add checkpoint cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast_vs0p05

.gitattributes

@@ -292,3 +292,14 @@ checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-648/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-6480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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_s2_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_s2_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_s2_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_s2_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_s2_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_s2_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_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_s2_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_s2_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": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "o_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_s2_vt_project_a1_ALL_bcast_vs0p05/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd1bc7163e3ffb4db5715a37d5d0eacc877e4c2c2d2bb78b3443a9c72670106
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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_s2_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_s2_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": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "o_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_s2_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1296/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e75287b0f48c19572697b49fc87165773e815ffdc12a3da5787f773340a916
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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_s2_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_s2_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_s2_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_s2_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": 3.642612934112549,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 2.4646,
+      "mean_token_accuracy": 0.5422549068927764,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.030864197530864196,
+      "grad_norm": 3.9434099197387695,
+      "learning_rate": 5.864197530864198e-06,
+      "loss": 2.4441,
+      "mean_token_accuracy": 0.5425980448722839,
+      "num_tokens": 40960.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.046296296296296294,
+      "grad_norm": 3.700989246368408,
+      "learning_rate": 8.950617283950618e-06,
+      "loss": 2.3243,
+      "mean_token_accuracy": 0.5584313631057739,
+      "num_tokens": 61440.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.06172839506172839,
+      "grad_norm": 1.9946578741073608,
+      "learning_rate": 1.2037037037037037e-05,
+      "loss": 2.0389,
+      "mean_token_accuracy": 0.575637263059616,
+      "num_tokens": 81920.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07716049382716049,
+      "grad_norm": 1.3853442668914795,
+      "learning_rate": 1.5123456790123458e-05,
+      "loss": 1.7642,
+      "mean_token_accuracy": 0.5935294091701507,
+      "num_tokens": 102400.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.09259259259259259,
+      "grad_norm": 1.0514497756958008,
+      "learning_rate": 1.8209876543209877e-05,
+      "loss": 1.5084,
+      "mean_token_accuracy": 0.6130882322788238,
+      "num_tokens": 122880.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.10802469135802469,
+      "grad_norm": 0.8691298365592957,
+      "learning_rate": 2.1296296296296296e-05,
+      "loss": 1.3515,
+      "mean_token_accuracy": 0.628529405593872,
+      "num_tokens": 143360.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 0.8635798096656799,
+      "learning_rate": 2.438271604938272e-05,
+      "loss": 1.186,
+      "mean_token_accuracy": 0.6466176509857178,
+      "num_tokens": 163840.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 1.0584197044372559,
+      "learning_rate": 2.7469135802469138e-05,
+      "loss": 1.0054,
+      "mean_token_accuracy": 0.6829411745071411,
+      "num_tokens": 184320.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.15432098765432098,
+      "grad_norm": 1.2961719036102295,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.9019,
+      "mean_token_accuracy": 0.6948529422283173,
+      "num_tokens": 204800.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.1697530864197531,
+      "grad_norm": 0.9584153890609741,
+      "learning_rate": 3.364197530864198e-05,
+      "loss": 0.8,
+      "mean_token_accuracy": 0.7179901957511902,
+      "num_tokens": 225280.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 1.0122414827346802,
+      "learning_rate": 3.67283950617284e-05,
+      "loss": 0.7736,
+      "mean_token_accuracy": 0.7223033726215362,
+      "num_tokens": 245510.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.2006172839506173,
+      "grad_norm": 1.164900302886963,
+      "learning_rate": 3.981481481481482e-05,
+      "loss": 0.7387,
+      "mean_token_accuracy": 0.7296568572521209,
+      "num_tokens": 265990.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.21604938271604937,
+      "grad_norm": 1.3156484365463257,
+      "learning_rate": 4.290123456790124e-05,
+      "loss": 0.7131,
+      "mean_token_accuracy": 0.740049022436142,
+      "num_tokens": 286470.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.23148148148148148,
+      "grad_norm": 1.017964243888855,
+      "learning_rate": 4.5987654320987656e-05,
+      "loss": 0.6822,
+      "mean_token_accuracy": 0.7473039209842682,
+      "num_tokens": 306950.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 0.9417504668235779,
+      "learning_rate": 4.9074074074074075e-05,
+      "loss": 0.6739,
+      "mean_token_accuracy": 0.7507843136787414,
+      "num_tokens": 327430.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.2623456790123457,
+      "grad_norm": 0.8708726167678833,
+      "learning_rate": 5.2160493827160494e-05,
+      "loss": 0.6713,
+      "mean_token_accuracy": 0.7505392134189606,
+      "num_tokens": 347910.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 1.0337103605270386,
+      "learning_rate": 5.524691358024692e-05,
+      "loss": 0.691,
+      "mean_token_accuracy": 0.7461764752864838,
+      "num_tokens": 368390.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2932098765432099,
+      "grad_norm": 0.947323739528656,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 0.6836,
+      "mean_token_accuracy": 0.742941164970398,
+      "num_tokens": 388870.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.30864197530864196,
+      "grad_norm": 0.8118940591812134,
+      "learning_rate": 6.141975308641975e-05,
+      "loss": 0.6757,
+      "mean_token_accuracy": 0.7460784316062927,
+      "num_tokens": 409350.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.32407407407407407,
+      "grad_norm": 0.8250467777252197,
+      "learning_rate": 6.450617283950617e-05,
+      "loss": 0.6566,
+      "mean_token_accuracy": 0.7514705836772919,
+      "num_tokens": 429830.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3395061728395062,
+      "grad_norm": 0.813636839389801,
+      "learning_rate": 6.759259259259259e-05,
+      "loss": 0.6705,
+      "mean_token_accuracy": 0.748235285282135,
+      "num_tokens": 450310.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.3549382716049383,
+      "grad_norm": 0.7828725576400757,
+      "learning_rate": 7.067901234567902e-05,
+      "loss": 0.6477,
+      "mean_token_accuracy": 0.7533458650112153,
+      "num_tokens": 470636.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.8237150311470032,
+      "learning_rate": 7.376543209876543e-05,
+      "loss": 0.67,
+      "mean_token_accuracy": 0.7494240999221802,
+      "num_tokens": 491067.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.38580246913580246,
+      "grad_norm": 0.9318073987960815,
+      "learning_rate": 7.685185185185185e-05,
+      "loss": 0.65,
+      "mean_token_accuracy": 0.7544607818126678,
+      "num_tokens": 511547.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4012345679012346,
+      "grad_norm": 0.796583890914917,
+      "learning_rate": 7.993827160493828e-05,
+      "loss": 0.6754,
+      "mean_token_accuracy": 0.7434313535690308,
+      "num_tokens": 532027.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.9032039046287537,
+      "learning_rate": 8.30246913580247e-05,
+      "loss": 0.6606,
+      "mean_token_accuracy": 0.7502451062202453,
+      "num_tokens": 552507.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.43209876543209874,
+      "grad_norm": 0.716952383518219,
+      "learning_rate": 8.611111111111112e-05,
+      "loss": 0.6418,
+      "mean_token_accuracy": 0.7555392146110534,
+      "num_tokens": 572987.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.44753086419753085,
+      "grad_norm": 0.7230756878852844,
+      "learning_rate": 8.919753086419754e-05,
+      "loss": 0.6494,
+      "mean_token_accuracy": 0.7528663039207458,
+      "num_tokens": 593305.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 0.8555248379707336,
+      "learning_rate": 9.228395061728396e-05,
+      "loss": 0.6636,
+      "mean_token_accuracy": 0.7458823561668396,
+      "num_tokens": 613785.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.4783950617283951,
+      "grad_norm": 0.666594922542572,
+      "learning_rate": 9.537037037037038e-05,
+      "loss": 0.6367,
+      "mean_token_accuracy": 0.7563725471496582,
+      "num_tokens": 634265.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.6590859293937683,
+      "learning_rate": 9.84567901234568e-05,
+      "loss": 0.6508,
+      "mean_token_accuracy": 0.7519607841968536,
+      "num_tokens": 654745.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.5092592592592593,
+      "grad_norm": 0.7278088927268982,
+      "learning_rate": 9.999983722702365e-05,
+      "loss": 0.6534,
+      "mean_token_accuracy": 0.7518137276172638,
+      "num_tokens": 675225.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.5246913580246914,
+      "grad_norm": 0.6529048681259155,
+      "learning_rate": 9.999853504957158e-05,
+      "loss": 0.6375,
+      "mean_token_accuracy": 0.757303923368454,
+      "num_tokens": 695705.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5401234567901234,
+      "grad_norm": 0.6195814609527588,
+      "learning_rate": 9.999593072858088e-05,
+      "loss": 0.6444,
+      "mean_token_accuracy": 0.753872549533844,
+      "num_tokens": 716185.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.6766397953033447,
+      "learning_rate": 9.999202433187755e-05,
+      "loss": 0.6665,
+      "mean_token_accuracy": 0.7452171981334687,
+      "num_tokens": 736470.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5709876543209876,
+      "grad_norm": 0.5934011936187744,
+      "learning_rate": 9.998681596119832e-05,
+      "loss": 0.6537,
+      "mean_token_accuracy": 0.7506862759590149,
+      "num_tokens": 756950.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5864197530864198,
+      "grad_norm": 0.872284471988678,
+      "learning_rate": 9.998030575218811e-05,
+      "loss": 0.6562,
+      "mean_token_accuracy": 0.7521078407764434,
+      "num_tokens": 777430.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.6018518518518519,
+      "grad_norm": 0.6015172004699707,
+      "learning_rate": 9.997249387439643e-05,
+      "loss": 0.6459,
+      "mean_token_accuracy": 0.7544117629528045,
+      "num_tokens": 797910.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 0.5660067200660706,
+      "learning_rate": 9.996338053127292e-05,
+      "loss": 0.6354,
+      "mean_token_accuracy": 0.7564705908298492,
+      "num_tokens": 818390.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6327160493827161,
+      "grad_norm": 0.604268491268158,
+      "learning_rate": 9.99529659601622e-05,
+      "loss": 0.6534,
+      "mean_token_accuracy": 0.7492156803607941,
+      "num_tokens": 838870.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6481481481481481,
+      "grad_norm": 0.5622531175613403,
+      "learning_rate": 9.994125043229752e-05,
+      "loss": 0.6538,
+      "mean_token_accuracy": 0.7499509811401367,
+      "num_tokens": 859350.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.6635802469135802,
+      "grad_norm": 0.5512784719467163,
+      "learning_rate": 9.992823425279382e-05,
+      "loss": 0.6425,
+      "mean_token_accuracy": 0.7543627440929412,
+      "num_tokens": 879830.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6790123456790124,
+      "grad_norm": 0.6505032777786255,
+      "learning_rate": 9.991391776063969e-05,
+      "loss": 0.649,
+      "mean_token_accuracy": 0.7518137216567993,
+      "num_tokens": 900310.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 0.5469474196434021,
+      "learning_rate": 9.98983013286886e-05,
+      "loss": 0.6451,
+      "mean_token_accuracy": 0.7538235247135162,
+      "num_tokens": 920790.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.7098765432098766,
+      "grad_norm": 0.48557355999946594,
+      "learning_rate": 9.988138536364922e-05,
+      "loss": 0.6607,
+      "mean_token_accuracy": 0.7458333253860474,
+      "num_tokens": 941270.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.7253086419753086,
+      "grad_norm": 0.6949014067649841,
+      "learning_rate": 9.986317030607475e-05,
+      "loss": 0.6467,
+      "mean_token_accuracy": 0.7520922362804413,
+      "num_tokens": 961595.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.5359596610069275,
+      "learning_rate": 9.984365663035144e-05,
+      "loss": 0.6452,
+      "mean_token_accuracy": 0.7529411792755127,
+      "num_tokens": 982075.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.7561728395061729,
+      "grad_norm": 0.46560513973236084,
+      "learning_rate": 9.982284484468634e-05,
+      "loss": 0.6479,
+      "mean_token_accuracy": 0.7506862640380859,
+      "num_tokens": 1002555.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7716049382716049,
+      "grad_norm": 0.7050852179527283,
+      "learning_rate": 9.980073549109397e-05,
+      "loss": 0.653,
+      "mean_token_accuracy": 0.7522634565830231,
+      "num_tokens": 1022822.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.7870370370370371,
+      "grad_norm": 0.49813297390937805,
+      "learning_rate": 9.977732914538225e-05,
+      "loss": 0.6392,
+      "mean_token_accuracy": 0.7561274647712708,
+      "num_tokens": 1043302.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.8024691358024691,
+      "grad_norm": 0.5180872082710266,
+      "learning_rate": 9.975262641713746e-05,
+      "loss": 0.6492,
+      "mean_token_accuracy": 0.7488725483417511,
+      "num_tokens": 1063782.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.8179012345679012,
+      "grad_norm": 0.526536762714386,
+      "learning_rate": 9.972662794970841e-05,
+      "loss": 0.6478,
+      "mean_token_accuracy": 0.7515686273574829,
+      "num_tokens": 1084262.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.5425621271133423,
+      "learning_rate": 9.969933442018968e-05,
+      "loss": 0.6157,
+      "mean_token_accuracy": 0.7639407038688659,
+      "num_tokens": 1104337.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8487654320987654,
+      "grad_norm": 0.6052752733230591,
+      "learning_rate": 9.967074653940396e-05,
+      "loss": 0.6449,
+      "mean_token_accuracy": 0.753088241815567,
+      "num_tokens": 1124817.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 0.5158132910728455,
+      "learning_rate": 9.964086505188352e-05,
+      "loss": 0.6342,
+      "mean_token_accuracy": 0.7589705944061279,
+      "num_tokens": 1145297.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8796296296296297,
+      "grad_norm": 0.558788001537323,
+      "learning_rate": 9.960969073585091e-05,
+      "loss": 0.65,
+      "mean_token_accuracy": 0.75220587849617,
+      "num_tokens": 1165777.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8950617283950617,
+      "grad_norm": 0.5892021059989929,
+      "learning_rate": 9.95772244031986e-05,
+      "loss": 0.6299,
+      "mean_token_accuracy": 0.7599019587039948,
+      "num_tokens": 1186257.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.9104938271604939,
+      "grad_norm": 0.49645981192588806,
+      "learning_rate": 9.954346689946785e-05,
+      "loss": 0.6353,
+      "mean_token_accuracy": 0.7553921580314636,
+      "num_tokens": 1206737.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 0.5327996611595154,
+      "learning_rate": 9.950841910382675e-05,
+      "loss": 0.6336,
+      "mean_token_accuracy": 0.7565686404705048,
+      "num_tokens": 1227217.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.941358024691358,
+      "grad_norm": 0.6819751262664795,
+      "learning_rate": 9.947208192904722e-05,
+      "loss": 0.6521,
+      "mean_token_accuracy": 0.747107845544815,
+      "num_tokens": 1247697.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9567901234567902,
+      "grad_norm": 0.5382965207099915,
+      "learning_rate": 9.943445632148138e-05,
+      "loss": 0.6512,
+      "mean_token_accuracy": 0.7521078407764434,
+      "num_tokens": 1268177.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 0.5911397337913513,
+      "learning_rate": 9.939554326103673e-05,
+      "loss": 0.6269,
+      "mean_token_accuracy": 0.7610294163227082,
+      "num_tokens": 1288657.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.5044689178466797,
+      "learning_rate": 9.935534376115081e-05,
+      "loss": 0.6359,
+      "mean_token_accuracy": 0.7558333456516266,
+      "num_tokens": 1309137.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6373786330223083,
+      "eval_mean_token_accuracy": 0.7553163358143398,
+      "eval_num_tokens": 1323985.0,
+      "eval_runtime": 3.2784,
+      "eval_samples_per_second": 83.272,
+      "eval_steps_per_second": 10.676,
+      "step": 648
+    },
+    {
+      "epoch": 1.0030864197530864,
+      "grad_norm": 0.5726162791252136,
+      "learning_rate": 9.931385886876466e-05,
+      "loss": 0.6273,
+      "mean_token_accuracy": 0.7600000083446503,
+      "num_tokens": 1328081.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.0185185185185186,
+      "grad_norm": 0.6138848662376404,
+      "learning_rate": 9.927108966429559e-05,
+      "loss": 0.6149,
+      "mean_token_accuracy": 0.7639705955982208,
+      "num_tokens": 1348561.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.0339506172839505,
+      "grad_norm": 0.5624936819076538,
+      "learning_rate": 9.922703726160915e-05,
+      "loss": 0.6093,
+      "mean_token_accuracy": 0.7660784363746643,
+      "num_tokens": 1369041.0,
+      "step": 670
+    },
+    {
+      "epoch": 1.0493827160493827,
+      "grad_norm": 0.6030348539352417,
+      "learning_rate": 9.918170280798997e-05,
