.0,
+      "step": 1520
+    },
+    {
+      "epoch": 2.361111111111111,
+      "grad_norm": 0.7915614247322083,
+      "learning_rate": 9.084017585146653e-05,
+      "loss": 0.5927,
+      "mean_token_accuracy": 0.7707352995872497,
+      "num_tokens": 3126809.0,
+      "step": 1530
+    },
+    {
+      "epoch": 2.376543209876543,
+      "grad_norm": 0.5830466151237488,
+      "learning_rate": 9.069243586350975e-05,
+      "loss": 0.599,
+      "mean_token_accuracy": 0.7685294091701508,
+      "num_tokens": 3147289.0,
+      "step": 1540
+    },
+    {
+      "epoch": 2.3919753086419755,
+      "grad_norm": 0.6367495059967041,
+      "learning_rate": 9.054363609665388e-05,
+      "loss": 0.6026,
+      "mean_token_accuracy": 0.7685784339904785,
+      "num_tokens": 3167769.0,
+      "step": 1550
+    },
+    {
+      "epoch": 2.4074074074074074,
+      "grad_norm": 0.9314106702804565,
+      "learning_rate": 9.039378042618556e-05,
+      "loss": 0.5914,
+      "mean_token_accuracy": 0.774117648601532,
+      "num_tokens": 3188249.0,
+      "step": 1560
+    },
+    {
+      "epoch": 2.4228395061728394,
+      "grad_norm": 0.6892368197441101,
+      "learning_rate": 9.0242872754891e-05,
+      "loss": 0.5939,
+      "mean_token_accuracy": 0.7718548774719238,
+      "num_tokens": 3208619.0,
+      "step": 1570
+    },
+    {
+      "epoch": 2.4382716049382718,
+      "grad_norm": 0.5464644432067871,
+      "learning_rate": 9.009091701295434e-05,
+      "loss": 0.5905,
+      "mean_token_accuracy": 0.7747549057006836,
+      "num_tokens": 3229099.0,
+      "step": 1580
+    },
+    {
+      "epoch": 2.4537037037037037,
+      "grad_norm": 0.5427695512771606,
+      "learning_rate": 8.993791715785528e-05,
+      "loss": 0.6031,
+      "mean_token_accuracy": 0.7664862751960755,
+      "num_tokens": 3249421.0,
+      "step": 1590
+    },
+    {
+      "epoch": 2.4691358024691357,
+      "grad_norm": 0.6546815037727356,
+      "learning_rate": 8.978387717426601e-05,
+      "loss": 0.5918,
+      "mean_token_accuracy": 0.7709313809871674,
+      "num_tokens": 3269901.0,
+      "step": 1600
+    },
+    {
+      "epoch": 2.484567901234568,
+      "grad_norm": 0.6619100570678711,
+      "learning_rate": 8.962880107394747e-05,
+      "loss": 0.6081,
+      "mean_token_accuracy": 0.7659300684928894,
+      "num_tokens": 3290252.0,
+      "step": 1610
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.722586452960968,
+      "learning_rate": 8.947269289564482e-05,
+      "loss": 0.5891,
+      "mean_token_accuracy": 0.7740368068218231,
+      "num_tokens": 3310540.0,
+      "step": 1620
+    },
+    {
+      "epoch": 2.515432098765432,
+      "grad_norm": 0.5784828066825867,
+      "learning_rate": 8.931555670498229e-05,
+      "loss": 0.5961,
+      "mean_token_accuracy": 0.7705882370471955,
+      "num_tokens": 3331020.0,
+      "step": 1630
+    },
+    {
+      "epoch": 2.5308641975308643,
+      "grad_norm": 0.7214418649673462,
+      "learning_rate": 8.915739659435732e-05,
+      "loss": 0.5771,
+      "mean_token_accuracy": 0.7781862795352936,
+      "num_tokens": 3351500.0,
+      "step": 1640
+    },
+    {
+      "epoch": 2.5462962962962963,
+      "grad_norm": 0.6226558685302734,
+      "learning_rate": 8.899821668283388e-05,
+      "loss": 0.5896,
+      "mean_token_accuracy": 0.7740686297416687,
+      "num_tokens": 3371980.0,
+      "step": 1650
+    },
+    {
+      "epoch": 2.5617283950617287,
+      "grad_norm": 0.5680100917816162,
+      "learning_rate": 8.883802111603532e-05,
+      "loss": 0.5905,
+      "mean_token_accuracy": 0.7712745130062103,
+      "num_tokens": 3392460.0,
+      "step": 1660
+    },