+      "loss": 0.6029,
+      "mean_token_accuracy": 0.7672549068927765,
+      "num_tokens": 1389521.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.0648148148148149,
+      "grad_norm": 0.6273998618125916,
+      "learning_rate": 9.913508748411195e-05,
+      "loss": 0.6224,
+      "mean_token_accuracy": 0.7597549080848693,
+      "num_tokens": 1410001.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0802469135802468,
+      "grad_norm": 0.5929473638534546,
+      "learning_rate": 9.908719250400751e-05,
+      "loss": 0.6264,
+      "mean_token_accuracy": 0.7589215755462646,
+      "num_tokens": 1430481.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.095679012345679,
+      "grad_norm": 0.6457216143608093,
+      "learning_rate": 9.903801911503601e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7606862783432007,
+      "num_tokens": 1450961.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.5677434206008911,
+      "learning_rate": 9.898756859785114e-05,
+      "loss": 0.6479,
+      "mean_token_accuracy": 0.7513552784919739,
+      "num_tokens": 1471334.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.126543209876543,
+      "grad_norm": 0.5023089051246643,
+      "learning_rate": 9.893584226636772e-05,
+      "loss": 0.643,
+      "mean_token_accuracy": 0.7502450942993164,
+      "num_tokens": 1491814.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.1419753086419753,
+      "grad_norm": 0.5853515267372131,
+      "learning_rate": 9.88828414677274e-05,
+      "loss": 0.6181,
+      "mean_token_accuracy": 0.762156856060028,
+      "num_tokens": 1512294.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.1574074074074074,
+      "grad_norm": 0.6769473552703857,
+      "learning_rate": 9.882856758226355e-05,
+      "loss": 0.6193,
+      "mean_token_accuracy": 0.763762366771698,
+      "num_tokens": 1532542.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1728395061728394,
+      "grad_norm": 0.5814151167869568,
+      "learning_rate": 9.877302202346537e-05,
+      "loss": 0.6193,
+      "mean_token_accuracy": 0.7625367939472198,
+      "num_tokens": 1552867.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.1882716049382716,
+      "grad_norm": 0.7868801355361938,
+      "learning_rate": 9.871620623794107e-05,
+      "loss": 0.6119,
+      "mean_token_accuracy": 0.7656372606754303,
+      "num_tokens": 1573347.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.2037037037037037,
+      "grad_norm": 0.5902999043464661,
+      "learning_rate": 9.865812170538014e-05,
+      "loss": 0.6106,
+      "mean_token_accuracy": 0.7653431355953216,
+      "num_tokens": 1593827.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.2191358024691359,
+      "grad_norm": 0.5042413473129272,
+      "learning_rate": 9.859876993851489e-05,
+      "loss": 0.6258,
+      "mean_token_accuracy": 0.7603431344032288,
+      "num_tokens": 1614307.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 0.6255024671554565,
+      "learning_rate": 9.853815248308101e-05,
+      "loss": 0.6181,
+      "mean_token_accuracy": 0.7631550431251526,
+      "num_tokens": 1634681.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.5640517473220825,
+      "learning_rate": 9.847627091777729e-05,
+      "loss": 0.6138,
+      "mean_token_accuracy": 0.7638725519180298,
+      "num_tokens": 1655161.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2654320987654322,
+      "grad_norm": 0.5596677660942078,
+      "learning_rate": 9.841312685422459e-05,
+      "loss": 0.6173,
+      "mean_token_accuracy": 0.7628921627998352,
+      "num_tokens": 1675641.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.2808641975308643,
+      "grad_norm": 0.6959637403488159,
+      "learning_rate": 9.834872193692378e-05,
+      "loss": 0.631,
+      "mean_token_accuracy": 0.7579901933670044,
+      "num_tokens": 1696121.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.5890873670578003,
+      "learning_rate": 9.828305784321289e-05,
+      "loss": 0.6194,
+      "mean_token_accuracy": 0.7610294044017791,
+      "num_tokens": 1716601.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.3117283950617284,
+      "grad_norm": 0.5236982107162476,
+      "learning_rate": 9.821613628322358e-05,
+      "loss": 0.6353,
+      "mean_token_accuracy": 0.7555392146110534,
+      "num_tokens": 1737081.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.3271604938271606,
+      "grad_norm": 0.4920688271522522,
+      "learning_rate": 9.814795899983645e-05,
+      "loss": 0.6203,
+      "mean_token_accuracy": 0.7605464220046997,
+      "num_tokens": 1757399.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.3425925925925926,
+      "grad_norm": 0.5151636004447937,
+      "learning_rate": 9.807852776863568e-05,
+      "loss": 0.6316,
+      "mean_token_accuracy": 0.757401955127716,
+      "num_tokens": 1777879.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.3580246913580247,
+      "grad_norm": 0.5221789479255676,
+      "learning_rate": 9.800784439786286e-05,
+      "loss": 0.6021,
+      "mean_token_accuracy": 0.7678921699523926,
+      "num_tokens": 1798359.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.373456790123457,
+      "grad_norm": 0.6253092885017395,
+      "learning_rate": 9.793591072836978e-05,
+      "loss": 0.6189,
+      "mean_token_accuracy": 0.7627451002597809,
+      "num_tokens": 1818839.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 0.5362826585769653,
+      "learning_rate": 9.786272863357063e-05,
+      "loss": 0.6218,
+      "mean_token_accuracy": 0.7601960837841034,
+      "num_tokens": 1839319.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.404320987654321,
+      "grad_norm": 0.5733498930931091,
+      "learning_rate": 9.778830001939307e-05,
+      "loss": 0.6243,
+      "mean_token_accuracy": 0.7575980484485626,
+      "num_tokens": 1859799.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.4197530864197532,
+      "grad_norm": 0.5503411293029785,
+      "learning_rate": 9.771262682422866e-05,
+      "loss": 0.6043,
+      "mean_token_accuracy": 0.768676483631134,
+      "num_tokens": 1880279.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.4351851851851851,
+      "grad_norm": 0.5697808265686035,
+      "learning_rate": 9.76357110188824e-05,
+      "loss": 0.619,
+      "mean_token_accuracy": 0.7615686297416687,
+      "num_tokens": 1900759.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.4506172839506173,
+      "grad_norm": 0.5639927387237549,
+      "learning_rate": 9.755755460652137e-05,
+      "loss": 0.6287,
+      "mean_token_accuracy": 0.7581372559070587,
+      "num_tokens": 1921239.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.4660493827160495,
+      "grad_norm": 0.4238158166408539,
+      "learning_rate": 9.747815962262255e-05,
+      "loss": 0.6179,
+      "mean_token_accuracy": 0.7624019682407379,
+      "num_tokens": 1941719.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.5610195398330688,
+      "learning_rate": 9.73975281349198e-05,
+      "loss": 0.6198,
+      "mean_token_accuracy": 0.7611274600028992,
+      "num_tokens": 1962199.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4969135802469136,
+      "grad_norm": 0.5397023558616638,
+      "learning_rate": 9.73156622433501e-05,
+      "loss": 0.6262,
+      "mean_token_accuracy": 0.7573529422283173,
+      "num_tokens": 1982679.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.5123456790123457,
+      "grad_norm": 0.627068042755127,
+      "learning_rate": 9.72325640799987e-05,
+      "loss": 0.6341,
+      "mean_token_accuracy": 0.7564705967903137,
+      "num_tokens": 2003159.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.5277777777777777,
+      "grad_norm": 0.6139004826545715,
+      "learning_rate": 9.71482358090438e-05,
+      "loss": 0.628,
+      "mean_token_accuracy": 0.7554846823215484,
+      "num_tokens": 2023485.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.5432098765432098,
+      "grad_norm": 0.5941593647003174,
+      "learning_rate": 9.706267962669998e-05,
+      "loss": 0.636,
+      "mean_token_accuracy": 0.756617647409439,
+      "num_tokens": 2043965.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.558641975308642,
+      "grad_norm": 0.5428718328475952,
+      "learning_rate": 9.697589776116113e-05,
+      "loss": 0.6288,
+      "mean_token_accuracy": 0.7563235223293304,
+      "num_tokens": 2064445.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.574074074074074,
+      "grad_norm": 0.679093599319458,
+      "learning_rate": 9.688789247254237e-05,
+      "loss": 0.6137,
+      "mean_token_accuracy": 0.7616176426410675,
+      "num_tokens": 2084925.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5895061728395061,
+      "grad_norm": 0.5914977192878723,
+      "learning_rate": 9.679866605282122e-05,
+      "loss": 0.6101,
+      "mean_token_accuracy": 0.7660278260707856,
+      "num_tokens": 2105210.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6049382716049383,
+      "grad_norm": 0.6366807818412781,
+      "learning_rate": 9.670822082577787e-05,
+      "loss": 0.6221,
+      "mean_token_accuracy": 0.7630392193794251,
+      "num_tokens": 2125690.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6203703703703702,
+      "grad_norm": 0.537667453289032,
+      "learning_rate": 9.661655914693471e-05,
+      "loss": 0.6276,
+      "mean_token_accuracy": 0.7600000083446503,
+      "num_tokens": 2146170.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6358024691358026,
+      "grad_norm": 0.6829613447189331,
+      "learning_rate": 9.652368340349494e-05,
+      "loss": 0.6231,
+      "mean_token_accuracy": 0.7614292323589325,
+      "num_tokens": 2166400.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.6512345679012346,
+      "grad_norm": 0.46796467900276184,
+      "learning_rate": 9.642959601428039e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7614705860614777,
+      "num_tokens": 2186880.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.6203200221061707,
+      "learning_rate": 9.63342994296686e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7601960718631744,
+      "num_tokens": 2207360.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.682098765432099,
+      "grad_norm": 0.4808056652545929,
+      "learning_rate": 9.623779613152893e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7597549021244049,
+      "num_tokens": 2227840.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6975308641975309,
+      "grad_norm": 0.831586480140686,
+      "learning_rate": 9.614008863315789e-05,
+      "loss": 0.6031,
+      "mean_token_accuracy": 0.7655882358551025,
+      "num_tokens": 2248320.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7129629629629628,
+      "grad_norm": 0.5528991222381592,
+      "learning_rate": 9.604117947921385e-05,
+      "loss": 0.6255,
+      "mean_token_accuracy": 0.7599509835243226,
+      "num_tokens": 2268800.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7283950617283952,
+      "grad_norm": 0.518021821975708,
+      "learning_rate": 9.594107124565056e-05,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.7617159247398376,
+      "num_tokens": 2289107.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7438271604938271,
+      "grad_norm": 0.5663719177246094,
+      "learning_rate": 9.58397665396502e-05,
+      "loss": 0.6239,
+      "mean_token_accuracy": 0.7579901993274689,
+      "num_tokens": 2309587.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.7592592592592593,
+      "grad_norm": 0.6976074576377869,
+      "learning_rate": 9.573726799955544e-05,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.7644607961177826,
+      "num_tokens": 2330067.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7746913580246915,
+      "grad_norm": 0.491929829120636,
+      "learning_rate": 9.563357829480076e-05,
+      "loss": 0.6175,
+      "mean_token_accuracy": 0.7621568620204926,
+      "num_tokens": 2350547.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7901234567901234,
+      "grad_norm": 0.5365603566169739,
+      "learning_rate": 9.552870012584282e-05,
+      "loss": 0.6207,
+      "mean_token_accuracy": 0.7618627429008484,
+      "num_tokens": 2371027.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8055555555555556,
+      "grad_norm": 0.4748326241970062,
+      "learning_rate": 9.542263622409027e-05,
+      "loss": 0.6304,
+      "mean_token_accuracy": 0.7585784316062927,
+      "num_tokens": 2391507.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.8209876543209877,
+      "grad_norm": 0.6071013808250427,
+      "learning_rate": 9.53153893518325e-05,
+      "loss": 0.6242,
+      "mean_token_accuracy": 0.7582843065261841,
+      "num_tokens": 2411987.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.8364197530864197,
+      "grad_norm": 0.5693532228469849,
+      "learning_rate": 9.520696230216781e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7624019622802735,
+      "num_tokens": 2432467.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.5890586376190186,
+      "learning_rate": 9.509735789893059e-05,
+      "loss": 0.6261,
+      "mean_token_accuracy": 0.7603431344032288,
+      "num_tokens": 2452947.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.867283950617284,
+      "grad_norm": 0.5754212737083435,
+      "learning_rate": 9.498657899661774e-05,
+      "loss": 0.6201,
+      "mean_token_accuracy": 0.7618137300014496,
+      "num_tokens": 2473427.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.882716049382716,
+      "grad_norm": 0.48493534326553345,
+      "learning_rate": 9.487462848031445e-05,
+      "loss": 0.6411,
+      "mean_token_accuracy": 0.754411768913269,
+      "num_tokens": 2493907.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8981481481481481,
+      "grad_norm": 0.6793274283409119,
+      "learning_rate": 9.4761509265619e-05,
+      "loss": 0.6094,
+      "mean_token_accuracy": 0.7683333337306977,
+      "num_tokens": 2514387.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.9135802469135803,
+      "grad_norm": 0.43587443232536316,
+      "learning_rate": 9.464722429856674e-05,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.763382351398468,
+      "num_tokens": 2534867.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.9290123456790123,
+      "grad_norm": 0.5037091970443726,
+      "learning_rate": 9.453177655555355e-05,
+      "loss": 0.6215,
+      "mean_token_accuracy": 0.7608333349227905,
+      "num_tokens": 2555347.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 0.48443400859832764,
+      "learning_rate": 9.441516904325816e-05,
+      "loss": 0.6326,
+      "mean_token_accuracy": 0.7566666662693023,
+      "num_tokens": 2575827.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.9598765432098766,
+      "grad_norm": 0.5313301086425781,
+      "learning_rate": 9.42974047985639e-05,
+      "loss": 0.6059,
+      "mean_token_accuracy": 0.7671078443527222,
+      "num_tokens": 2596307.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.4752209186553955,
+      "learning_rate": 9.417848688847968e-05,
+      "loss": 0.6221,
+      "mean_token_accuracy": 0.7612836718559265,
+      "num_tokens": 2616738.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.9907407407407407,
+      "grad_norm": 0.6168082356452942,
+      "learning_rate": 9.405841841005998e-05,
+      "loss": 0.6199,
+      "mean_token_accuracy": 0.7622058808803558,
+      "num_tokens": 2637218.0,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.628555953502655,
+      "eval_mean_token_accuracy": 0.7592301794460842,
+      "eval_num_tokens": 2647970.0,
+      "eval_runtime": 3.2461,
+      "eval_samples_per_second": 84.102,
+      "eval_steps_per_second": 10.782,
+      "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_s2_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:a6ae2e45c24ad2de3ad1c1a2451eabb81c07194ae1361d646cc4fc0918792a0e
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "o_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_s2_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1944/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ef1a344eb32900fe357f475a3d1a92561f92df7a87025ec786e37590e26053d
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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_s2_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_s2_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_s2_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_s2_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": 3.642612934112549,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 2.4646,
+      "mean_token_accuracy": 0.5422549068927764,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.030864197530864196,
+      "grad_norm": 3.9434099197387695,
+      "learning_rate": 5.864197530864198e-06,
+      "loss": 2.4441,
+      "mean_token_accuracy": 0.5425980448722839,
+      "num_tokens": 40960.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.046296296296296294,
+      "grad_norm": 3.700989246368408,
+      "learning_rate": 8.950617283950618e-06,
+      "loss": 2.3243,
+      "mean_token_accuracy": 0.5584313631057739,
+      "num_tokens": 61440.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.06172839506172839,
+      "grad_norm": 1.9946578741073608,
+      "learning_rate": 1.2037037037037037e-05,
+      "loss": 2.0389,
+      "mean_token_accuracy": 0.575637263059616,
+      "num_tokens": 81920.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07716049382716049,
+      "grad_norm": 1.3853442668914795,
+      "learning_rate": 1.5123456790123458e-05,
+      "loss": 1.7642,
+      "mean_token_accuracy": 0.5935294091701507,
+      "num_tokens": 102400.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.09259259259259259,
+      "grad_norm": 1.0514497756958008,
+      "learning_rate": 1.8209876543209877e-05,
+      "loss": 1.5084,
+      "mean_token_accuracy": 0.6130882322788238,
+      "num_tokens": 122880.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.10802469135802469,
+      "grad_norm": 0.8691298365592957,
+      "learning_rate": 2.1296296296296296e-05,
+      "loss": 1.3515,
+      "mean_token_accuracy": 0.628529405593872,
+      "num_tokens": 143360.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 0.8635798096656799,
+      "learning_rate": 2.438271604938272e-05,
+      "loss": 1.186,
+      "mean_token_accuracy": 0.6466176509857178,
+      "num_tokens": 163840.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 1.0584197044372559,
+      "learning_rate": 2.7469135802469138e-05,
+      "loss": 1.0054,
+      "mean_token_accuracy": 0.6829411745071411,
+      "num_tokens": 184320.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.15432098765432098,
+      "grad_norm": 1.2961719036102295,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.9019,
+      "mean_token_accuracy": 0.6948529422283173,
+      "num_tokens": 204800.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.1697530864197531,
+      "grad_norm": 0.9584153890609741,
+      "learning_rate": 3.364197530864198e-05,
+      "loss": 0.8,
+      "mean_token_accuracy": 0.7179901957511902,
+      "num_tokens": 225280.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 1.0122414827346802,
+      "learning_rate": 3.67283950617284e-05,
+      "loss": 0.7736,
+      "mean_token_accuracy": 0.7223033726215362,
+      "num_tokens": 245510.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.2006172839506173,
+      "grad_norm": 1.164900302886963,
+      "learning_rate": 3.981481481481482e-05,
+      "loss": 0.7387,
+      "mean_token_accuracy": 0.7296568572521209,
+      "num_tokens": 265990.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.21604938271604937,
+      "grad_norm": 1.3156484365463257,
+      "learning_rate": 4.290123456790124e-05,
+      "loss": 0.7131,
+      "mean_token_accuracy": 0.740049022436142,
+      "num_tokens": 286470.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.23148148148148148,
+      "grad_norm": 1.017964243888855,
+      "learning_rate": 4.5987654320987656e-05,
+      "loss": 0.6822,
+      "mean_token_accuracy": 0.7473039209842682,
+      "num_tokens": 306950.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 0.9417504668235779,
+      "learning_rate": 4.9074074074074075e-05,
+      "loss": 0.6739,
+      "mean_token_accuracy": 0.7507843136787414,
+      "num_tokens": 327430.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.2623456790123457,
+      "grad_norm": 0.8708726167678833,
+      "learning_rate": 5.2160493827160494e-05,
+      "loss": 0.6713,
+      "mean_token_accuracy": 0.7505392134189606,
+      "num_tokens": 347910.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 1.0337103605270386,
+      "learning_rate": 5.524691358024692e-05,
+      "loss": 0.691,
+      "mean_token_accuracy": 0.7461764752864838,
+      "num_tokens": 368390.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2932098765432099,
+      "grad_norm": 0.947323739528656,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 0.6836,
+      "mean_token_accuracy": 0.742941164970398,
+      "num_tokens": 388870.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.30864197530864196,
+      "grad_norm": 0.8118940591812134,
+      "learning_rate": 6.141975308641975e-05,
+      "loss": 0.6757,
+      "mean_token_accuracy": 0.7460784316062927,
+      "num_tokens": 409350.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.32407407407407407,
+      "grad_norm": 0.8250467777252197,
+      "learning_rate": 6.450617283950617e-05,
+      "loss": 0.6566,
+      "mean_token_accuracy": 0.7514705836772919,
+      "num_tokens": 429830.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3395061728395062,
+      "grad_norm": 0.813636839389801,
+      "learning_rate": 6.759259259259259e-05,
+      "loss": 0.6705,
+      "mean_token_accuracy": 0.748235285282135,
+      "num_tokens": 450310.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.3549382716049383,
+      "grad_norm": 0.7828725576400757,
+      "learning_rate": 7.067901234567902e-05,
+      "loss": 0.6477,
+      "mean_token_accuracy": 0.7533458650112153,
+      "num_tokens": 470636.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.8237150311470032,
+      "learning_rate": 7.376543209876543e-05,
+      "loss": 0.67,
+      "mean_token_accuracy": 0.7494240999221802,
+      "num_tokens": 491067.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.38580246913580246,
+      "grad_norm": 0.9318073987960815,
+      "learning_rate": 7.685185185185185e-05,
+      "loss": 0.65,
+      "mean_token_accuracy": 0.7544607818126678,
+      "num_tokens": 511547.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4012345679012346,
+      "grad_norm": 0.796583890914917,
+      "learning_rate": 7.993827160493828e-05,
+      "loss": 0.6754,
+      "mean_token_accuracy": 0.7434313535690308,
+      "num_tokens": 532027.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.9032039046287537,
+      "learning_rate": 8.30246913580247e-05,
+      "loss": 0.6606,
+      "mean_token_accuracy": 0.7502451062202453,
+      "num_tokens": 552507.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.43209876543209874,
+      "grad_norm": 0.716952383518219,
+      "learning_rate": 8.611111111111112e-05,
+      "loss": 0.6418,
+      "mean_token_accuracy": 0.7555392146110534,
+      "num_tokens": 572987.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.44753086419753085,
+      "grad_norm": 0.7230756878852844,
+      "learning_rate": 8.919753086419754e-05,
+      "loss": 0.6494,
+      "mean_token_accuracy": 0.7528663039207458,
+      "num_tokens": 593305.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 0.8555248379707336,
+      "learning_rate": 9.228395061728396e-05,
+      "loss": 0.6636,
+      "mean_token_accuracy": 0.7458823561668396,
+      "num_tokens": 613785.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.4783950617283951,
+      "grad_norm": 0.666594922542572,
+      "learning_rate": 9.537037037037038e-05,
+      "loss": 0.6367,
+      "mean_token_accuracy": 0.7563725471496582,
+      "num_tokens": 634265.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.6590859293937683,
+      "learning_rate": 9.84567901234568e-05,
+      "loss": 0.6508,
+      "mean_token_accuracy": 0.7519607841968536,
+      "num_tokens": 654745.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.5092592592592593,
+      "grad_norm": 0.7278088927268982,
+      "learning_rate": 9.999983722702365e-05,
+      "loss": 0.6534,
+      "mean_token_accuracy": 0.7518137276172638,
+      "num_tokens": 675225.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.5246913580246914,
+      "grad_norm": 0.6529048681259155,
+      "learning_rate": 9.999853504957158e-05,
+      "loss": 0.6375,
+      "mean_token_accuracy": 0.757303923368454,
+      "num_tokens": 695705.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5401234567901234,
+      "grad_norm": 0.6195814609527588,
+      "learning_rate": 9.999593072858088e-05,
+      "loss": 0.6444,
+      "mean_token_accuracy": 0.753872549533844,
+      "num_tokens": 716185.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.6766397953033447,
+      "learning_rate": 9.999202433187755e-05,
+      "loss": 0.6665,
+      "mean_token_accuracy": 0.7452171981334687,
+      "num_tokens": 736470.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5709876543209876,
+      "grad_norm": 0.5934011936187744,
+      "learning_rate": 9.998681596119832e-05,
+      "loss": 0.6537,
+      "mean_token_accuracy": 0.7506862759590149,
+      "num_tokens": 756950.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5864197530864198,
+      "grad_norm": 0.872284471988678,
+      "learning_rate": 9.998030575218811e-05,
+      "loss": 0.6562,
+      "mean_token_accuracy": 0.7521078407764434,
+      "num_tokens": 777430.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.6018518518518519,
+      "grad_norm": 0.6015172004699707,
+      "learning_rate": 9.997249387439643e-05,
+      "loss": 0.6459,
+      "mean_token_accuracy": 0.7544117629528045,
+      "num_tokens": 797910.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 0.5660067200660706,
+      "learning_rate": 9.996338053127292e-05,
+      "loss": 0.6354,
+      "mean_token_accuracy": 0.7564705908298492,
+      "num_tokens": 818390.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6327160493827161,
+      "grad_norm": 0.604268491268158,
+      "learning_rate": 9.99529659601622e-05,
+      "loss": 0.6534,
+      "mean_token_accuracy": 0.7492156803607941,
+      "num_tokens": 838870.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6481481481481481,
+      "grad_norm": 0.5622531175613403,
+      "learning_rate": 9.994125043229752e-05,
+      "loss": 0.6538,
+      "mean_token_accuracy": 0.7499509811401367,
+      "num_tokens": 859350.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.6635802469135802,
+      "grad_norm": 0.5512784719467163,
+      "learning_rate": 9.992823425279382e-05,
+      "loss": 0.6425,
+      "mean_token_accuracy": 0.7543627440929412,
+      "num_tokens": 879830.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6790123456790124,
+      "grad_norm": 0.6505032777786255,
+      "learning_rate": 9.991391776063969e-05,
+      "loss": 0.649,
+      "mean_token_accuracy": 0.7518137216567993,
+      "num_tokens": 900310.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 0.5469474196434021,
+      "learning_rate": 9.98983013286886e-05,
+      "loss": 0.6451,
+      "mean_token_accuracy": 0.7538235247135162,
+      "num_tokens": 920790.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.7098765432098766,
+      "grad_norm": 0.48557355999946594,
+      "learning_rate": 9.988138536364922e-05,
+      "loss": 0.6607,
+      "mean_token_accuracy": 0.7458333253860474,
+      "num_tokens": 941270.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.7253086419753086,
+      "grad_norm": 0.6949014067649841,
+      "learning_rate": 9.986317030607475e-05,
+      "loss": 0.6467,
+      "mean_token_accuracy": 0.7520922362804413,
+      "num_tokens": 961595.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.5359596610069275,
+      "learning_rate": 9.984365663035144e-05,
+      "loss": 0.6452,
+      "mean_token_accuracy": 0.7529411792755127,
+      "num_tokens": 982075.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.7561728395061729,
+      "grad_norm": 0.46560513973236084,
+      "learning_rate": 9.982284484468634e-05,
+      "loss": 0.6479,
+      "mean_token_accuracy": 0.7506862640380859,
+      "num_tokens": 1002555.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7716049382716049,
+      "grad_norm": 0.7050852179527283,
+      "learning_rate": 9.980073549109397e-05,
+      "loss": 0.653,
+      "mean_token_accuracy": 0.7522634565830231,
+      "num_tokens": 1022822.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.7870370370370371,
+      "grad_norm": 0.49813297390937805,
+      "learning_rate": 9.977732914538225e-05,
+      "loss": 0.6392,
+      "mean_token_accuracy": 0.7561274647712708,
+      "num_tokens": 1043302.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.8024691358024691,
+      "grad_norm": 0.5180872082710266,
+      "learning_rate": 9.975262641713746e-05,
+      "loss": 0.6492,
+      "mean_token_accuracy": 0.7488725483417511,
+      "num_tokens": 1063782.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.8179012345679012,
+      "grad_norm": 0.526536762714386,
+      "learning_rate": 9.972662794970841e-05,
+      "loss": 0.6478,
+      "mean_token_accuracy": 0.7515686273574829,
+      "num_tokens": 1084262.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.5425621271133423,
+      "learning_rate": 9.969933442018968e-05,
+      "loss": 0.6157,
+      "mean_token_accuracy": 0.7639407038688659,
+      "num_tokens": 1104337.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8487654320987654,
+      "grad_norm": 0.6052752733230591,
+      "learning_rate": 9.967074653940396e-05,
+      "loss": 0.6449,
+      "mean_token_accuracy": 0.753088241815567,
+      "num_tokens": 1124817.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 0.5158132910728455,
+      "learning_rate": 9.964086505188352e-05,
+      "loss": 0.6342,
+      "mean_token_accuracy": 0.7589705944061279,
+      "num_tokens": 1145297.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8796296296296297,
+      "grad_norm": 0.558788001537323,
+      "learning_rate": 9.960969073585091e-05,
+      "loss": 0.65,
+      "mean_token_accuracy": 0.75220587849617,
+      "num_tokens": 1165777.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8950617283950617,
+      "grad_norm": 0.5892021059989929,
+      "learning_rate": 9.95772244031986e-05,
+      "loss": 0.6299,
+      "mean_token_accuracy": 0.7599019587039948,
+      "num_tokens": 1186257.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.9104938271604939,
+      "grad_norm": 0.49645981192588806,
+      "learning_rate": 9.954346689946785e-05,
+      "loss": 0.6353,
+      "mean_token_accuracy": 0.7553921580314636,
+      "num_tokens": 1206737.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 0.5327996611595154,
+      "learning_rate": 9.950841910382675e-05,
+      "loss": 0.6336,
+      "mean_token_accuracy": 0.7565686404705048,
+      "num_tokens": 1227217.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.941358024691358,
+      "grad_norm": 0.6819751262664795,
+      "learning_rate": 9.947208192904722e-05,
+      "loss": 0.6521,
+      "mean_token_accuracy": 0.747107845544815,
+      "num_tokens": 1247697.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9567901234567902,
+      "grad_norm": 0.5382965207099915,
+      "learning_rate": 9.943445632148138e-05,
+      "loss": 0.6512,
+      "mean_token_accuracy": 0.7521078407764434,
+      "num_tokens": 1268177.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 0.5911397337913513,
+      "learning_rate": 9.939554326103673e-05,
+      "loss": 0.6269,
+      "mean_token_accuracy": 0.7610294163227082,
+      "num_tokens": 1288657.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.5044689178466797,
+      "learning_rate": 9.935534376115081e-05,
+      "loss": 0.6359,
+      "mean_token_accuracy": 0.7558333456516266,
+      "num_tokens": 1309137.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6373786330223083,
+      "eval_mean_token_accuracy": 0.7553163358143398,
+      "eval_num_tokens": 1323985.0,
+      "eval_runtime": 3.2784,
+      "eval_samples_per_second": 83.272,
+      "eval_steps_per_second": 10.676,
+      "step": 648
+    },
+    {
+      "epoch": 1.0030864197530864,
+      "grad_norm": 0.5726162791252136,
+      "learning_rate": 9.931385886876466e-05,
+      "loss": 0.6273,
+      "mean_token_accuracy": 0.7600000083446503,
+      "num_tokens": 1328081.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.0185185185185186,
+      "grad_norm": 0.6138848662376404,
+      "learning_rate": 9.927108966429559e-05,
+      "loss": 0.6149,
+      "mean_token_accuracy": 0.7639705955982208,
+      "num_tokens": 1348561.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.0339506172839505,
+      "grad_norm": 0.5624936819076538,
+      "learning_rate": 9.922703726160915e-05,
+      "loss": 0.6093,
+      "mean_token_accuracy": 0.7660784363746643,
+      "num_tokens": 1369041.0,
+      "step": 670
+    },
+    {
+      "epoch": 1.0493827160493827,
+      "grad_norm": 0.6030348539352417,
+      "learning_rate": 9.918170280798997e-05,
+      "loss": 0.6029,
+      "mean_token_accuracy": 0.7672549068927765,
+      "num_tokens": 1389521.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.0648148148148149,
+      "grad_norm": 0.6273998618125916,
+      "learning_rate": 9.913508748411195e-05,
+      "loss": 0.6224,
+      "mean_token_accuracy": 0.7597549080848693,
+      "num_tokens": 1410001.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0802469135802468,
+      "grad_norm": 0.5929473638534546,
+      "learning_rate": 9.908719250400751e-05,
+      "loss": 0.6264,
+      "mean_token_accuracy": 0.7589215755462646,
+      "num_tokens": 1430481.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.095679012345679,
+      "grad_norm": 0.6457216143608093,
+      "learning_rate": 9.903801911503601e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7606862783432007,
+      "num_tokens": 1450961.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.5677434206008911,
+      "learning_rate": 9.898756859785114e-05,
+      "loss": 0.6479,
+      "mean_token_accuracy": 0.7513552784919739,
+      "num_tokens": 1471334.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.126543209876543,
+      "grad_norm": 0.5023089051246643,
+      "learning_rate": 9.893584226636772e-05,
+      "loss": 0.643,
+      "mean_token_accuracy": 0.7502450942993164,
+      "num_tokens": 1491814.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.1419753086419753,
+      "grad_norm": 0.5853515267372131,
+      "learning_rate": 9.88828414677274e-05,
+      "loss": 0.6181,
+      "mean_token_accuracy": 0.762156856060028,
+      "num_tokens": 1512294.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.1574074074074074,
+      "grad_norm": 0.6769473552703857,
+      "learning_rate": 9.882856758226355e-05,
+      "loss": 0.6193,
+      "mean_token_accuracy": 0.763762366771698,
+      "num_tokens": 1532542.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1728395061728394,
+      "grad_norm": 0.5814151167869568,
+      "learning_rate": 9.877302202346537e-05,
+      "loss": 0.6193,
+      "mean_token_accuracy": 0.7625367939472198,
+      "num_tokens": 1552867.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.1882716049382716,
+      "grad_norm": 0.7868801355361938,
+      "learning_rate": 9.871620623794107e-05,
+      "loss": 0.6119,
+      "mean_token_accuracy": 0.7656372606754303,
+      "num_tokens": 1573347.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.2037037037037037,
+      "grad_norm": 0.5902999043464661,
+      "learning_rate": 9.865812170538014e-05,
+      "loss": 0.6106,
+      "mean_token_accuracy": 0.7653431355953216,
+      "num_tokens": 1593827.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.2191358024691359,
+      "grad_norm": 0.5042413473129272,
+      "learning_rate": 9.859876993851489e-05,
+      "loss": 0.6258,
+      "mean_token_accuracy": 0.7603431344032288,
+      "num_tokens": 1614307.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 0.6255024671554565,
+      "learning_rate": 9.853815248308101e-05,
+      "loss": 0.6181,
+      "mean_token_accuracy": 0.7631550431251526,
+      "num_tokens": 1634681.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.5640517473220825,
+      "learning_rate": 9.847627091777729e-05,
+      "loss": 0.6138,
+      "mean_token_accuracy": 0.7638725519180298,
+      "num_tokens": 1655161.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2654320987654322,
+      "grad_norm": 0.5596677660942078,
+      "learning_rate": 9.841312685422459e-05,
+      "loss": 0.6173,
+      "mean_token_accuracy": 0.7628921627998352,
+      "num_tokens": 1675641.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.2808641975308643,
+      "grad_norm": 0.6959637403488159,
+      "learning_rate": 9.834872193692378e-05,
+      "loss": 0.631,
+      "mean_token_accuracy": 0.7579901933670044,
+      "num_tokens": 1696121.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.5890873670578003,
+      "learning_rate": 9.828305784321289e-05,
+      "loss": 0.6194,
+      "mean_token_accuracy": 0.7610294044017791,
+      "num_tokens": 1716601.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.3117283950617284,
+      "grad_norm": 0.5236982107162476,
+      "learning_rate": 9.821613628322358e-05,
+      "loss": 0.6353,