+    {
+      "epoch": 2.5771604938271606,
+      "grad_norm": 0.6910707950592041,
+      "learning_rate": 8.867681406603632e-05,
+      "loss": 0.5973,
+      "mean_token_accuracy": 0.7682352960109711,
+      "num_tokens": 3412940.0,
+      "step": 1670
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.5533532500267029,
+      "learning_rate": 8.851459973125424e-05,
+      "loss": 0.6045,
+      "mean_token_accuracy": 0.7657843172550202,
+      "num_tokens": 3433420.0,
+      "step": 1680
+    },
+    {
+      "epoch": 2.6080246913580245,
+      "grad_norm": 0.6664072275161743,
+      "learning_rate": 8.835138233633986e-05,
+      "loss": 0.6021,
+      "mean_token_accuracy": 0.7676470637321472,
+      "num_tokens": 3453900.0,
+      "step": 1690
+    },
+    {
+      "epoch": 2.623456790123457,
+      "grad_norm": 0.7590135931968689,
+      "learning_rate": 8.818716613206718e-05,
+      "loss": 0.6085,
+      "mean_token_accuracy": 0.7683761894702912,
+      "num_tokens": 3474217.0,
+      "step": 1700
+    },
+    {
+      "epoch": 2.638888888888889,
+      "grad_norm": 0.7670077681541443,
+      "learning_rate": 8.802195539522298e-05,
+      "loss": 0.6063,
+      "mean_token_accuracy": 0.7649509847164154,
+      "num_tokens": 3494697.0,
+      "step": 1710
+    },
+    {
+      "epoch": 2.6543209876543212,
+      "grad_norm": 0.6275266408920288,
+      "learning_rate": 8.785575442849512e-05,
+      "loss": 0.6012,
+      "mean_token_accuracy": 0.766274505853653,
+      "num_tokens": 3515177.0,
+      "step": 1720
+    },
+    {
+      "epoch": 2.669753086419753,
+      "grad_norm": 0.5899403691291809,
+      "learning_rate": 8.768856756036075e-05,
+      "loss": 0.5784,
+      "mean_token_accuracy": 0.7777941226959229,
+      "num_tokens": 3535657.0,
+      "step": 1730
+    },
+    {
+      "epoch": 2.685185185185185,
+      "grad_norm": 0.767240583896637,
+      "learning_rate": 8.752039914497344e-05,
+      "loss": 0.6064,
+      "mean_token_accuracy": 0.7683333456516266,
+      "num_tokens": 3556137.0,
+      "step": 1740
+    },
+    {
+      "epoch": 2.700617283950617,
+      "grad_norm": 0.6055841445922852,
+      "learning_rate": 8.73512535620498e-05,
+      "loss": 0.6111,
+      "mean_token_accuracy": 0.7638725459575653,
+      "num_tokens": 3576617.0,
+      "step": 1750
+    },
+    {
+      "epoch": 2.7160493827160495,
+      "grad_norm": 0.5842066407203674,
+      "learning_rate": 8.718113521675551e-05,
+      "loss": 0.5959,
+      "mean_token_accuracy": 0.7691176474094391,
+      "num_tokens": 3597097.0,
+      "step": 1760
+    },
+    {
+      "epoch": 2.7314814814814814,
+      "grad_norm": 0.6634451746940613,
+      "learning_rate": 8.70100485395904e-05,
+      "loss": 0.5886,
+      "mean_token_accuracy": 0.7744088768959045,
+      "num_tokens": 3617336.0,
+      "step": 1770
+    },
+    {
+      "epoch": 2.746913580246914,
+      "grad_norm": 0.670170247554779,
+      "learning_rate": 8.683799798627327e-05,
+      "loss": 0.5917,
+      "mean_token_accuracy": 0.7728895008563995,
+      "num_tokens": 3637802.0,
+      "step": 1780
+    },
+    {
+      "epoch": 2.7623456790123457,
+      "grad_norm": 0.7129385471343994,
+      "learning_rate": 8.666498803762575e-05,
+      "loss": 0.5779,
+      "mean_token_accuracy": 0.7773529410362243,
+      "num_tokens": 3658282.0,
+      "step": 1790
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.6470578908920288,
+      "learning_rate": 8.649102319945556e-05,
+      "loss": 0.5944,
+      "mean_token_accuracy": 0.771666657924652,
+      "num_tokens": 3678762.0,
+      "step": 1800
+    },
+    {
+      "epoch": 2.7932098765432096,
+      "grad_norm": 0.6014609932899475,
+      "learning_rate": 8.631610800243926e-05,
+      "loss": 0.596,
+      "mean_token_accuracy": 0.7687254965305328,
+      "num_tokens": 3699242.0,
+      "step": 1810
+    },
+    {
+      "epoch": 2.808641975308642,
+      "grad_norm": 0.6266966462135315,
+      "learning_rate": 8.614024700200418e-05,
+      "loss": 0.5896,
+      "mean_token_accuracy": 0.7722058892250061,
+      "num_tokens": 3719722.0,
+      "step": 1820
+    },
+    {
+      "epoch": 2.824074074074074,
+      "grad_norm": 0.7801739573478699,
+      "learning_rate": 8.596344477820982e-05,
+      "loss": 0.5912,
+      "mean_token_accuracy": 0.7734313845634461,
+      "num_tokens": 3740202.0,
+      "step": 1830
+    },
+    {
+      "epoch": 2.8395061728395063,
+      "grad_norm": 0.5488538146018982,
+      "learning_rate": 8.578570593562856e-05,
+      "loss": 0.6044,
+      "mean_token_accuracy": 0.7692156851291656,
+      "num_tokens": 3760682.0,
+      "step": 1840
+    },
+    {
+      "epoch": 2.8549382716049383,
+      "grad_norm": 0.5966465473175049,
+      "learning_rate": 8.560703510322574e-05,
+      "loss": 0.5958,
+      "mean_token_accuracy": 0.7715196192264557,
+      "num_tokens": 3781162.0,
+      "step": 1850
+    },
+    {
+      "epoch": 2.8703703703703702,
+      "grad_norm": 0.6425583362579346,
+      "learning_rate": 8.54274369342391e-05,
+      "loss": 0.594,
+      "mean_token_accuracy": 0.7702941179275513,
+      "num_tokens": 3801642.0,
+      "step": 1860
+    },
+    {
+      "epoch": 2.8858024691358026,
+      "grad_norm": 0.6507608294487,
+      "learning_rate": 8.524691610605755e-05,
+      "loss": 0.6128,
+      "mean_token_accuracy": 0.7628431439399719,
+      "num_tokens": 3822122.0,
+      "step": 1870
+    },
+    {
+      "epoch": 2.9012345679012346,
+      "grad_norm": 0.6581034660339355,
+      "learning_rate": 8.506547732009949e-05,
+      "loss": 0.6006,
+      "mean_token_accuracy": 0.7693137288093567,
+      "num_tokens": 3842602.0,
+      "step": 1880
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 0.639123797416687,
+      "learning_rate": 8.488312530169019e-05,
+      "loss": 0.6165,
+      "mean_token_accuracy": 0.7635294079780579,
+      "num_tokens": 3863082.0,
+      "step": 1890
+    },
+    {
+      "epoch": 2.932098765432099,
+      "grad_norm": 0.633488118648529,
+      "learning_rate": 8.469986479993885e-05,
+      "loss": 0.6015,
+      "mean_token_accuracy": 0.7681862771511078,
+      "num_tokens": 3883562.0,
+      "step": 1900
+    },
+    {
+      "epoch": 2.947530864197531,
+      "grad_norm": 0.7640633583068848,
+      "learning_rate": 8.451570058761487e-05,
+      "loss": 0.5788,
+      "mean_token_accuracy": 0.7772058844566345,
+      "num_tokens": 3904042.0,
+      "step": 1910
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.6150678396224976,
+      "learning_rate": 8.433063746102357e-05,
+      "loss": 0.5874,
+      "mean_token_accuracy": 0.7721568644046783,
+      "num_tokens": 3924522.0,
+      "step": 1920
+    },
+    {
+      "epoch": 2.978395061728395,
+      "grad_norm": 0.5631530284881592,
+      "learning_rate": 8.414468023988124e-05,
+      "loss": 0.5957,
+      "mean_token_accuracy": 0.7705882310867309,
+      "num_tokens": 3945002.0,
+      "step": 1930
+    },
+    {
+      "epoch": 2.993827160493827,
+      "grad_norm": 0.5055695176124573,
+      "learning_rate": 8.395783376718966e-05,
+      "loss": 0.5886,
+      "mean_token_accuracy": 0.7745097994804382,
+      "num_tokens": 3965482.0,
+      "step": 1940
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6486226320266724,
+      "eval_mean_token_accuracy": 0.7536231398582458,