+      "mean_token_accuracy": 0.7555392146110534,
+      "num_tokens": 1737081.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.3271604938271606,
+      "grad_norm": 0.4920688271522522,
+      "learning_rate": 9.814795899983645e-05,
+      "loss": 0.6203,
+      "mean_token_accuracy": 0.7605464220046997,
+      "num_tokens": 1757399.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.3425925925925926,
+      "grad_norm": 0.5151636004447937,
+      "learning_rate": 9.807852776863568e-05,
+      "loss": 0.6316,
+      "mean_token_accuracy": 0.757401955127716,
+      "num_tokens": 1777879.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.3580246913580247,
+      "grad_norm": 0.5221789479255676,
+      "learning_rate": 9.800784439786286e-05,
+      "loss": 0.6021,
+      "mean_token_accuracy": 0.7678921699523926,
+      "num_tokens": 1798359.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.373456790123457,
+      "grad_norm": 0.6253092885017395,
+      "learning_rate": 9.793591072836978e-05,
+      "loss": 0.6189,
+      "mean_token_accuracy": 0.7627451002597809,
+      "num_tokens": 1818839.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 0.5362826585769653,
+      "learning_rate": 9.786272863357063e-05,
+      "loss": 0.6218,
+      "mean_token_accuracy": 0.7601960837841034,
+      "num_tokens": 1839319.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.404320987654321,
+      "grad_norm": 0.5733498930931091,
+      "learning_rate": 9.778830001939307e-05,
+      "loss": 0.6243,
+      "mean_token_accuracy": 0.7575980484485626,
+      "num_tokens": 1859799.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.4197530864197532,
+      "grad_norm": 0.5503411293029785,
+      "learning_rate": 9.771262682422866e-05,
+      "loss": 0.6043,
+      "mean_token_accuracy": 0.768676483631134,
+      "num_tokens": 1880279.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.4351851851851851,
+      "grad_norm": 0.5697808265686035,
+      "learning_rate": 9.76357110188824e-05,
+      "loss": 0.619,
+      "mean_token_accuracy": 0.7615686297416687,
+      "num_tokens": 1900759.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.4506172839506173,
+      "grad_norm": 0.5639927387237549,
+      "learning_rate": 9.755755460652137e-05,
+      "loss": 0.6287,
+      "mean_token_accuracy": 0.7581372559070587,
+      "num_tokens": 1921239.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.4660493827160495,
+      "grad_norm": 0.4238158166408539,
+      "learning_rate": 9.747815962262255e-05,
+      "loss": 0.6179,
+      "mean_token_accuracy": 0.7624019682407379,
+      "num_tokens": 1941719.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.5610195398330688,
+      "learning_rate": 9.73975281349198e-05,
+      "loss": 0.6198,
+      "mean_token_accuracy": 0.7611274600028992,
+      "num_tokens": 1962199.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4969135802469136,
+      "grad_norm": 0.5397023558616638,
+      "learning_rate": 9.73156622433501e-05,
+      "loss": 0.6262,
+      "mean_token_accuracy": 0.7573529422283173,
+      "num_tokens": 1982679.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.5123456790123457,
+      "grad_norm": 0.627068042755127,
+      "learning_rate": 9.72325640799987e-05,
+      "loss": 0.6341,
+      "mean_token_accuracy": 0.7564705967903137,
+      "num_tokens": 2003159.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.5277777777777777,
+      "grad_norm": 0.6139004826545715,
+      "learning_rate": 9.71482358090438e-05,
+      "loss": 0.628,
+      "mean_token_accuracy": 0.7554846823215484,
+      "num_tokens": 2023485.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.5432098765432098,
+      "grad_norm": 0.5941593647003174,
+      "learning_rate": 9.706267962669998e-05,
+      "loss": 0.636,
+      "mean_token_accuracy": 0.756617647409439,
+      "num_tokens": 2043965.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.558641975308642,
+      "grad_norm": 0.5428718328475952,
+      "learning_rate": 9.697589776116113e-05,
+      "loss": 0.6288,
+      "mean_token_accuracy": 0.7563235223293304,
+      "num_tokens": 2064445.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.574074074074074,
+      "grad_norm": 0.679093599319458,
+      "learning_rate": 9.688789247254237e-05,
+      "loss": 0.6137,
+      "mean_token_accuracy": 0.7616176426410675,
+      "num_tokens": 2084925.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5895061728395061,
+      "grad_norm": 0.5914977192878723,
+      "learning_rate": 9.679866605282122e-05,
+      "loss": 0.6101,
+      "mean_token_accuracy": 0.7660278260707856,
+      "num_tokens": 2105210.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6049382716049383,
+      "grad_norm": 0.6366807818412781,
+      "learning_rate": 9.670822082577787e-05,
+      "loss": 0.6221,
+      "mean_token_accuracy": 0.7630392193794251,
+      "num_tokens": 2125690.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6203703703703702,
+      "grad_norm": 0.537667453289032,
+      "learning_rate": 9.661655914693471e-05,
+      "loss": 0.6276,
+      "mean_token_accuracy": 0.7600000083446503,
+      "num_tokens": 2146170.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6358024691358026,
+      "grad_norm": 0.6829613447189331,
+      "learning_rate": 9.652368340349494e-05,
+      "loss": 0.6231,
+      "mean_token_accuracy": 0.7614292323589325,
+      "num_tokens": 2166400.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.6512345679012346,
+      "grad_norm": 0.46796467900276184,
+      "learning_rate": 9.642959601428039e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7614705860614777,
+      "num_tokens": 2186880.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.6203200221061707,
+      "learning_rate": 9.63342994296686e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7601960718631744,
+      "num_tokens": 2207360.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.682098765432099,
+      "grad_norm": 0.4808056652545929,
+      "learning_rate": 9.623779613152893e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7597549021244049,
+      "num_tokens": 2227840.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6975308641975309,
+      "grad_norm": 0.831586480140686,
+      "learning_rate": 9.614008863315789e-05,
+      "loss": 0.6031,
+      "mean_token_accuracy": 0.7655882358551025,
+      "num_tokens": 2248320.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7129629629629628,
+      "grad_norm": 0.5528991222381592,
+      "learning_rate": 9.604117947921385e-05,
+      "loss": 0.6255,
+      "mean_token_accuracy": 0.7599509835243226,
+      "num_tokens": 2268800.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7283950617283952,
+      "grad_norm": 0.518021821975708,
+      "learning_rate": 9.594107124565056e-05,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.7617159247398376,
+      "num_tokens": 2289107.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7438271604938271,
+      "grad_norm": 0.5663719177246094,
+      "learning_rate": 9.58397665396502e-05,
+      "loss": 0.6239,
+      "mean_token_accuracy": 0.7579901993274689,
+      "num_tokens": 2309587.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.7592592592592593,
+      "grad_norm": 0.6976074576377869,
+      "learning_rate": 9.573726799955544e-05,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.7644607961177826,
+      "num_tokens": 2330067.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7746913580246915,
+      "grad_norm": 0.491929829120636,
+      "learning_rate": 9.563357829480076e-05,
+      "loss": 0.6175,
+      "mean_token_accuracy": 0.7621568620204926,
+      "num_tokens": 2350547.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7901234567901234,
+      "grad_norm": 0.5365603566169739,
+      "learning_rate": 9.552870012584282e-05,
+      "loss": 0.6207,
+      "mean_token_accuracy": 0.7618627429008484,
+      "num_tokens": 2371027.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8055555555555556,
+      "grad_norm": 0.4748326241970062,
+      "learning_rate": 9.542263622409027e-05,
+      "loss": 0.6304,
+      "mean_token_accuracy": 0.7585784316062927,
+      "num_tokens": 2391507.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.8209876543209877,
+      "grad_norm": 0.6071013808250427,
+      "learning_rate": 9.53153893518325e-05,
+      "loss": 0.6242,
+      "mean_token_accuracy": 0.7582843065261841,
+      "num_tokens": 2411987.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.8364197530864197,
+      "grad_norm": 0.5693532228469849,
+      "learning_rate": 9.520696230216781e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7624019622802735,
+      "num_tokens": 2432467.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.5890586376190186,
+      "learning_rate": 9.509735789893059e-05,
+      "loss": 0.6261,
+      "mean_token_accuracy": 0.7603431344032288,
+      "num_tokens": 2452947.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.867283950617284,
+      "grad_norm": 0.5754212737083435,
+      "learning_rate": 9.498657899661774e-05,
+      "loss": 0.6201,
+      "mean_token_accuracy": 0.7618137300014496,
+      "num_tokens": 2473427.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.882716049382716,
+      "grad_norm": 0.48493534326553345,
+      "learning_rate": 9.487462848031445e-05,
+      "loss": 0.6411,
+      "mean_token_accuracy": 0.754411768913269,
+      "num_tokens": 2493907.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8981481481481481,
+      "grad_norm": 0.6793274283409119,
+      "learning_rate": 9.4761509265619e-05,
+      "loss": 0.6094,
+      "mean_token_accuracy": 0.7683333337306977,
+      "num_tokens": 2514387.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.9135802469135803,
+      "grad_norm": 0.43587443232536316,
+      "learning_rate": 9.464722429856674e-05,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.763382351398468,
+      "num_tokens": 2534867.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.9290123456790123,
+      "grad_norm": 0.5037091970443726,
+      "learning_rate": 9.453177655555355e-05,
+      "loss": 0.6215,
+      "mean_token_accuracy": 0.7608333349227905,
+      "num_tokens": 2555347.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 0.48443400859832764,
+      "learning_rate": 9.441516904325816e-05,
+      "loss": 0.6326,
+      "mean_token_accuracy": 0.7566666662693023,
+      "num_tokens": 2575827.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.9598765432098766,
+      "grad_norm": 0.5313301086425781,
+      "learning_rate": 9.42974047985639e-05,
+      "loss": 0.6059,
+      "mean_token_accuracy": 0.7671078443527222,
+      "num_tokens": 2596307.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.4752209186553955,
+      "learning_rate": 9.417848688847968e-05,
+      "loss": 0.6221,
+      "mean_token_accuracy": 0.7612836718559265,
+      "num_tokens": 2616738.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.9907407407407407,
+      "grad_norm": 0.6168082356452942,
+      "learning_rate": 9.405841841005998e-05,
+      "loss": 0.6199,
+      "mean_token_accuracy": 0.7622058808803558,
+      "num_tokens": 2637218.0,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.628555953502655,
+      "eval_mean_token_accuracy": 0.7592301794460842,
+      "eval_num_tokens": 2647970.0,
+      "eval_runtime": 3.2461,
+      "eval_samples_per_second": 84.102,
+      "eval_steps_per_second": 10.782,
+      "step": 1296
+    },
+    {
+      "epoch": 2.006172839506173,
+      "grad_norm": 0.5350890755653381,
+      "learning_rate": 9.393720249032428e-05,
+      "loss": 0.5952,
+      "mean_token_accuracy": 0.7718137264251709,
+      "num_tokens": 2656162.0,
+      "step": 1300
+    },
+    {
+      "epoch": 2.021604938271605,
+      "grad_norm": 0.7325437664985657,
+      "learning_rate": 9.381484228617561e-05,
+      "loss": 0.6002,
+      "mean_token_accuracy": 0.7719117701053619,
+      "num_tokens": 2676642.0,
+      "step": 1310
+    },
+    {
+      "epoch": 2.037037037037037,
+      "grad_norm": 0.5555301308631897,
+      "learning_rate": 9.369134098431836e-05,
+      "loss": 0.5987,
+      "mean_token_accuracy": 0.7709803938865661,
+      "num_tokens": 2697122.0,
+      "step": 1320
+    },
+    {
+      "epoch": 2.052469135802469,
+      "grad_norm": 0.6631981134414673,
+      "learning_rate": 9.356670180117515e-05,
+      "loss": 0.5884,
+      "mean_token_accuracy": 0.7728506803512574,
+      "num_tokens": 2717448.0,
+      "step": 1330
+    },
+    {
+      "epoch": 2.067901234567901,
+      "grad_norm": 0.533174455165863,
+      "learning_rate": 9.344092798280326e-05,
+      "loss": 0.5974,
+      "mean_token_accuracy": 0.77112957239151,
+      "num_tokens": 2737755.0,
+      "step": 1340
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.8145793676376343,
+      "learning_rate": 9.331402280480996e-05,
+      "loss": 0.5724,
+      "mean_token_accuracy": 0.7805882334709168,
+      "num_tokens": 2758235.0,
+      "step": 1350
+    },
+    {
+      "epoch": 2.0987654320987654,
+      "grad_norm": 0.5709875226020813,
+      "learning_rate": 9.318598957226722e-05,
+      "loss": 0.593,
+      "mean_token_accuracy": 0.7734803974628448,
+      "num_tokens": 2778715.0,
+      "step": 1360
+    },
+    {
+      "epoch": 2.1141975308641974,
+      "grad_norm": 0.7765586972236633,
+      "learning_rate": 9.305683161962569e-05,
+      "loss": 0.5943,
+      "mean_token_accuracy": 0.773333340883255,
+      "num_tokens": 2799195.0,
+      "step": 1370
+    },
+    {
+      "epoch": 2.1296296296296298,
+      "grad_norm": 0.9367417097091675,
+      "learning_rate": 9.292655231062777e-05,
+      "loss": 0.5902,
+      "mean_token_accuracy": 0.770686274766922,
+      "num_tokens": 2819675.0,
+      "step": 1380
+    },
+    {
+      "epoch": 2.1450617283950617,
+      "grad_norm": 0.5698003172874451,
+      "learning_rate": 9.279515503822012e-05,
+      "loss": 0.5999,
+      "mean_token_accuracy": 0.7680392146110535,
+      "num_tokens": 2840155.0,
+      "step": 1390
+    },
+    {
+      "epoch": 2.1604938271604937,
+      "grad_norm": 0.5707505345344543,
+      "learning_rate": 9.266264322446513e-05,
+      "loss": 0.5818,
+      "mean_token_accuracy": 0.7765196144580842,
+      "num_tokens": 2860635.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.175925925925926,
+      "grad_norm": 0.626613974571228,
+      "learning_rate": 9.2529020320452e-05,
+      "loss": 0.581,
+      "mean_token_accuracy": 0.775245088338852,
+      "num_tokens": 2881115.0,
+      "step": 1410
+    },
+    {
+      "epoch": 2.191358024691358,
+      "grad_norm": 0.7097243070602417,
+      "learning_rate": 9.239428980620668e-05,
+      "loss": 0.6057,
+      "mean_token_accuracy": 0.7675980448722839,
+      "num_tokens": 2901595.0,
+      "step": 1420
+    },
+    {
+      "epoch": 2.20679012345679,
+      "grad_norm": 0.6461248993873596,
+      "learning_rate": 9.22584551906014e-05,
+      "loss": 0.6072,
+      "mean_token_accuracy": 0.7674509882926941,
+      "num_tokens": 2922075.0,
+      "step": 1430
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.7755699157714844,
+      "learning_rate": 9.212152001126309e-05,
+      "loss": 0.5992,
+      "mean_token_accuracy": 0.7677941083908081,
+      "num_tokens": 2942555.0,
+      "step": 1440
+    },
+    {
+      "epoch": 2.2376543209876543,
+      "grad_norm": 0.5984106659889221,
+      "learning_rate": 9.198348783448143e-05,
+      "loss": 0.5733,
+      "mean_token_accuracy": 0.7785784363746643,
+      "num_tokens": 2963035.0,
+      "step": 1450
+    },
+    {
+      "epoch": 2.253086419753086,
+      "grad_norm": 0.683435320854187,
+      "learning_rate": 9.184436225511593e-05,
+      "loss": 0.5867,
+      "mean_token_accuracy": 0.772892153263092,
+      "num_tokens": 2983515.0,
+      "step": 1460
+    },
+    {
+      "epoch": 2.2685185185185186,
+      "grad_norm": 0.6326505541801453,
+      "learning_rate": 9.170414689650218e-05,
+      "loss": 0.5955,
+      "mean_token_accuracy": 0.7710784256458283,
+      "num_tokens": 3003995.0,
+      "step": 1470
+    },
+    {
+      "epoch": 2.2839506172839505,
+      "grad_norm": 0.5087013840675354,
+      "learning_rate": 9.156284541035767e-05,
+      "loss": 0.5941,
+      "mean_token_accuracy": 0.770262885093689,
+      "num_tokens": 3024243.0,
+      "step": 1480
+    },
+    {
+      "epoch": 2.299382716049383,
+      "grad_norm": 0.5956624746322632,
+      "learning_rate": 9.142046147668656e-05,
+      "loss": 0.5961,
+      "mean_token_accuracy": 0.7705882370471955,
+      "num_tokens": 3044723.0,
+      "step": 1490
+    },
+    {
+      "epoch": 2.314814814814815,
+      "grad_norm": 0.5642819404602051,
+      "learning_rate": 9.127699880368388e-05,
+      "loss": 0.579,
+      "mean_token_accuracy": 0.7750980377197265,
+      "num_tokens": 3065203.0,
+      "step": 1500
+    },
+    {
+      "epoch": 2.330246913580247,
+      "grad_norm": 0.7624996900558472,
+      "learning_rate": 9.113246112763896e-05,
+      "loss": 0.5968,
+      "mean_token_accuracy": 0.7697415828704834,
+      "num_tokens": 3085634.0,
+      "step": 1510
+    },
+    {
+      "epoch": 2.3456790123456788,
+      "grad_norm": 0.6217107176780701,
+      "learning_rate": 9.098685221283809e-05,
+      "loss": 0.5945,
+      "mean_token_accuracy": 0.77044118642807,
+      "num_tokens": 3106114.0,
+      "step": 1520
+    },
+    {
+      "epoch": 2.361111111111111,
+      "grad_norm": 0.6848967671394348,
+      "learning_rate": 9.084017585146653e-05,
+      "loss": 0.6086,
+      "mean_token_accuracy": 0.7675980448722839,
+      "num_tokens": 3126594.0,
+      "step": 1530
+    },
+    {
+      "epoch": 2.376543209876543,
+      "grad_norm": 0.7084946632385254,
+      "learning_rate": 9.069243586350975e-05,
+      "loss": 0.5948,
+      "mean_token_accuracy": 0.7736274540424347,
+      "num_tokens": 3147074.0,
+      "step": 1540
+    },
+    {
+      "epoch": 2.3919753086419755,
+      "grad_norm": 0.6253333687782288,
+      "learning_rate": 9.054363609665388e-05,
+      "loss": 0.5987,
+      "mean_token_accuracy": 0.7670588254928589,
+      "num_tokens": 3167554.0,
+      "step": 1550
+    },
+    {
+      "epoch": 2.4074074074074074,
+      "grad_norm": 0.7215299010276794,
+      "learning_rate": 9.039378042618556e-05,
+      "loss": 0.6118,
+      "mean_token_accuracy": 0.7658778011798859,
+      "num_tokens": 3187872.0,
+      "step": 1560
+    },
+    {
+      "epoch": 2.4228395061728394,
+      "grad_norm": 0.5760617852210999,
+      "learning_rate": 9.0242872754891e-05,
+      "loss": 0.5893,
+      "mean_token_accuracy": 0.7756372570991517,
+      "num_tokens": 3208352.0,
+      "step": 1570
+    },
+    {
+      "epoch": 2.4382716049382718,
+      "grad_norm": 0.6861734390258789,
+      "learning_rate": 9.009091701295434e-05,