+      "eval_num_tokens": 3972138.0,
+      "eval_runtime": 3.2699,
+      "eval_samples_per_second": 83.488,
+      "eval_steps_per_second": 10.704,
+      "step": 1944
+    },
+    {
+      "epoch": 3.009259259259259,
+      "grad_norm": 0.6203161478042603,
+      "learning_rate": 8.377010290910996e-05,
+      "loss": 0.5979,
+      "mean_token_accuracy": 0.7712745070457458,
+      "num_tokens": 3984426.0,
+      "step": 1950
+    },
+    {
+      "epoch": 3.0246913580246915,
+      "grad_norm": 0.9652954936027527,
+      "learning_rate": 8.358149255483585e-05,
+      "loss": 0.5869,
+      "mean_token_accuracy": 0.7755882382392884,
+      "num_tokens": 4004906.0,
+      "step": 1960
+    },
+    {
+      "epoch": 3.0401234567901234,
+      "grad_norm": 0.7981434464454651,
+      "learning_rate": 8.339200761646633e-05,
+      "loss": 0.556,
+      "mean_token_accuracy": 0.7872981905937195,
+      "num_tokens": 4025194.0,
+      "step": 1970
+    },
+    {
+      "epoch": 3.0555555555555554,
+      "grad_norm": 0.9313560724258423,
+      "learning_rate": 8.320165302887776e-05,
+      "loss": 0.5537,
+      "mean_token_accuracy": 0.7861764788627624,
+      "num_tokens": 4045674.0,
+      "step": 1980
+    },
+    {
+      "epoch": 3.0709876543209877,
+      "grad_norm": 0.5494497418403625,
+      "learning_rate": 8.301043374959532e-05,
+      "loss": 0.549,
+      "mean_token_accuracy": 0.7880392134189605,
+      "num_tokens": 4066154.0,
+      "step": 1990
+    },
+    {
+      "epoch": 3.0864197530864197,
+      "grad_norm": 0.8959032297134399,
+      "learning_rate": 8.281835475866388e-05,
+      "loss": 0.5554,
+      "mean_token_accuracy": 0.7859803915023804,
+      "num_tokens": 4086634.0,
+      "step": 2000
+    },
+    {
+      "epoch": 3.1018518518518516,
+      "grad_norm": 1.0864795446395874,
+      "learning_rate": 8.262542105851836e-05,
+      "loss": 0.5572,
+      "mean_token_accuracy": 0.788381040096283,
+      "num_tokens": 4107043.0,
+      "step": 2010
+    },
+    {
+      "epoch": 3.117283950617284,
+      "grad_norm": 0.8090967535972595,
+      "learning_rate": 8.24316376738534e-05,
+      "loss": 0.5615,
+      "mean_token_accuracy": 0.784509801864624,
+      "num_tokens": 4127523.0,
+      "step": 2020
+    },
+    {
+      "epoch": 3.132716049382716,
+      "grad_norm": 0.8810270428657532,
+      "learning_rate": 8.22370096514925e-05,
+      "loss": 0.5554,
+      "mean_token_accuracy": 0.7892647027969361,
+      "num_tokens": 4148003.0,
+      "step": 2030
+    },
+    {
+      "epoch": 3.148148148148148,
+      "grad_norm": 0.775962233543396,
+      "learning_rate": 8.204154206025664e-05,
+      "loss": 0.5553,
+      "mean_token_accuracy": 0.787058824300766,
+      "num_tokens": 4168483.0,
+      "step": 2040
+    },
+    {
+      "epoch": 3.1635802469135803,
+      "grad_norm": 0.7970689535140991,
+      "learning_rate": 8.184523999083215e-05,
+      "loss": 0.5506,
+      "mean_token_accuracy": 0.7893137335777283,
+      "num_tokens": 4188963.0,
+      "step": 2050
+    },
+    {
+      "epoch": 3.1790123456790123,
+      "grad_norm": 0.7264294028282166,
+      "learning_rate": 8.164810855563826e-05,
+      "loss": 0.5427,
+      "mean_token_accuracy": 0.7917156875133514,
+      "num_tokens": 4209443.0,
+      "step": 2060
+    },
+    {
+      "epoch": 3.1944444444444446,
+      "grad_norm": 0.7700381875038147,
+      "learning_rate": 8.14501528886939e-05,
+      "loss": 0.5596,
+      "mean_token_accuracy": 0.7846568584442138,
+      "num_tokens": 4229923.0,
+      "step": 2070
+    },
+    {
+      "epoch": 3.2098765432098766,
+      "grad_norm": 0.6869605779647827,
+      "learning_rate": 8.125137814548393e-05,
+      "loss": 0.565,
+      "mean_token_accuracy": 0.7816666662693024,
+      "num_tokens": 4250403.0,
+      "step": 2080
+    },
+    {
+      "epoch": 3.2253086419753085,
+      "grad_norm": 0.9533533453941345,
+      "learning_rate": 8.105178950282502e-05,
+      "loss": 0.5558,
+      "mean_token_accuracy": 0.7848656356334687,
+      "num_tokens": 4270681.0,
+      "step": 2090
+    },
+    {
+      "epoch": 3.240740740740741,
+      "grad_norm": 0.6663597226142883,
+      "learning_rate": 8.085139215873068e-05,
+      "loss": 0.568,
+      "mean_token_accuracy": 0.7806372523307801,
+      "num_tokens": 4291161.0,
+      "step": 2100
+    },
+    {
+      "epoch": 3.256172839506173,
+      "grad_norm": 0.7175901532173157,
+      "learning_rate": 8.065019133227595e-05,
+      "loss": 0.5582,
+      "mean_token_accuracy": 0.7855882346630096,
+      "num_tokens": 4311641.0,
+      "step": 2110
+    },
+    {
+      "epoch": 3.271604938271605,
+      "grad_norm": 0.6771725416183472,
+      "learning_rate": 8.04481922634615e-05,
+      "loss": 0.5646,
+      "mean_token_accuracy": 0.7815686285495758,
+      "num_tokens": 4332121.0,
+      "step": 2120
+    },
+    {
+      "epoch": 3.287037037037037,
+      "grad_norm": 0.857525646686554,
+      "learning_rate": 8.024540021307708e-05,
+      "loss": 0.5595,
+      "mean_token_accuracy": 0.7864215731620788,
+      "num_tokens": 4352601.0,
+      "step": 2130
+    },
+    {
+      "epoch": 3.302469135802469,
+      "grad_norm": 0.7147991061210632,
+      "learning_rate": 8.004182046256463e-05,
+      "loss": 0.5696,
+      "mean_token_accuracy": 0.7819607973098754,
+      "num_tokens": 4373081.0,
+      "step": 2140
+    },
+    {
+      "epoch": 3.317901234567901,
+      "grad_norm": 0.9903934597969055,
+      "learning_rate": 7.983745831388061e-05,
+      "loss": 0.5676,
+      "mean_token_accuracy": 0.7822549104690552,
+      "num_tokens": 4393561.0,
+      "step": 2150
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.6776948571205139,
+      "learning_rate": 7.963231908935798e-05,
+      "loss": 0.557,
+      "mean_token_accuracy": 0.7848039329051971,
+      "num_tokens": 4414041.0,
+      "step": 2160
+    },
+    {
+      "epoch": 3.3487654320987654,
+      "grad_norm": 1.0719963312149048,
+      "learning_rate": 7.942640813156759e-05,
+      "loss": 0.5309,
+      "mean_token_accuracy": 0.7917156994342804,
+      "num_tokens": 4434521.0,
+      "step": 2170
+    },
+    {
+      "epoch": 3.3641975308641974,
+      "grad_norm": 1.040563702583313,
+      "learning_rate": 7.921973080317904e-05,
+      "loss": 0.5558,
+      "mean_token_accuracy": 0.7859313726425171,
+      "num_tokens": 4455001.0,
+      "step": 2180
+    },
+    {
+      "epoch": 3.3796296296296298,
+      "grad_norm": 0.7600565552711487,
+      "learning_rate": 7.901229248682096e-05,
+      "loss": 0.5506,
+      "mean_token_accuracy": 0.7896078407764435,
+      "num_tokens": 4475481.0,
+      "step": 2190
+    },
+    {
+      "epoch": 3.3950617283950617,
+      "grad_norm": 0.9521936774253845,
+      "learning_rate": 7.880409858494094e-05,
+      "loss": 0.5542,
+      "mean_token_accuracy": 0.7869117617607116,
+      "num_tokens": 4495961.0,
+      "step": 2200
+    },
+    {
+      "epoch": 3.4104938271604937,
+      "grad_norm": 0.8253932595252991,
+      "learning_rate": 7.85951545196647e-05,
+      "loss": 0.553,
+      "mean_token_accuracy": 0.7902941167354584,
+      "num_tokens": 4516441.0,
+      "step": 2210
+    },
+    {
+      "epoch": 3.425925925925926,
+      "grad_norm": 0.6921856999397278,
+      "learning_rate": 7.838546573265497e-05,