+      "loss": 0.5842,
+      "mean_token_accuracy": 0.7753921568393707,
+      "num_tokens": 3228832.0,
+      "step": 1580
+    },
+    {
+      "epoch": 2.4537037037037037,
+      "grad_norm": 0.6804457902908325,
+      "learning_rate": 8.993791715785528e-05,
+      "loss": 0.5917,
+      "mean_token_accuracy": 0.772210317850113,
+      "num_tokens": 3249205.0,
+      "step": 1590
+    },
+    {
+      "epoch": 2.4691358024691357,
+      "grad_norm": 0.6913892030715942,
+      "learning_rate": 8.978387717426601e-05,
+      "loss": 0.5909,
+      "mean_token_accuracy": 0.7718627512454986,
+      "num_tokens": 3269685.0,
+      "step": 1600
+    },
+    {
+      "epoch": 2.484567901234568,
+      "grad_norm": 0.7079524993896484,
+      "learning_rate": 8.962880107394747e-05,
+      "loss": 0.5927,
+      "mean_token_accuracy": 0.7718627452850342,
+      "num_tokens": 3290165.0,
+      "step": 1610
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.6033655405044556,
+      "learning_rate": 8.947269289564482e-05,
+      "loss": 0.5912,
+      "mean_token_accuracy": 0.7717647075653076,
+      "num_tokens": 3310645.0,
+      "step": 1620
+    },
+    {
+      "epoch": 2.515432098765432,
+      "grad_norm": 0.7890419363975525,
+      "learning_rate": 8.931555670498229e-05,
+      "loss": 0.5895,
+      "mean_token_accuracy": 0.7722058832645416,
+      "num_tokens": 3331125.0,
+      "step": 1630
+    },
+    {
+      "epoch": 2.5308641975308643,
+      "grad_norm": 0.5943073630332947,
+      "learning_rate": 8.915739659435732e-05,
+      "loss": 0.5882,
+      "mean_token_accuracy": 0.7717156887054444,
+      "num_tokens": 3351605.0,
+      "step": 1640
+    },
+    {
+      "epoch": 2.5462962962962963,
+      "grad_norm": 0.6067966222763062,
+      "learning_rate": 8.899821668283388e-05,
+      "loss": 0.5817,
+      "mean_token_accuracy": 0.7767156839370728,
+      "num_tokens": 3372085.0,
+      "step": 1650
+    },
+    {
+      "epoch": 2.5617283950617287,
+      "grad_norm": 0.6475111246109009,
+      "learning_rate": 8.883802111603532e-05,
+      "loss": 0.6051,
+      "mean_token_accuracy": 0.7653431475162507,
+      "num_tokens": 3392565.0,
+      "step": 1660
+    },
+    {
+      "epoch": 2.5771604938271606,
+      "grad_norm": 0.6153448224067688,
+      "learning_rate": 8.867681406603632e-05,
+      "loss": 0.6031,
+      "mean_token_accuracy": 0.7666176497936249,
+      "num_tokens": 3413045.0,
+      "step": 1670
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.658183217048645,
+      "learning_rate": 8.851459973125424e-05,
+      "loss": 0.5952,
+      "mean_token_accuracy": 0.7705015063285827,
+      "num_tokens": 3433370.0,
+      "step": 1680
+    },
+    {
+      "epoch": 2.6080246913580245,
+      "grad_norm": 0.6191939115524292,
+      "learning_rate": 8.835138233633986e-05,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.7691666722297669,
+      "num_tokens": 3453850.0,
+      "step": 1690
+    },
+    {
+      "epoch": 2.623456790123457,
+      "grad_norm": 0.5918915271759033,
+      "learning_rate": 8.818716613206718e-05,
+      "loss": 0.6046,
+      "mean_token_accuracy": 0.7666176497936249,
+      "num_tokens": 3474330.0,
+      "step": 1700
+    },
+    {
+      "epoch": 2.638888888888889,
+      "grad_norm": 0.5293189287185669,
+      "learning_rate": 8.802195539522298e-05,
+      "loss": 0.577,
+      "mean_token_accuracy": 0.7772549033164978,
+      "num_tokens": 3494810.0,
+      "step": 1710
+    },
+    {
+      "epoch": 2.6543209876543212,
+      "grad_norm": 0.7564029097557068,
+      "learning_rate": 8.785575442849512e-05,
+      "loss": 0.5993,
+      "mean_token_accuracy": 0.7706372559070587,
+      "num_tokens": 3515290.0,
+      "step": 1720
+    },
+    {
+      "epoch": 2.669753086419753,
+      "grad_norm": 0.6666939854621887,
+      "learning_rate": 8.768856756036075e-05,
+      "loss": 0.6004,
+      "mean_token_accuracy": 0.7707352936267853,
+      "num_tokens": 3535770.0,
+      "step": 1730
+    },
+    {
+      "epoch": 2.685185185185185,
+      "grad_norm": 0.7649972438812256,
+      "learning_rate": 8.752039914497344e-05,
+      "loss": 0.5803,
+      "mean_token_accuracy": 0.7755699038505555,
+      "num_tokens": 3556055.0,
+      "step": 1740
+    },
+    {
+      "epoch": 2.700617283950617,
+      "grad_norm": 0.6303521394729614,
+      "learning_rate": 8.73512535620498e-05,
+      "loss": 0.5823,
+      "mean_token_accuracy": 0.7731906652450562,
+      "num_tokens": 3576285.0,
+      "step": 1750
+    },
+    {
+      "epoch": 2.7160493827160495,
+      "grad_norm": 0.6482508778572083,
+      "learning_rate": 8.718113521675551e-05,
+      "loss": 0.5833,
+      "mean_token_accuracy": 0.7746078491210937,
+      "num_tokens": 3596765.0,
+      "step": 1760
+    },
+    {
+      "epoch": 2.7314814814814814,
+      "grad_norm": 0.6496692299842834,
+      "learning_rate": 8.70100485395904e-05,
+      "loss": 0.5796,
+      "mean_token_accuracy": 0.77576185464859,
+      "num_tokens": 3617139.0,
+      "step": 1770
+    },
+    {
+      "epoch": 2.746913580246914,
+      "grad_norm": 0.7126871943473816,
+      "learning_rate": 8.683799798627327e-05,
+      "loss": 0.5932,
+      "mean_token_accuracy": 0.7718137383460999,
+      "num_tokens": 3637619.0,
+      "step": 1780
+    },
+    {
+      "epoch": 2.7623456790123457,
+      "grad_norm": 0.536176860332489,
+      "learning_rate": 8.666498803762575e-05,
+      "loss": 0.6127,
+      "mean_token_accuracy": 0.7644607901573182,
+      "num_tokens": 3658099.0,
+      "step": 1790
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.5753297209739685,
+      "learning_rate": 8.649102319945556e-05,
+      "loss": 0.6003,
+      "mean_token_accuracy": 0.7688235282897949,
+      "num_tokens": 3678579.0,
+      "step": 1800
+    },
+    {
+      "epoch": 2.7932098765432096,
+      "grad_norm": 0.7861889004707336,
+      "learning_rate": 8.631610800243926e-05,
+      "loss": 0.5948,
+      "mean_token_accuracy": 0.7707352876663208,
+      "num_tokens": 3699059.0,
+      "step": 1810
+    },
+    {
+      "epoch": 2.808641975308642,
+      "grad_norm": 0.7440711855888367,
+      "learning_rate": 8.614024700200418e-05,
+      "loss": 0.5974,
+      "mean_token_accuracy": 0.7701960802078247,
+      "num_tokens": 3719539.0,
+      "step": 1820
+    },
+    {
+      "epoch": 2.824074074074074,
+      "grad_norm": 0.7377384305000305,
+      "learning_rate": 8.596344477820982e-05,
+      "loss": 0.6059,
+      "mean_token_accuracy": 0.7668627500534058,
+      "num_tokens": 3740019.0,
+      "step": 1830
+    },
+    {
+      "epoch": 2.8395061728395063,
+      "grad_norm": 0.6190456748008728,
+      "learning_rate": 8.578570593562856e-05,
+      "loss": 0.5955,
+      "mean_token_accuracy": 0.7732352972030639,
+      "num_tokens": 3760499.0,
+      "step": 1840
+    },
+    {
+      "epoch": 2.8549382716049383,
+      "grad_norm": 0.695401668548584,
+      "learning_rate": 8.560703510322574e-05,
+      "loss": 0.5834,
+      "mean_token_accuracy": 0.7763725578784942,
+      "num_tokens": 3780979.0,
+      "step": 1850
+    },
+    {
+      "epoch": 2.8703703703703702,
+      "grad_norm": 0.6935811638832092,
+      "learning_rate": 8.54274369342391e-05,
+      "loss": 0.6105,
+      "mean_token_accuracy": 0.7648529410362244,
+      "num_tokens": 3801459.0,
+      "step": 1860
+    },
+    {
+      "epoch": 2.8858024691358026,
+      "grad_norm": 0.8666762113571167,
+      "learning_rate": 8.524691610605755e-05,
+      "loss": 0.5848,
+      "mean_token_accuracy": 0.775196087360382,
+      "num_tokens": 3821939.0,
+      "step": 1870
+    },
+    {
+      "epoch": 2.9012345679012346,
+      "grad_norm": 0.8038449287414551,
+      "learning_rate": 8.506547732009949e-05,
+      "loss": 0.6048,
+      "mean_token_accuracy": 0.7674509882926941,
+      "num_tokens": 3842419.0,
+      "step": 1880
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 0.6401634812355042,
+      "learning_rate": 8.488312530169019e-05,
+      "loss": 0.5946,
+      "mean_token_accuracy": 0.7687254846096039,
+      "num_tokens": 3862899.0,
+      "step": 1890
+    },
+    {
+      "epoch": 2.932098765432099,
+      "grad_norm": 0.6001216769218445,
+      "learning_rate": 8.469986479993885e-05,
+      "loss": 0.5909,
+      "mean_token_accuracy": 0.7719607830047608,
+      "num_tokens": 3883379.0,
+      "step": 1900
+    },
+    {
+      "epoch": 2.947530864197531,
+      "grad_norm": 0.6955755352973938,
+      "learning_rate": 8.451570058761487e-05,
+      "loss": 0.6008,
+      "mean_token_accuracy": 0.7700000047683716,
+      "num_tokens": 3903859.0,
+      "step": 1910
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.5965796113014221,
+      "learning_rate": 8.433063746102357e-05,
+      "loss": 0.5778,
+      "mean_token_accuracy": 0.7758823573589325,
+      "num_tokens": 3924339.0,
+      "step": 1920
+    },
+    {
+      "epoch": 2.978395061728395,
+      "grad_norm": 0.6863985061645508,
+      "learning_rate": 8.414468023988124e-05,
+      "loss": 0.5811,
+      "mean_token_accuracy": 0.775784307718277,
+      "num_tokens": 3944819.0,
+      "step": 1930
+    },
+    {
+      "epoch": 2.993827160493827,
+      "grad_norm": 0.6362125277519226,
+      "learning_rate": 8.395783376718966e-05,
+      "loss": 0.6043,
+      "mean_token_accuracy": 0.7676960825920105,
+      "num_tokens": 3965299.0,
+      "step": 1940
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6355003714561462,
+      "eval_mean_token_accuracy": 0.7551294309752328,
+      "eval_num_tokens": 3971955.0,
+      "eval_runtime": 3.251,
+      "eval_samples_per_second": 83.974,
+      "eval_steps_per_second": 10.766,
+      "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_s2_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:a6ae2e45c24ad2de3ad1c1a2451eabb81c07194ae1361d646cc4fc0918792a0e
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "o_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_s2_vt_project_a1_ALL_bcast_vs0p05/checkpoint-2592/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99babd6f33e942a9f2245f91ba619b183536d10d2861b762f4fa68ff37707462
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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_s2_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_s2_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_s2_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_s2_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": 3.642612934112549,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 2.4646,
+      "mean_token_accuracy": 0.5422549068927764,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.030864197530864196,
+      "grad_norm": 3.9434099197387695,
+      "learning_rate": 5.864197530864198e-06,
+      "loss": 2.4441,
+      "mean_token_accuracy": 0.5425980448722839,
+      "num_tokens": 40960.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.046296296296296294,
+      "grad_norm": 3.700989246368408,
+      "learning_rate": 8.950617283950618e-06,
+      "loss": 2.3243,
+      "mean_token_accuracy": 0.5584313631057739,
+      "num_tokens": 61440.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.06172839506172839,
+      "grad_norm": 1.9946578741073608,
+      "learning_rate": 1.2037037037037037e-05,
+      "loss": 2.0389,
+      "mean_token_accuracy": 0.575637263059616,
+      "num_tokens": 81920.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07716049382716049,
+      "grad_norm": 1.3853442668914795,
+      "learning_rate": 1.5123456790123458e-05,
+      "loss": 1.7642,
+      "mean_token_accuracy": 0.5935294091701507,
+      "num_tokens": 102400.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.09259259259259259,
+      "grad_norm": 1.0514497756958008,
+      "learning_rate": 1.8209876543209877e-05,
+      "loss": 1.5084,
+      "mean_token_accuracy": 0.6130882322788238,
+      "num_tokens": 122880.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.10802469135802469,
+      "grad_norm": 0.8691298365592957,
+      "learning_rate": 2.1296296296296296e-05,
+      "loss": 1.3515,
+      "mean_token_accuracy": 0.628529405593872,
+      "num_tokens": 143360.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 0.8635798096656799,
+      "learning_rate": 2.438271604938272e-05,
+      "loss": 1.186,
+      "mean_token_accuracy": 0.6466176509857178,
+      "num_tokens": 163840.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 1.0584197044372559,
+      "learning_rate": 2.7469135802469138e-05,
+      "loss": 1.0054,
+      "mean_token_accuracy": 0.6829411745071411,
+      "num_tokens": 184320.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.15432098765432098,
+      "grad_norm": 1.2961719036102295,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.9019,
+      "mean_token_accuracy": 0.6948529422283173,
+      "num_tokens": 204800.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.1697530864197531,
+      "grad_norm": 0.9584153890609741,
+      "learning_rate": 3.364197530864198e-05,
+      "loss": 0.8,
+      "mean_token_accuracy": 0.7179901957511902,
+      "num_tokens": 225280.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 1.0122414827346802,
+      "learning_rate": 3.67283950617284e-05,
+      "loss": 0.7736,
+      "mean_token_accuracy": 0.7223033726215362,
+      "num_tokens": 245510.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.2006172839506173,
+      "grad_norm": 1.164900302886963,
+      "learning_rate": 3.981481481481482e-05,
+      "loss": 0.7387,
+      "mean_token_accuracy": 0.7296568572521209,
+      "num_tokens": 265990.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.21604938271604937,
+      "grad_norm": 1.3156484365463257,
+      "learning_rate": 4.290123456790124e-05,
+      "loss": 0.7131,
+      "mean_token_accuracy": 0.740049022436142,
+      "num_tokens": 286470.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.23148148148148148,
+      "grad_norm": 1.017964243888855,
+      "learning_rate": 4.5987654320987656e-05,
+      "loss": 0.6822,
+      "mean_token_accuracy": 0.7473039209842682,
+      "num_tokens": 306950.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 0.9417504668235779,
+      "learning_rate": 4.9074074074074075e-05,
+      "loss": 0.6739,
+      "mean_token_accuracy": 0.7507843136787414,
+      "num_tokens": 327430.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.2623456790123457,
+      "grad_norm": 0.8708726167678833,
+      "learning_rate": 5.2160493827160494e-05,
+      "loss": 0.6713,
+      "mean_token_accuracy": 0.7505392134189606,
+      "num_tokens": 347910.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 1.0337103605270386,
+      "learning_rate": 5.524691358024692e-05,
+      "loss": 0.691,
+      "mean_token_accuracy": 0.7461764752864838,
+      "num_tokens": 368390.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2932098765432099,
+      "grad_norm": 0.947323739528656,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 0.6836,
+      "mean_token_accuracy": 0.742941164970398,
+      "num_tokens": 388870.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.30864197530864196,
+      "grad_norm": 0.8118940591812134,
+      "learning_rate": 6.141975308641975e-05,
+      "loss": 0.6757,
+      "mean_token_accuracy": 0.7460784316062927,
+      "num_tokens": 409350.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.32407407407407407,
+      "grad_norm": 0.8250467777252197,
+      "learning_rate": 6.450617283950617e-05,
+      "loss": 0.6566,
+      "mean_token_accuracy": 0.7514705836772919,
+      "num_tokens": 429830.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3395061728395062,
+      "grad_norm": 0.813636839389801,
+      "learning_rate": 6.759259259259259e-05,
+      "loss": 0.6705,
+      "mean_token_accuracy": 0.748235285282135,
+      "num_tokens": 450310.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.3549382716049383,
+      "grad_norm": 0.7828725576400757,
+      "learning_rate": 7.067901234567902e-05,
+      "loss": 0.6477,
+      "mean_token_accuracy": 0.7533458650112153,
+      "num_tokens": 470636.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.8237150311470032,
+      "learning_rate": 7.376543209876543e-05,
+      "loss": 0.67,
+      "mean_token_accuracy": 0.7494240999221802,
+      "num_tokens": 491067.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.38580246913580246,
+      "grad_norm": 0.9318073987960815,
+      "learning_rate": 7.685185185185185e-05,
+      "loss": 0.65,
+      "mean_token_accuracy": 0.7544607818126678,
+      "num_tokens": 511547.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4012345679012346,
+      "grad_norm": 0.796583890914917,
+      "learning_rate": 7.993827160493828e-05,
+      "loss": 0.6754,
+      "mean_token_accuracy": 0.7434313535690308,
+      "num_tokens": 532027.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.9032039046287537,
+      "learning_rate": 8.30246913580247e-05,
+      "loss": 0.6606,
+      "mean_token_accuracy": 0.7502451062202453,
+      "num_tokens": 552507.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.43209876543209874,
+      "grad_norm": 0.716952383518219,
+      "learning_rate": 8.611111111111112e-05,
+      "loss": 0.6418,
+      "mean_token_accuracy": 0.7555392146110534,
+      "num_tokens": 572987.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.44753086419753085,
+      "grad_norm": 0.7230756878852844,
+      "learning_rate": 8.919753086419754e-05,
+      "loss": 0.6494,
+      "mean_token_accuracy": 0.7528663039207458,
+      "num_tokens": 593305.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 0.8555248379707336,
+      "learning_rate": 9.228395061728396e-05,
+      "loss": 0.6636,
+      "mean_token_accuracy": 0.7458823561668396,
+      "num_tokens": 613785.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.4783950617283951,
+      "grad_norm": 0.666594922542572,
+      "learning_rate": 9.537037037037038e-05,
+      "loss": 0.6367,
+      "mean_token_accuracy": 0.7563725471496582,
+      "num_tokens": 634265.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.6590859293937683,
+      "learning_rate": 9.84567901234568e-05,
+      "loss": 0.6508,
+      "mean_token_accuracy": 0.7519607841968536,
+      "num_tokens": 654745.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.5092592592592593,
+      "grad_norm": 0.7278088927268982,
+      "learning_rate": 9.999983722702365e-05,
+      "loss": 0.6534,
+      "mean_token_accuracy": 0.7518137276172638,
+      "num_tokens": 675225.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.5246913580246914,
+      "grad_norm": 0.6529048681259155,
+      "learning_rate": 9.999853504957158e-05,
+      "loss": 0.6375,
+      "mean_token_accuracy": 0.757303923368454,
+      "num_tokens": 695705.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5401234567901234,