+      "loss": 0.5571,
+      "mean_token_accuracy": 0.7853431403636932,
+      "num_tokens": 4536921.0,
+      "step": 2220
+    },
+    {
+      "epoch": 3.441358024691358,
+      "grad_norm": 1.0502287149429321,
+      "learning_rate": 7.817503768496974e-05,
+      "loss": 0.5536,
+      "mean_token_accuracy": 0.7885784268379211,
+      "num_tokens": 4557401.0,
+      "step": 2230
+    },
+    {
+      "epoch": 3.45679012345679,
+      "grad_norm": 0.7708560228347778,
+      "learning_rate": 7.796387585692004e-05,
+      "loss": 0.5467,
+      "mean_token_accuracy": 0.7899278044700623,
+      "num_tokens": 4577639.0,
+      "step": 2240
+    },
+    {
+      "epoch": 3.4722222222222223,
+      "grad_norm": 0.7451075315475464,
+      "learning_rate": 7.775198574792718e-05,
+      "loss": 0.5785,
+      "mean_token_accuracy": 0.7762254893779754,
+      "num_tokens": 4598119.0,
+      "step": 2250
+    },
+    {
+      "epoch": 3.4876543209876543,
+      "grad_norm": 0.8659241795539856,
+      "learning_rate": 7.753937287637958e-05,
+      "loss": 0.5712,
+      "mean_token_accuracy": 0.7794876754283905,
+      "num_tokens": 4618358.0,
+      "step": 2260
+    },
+    {
+      "epoch": 3.503086419753086,
+      "grad_norm": 0.7298393249511719,
+      "learning_rate": 7.7326042779489e-05,
+      "loss": 0.5672,
+      "mean_token_accuracy": 0.780980396270752,
+      "num_tokens": 4638838.0,
+      "step": 2270
+    },
+    {
+      "epoch": 3.5185185185185186,
+      "grad_norm": 0.7848004102706909,
+      "learning_rate": 7.71120010131464e-05,
+      "loss": 0.5694,
+      "mean_token_accuracy": 0.781519603729248,
+      "num_tokens": 4659318.0,
+      "step": 2280
+    },
+    {
+      "epoch": 3.5339506172839505,
+      "grad_norm": 0.6988353133201599,
+      "learning_rate": 7.689725315177712e-05,
+      "loss": 0.5775,
+      "mean_token_accuracy": 0.7789215743541718,
+      "num_tokens": 4679798.0,
+      "step": 2290
+    },
+    {
+      "epoch": 3.549382716049383,
+      "grad_norm": 0.8431084156036377,
+      "learning_rate": 7.668180478819586e-05,
+      "loss": 0.5543,
+      "mean_token_accuracy": 0.7889705955982208,
+      "num_tokens": 4700278.0,
+      "step": 2300
+    },
+    {
+      "epoch": 3.564814814814815,
+      "grad_norm": 0.8930009007453918,
+      "learning_rate": 7.64656615334609e-05,
+      "loss": 0.5751,
+      "mean_token_accuracy": 0.778970581293106,
+      "num_tokens": 4720758.0,
+      "step": 2310
+    },
+    {
+      "epoch": 3.580246913580247,
+      "grad_norm": 0.6832001805305481,
+      "learning_rate": 7.6248829016728e-05,
+      "loss": 0.5582,
+      "mean_token_accuracy": 0.7844607830047607,
+      "num_tokens": 4741238.0,
+      "step": 2320
+    },
+    {
+      "epoch": 3.5956790123456788,
+      "grad_norm": 0.8667986989021301,
+      "learning_rate": 7.603131288510388e-05,
+      "loss": 0.5713,
+      "mean_token_accuracy": 0.7819117605686188,
+      "num_tokens": 4761718.0,
+      "step": 2330
+    },
+    {
+      "epoch": 3.611111111111111,
+      "grad_norm": 1.0461276769638062,
+      "learning_rate": 7.581311880349897e-05,
+      "loss": 0.5767,
+      "mean_token_accuracy": 0.7767647087574006,
+      "num_tokens": 4782198.0,
+      "step": 2340
+    },
+    {
+      "epoch": 3.626543209876543,
+      "grad_norm": 0.9188404679298401,
+      "learning_rate": 7.559425245448006e-05,
+      "loss": 0.5698,
+      "mean_token_accuracy": 0.7805882334709168,
+      "num_tokens": 4802678.0,
+      "step": 2350
+    },
+    {
+      "epoch": 3.6419753086419755,
+      "grad_norm": 0.7836340069770813,
+      "learning_rate": 7.537471953812219e-05,
+      "loss": 0.5619,
+      "mean_token_accuracy": 0.7834803938865662,
+      "num_tokens": 4823158.0,
+      "step": 2360
+    },
+    {
+      "epoch": 3.6574074074074074,
+      "grad_norm": 0.7945846319198608,
+      "learning_rate": 7.515452577186025e-05,
+      "loss": 0.5763,
+      "mean_token_accuracy": 0.7787730455398559,
+      "num_tokens": 4843370.0,
+      "step": 2370
+    },
+    {
+      "epoch": 3.6728395061728394,
+      "grad_norm": 0.8514427542686462,
+      "learning_rate": 7.493367689034005e-05,
+      "loss": 0.5719,
+      "mean_token_accuracy": 0.7798039257526398,
+      "num_tokens": 4863850.0,
+      "step": 2380
+    },
+    {
+      "epoch": 3.6882716049382713,
+      "grad_norm": 0.8486166596412659,
+      "learning_rate": 7.471217864526901e-05,
+      "loss": 0.5651,
+      "mean_token_accuracy": 0.7819032847881318,
+      "num_tokens": 4884167.0,
+      "step": 2390
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 0.8120325207710266,
+      "learning_rate": 7.449003680526631e-05,
+      "loss": 0.5498,
+      "mean_token_accuracy": 0.7903431355953217,
+      "num_tokens": 4904647.0,
+      "step": 2400
+    },
+    {
+      "epoch": 3.7191358024691357,
+      "grad_norm": 0.872773289680481,
+      "learning_rate": 7.426725715571268e-05,
+      "loss": 0.5708,
+      "mean_token_accuracy": 0.7812745153903962,
+      "num_tokens": 4925127.0,
+      "step": 2410
+    },
+    {
+      "epoch": 3.734567901234568,
+      "grad_norm": 0.8291837573051453,
+      "learning_rate": 7.404384549859976e-05,
+      "loss": 0.5563,
+      "mean_token_accuracy": 0.7865686237812042,
+      "num_tokens": 4945607.0,
+      "step": 2420
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 1.0184736251831055,
+      "learning_rate": 7.381980765237891e-05,
+      "loss": 0.5545,
+      "mean_token_accuracy": 0.7858823418617249,
+      "num_tokens": 4966087.0,
+      "step": 2430
+    },
+    {
+      "epoch": 3.765432098765432,
+      "grad_norm": 0.8172715902328491,
+      "learning_rate": 7.359514945180978e-05,
+      "loss": 0.5635,
+      "mean_token_accuracy": 0.7825980424880982,
+      "num_tokens": 4986567.0,
+      "step": 2440
+    },
+    {
+      "epoch": 3.7808641975308643,
+      "grad_norm": 0.7683674693107605,
+      "learning_rate": 7.336987674780826e-05,
+      "loss": 0.5681,
+      "mean_token_accuracy": 0.7802941262722015,
+      "num_tokens": 5007047.0,
+      "step": 2450
+    },
+    {
+      "epoch": 3.7962962962962963,
+      "grad_norm": 0.7618924379348755,
+      "learning_rate": 7.31439954072942e-05,
+      "loss": 0.5452,
+      "mean_token_accuracy": 0.7907352864742279,
+      "num_tokens": 5027527.0,
+      "step": 2460
+    },
+    {
+      "epoch": 3.8117283950617287,
+      "grad_norm": 0.6154319047927856,
+      "learning_rate": 7.291751131303848e-05,
+      "loss": 0.5443,
+      "mean_token_accuracy": 0.7892647027969361,
+      "num_tokens": 5048007.0,
+      "step": 2470
+    },
+    {
+      "epoch": 3.8271604938271606,
+      "grad_norm": 0.7860175371170044,
+      "learning_rate": 7.269043036350995e-05,
+      "loss": 0.5623,
+      "mean_token_accuracy": 0.7838725566864013,
+      "num_tokens": 5068487.0,
+      "step": 2480
+    },
+    {
+      "epoch": 3.8425925925925926,
+      "grad_norm": 0.7870749831199646,
+      "learning_rate": 7.246275847272168e-05,
+      "loss": 0.5512,
+      "mean_token_accuracy": 0.7894117593765259,
+      "num_tokens": 5088967.0,
+      "step": 2490
+    },
+    {
+      "epoch": 3.8580246913580245,
+      "grad_norm": 0.7399156093597412,
+      "learning_rate": 7.223450157007706e-05,
+      "loss": 0.5688,
+      "mean_token_accuracy": 0.7833823561668396,