+      "grad_norm": 0.6195814609527588,
+      "learning_rate": 9.999593072858088e-05,
+      "loss": 0.6444,
+      "mean_token_accuracy": 0.753872549533844,
+      "num_tokens": 716185.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.6766397953033447,
+      "learning_rate": 9.999202433187755e-05,
+      "loss": 0.6665,
+      "mean_token_accuracy": 0.7452171981334687,
+      "num_tokens": 736470.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5709876543209876,
+      "grad_norm": 0.5934011936187744,
+      "learning_rate": 9.998681596119832e-05,
+      "loss": 0.6537,
+      "mean_token_accuracy": 0.7506862759590149,
+      "num_tokens": 756950.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5864197530864198,
+      "grad_norm": 0.872284471988678,
+      "learning_rate": 9.998030575218811e-05,
+      "loss": 0.6562,
+      "mean_token_accuracy": 0.7521078407764434,
+      "num_tokens": 777430.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.6018518518518519,
+      "grad_norm": 0.6015172004699707,
+      "learning_rate": 9.997249387439643e-05,
+      "loss": 0.6459,
+      "mean_token_accuracy": 0.7544117629528045,
+      "num_tokens": 797910.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 0.5660067200660706,
+      "learning_rate": 9.996338053127292e-05,
+      "loss": 0.6354,
+      "mean_token_accuracy": 0.7564705908298492,
+      "num_tokens": 818390.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6327160493827161,
+      "grad_norm": 0.604268491268158,
+      "learning_rate": 9.99529659601622e-05,
+      "loss": 0.6534,
+      "mean_token_accuracy": 0.7492156803607941,
+      "num_tokens": 838870.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6481481481481481,
+      "grad_norm": 0.5622531175613403,
+      "learning_rate": 9.994125043229752e-05,
+      "loss": 0.6538,
+      "mean_token_accuracy": 0.7499509811401367,
+      "num_tokens": 859350.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.6635802469135802,
+      "grad_norm": 0.5512784719467163,
+      "learning_rate": 9.992823425279382e-05,
+      "loss": 0.6425,
+      "mean_token_accuracy": 0.7543627440929412,
+      "num_tokens": 879830.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6790123456790124,
+      "grad_norm": 0.6505032777786255,
+      "learning_rate": 9.991391776063969e-05,
+      "loss": 0.649,
+      "mean_token_accuracy": 0.7518137216567993,
+      "num_tokens": 900310.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 0.5469474196434021,
+      "learning_rate": 9.98983013286886e-05,
+      "loss": 0.6451,
+      "mean_token_accuracy": 0.7538235247135162,
+      "num_tokens": 920790.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.7098765432098766,
+      "grad_norm": 0.48557355999946594,
+      "learning_rate": 9.988138536364922e-05,
+      "loss": 0.6607,
+      "mean_token_accuracy": 0.7458333253860474,
+      "num_tokens": 941270.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.7253086419753086,
+      "grad_norm": 0.6949014067649841,
+      "learning_rate": 9.986317030607475e-05,
+      "loss": 0.6467,
+      "mean_token_accuracy": 0.7520922362804413,
+      "num_tokens": 961595.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.5359596610069275,
+      "learning_rate": 9.984365663035144e-05,
+      "loss": 0.6452,
+      "mean_token_accuracy": 0.7529411792755127,
+      "num_tokens": 982075.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.7561728395061729,
+      "grad_norm": 0.46560513973236084,
+      "learning_rate": 9.982284484468634e-05,
+      "loss": 0.6479,
+      "mean_token_accuracy": 0.7506862640380859,
+      "num_tokens": 1002555.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7716049382716049,
+      "grad_norm": 0.7050852179527283,
+      "learning_rate": 9.980073549109397e-05,
+      "loss": 0.653,
+      "mean_token_accuracy": 0.7522634565830231,
+      "num_tokens": 1022822.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.7870370370370371,
+      "grad_norm": 0.49813297390937805,
+      "learning_rate": 9.977732914538225e-05,
+      "loss": 0.6392,
+      "mean_token_accuracy": 0.7561274647712708,
+      "num_tokens": 1043302.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.8024691358024691,
+      "grad_norm": 0.5180872082710266,
+      "learning_rate": 9.975262641713746e-05,
+      "loss": 0.6492,
+      "mean_token_accuracy": 0.7488725483417511,
+      "num_tokens": 1063782.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.8179012345679012,
+      "grad_norm": 0.526536762714386,
+      "learning_rate": 9.972662794970841e-05,
+      "loss": 0.6478,
+      "mean_token_accuracy": 0.7515686273574829,
+      "num_tokens": 1084262.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.5425621271133423,
+      "learning_rate": 9.969933442018968e-05,
+      "loss": 0.6157,
+      "mean_token_accuracy": 0.7639407038688659,
+      "num_tokens": 1104337.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8487654320987654,
+      "grad_norm": 0.6052752733230591,
+      "learning_rate": 9.967074653940396e-05,
+      "loss": 0.6449,
+      "mean_token_accuracy": 0.753088241815567,
+      "num_tokens": 1124817.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 0.5158132910728455,
+      "learning_rate": 9.964086505188352e-05,
+      "loss": 0.6342,
+      "mean_token_accuracy": 0.7589705944061279,
+      "num_tokens": 1145297.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8796296296296297,
+      "grad_norm": 0.558788001537323,
+      "learning_rate": 9.960969073585091e-05,
+      "loss": 0.65,
+      "mean_token_accuracy": 0.75220587849617,
+      "num_tokens": 1165777.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8950617283950617,
+      "grad_norm": 0.5892021059989929,
+      "learning_rate": 9.95772244031986e-05,
+      "loss": 0.6299,
+      "mean_token_accuracy": 0.7599019587039948,
+      "num_tokens": 1186257.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.9104938271604939,
+      "grad_norm": 0.49645981192588806,
+      "learning_rate": 9.954346689946785e-05,
+      "loss": 0.6353,
+      "mean_token_accuracy": 0.7553921580314636,
+      "num_tokens": 1206737.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 0.5327996611595154,
+      "learning_rate": 9.950841910382675e-05,
+      "loss": 0.6336,
+      "mean_token_accuracy": 0.7565686404705048,
+      "num_tokens": 1227217.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.941358024691358,
+      "grad_norm": 0.6819751262664795,
+      "learning_rate": 9.947208192904722e-05,
+      "loss": 0.6521,
+      "mean_token_accuracy": 0.747107845544815,
+      "num_tokens": 1247697.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9567901234567902,
+      "grad_norm": 0.5382965207099915,
+      "learning_rate": 9.943445632148138e-05,
+      "loss": 0.6512,
+      "mean_token_accuracy": 0.7521078407764434,
+      "num_tokens": 1268177.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 0.5911397337913513,
+      "learning_rate": 9.939554326103673e-05,
+      "loss": 0.6269,
+      "mean_token_accuracy": 0.7610294163227082,
+      "num_tokens": 1288657.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.5044689178466797,
+      "learning_rate": 9.935534376115081e-05,
+      "loss": 0.6359,
+      "mean_token_accuracy": 0.7558333456516266,
+      "num_tokens": 1309137.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6373786330223083,
+      "eval_mean_token_accuracy": 0.7553163358143398,
+      "eval_num_tokens": 1323985.0,
+      "eval_runtime": 3.2784,
+      "eval_samples_per_second": 83.272,
+      "eval_steps_per_second": 10.676,
+      "step": 648
+    },
+    {
+      "epoch": 1.0030864197530864,
+      "grad_norm": 0.5726162791252136,
+      "learning_rate": 9.931385886876466e-05,
+      "loss": 0.6273,
+      "mean_token_accuracy": 0.7600000083446503,
+      "num_tokens": 1328081.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.0185185185185186,
+      "grad_norm": 0.6138848662376404,
+      "learning_rate": 9.927108966429559e-05,
+      "loss": 0.6149,
+      "mean_token_accuracy": 0.7639705955982208,
+      "num_tokens": 1348561.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.0339506172839505,
+      "grad_norm": 0.5624936819076538,
+      "learning_rate": 9.922703726160915e-05,
+      "loss": 0.6093,
+      "mean_token_accuracy": 0.7660784363746643,
+      "num_tokens": 1369041.0,
+      "step": 670
+    },
+    {
+      "epoch": 1.0493827160493827,
+      "grad_norm": 0.6030348539352417,
+      "learning_rate": 9.918170280798997e-05,
+      "loss": 0.6029,
+      "mean_token_accuracy": 0.7672549068927765,
+      "num_tokens": 1389521.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.0648148148148149,
+      "grad_norm": 0.6273998618125916,
+      "learning_rate": 9.913508748411195e-05,
+      "loss": 0.6224,
+      "mean_token_accuracy": 0.7597549080848693,
+      "num_tokens": 1410001.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0802469135802468,
+      "grad_norm": 0.5929473638534546,
+      "learning_rate": 9.908719250400751e-05,
+      "loss": 0.6264,
+      "mean_token_accuracy": 0.7589215755462646,
+      "num_tokens": 1430481.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.095679012345679,
+      "grad_norm": 0.6457216143608093,
+      "learning_rate": 9.903801911503601e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7606862783432007,
+      "num_tokens": 1450961.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.5677434206008911,
+      "learning_rate": 9.898756859785114e-05,
+      "loss": 0.6479,
+      "mean_token_accuracy": 0.7513552784919739,
+      "num_tokens": 1471334.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.126543209876543,
+      "grad_norm": 0.5023089051246643,
+      "learning_rate": 9.893584226636772e-05,
+      "loss": 0.643,
+      "mean_token_accuracy": 0.7502450942993164,
+      "num_tokens": 1491814.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.1419753086419753,
+      "grad_norm": 0.5853515267372131,
+      "learning_rate": 9.88828414677274e-05,
+      "loss": 0.6181,
+      "mean_token_accuracy": 0.762156856060028,
+      "num_tokens": 1512294.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.1574074074074074,
+      "grad_norm": 0.6769473552703857,
+      "learning_rate": 9.882856758226355e-05,
+      "loss": 0.6193,
+      "mean_token_accuracy": 0.763762366771698,
+      "num_tokens": 1532542.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1728395061728394,
+      "grad_norm": 0.5814151167869568,
+      "learning_rate": 9.877302202346537e-05,
+      "loss": 0.6193,
+      "mean_token_accuracy": 0.7625367939472198,
+      "num_tokens": 1552867.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.1882716049382716,
+      "grad_norm": 0.7868801355361938,
+      "learning_rate": 9.871620623794107e-05,
+      "loss": 0.6119,
+      "mean_token_accuracy": 0.7656372606754303,
+      "num_tokens": 1573347.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.2037037037037037,
+      "grad_norm": 0.5902999043464661,
+      "learning_rate": 9.865812170538014e-05,
+      "loss": 0.6106,
+      "mean_token_accuracy": 0.7653431355953216,
+      "num_tokens": 1593827.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.2191358024691359,
+      "grad_norm": 0.5042413473129272,
+      "learning_rate": 9.859876993851489e-05,
+      "loss": 0.6258,
+      "mean_token_accuracy": 0.7603431344032288,
+      "num_tokens": 1614307.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 0.6255024671554565,
+      "learning_rate": 9.853815248308101e-05,
+      "loss": 0.6181,
+      "mean_token_accuracy": 0.7631550431251526,
+      "num_tokens": 1634681.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.5640517473220825,
+      "learning_rate": 9.847627091777729e-05,
+      "loss": 0.6138,
+      "mean_token_accuracy": 0.7638725519180298,
+      "num_tokens": 1655161.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2654320987654322,
+      "grad_norm": 0.5596677660942078,
+      "learning_rate": 9.841312685422459e-05,
+      "loss": 0.6173,
+      "mean_token_accuracy": 0.7628921627998352,
+      "num_tokens": 1675641.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.2808641975308643,
+      "grad_norm": 0.6959637403488159,
+      "learning_rate": 9.834872193692378e-05,
+      "loss": 0.631,
+      "mean_token_accuracy": 0.7579901933670044,
+      "num_tokens": 1696121.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.5890873670578003,
+      "learning_rate": 9.828305784321289e-05,
+      "loss": 0.6194,
+      "mean_token_accuracy": 0.7610294044017791,
+      "num_tokens": 1716601.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.3117283950617284,
+      "grad_norm": 0.5236982107162476,
+      "learning_rate": 9.821613628322358e-05,
+      "loss": 0.6353,
+      "mean_token_accuracy": 0.7555392146110534,
+      "num_tokens": 1737081.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.3271604938271606,
+      "grad_norm": 0.4920688271522522,
+      "learning_rate": 9.814795899983645e-05,
+      "loss": 0.6203,
+      "mean_token_accuracy": 0.7605464220046997,
+      "num_tokens": 1757399.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.3425925925925926,
+      "grad_norm": 0.5151636004447937,
+      "learning_rate": 9.807852776863568e-05,
+      "loss": 0.6316,
+      "mean_token_accuracy": 0.757401955127716,
+      "num_tokens": 1777879.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.3580246913580247,
+      "grad_norm": 0.5221789479255676,
+      "learning_rate": 9.800784439786286e-05,
+      "loss": 0.6021,
+      "mean_token_accuracy": 0.7678921699523926,
+      "num_tokens": 1798359.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.373456790123457,
+      "grad_norm": 0.6253092885017395,
+      "learning_rate": 9.793591072836978e-05,
+      "loss": 0.6189,
+      "mean_token_accuracy": 0.7627451002597809,
+      "num_tokens": 1818839.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 0.5362826585769653,
+      "learning_rate": 9.786272863357063e-05,
+      "loss": 0.6218,
+      "mean_token_accuracy": 0.7601960837841034,
+      "num_tokens": 1839319.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.404320987654321,
+      "grad_norm": 0.5733498930931091,
+      "learning_rate": 9.778830001939307e-05,
+      "loss": 0.6243,
+      "mean_token_accuracy": 0.7575980484485626,
+      "num_tokens": 1859799.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.4197530864197532,
+      "grad_norm": 0.5503411293029785,
+      "learning_rate": 9.771262682422866e-05,
+      "loss": 0.6043,
+      "mean_token_accuracy": 0.768676483631134,
+      "num_tokens": 1880279.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.4351851851851851,
+      "grad_norm": 0.5697808265686035,
+      "learning_rate": 9.76357110188824e-05,
+      "loss": 0.619,
+      "mean_token_accuracy": 0.7615686297416687,
+      "num_tokens": 1900759.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.4506172839506173,
+      "grad_norm": 0.5639927387237549,
+      "learning_rate": 9.755755460652137e-05,
+      "loss": 0.6287,
+      "mean_token_accuracy": 0.7581372559070587,
+      "num_tokens": 1921239.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.4660493827160495,
+      "grad_norm": 0.4238158166408539,
+      "learning_rate": 9.747815962262255e-05,
+      "loss": 0.6179,
+      "mean_token_accuracy": 0.7624019682407379,
+      "num_tokens": 1941719.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.5610195398330688,
+      "learning_rate": 9.73975281349198e-05,
+      "loss": 0.6198,
+      "mean_token_accuracy": 0.7611274600028992,
+      "num_tokens": 1962199.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4969135802469136,
+      "grad_norm": 0.5397023558616638,
+      "learning_rate": 9.73156622433501e-05,
+      "loss": 0.6262,
+      "mean_token_accuracy": 0.7573529422283173,
+      "num_tokens": 1982679.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.5123456790123457,
+      "grad_norm": 0.627068042755127,
+      "learning_rate": 9.72325640799987e-05,
+      "loss": 0.6341,
+      "mean_token_accuracy": 0.7564705967903137,
+      "num_tokens": 2003159.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.5277777777777777,
+      "grad_norm": 0.6139004826545715,
+      "learning_rate": 9.71482358090438e-05,
+      "loss": 0.628,
+      "mean_token_accuracy": 0.7554846823215484,
+      "num_tokens": 2023485.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.5432098765432098,
+      "grad_norm": 0.5941593647003174,
+      "learning_rate": 9.706267962669998e-05,
+      "loss": 0.636,
+      "mean_token_accuracy": 0.756617647409439,
+      "num_tokens": 2043965.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.558641975308642,
+      "grad_norm": 0.5428718328475952,
+      "learning_rate": 9.697589776116113e-05,
+      "loss": 0.6288,
+      "mean_token_accuracy": 0.7563235223293304,
+      "num_tokens": 2064445.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.574074074074074,
+      "grad_norm": 0.679093599319458,
+      "learning_rate": 9.688789247254237e-05,
+      "loss": 0.6137,
+      "mean_token_accuracy": 0.7616176426410675,
+      "num_tokens": 2084925.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5895061728395061,
+      "grad_norm": 0.5914977192878723,
+      "learning_rate": 9.679866605282122e-05,
+      "loss": 0.6101,
+      "mean_token_accuracy": 0.7660278260707856,
+      "num_tokens": 2105210.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6049382716049383,
+      "grad_norm": 0.6366807818412781,
+      "learning_rate": 9.670822082577787e-05,
+      "loss": 0.6221,
+      "mean_token_accuracy": 0.7630392193794251,
+      "num_tokens": 2125690.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6203703703703702,
+      "grad_norm": 0.537667453289032,
+      "learning_rate": 9.661655914693471e-05,
+      "loss": 0.6276,
+      "mean_token_accuracy": 0.7600000083446503,
+      "num_tokens": 2146170.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6358024691358026,
+      "grad_norm": 0.6829613447189331,
+      "learning_rate": 9.652368340349494e-05,
+      "loss": 0.6231,
+      "mean_token_accuracy": 0.7614292323589325,
+      "num_tokens": 2166400.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.6512345679012346,
+      "grad_norm": 0.46796467900276184,
+      "learning_rate": 9.642959601428039e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7614705860614777,
+      "num_tokens": 2186880.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.6203200221061707,
+      "learning_rate": 9.63342994296686e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7601960718631744,
+      "num_tokens": 2207360.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.682098765432099,
+      "grad_norm": 0.4808056652545929,
+      "learning_rate": 9.623779613152893e-05,
+      "loss": 0.6211,
+      "mean_token_accuracy": 0.7597549021244049,
+      "num_tokens": 2227840.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6975308641975309,
+      "grad_norm": 0.831586480140686,
+      "learning_rate": 9.614008863315789e-05,
+      "loss": 0.6031,
+      "mean_token_accuracy": 0.7655882358551025,
+      "num_tokens": 2248320.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7129629629629628,
+      "grad_norm": 0.5528991222381592,
+      "learning_rate": 9.604117947921385e-05,
+      "loss": 0.6255,
+      "mean_token_accuracy": 0.7599509835243226,
+      "num_tokens": 2268800.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7283950617283952,
+      "grad_norm": 0.518021821975708,
+      "learning_rate": 9.594107124565056e-05,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.7617159247398376,
+      "num_tokens": 2289107.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7438271604938271,
+      "grad_norm": 0.5663719177246094,
+      "learning_rate": 9.58397665396502e-05,
+      "loss": 0.6239,
+      "mean_token_accuracy": 0.7579901993274689,
+      "num_tokens": 2309587.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.7592592592592593,
+      "grad_norm": 0.6976074576377869,
+      "learning_rate": 9.573726799955544e-05,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.7644607961177826,
+      "num_tokens": 2330067.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7746913580246915,
+      "grad_norm": 0.491929829120636,
+      "learning_rate": 9.563357829480076e-05,
+      "loss": 0.6175,
+      "mean_token_accuracy": 0.7621568620204926,
+      "num_tokens": 2350547.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7901234567901234,
+      "grad_norm": 0.5365603566169739,
+      "learning_rate": 9.552870012584282e-05,
+      "loss": 0.6207,
+      "mean_token_accuracy": 0.7618627429008484,
+      "num_tokens": 2371027.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8055555555555556,
+      "grad_norm": 0.4748326241970062,
+      "learning_rate": 9.542263622409027e-05,
+      "loss": 0.6304,
+      "mean_token_accuracy": 0.7585784316062927,
+      "num_tokens": 2391507.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.8209876543209877,
+      "grad_norm": 0.6071013808250427,
+      "learning_rate": 9.53153893518325e-05,
+      "loss": 0.6242,
+      "mean_token_accuracy": 0.7582843065261841,
+      "num_tokens": 2411987.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.8364197530864197,
+      "grad_norm": 0.5693532228469849,
+      "learning_rate": 9.520696230216781e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7624019622802735,
+      "num_tokens": 2432467.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 0.5890586376190186,
+      "learning_rate": 9.509735789893059e-05,
+      "loss": 0.6261,
+      "mean_token_accuracy": 0.7603431344032288,
+      "num_tokens": 2452947.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.867283950617284,
+      "grad_norm": 0.5754212737083435,
+      "learning_rate": 9.498657899661774e-05,
+      "loss": 0.6201,
+      "mean_token_accuracy": 0.7618137300014496,
+      "num_tokens": 2473427.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.882716049382716,
+      "grad_norm": 0.48493534326553345,
+      "learning_rate": 9.487462848031445e-05,
+      "loss": 0.6411,
+      "mean_token_accuracy": 0.754411768913269,
+      "num_tokens": 2493907.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8981481481481481,
+      "grad_norm": 0.6793274283409119,
+      "learning_rate": 9.4761509265619e-05,
+      "loss": 0.6094,
+      "mean_token_accuracy": 0.7683333337306977,
+      "num_tokens": 2514387.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.9135802469135803,
+      "grad_norm": 0.43587443232536316,
+      "learning_rate": 9.464722429856674e-05,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.763382351398468,
+      "num_tokens": 2534867.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.9290123456790123,
+      "grad_norm": 0.5037091970443726,
+      "learning_rate": 9.453177655555355e-05,
+      "loss": 0.6215,
+      "mean_token_accuracy": 0.7608333349227905,
+      "num_tokens": 2555347.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 0.48443400859832764,
+      "learning_rate": 9.441516904325816e-05,
+      "loss": 0.6326,
+      "mean_token_accuracy": 0.7566666662693023,
+      "num_tokens": 2575827.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.9598765432098766,
+      "grad_norm": 0.5313301086425781,
+      "learning_rate": 9.42974047985639e-05,
+      "loss": 0.6059,
+      "mean_token_accuracy": 0.7671078443527222,
+      "num_tokens": 2596307.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 0.4752209186553955,
+      "learning_rate": 9.417848688847968e-05,
+      "loss": 0.6221,
+      "mean_token_accuracy": 0.7612836718559265,
+      "num_tokens": 2616738.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.9907407407407407,
+      "grad_norm": 0.6168082356452942,
+      "learning_rate": 9.405841841005998e-05,
+      "loss": 0.6199,
+      "mean_token_accuracy": 0.7622058808803558,
+      "num_tokens": 2637218.0,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.628555953502655,
+      "eval_mean_token_accuracy": 0.7592301794460842,
+      "eval_num_tokens": 2647970.0,
+      "eval_runtime": 3.2461,
+      "eval_samples_per_second": 84.102,
+      "eval_steps_per_second": 10.782,
+      "step": 1296
+    },
+    {
+      "epoch": 2.006172839506173,
+      "grad_norm": 0.5350890755653381,
+      "learning_rate": 9.393720249032428e-05,
+      "loss": 0.5952,
+      "mean_token_accuracy": 0.7718137264251709,
+      "num_tokens": 2656162.0,
+      "step": 1300
+    },
+    {
+      "epoch": 2.021604938271605,
+      "grad_norm": 0.7325437664985657,
+      "learning_rate": 9.381484228617561e-05,
+      "loss": 0.6002,
+      "mean_token_accuracy": 0.7719117701053619,
+      "num_tokens": 2676642.0,
+      "step": 1310
+    },
+    {
+      "epoch": 2.037037037037037,
+      "grad_norm": 0.5555301308631897,
+      "learning_rate": 9.369134098431836e-05,
+      "loss": 0.5987,
+      "mean_token_accuracy": 0.7709803938865661,
+      "num_tokens": 2697122.0,
+      "step": 1320
+    },
+    {
+      "epoch": 2.052469135802469,
+      "grad_norm": 0.6631981134414673,
+      "learning_rate": 9.356670180117515e-05,
+      "loss": 0.5884,
+      "mean_token_accuracy": 0.7728506803512574,
+      "num_tokens": 2717448.0,
+      "step": 1330
+    },
+    {
+      "epoch": 2.067901234567901,
+      "grad_norm": 0.533174455165863,
+      "learning_rate": 9.344092798280326e-05,
+      "loss": 0.5974,
+      "mean_token_accuracy": 0.77112957239151,
+      "num_tokens": 2737755.0,
+      "step": 1340
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.8145793676376343,
+      "learning_rate": 9.331402280480996e-05,
+      "loss": 0.5724,
+      "mean_token_accuracy": 0.7805882334709168,
+      "num_tokens": 2758235.0,
+      "step": 1350
+    },
+    {
+      "epoch": 2.0987654320987654,
+      "grad_norm": 0.5709875226020813,
+      "learning_rate": 9.318598957226722e-05,
+      "loss": 0.593,
+      "mean_token_accuracy": 0.7734803974628448,
+      "num_tokens": 2778715.0,
+      "step": 1360
+    },
+    {
+      "epoch": 2.1141975308641974,
+      "grad_norm": 0.7765586972236633,
+      "learning_rate": 9.305683161962569e-05,
+      "loss": 0.5943,
+      "mean_token_accuracy": 0.773333340883255,
+      "num_tokens": 2799195.0,
+      "step": 1370
+    },
+    {
+      "epoch": 2.1296296296296298,
+      "grad_norm": 0.9367417097091675,
+      "learning_rate": 9.292655231062777e-05,
+      "loss": 0.5902,
+      "mean_token_accuracy": 0.770686274766922,
+      "num_tokens": 2819675.0,
+      "step": 1380
+    },
+    {
+      "epoch": 2.1450617283950617,
+      "grad_norm": 0.5698003172874451,
+      "learning_rate": 9.279515503822012e-05,
+      "loss": 0.5999,
+      "mean_token_accuracy": 0.7680392146110535,
+      "num_tokens": 2840155.0,
+      "step": 1390
+    },
+    {
+      "epoch": 2.1604938271604937,
+      "grad_norm": 0.5707505345344543,
+      "learning_rate": 9.266264322446513e-05,
+      "loss": 0.5818,
+      "mean_token_accuracy": 0.7765196144580842,
+      "num_tokens": 2860635.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.175925925925926,
+      "grad_norm": 0.626613974571228,
+      "learning_rate": 9.2529020320452e-05,
+      "loss": 0.581,
+      "mean_token_accuracy": 0.775245088338852,
+      "num_tokens": 2881115.0,
+      "step": 1410
+    },
+    {
+      "epoch": 2.191358024691358,
+      "grad_norm": 0.7097243070602417,
+      "learning_rate": 9.239428980620668e-05,
+      "loss": 0.6057,
+      "mean_token_accuracy": 0.7675980448722839,
+      "num_tokens": 2901595.0,
+      "step": 1420
+    },
+    {
+      "epoch": 2.20679012345679,
+      "grad_norm": 0.6461248993873596,
+      "learning_rate": 9.22584551906014e-05,
+      "loss": 0.6072,
+      "mean_token_accuracy": 0.7674509882926941,
+      "num_tokens": 2922075.0,
+      "step": 1430
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.7755699157714844,
+      "learning_rate": 9.212152001126309e-05,
+      "loss": 0.5992,
+      "mean_token_accuracy": 0.7677941083908081,
+      "num_tokens": 2942555.0,
+      "step": 1440
+    },
+    {
+      "epoch": 2.2376543209876543,
+      "grad_norm": 0.5984106659889221,
+      "learning_rate": 9.198348783448143e-05,
+      "loss": 0.5733,
+      "mean_token_accuracy": 0.7785784363746643,
+      "num_tokens": 2963035.0,
+      "step": 1450
+    },
+    {
+      "epoch": 2.253086419753086,
+      "grad_norm": 0.683435320854187,
+      "learning_rate": 9.184436225511593e-05,
+      "loss": 0.5867,
+      "mean_token_accuracy": 0.772892153263092,
+      "num_tokens": 2983515.0,
+      "step": 1460
+    },
+    {
+      "epoch": 2.2685185185185186,
+      "grad_norm": 0.6326505541801453,
+      "learning_rate": 9.170414689650218e-05,
+      "loss": 0.5955,
+      "mean_token_accuracy": 0.7710784256458283,
+      "num_tokens": 3003995.0,
+      "step": 1470
+    },
+    {
+      "epoch": 2.2839506172839505,
+      "grad_norm": 0.5087013840675354,
+      "learning_rate": 9.156284541035767e-05,
+      "loss": 0.5941,
+      "mean_token_accuracy": 0.770262885093689,
+      "num_tokens": 3024243.0,
+      "step": 1480
+    },
+    {
+      "epoch": 2.299382716049383,
+      "grad_norm": 0.5956624746322632,
+      "learning_rate": 9.142046147668656e-05,
+      "loss": 0.5961,
+      "mean_token_accuracy": 0.7705882370471955,
+      "num_tokens": 3044723.0,
+      "step": 1490
+    },
+    {
+      "epoch": 2.314814814814815,
+      "grad_norm": 0.5642819404602051,
+      "learning_rate": 9.127699880368388e-05,
+      "loss": 0.579,
+      "mean_token_accuracy": 0.7750980377197265,
+      "num_tokens": 3065203.0,
+      "step": 1500
+    },
+    {
+      "epoch": 2.330246913580247,
+      "grad_norm": 0.7624996900558472,
+      "learning_rate": 9.113246112763896e-05,
+      "loss": 0.5968,
+      "mean_token_accuracy": 0.7697415828704834,
+      "num_tokens": 3085634.0,
+      "step": 1510
+    },
+    {
+      "epoch": 2.3456790123456788,
+      "grad_norm": 0.6217107176780701,
+      "learning_rate": 9.098685221283809e-05,
+      "loss": 0.5945,
+      "mean_token_accuracy": 0.77044118642807,
+      "num_tokens": 3106114.0,
+      "step": 1520
+    },
+    {
+      "epoch": 2.361111111111111,
+      "grad_norm": 0.6848967671394348,
+      "learning_rate": 9.084017585146653e-05,
+      "loss": 0.6086,
+      "mean_token_accuracy": 0.7675980448722839,
+      "num_tokens": 3126594.0,
+      "step": 1530
+    },
+    {
+      "epoch": 2.376543209876543,
+      "grad_norm": 0.7084946632385254,
+      "learning_rate": 9.069243586350975e-05,
+      "loss": 0.5948,
+      "mean_token_accuracy": 0.7736274540424347,
+      "num_tokens": 3147074.0,
+      "step": 1540
+    },
+    {
+      "epoch": 2.3919753086419755,
+      "grad_norm": 0.6253333687782288,
+      "learning_rate": 9.054363609665388e-05,
+      "loss": 0.5987,
+      "mean_token_accuracy": 0.7670588254928589,
+      "num_tokens": 3167554.0,
+      "step": 1550
+    },
+    {
+      "epoch": 2.4074074074074074,
+      "grad_norm": 0.7215299010276794,
+      "learning_rate": 9.039378042618556e-05,
+      "loss": 0.6118,
+      "mean_token_accuracy": 0.7658778011798859,
+      "num_tokens": 3187872.0,
+      "step": 1560
+    },
+    {
+      "epoch": 2.4228395061728394,
+      "grad_norm": 0.5760617852210999,
+      "learning_rate": 9.0242872754891e-05,
+      "loss": 0.5893,
+      "mean_token_accuracy": 0.7756372570991517,
+      "num_tokens": 3208352.0,
+      "step": 1570
+    },
+    {
+      "epoch": 2.4382716049382718,
+      "grad_norm": 0.6861734390258789,
+      "learning_rate": 9.009091701295434e-05,
+      "loss": 0.5842,
+      "mean_token_accuracy": 0.7753921568393707,
+      "num_tokens": 3228832.0,
+      "step": 1580
+    },
+    {
+      "epoch": 2.4537037037037037,
+      "grad_norm": 0.6804457902908325,
+      "learning_rate": 8.993791715785528e-05,
+      "loss": 0.5917,
+      "mean_token_accuracy": 0.772210317850113,
+      "num_tokens": 3249205.0,
+      "step": 1590
+    },
+    {
+      "epoch": 2.4691358024691357,
+      "grad_norm": 0.6913892030715942,
+      "learning_rate": 8.978387717426601e-05,
+      "loss": 0.5909,
+      "mean_token_accuracy": 0.7718627512454986,
+      "num_tokens": 3269685.0,
+      "step": 1600
+    },
+    {
+      "epoch": 2.484567901234568,
+      "grad_norm": 0.7079524993896484,
+      "learning_rate": 8.962880107394747e-05,
+      "loss": 0.5927,
+      "mean_token_accuracy": 0.7718627452850342,
+      "num_tokens": 3290165.0,
+      "step": 1610
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.6033655405044556,
+      "learning_rate": 8.947269289564482e-05,
+      "loss": 0.5912,
+      "mean_token_accuracy": 0.7717647075653076,
+      "num_tokens": 3310645.0,
+      "step": 1620
+    },
+    {
+      "epoch": 2.515432098765432,
+      "grad_norm": 0.7890419363975525,
+      "learning_rate": 8.931555670498229e-05,
+      "loss": 0.5895,
+      "mean_token_accuracy": 0.7722058832645416,
+      "num_tokens": 3331125.0,
+      "step": 1630
+    },
+    {
+      "epoch": 2.5308641975308643,
+      "grad_norm": 0.5943073630332947,
+      "learning_rate": 8.915739659435732e-05,
+      "loss": 0.5882,
+      "mean_token_accuracy": 0.7717156887054444,
+      "num_tokens": 3351605.0,
+      "step": 1640
+    },
+    {
+      "epoch": 2.5462962962962963,
+      "grad_norm": 0.6067966222763062,
+      "learning_rate": 8.899821668283388e-05,
+      "loss": 0.5817,
+      "mean_token_accuracy": 0.7767156839370728,
+      "num_tokens": 3372085.0,
+      "step": 1650
+    },
+    {
+      "epoch": 2.5617283950617287,
+      "grad_norm": 0.6475111246109009,
+      "learning_rate": 8.883802111603532e-05,
+      "loss": 0.6051,
+      "mean_token_accuracy": 0.7653431475162507,
+      "num_tokens": 3392565.0,
+      "step": 1660
+    },
+    {
+      "epoch": 2.5771604938271606,
+      "grad_norm": 0.6153448224067688,
+      "learning_rate": 8.867681406603632e-05,
+      "loss": 0.6031,
+      "mean_token_accuracy": 0.7666176497936249,
+      "num_tokens": 3413045.0,
+      "step": 1670
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.658183217048645,
+      "learning_rate": 8.851459973125424e-05,
+      "loss": 0.5952,
+      "mean_token_accuracy": 0.7705015063285827,
+      "num_tokens": 3433370.0,
+      "step": 1680
+    },
+    {
+      "epoch": 2.6080246913580245,
+      "grad_norm": 0.6191939115524292,
+      "learning_rate": 8.835138233633986e-05,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.7691666722297669,
+      "num_tokens": 3453850.0,
+      "step": 1690
+    },
+    {
+      "epoch": 2.623456790123457,
+      "grad_norm": 0.5918915271759033,
+      "learning_rate": 8.818716613206718e-05,
+      "loss": 0.6046,
+      "mean_token_accuracy": 0.7666176497936249,
+      "num_tokens": 3474330.0,
+      "step": 1700
+    },
+    {
+      "epoch": 2.638888888888889,
+      "grad_norm": 0.5293189287185669,
+      "learning_rate": 8.802195539522298e-05,
+      "loss": 0.577,
+      "mean_token_accuracy": 0.7772549033164978,
+      "num_tokens": 3494810.0,
+      "step": 1710
+    },
+    {
+      "epoch": 2.6543209876543212,
+      "grad_norm": 0.7564029097557068,
+      "learning_rate": 8.785575442849512e-05,
+      "loss": 0.5993,
+      "mean_token_accuracy": 0.7706372559070587,
+      "num_tokens": 3515290.0,
+      "step": 1720
+    },
+    {
+      "epoch": 2.669753086419753,
+      "grad_norm": 0.6666939854621887,
+      "learning_rate": 8.768856756036075e-05,
+      "loss": 0.6004,
+      "mean_token_accuracy": 0.7707352936267853,
+      "num_tokens": 3535770.0,
+      "step": 1730
+    },
+    {
+      "epoch": 2.685185185185185,
+      "grad_norm": 0.7649972438812256,
+      "learning_rate": 8.752039914497344e-05,
+      "loss": 0.5803,
+      "mean_token_accuracy": 0.7755699038505555,
+      "num_tokens": 3556055.0,
+      "step": 1740
+    },
+    {
+      "epoch": 2.700617283950617,
+      "grad_norm": 0.6303521394729614,
+      "learning_rate": 8.73512535620498e-05,
+      "loss": 0.5823,
+      "mean_token_accuracy": 0.7731906652450562,
+      "num_tokens": 3576285.0,
+      "step": 1750
+    },
+    {
+      "epoch": 2.7160493827160495,
+      "grad_norm": 0.6482508778572083,
+      "learning_rate": 8.718113521675551e-05,
+      "loss": 0.5833,
+      "mean_token_accuracy": 0.7746078491210937,
+      "num_tokens": 3596765.0,
+      "step": 1760
+    },
+    {
+      "epoch": 2.7314814814814814,
+      "grad_norm": 0.6496692299842834,
+      "learning_rate": 8.70100485395904e-05,
+      "loss": 0.5796,
+      "mean_token_accuracy": 0.77576185464859,
+      "num_tokens": 3617139.0,
+      "step": 1770
+    },
+    {
+      "epoch": 2.746913580246914,
+      "grad_norm": 0.7126871943473816,
+      "learning_rate": 8.683799798627327e-05,
+      "loss": 0.5932,
+      "mean_token_accuracy": 0.7718137383460999,
+      "num_tokens": 3637619.0,
+      "step": 1780
+    },
+    {
+      "epoch": 2.7623456790123457,
+      "grad_norm": 0.536176860332489,
+      "learning_rate": 8.666498803762575e-05,
+      "loss": 0.6127,
+      "mean_token_accuracy": 0.7644607901573182,
+      "num_tokens": 3658099.0,
+      "step": 1790
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.5753297209739685,
+      "learning_rate": 8.649102319945556e-05,
+      "loss": 0.6003,
+      "mean_token_accuracy": 0.7688235282897949,
+      "num_tokens": 3678579.0,
+      "step": 1800
+    },
+    {
+      "epoch": 2.7932098765432096,
+      "grad_norm": 0.7861889004707336,
+      "learning_rate": 8.631610800243926e-05,
+      "loss": 0.5948,
+      "mean_token_accuracy": 0.7707352876663208,
+      "num_tokens": 3699059.0,