+      "num_tokens": 5109447.0,
+      "step": 2500
+    },
+    {
+      "epoch": 3.873456790123457,
+      "grad_norm": 0.7833046913146973,
+      "learning_rate": 7.200566560021524e-05,
+      "loss": 0.5744,
+      "mean_token_accuracy": 0.7807843148708343,
+      "num_tokens": 5129927.0,
+      "step": 2510
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.7414740920066833,
+      "learning_rate": 7.177625652285646e-05,
+      "loss": 0.5576,
+      "mean_token_accuracy": 0.785490196943283,
+      "num_tokens": 5150407.0,
+      "step": 2520
+    },
+    {
+      "epoch": 3.9043209876543212,
+      "grad_norm": 0.7602876424789429,
+      "learning_rate": 7.154628031264672e-05,
+      "loss": 0.5587,
+      "mean_token_accuracy": 0.7844607830047607,
+      "num_tokens": 5170887.0,
+      "step": 2530
+    },
+    {
+      "epoch": 3.919753086419753,
+      "grad_norm": 0.8457757234573364,
+      "learning_rate": 7.131574295900221e-05,
+      "loss": 0.5695,
+      "mean_token_accuracy": 0.7784683048725128,
+      "num_tokens": 5191238.0,
+      "step": 2540
+    },
+    {
+      "epoch": 3.935185185185185,
+      "grad_norm": 0.7168003916740417,
+      "learning_rate": 7.108465046595336e-05,
+      "loss": 0.5637,
+      "mean_token_accuracy": 0.7822058856487274,
+      "num_tokens": 5211718.0,
+      "step": 2550
+    },
+    {
+      "epoch": 3.950617283950617,
+      "grad_norm": 0.9155113101005554,
+      "learning_rate": 7.085300885198846e-05,
+      "loss": 0.5758,
+      "mean_token_accuracy": 0.7786274552345276,
+      "num_tokens": 5232198.0,
+      "step": 2560
+    },
+    {
+      "epoch": 3.9660493827160495,
+      "grad_norm": 0.9297204613685608,
+      "learning_rate": 7.062082414989684e-05,
+      "loss": 0.5592,
+      "mean_token_accuracy": 0.7843093752861023,
+      "num_tokens": 5252664.0,
+      "step": 2570
+    },
+    {
+      "epoch": 3.9814814814814814,
+      "grad_norm": 0.7999140620231628,
+      "learning_rate": 7.03881024066119e-05,
+      "loss": 0.5638,
+      "mean_token_accuracy": 0.783627450466156,
+      "num_tokens": 5273144.0,
+      "step": 2580
+    },
+    {
+      "epoch": 3.996913580246914,
+      "grad_norm": 0.7688170075416565,
+      "learning_rate": 7.015484968305348e-05,
+      "loss": 0.5524,
+      "mean_token_accuracy": 0.7889705896377563,
+      "num_tokens": 5293624.0,
+      "step": 2590
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6678392291069031,
+      "eval_mean_token_accuracy": 0.7533979739461626,
+      "eval_num_tokens": 5296184.0,
+      "eval_runtime": 3.269,
+      "eval_samples_per_second": 83.511,
+      "eval_steps_per_second": 10.707,
+      "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": 2.2558423616638157e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_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:ee630d3a769f8f4b4dcc99c709324068f5e26341c6ce13597153a1b7c73d3414
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_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_s3_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": [
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "down_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_s3_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3240/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:128af36ccc41fac8ba405225629af1131e8f58b58271893e21c66c02baa6571c
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_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_s3_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_s3_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_s3_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