+      "step": 1810
+    },
+    {
+      "epoch": 2.808641975308642,
+      "grad_norm": 0.7440711855888367,
+      "learning_rate": 8.614024700200418e-05,
+      "loss": 0.5974,
+      "mean_token_accuracy": 0.7701960802078247,
+      "num_tokens": 3719539.0,
+      "step": 1820
+    },
+    {
+      "epoch": 2.824074074074074,
+      "grad_norm": 0.7377384305000305,
+      "learning_rate": 8.596344477820982e-05,
+      "loss": 0.6059,
+      "mean_token_accuracy": 0.7668627500534058,
+      "num_tokens": 3740019.0,
+      "step": 1830
+    },
+    {
+      "epoch": 2.8395061728395063,
+      "grad_norm": 0.6190456748008728,
+      "learning_rate": 8.578570593562856e-05,
+      "loss": 0.5955,
+      "mean_token_accuracy": 0.7732352972030639,
+      "num_tokens": 3760499.0,
+      "step": 1840
+    },
+    {
+      "epoch": 2.8549382716049383,
+      "grad_norm": 0.695401668548584,
+      "learning_rate": 8.560703510322574e-05,
+      "loss": 0.5834,
+      "mean_token_accuracy": 0.7763725578784942,
+      "num_tokens": 3780979.0,
+      "step": 1850
+    },
+    {
+      "epoch": 2.8703703703703702,
+      "grad_norm": 0.6935811638832092,
+      "learning_rate": 8.54274369342391e-05,
+      "loss": 0.6105,
+      "mean_token_accuracy": 0.7648529410362244,
+      "num_tokens": 3801459.0,
+      "step": 1860
+    },
+    {
+      "epoch": 2.8858024691358026,
+      "grad_norm": 0.8666762113571167,
+      "learning_rate": 8.524691610605755e-05,
+      "loss": 0.5848,
+      "mean_token_accuracy": 0.775196087360382,
+      "num_tokens": 3821939.0,
+      "step": 1870
+    },
+    {
+      "epoch": 2.9012345679012346,
+      "grad_norm": 0.8038449287414551,
+      "learning_rate": 8.506547732009949e-05,
+      "loss": 0.6048,
+      "mean_token_accuracy": 0.7674509882926941,
+      "num_tokens": 3842419.0,
+      "step": 1880
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 0.6401634812355042,
+      "learning_rate": 8.488312530169019e-05,
+      "loss": 0.5946,
+      "mean_token_accuracy": 0.7687254846096039,
+      "num_tokens": 3862899.0,
+      "step": 1890
+    },
+    {
+      "epoch": 2.932098765432099,
+      "grad_norm": 0.6001216769218445,
+      "learning_rate": 8.469986479993885e-05,
+      "loss": 0.5909,
+      "mean_token_accuracy": 0.7719607830047608,
+      "num_tokens": 3883379.0,
+      "step": 1900
+    },
+    {
+      "epoch": 2.947530864197531,
+      "grad_norm": 0.6955755352973938,
+      "learning_rate": 8.451570058761487e-05,
+      "loss": 0.6008,
+      "mean_token_accuracy": 0.7700000047683716,
+      "num_tokens": 3903859.0,
+      "step": 1910
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.5965796113014221,
+      "learning_rate": 8.433063746102357e-05,
+      "loss": 0.5778,
+      "mean_token_accuracy": 0.7758823573589325,
+      "num_tokens": 3924339.0,
+      "step": 1920
+    },
+    {
+      "epoch": 2.978395061728395,
+      "grad_norm": 0.6863985061645508,
+      "learning_rate": 8.414468023988124e-05,
+      "loss": 0.5811,
+      "mean_token_accuracy": 0.775784307718277,
+      "num_tokens": 3944819.0,
+      "step": 1930
+    },
+    {
+      "epoch": 2.993827160493827,
+      "grad_norm": 0.6362125277519226,
+      "learning_rate": 8.395783376718966e-05,
+      "loss": 0.6043,
+      "mean_token_accuracy": 0.7676960825920105,
+      "num_tokens": 3965299.0,
+      "step": 1940
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6355003714561462,
+      "eval_mean_token_accuracy": 0.7551294309752328,
+      "eval_num_tokens": 3971955.0,
+      "eval_runtime": 3.251,
+      "eval_samples_per_second": 83.974,
+      "eval_steps_per_second": 10.766,
+      "step": 1944
+    },
+    {
+      "epoch": 3.009259259259259,
+      "grad_norm": 0.6707216501235962,
+      "learning_rate": 8.377010290910996e-05,
+      "loss": 0.5821,
+      "mean_token_accuracy": 0.7771568655967712,
+      "num_tokens": 3984243.0,
+      "step": 1950
+    },
+    {
+      "epoch": 3.0246913580246915,
+      "grad_norm": 0.8642926216125488,
+      "learning_rate": 8.358149255483585e-05,
+      "loss": 0.5521,
+      "mean_token_accuracy": 0.7871078372001648,
+      "num_tokens": 4004723.0,
+      "step": 1960
+    },
+    {
+      "epoch": 3.0401234567901234,
+      "grad_norm": 0.7402784824371338,
+      "learning_rate": 8.339200761646633e-05,
+      "loss": 0.5604,
+      "mean_token_accuracy": 0.785833328962326,
+      "num_tokens": 4025203.0,
+      "step": 1970
+    },
+    {
+      "epoch": 3.0555555555555554,
+      "grad_norm": 0.8474542498588562,
+      "learning_rate": 8.320165302887776e-05,
+      "loss": 0.5599,
+      "mean_token_accuracy": 0.784509801864624,
+      "num_tokens": 4045683.0,
+      "step": 1980
+    },
+    {
+      "epoch": 3.0709876543209877,
+      "grad_norm": 0.7444702386856079,
+      "learning_rate": 8.301043374959532e-05,
+      "loss": 0.5652,
+      "mean_token_accuracy": 0.7846568703651429,
+      "num_tokens": 4066163.0,
+      "step": 1990
+    },
+    {
+      "epoch": 3.0864197530864197,
+      "grad_norm": 0.8023507595062256,
+      "learning_rate": 8.281835475866388e-05,
+      "loss": 0.5708,
+      "mean_token_accuracy": 0.7822058737277985,
+      "num_tokens": 4086643.0,
+      "step": 2000
+    },
+    {
+      "epoch": 3.1018518518518516,
+      "grad_norm": 0.8974912762641907,
+      "learning_rate": 8.262542105851836e-05,
+      "loss": 0.5504,
+      "mean_token_accuracy": 0.7892429053783416,
+      "num_tokens": 4107017.0,
+      "step": 2010
+    },
+    {
+      "epoch": 3.117283950617284,
+      "grad_norm": 0.6585649847984314,
+      "learning_rate": 8.24316376738534e-05,
+      "loss": 0.5461,
+      "mean_token_accuracy": 0.788438218832016,
+      "num_tokens": 4127324.0,
+      "step": 2020
+    },
+    {
+      "epoch": 3.132716049382716,
+      "grad_norm": 0.9363825917243958,
+      "learning_rate": 8.22370096514925e-05,
+      "loss": 0.5565,
+      "mean_token_accuracy": 0.7876960754394531,
+      "num_tokens": 4147804.0,
+      "step": 2030
+    },
+    {
+      "epoch": 3.148148148148148,
+      "grad_norm": 0.8939400315284729,
+      "learning_rate": 8.204154206025664e-05,
+      "loss": 0.554,
+      "mean_token_accuracy": 0.7890196144580841,
+      "num_tokens": 4168284.0,
+      "step": 2040
+    },
+    {
+      "epoch": 3.1635802469135803,
+      "grad_norm": 0.8523621559143066,
+      "learning_rate": 8.184523999083215e-05,
+      "loss": 0.5708,
+      "mean_token_accuracy": 0.7841176569461823,
+      "num_tokens": 4188764.0,
+      "step": 2050
+    },
+    {
+      "epoch": 3.1790123456790123,
+      "grad_norm": 0.8111633062362671,
+      "learning_rate": 8.164810855563826e-05,
+      "loss": 0.5626,
+      "mean_token_accuracy": 0.7853431344032288,
+      "num_tokens": 4209244.0,
+      "step": 2060
+    },
+    {
+      "epoch": 3.1944444444444446,
+      "grad_norm": 0.7543109059333801,
+      "learning_rate": 8.14501528886939e-05,
+      "loss": 0.5627,
+      "mean_token_accuracy": 0.7822548985481262,
+      "num_tokens": 4229724.0,
+      "step": 2070
+    },
+    {
+      "epoch": 3.2098765432098766,
+      "grad_norm": 0.7999160885810852,
+      "learning_rate": 8.125137814548393e-05,
+      "loss": 0.5527,
+      "mean_token_accuracy": 0.7858823597431183,
+      "num_tokens": 4250204.0,
+      "step": 2080
+    },
+    {
+      "epoch": 3.2253086419753085,
+      "grad_norm": 0.7675942182540894,
+      "learning_rate": 8.105178950282502e-05,
+      "loss": 0.5482,
+      "mean_token_accuracy": 0.7899999976158142,
+      "num_tokens": 4270684.0,
+      "step": 2090
+    },
+    {
+      "epoch": 3.240740740740741,
+      "grad_norm": 0.8280269503593445,
+      "learning_rate": 8.085139215873068e-05,
+      "loss": 0.5581,
+      "mean_token_accuracy": 0.7855882346630096,
+      "num_tokens": 4291164.0,
+      "step": 2100
+    },
+    {
+      "epoch": 3.256172839506173,
+      "grad_norm": 0.6814813017845154,
+      "learning_rate": 8.065019133227595e-05,
+      "loss": 0.5595,
+      "mean_token_accuracy": 0.7858823537826538,
+      "num_tokens": 4311644.0,
+      "step": 2110
+    },
+    {
+      "epoch": 3.271604938271605,
+      "grad_norm": 0.8521413803100586,
+      "learning_rate": 8.04481922634615e-05,
+      "loss": 0.5518,
+      "mean_token_accuracy": 0.7869607865810394,
+      "num_tokens": 4332124.0,
+      "step": 2120
+    },
+    {
+      "epoch": 3.287037037037037,
+      "grad_norm": 0.8616065979003906,
+      "learning_rate": 8.024540021307708e-05,
+      "loss": 0.5729,
+      "mean_token_accuracy": 0.7777941286563873,
+      "num_tokens": 4352604.0,
+      "step": 2130
+    },
+    {
+      "epoch": 3.302469135802469,
+      "grad_norm": 0.7048208117485046,
+      "learning_rate": 8.004182046256463e-05,
+      "loss": 0.5618,
+      "mean_token_accuracy": 0.7817647099494934,
+      "num_tokens": 4373084.0,
+      "step": 2140
+    },
+    {
+      "epoch": 3.317901234567901,
+      "grad_norm": 0.6856017112731934,
+      "learning_rate": 7.983745831388061e-05,
+      "loss": 0.5703,
+      "mean_token_accuracy": 0.7832843244075776,
+      "num_tokens": 4393564.0,
+      "step": 2150
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.7711135745048523,
+      "learning_rate": 7.963231908935798e-05,
+      "loss": 0.576,
+      "mean_token_accuracy": 0.7818971931934356,
+      "num_tokens": 4413882.0,
+      "step": 2160
+    },
+    {
+      "epoch": 3.3487654320987654,
+      "grad_norm": 0.6115387082099915,
+      "learning_rate": 7.942640813156759e-05,
+      "loss": 0.5726,
+      "mean_token_accuracy": 0.780196076631546,
+      "num_tokens": 4434362.0,
+      "step": 2170
+    },
+    {
+      "epoch": 3.3641975308641974,
+      "grad_norm": 0.9882307052612305,
+      "learning_rate": 7.921973080317904e-05,
+      "loss": 0.5749,
+      "mean_token_accuracy": 0.7788235306739807,
+      "num_tokens": 4454842.0,
+      "step": 2180
+    },
+    {
+      "epoch": 3.3796296296296298,
+      "grad_norm": 0.780830979347229,
+      "learning_rate": 7.901229248682096e-05,
+      "loss": 0.563,
+      "mean_token_accuracy": 0.7848529279232025,
+      "num_tokens": 4475322.0,
+      "step": 2190
+    },
+    {
+      "epoch": 3.3950617283950617,
+      "grad_norm": 0.9862571954727173,
+      "learning_rate": 7.880409858494094e-05,
+      "loss": 0.5562,
+      "mean_token_accuracy": 0.7844607889652252,
+      "num_tokens": 4495802.0,
+      "step": 2200
+    },
+    {
+      "epoch": 3.4104938271604937,
+      "grad_norm": 0.7421197295188904,
+      "learning_rate": 7.85951545196647e-05,
+      "loss": 0.5333,
+      "mean_token_accuracy": 0.792254900932312,
+      "num_tokens": 4516282.0,
+      "step": 2210
+    },
+    {
+      "epoch": 3.425925925925926,
+      "grad_norm": 0.8560985326766968,
+      "learning_rate": 7.838546573265497e-05,
+      "loss": 0.5672,
+      "mean_token_accuracy": 0.7826960921287537,
+      "num_tokens": 4536762.0,
+      "step": 2220
+    },
+    {
+      "epoch": 3.441358024691358,
+      "grad_norm": 0.7836995720863342,
+      "learning_rate": 7.817503768496974e-05,
+      "loss": 0.5526,
+      "mean_token_accuracy": 0.784509801864624,
+      "num_tokens": 4557242.0,
+      "step": 2230
+    },
+    {
+      "epoch": 3.45679012345679,
+      "grad_norm": 0.6674602031707764,
+      "learning_rate": 7.796387585692004e-05,
+      "loss": 0.5437,
+      "mean_token_accuracy": 0.7897058963775635,
+      "num_tokens": 4577722.0,
+      "step": 2240
+    },
+    {
+      "epoch": 3.4722222222222223,
+      "grad_norm": 0.786738395690918,
+      "learning_rate": 7.775198574792718e-05,
+      "loss": 0.5557,
+      "mean_token_accuracy": 0.7871078550815582,
+      "num_tokens": 4598202.0,
+      "step": 2250
+    },
+    {
+      "epoch": 3.4876543209876543,
+      "grad_norm": 0.7223646640777588,
+      "learning_rate": 7.753937287637958e-05,
+      "loss": 0.5643,
+      "mean_token_accuracy": 0.7831155002117157,
+      "num_tokens": 4618228.0,
+      "step": 2260
+    },
+    {
+      "epoch": 3.503086419753086,
+      "grad_norm": 0.8668886423110962,
+      "learning_rate": 7.7326042779489e-05,
+      "loss": 0.5488,
+      "mean_token_accuracy": 0.7876960813999176,
+      "num_tokens": 4638708.0,
+      "step": 2270
+    },
+    {
+      "epoch": 3.5185185185185186,
+      "grad_norm": 0.751223623752594,
+      "learning_rate": 7.71120010131464e-05,
+      "loss": 0.5636,
+      "mean_token_accuracy": 0.7811764717102051,
+      "num_tokens": 4659188.0,
+      "step": 2280
+    },
+    {
+      "epoch": 3.5339506172839505,
+      "grad_norm": 0.913032054901123,
+      "learning_rate": 7.689725315177712e-05,
+      "loss": 0.5664,
+      "mean_token_accuracy": 0.7809313714504242,
+      "num_tokens": 4679668.0,
+      "step": 2290
+    },
+    {
+      "epoch": 3.549382716049383,
+      "grad_norm": 0.8360229730606079,
+      "learning_rate": 7.668180478819586e-05,
+      "loss": 0.5694,
+      "mean_token_accuracy": 0.782745099067688,
+      "num_tokens": 4700148.0,
+      "step": 2300
+    },
+    {
+      "epoch": 3.564814814814815,
+      "grad_norm": 0.77789306640625,
+      "learning_rate": 7.64656615334609e-05,
+      "loss": 0.5516,
+      "mean_token_accuracy": 0.7864705920219421,
+      "num_tokens": 4720628.0,
+      "step": 2310
+    },
+    {
+      "epoch": 3.580246913580247,
+      "grad_norm": 0.7813334465026855,
+      "learning_rate": 7.6248829016728e-05,
+      "loss": 0.554,
+      "mean_token_accuracy": 0.7865686297416687,
+      "num_tokens": 4741108.0,
+      "step": 2320
+    },
+    {
+      "epoch": 3.5956790123456788,
+      "grad_norm": 0.7807298302650452,
+      "learning_rate": 7.603131288510388e-05,
+      "loss": 0.5644,
+      "mean_token_accuracy": 0.782549011707306,
+      "num_tokens": 4761588.0,
+      "step": 2330
+    },
+    {
+      "epoch": 3.611111111111111,
+      "grad_norm": 0.9615110158920288,
+      "learning_rate": 7.581311880349897e-05,
+      "loss": 0.5452,
+      "mean_token_accuracy": 0.7875980317592621,
+      "num_tokens": 4782068.0,
+      "step": 2340
+    },
+    {
+      "epoch": 3.626543209876543,
+      "grad_norm": 1.0025591850280762,
+      "learning_rate": 7.559425245448006e-05,
+      "loss": 0.5614,
+      "mean_token_accuracy": 0.7830882370471954,
+      "num_tokens": 4802548.0,
+      "step": 2350
+    },
+    {
+      "epoch": 3.6419753086419755,
+      "grad_norm": 0.6889590620994568,
+      "learning_rate": 7.537471953812219e-05,
+      "loss": 0.5562,
+      "mean_token_accuracy": 0.7857843160629272,
+      "num_tokens": 4823028.0,
+      "step": 2360
+    },
+    {
+      "epoch": 3.6574074074074074,
+      "grad_norm": 0.8535559177398682,
+      "learning_rate": 7.515452577186025e-05,
+      "loss": 0.558,
+      "mean_token_accuracy": 0.7855882346630096,
+      "num_tokens": 4843508.0,
+      "step": 2370
+    },
+    {
+      "epoch": 3.6728395061728394,
+      "grad_norm": 1.0625262260437012,
+      "learning_rate": 7.493367689034005e-05,
+      "loss": 0.5539,
+      "mean_token_accuracy": 0.7852450966835022,
+      "num_tokens": 4863988.0,
+      "step": 2380
+    },
+    {
+      "epoch": 3.6882716049382713,
+      "grad_norm": 0.7771997451782227,
+      "learning_rate": 7.471217864526901e-05,
+      "loss": 0.5708,
+      "mean_token_accuracy": 0.780098044872284,
+      "num_tokens": 4884468.0,
+      "step": 2390
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 0.9132688045501709,
+      "learning_rate": 7.449003680526631e-05,
+      "loss": 0.5739,
+      "mean_token_accuracy": 0.7793432533740997,
+      "num_tokens": 4904794.0,
+      "step": 2400
+    },
+    {
+      "epoch": 3.7191358024691357,
+      "grad_norm": 0.7833852171897888,
+      "learning_rate": 7.426725715571268e-05,
+      "loss": 0.5571,
+      "mean_token_accuracy": 0.7855910241603852,
+      "num_tokens": 4925079.0,
+      "step": 2410
+    },
+    {
+      "epoch": 3.734567901234568,
+      "grad_norm": 0.8681535720825195,
+      "learning_rate": 7.404384549859976e-05,
+      "loss": 0.554,
+      "mean_token_accuracy": 0.7843137145042419,
+      "num_tokens": 4945559.0,
+      "step": 2420
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.8858405947685242,
+      "learning_rate": 7.381980765237891e-05,
+      "loss": 0.575,
+      "mean_token_accuracy": 0.7781372487545013,
+      "num_tokens": 4966039.0,
+      "step": 2430
+    },
+    {
+      "epoch": 3.765432098765432,
+      "grad_norm": 0.7430999875068665,
+      "learning_rate": 7.359514945180978e-05,
+      "loss": 0.5532,
+      "mean_token_accuracy": 0.7873997926712036,
+      "num_tokens": 4986287.0,
+      "step": 2440
+    },
+    {
+      "epoch": 3.7808641975308643,
+      "grad_norm": 0.9039332866668701,
+      "learning_rate": 7.336987674780826e-05,
+      "loss": 0.5623,
+      "mean_token_accuracy": 0.7854901909828186,
+      "num_tokens": 5006767.0,
+      "step": 2450
+    },
+    {
+      "epoch": 3.7962962962962963,
+      "grad_norm": 0.9440492987632751,
+      "learning_rate": 7.31439954072942e-05,
+      "loss": 0.5621,
+      "mean_token_accuracy": 0.7838235318660736,
+      "num_tokens": 5027247.0,
+      "step": 2460
+    },
+    {
+      "epoch": 3.8117283950617287,
+      "grad_norm": 0.8802239894866943,
+      "learning_rate": 7.291751131303848e-05,
+      "loss": 0.5539,
+      "mean_token_accuracy": 0.7860784292221069,
+      "num_tokens": 5047727.0,
+      "step": 2470
+    },
+    {
+      "epoch": 3.8271604938271606,
+      "grad_norm": 0.8055611252784729,
+      "learning_rate": 7.269043036350995e-05,
+      "loss": 0.5715,
+      "mean_token_accuracy": 0.7787745058536529,
+      "num_tokens": 5068207.0,
+      "step": 2480
+    },
+    {
+      "epoch": 3.8425925925925926,
+      "grad_norm": 0.7632115483283997,
+      "learning_rate": 7.246275847272168e-05,
+      "loss": 0.5548,
+      "mean_token_accuracy": 0.7863235294818878,
+      "num_tokens": 5088687.0,
+      "step": 2490
+    },
+    {
+      "epoch": 3.8580246913580245,
+      "grad_norm": 0.7207368016242981,
+      "learning_rate": 7.223450157007706e-05,
+      "loss": 0.5505,
+      "mean_token_accuracy": 0.78970587849617,
+      "num_tokens": 5109167.0,
+      "step": 2500
+    },
+    {
+      "epoch": 3.873456790123457,
+      "grad_norm": 1.0593148469924927,
+      "learning_rate": 7.200566560021524e-05,
+      "loss": 0.566,
+      "mean_token_accuracy": 0.7826960742473602,
+      "num_tokens": 5129647.0,
+      "step": 2510
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.6175971031188965,
+      "learning_rate": 7.177625652285646e-05,
+      "loss": 0.5432,
+      "mean_token_accuracy": 0.7926647126674652,
+      "num_tokens": 5150020.0,
+      "step": 2520
+    },
+    {
+      "epoch": 3.9043209876543212,
+      "grad_norm": 1.0054363012313843,
+      "learning_rate": 7.154628031264672e-05,
+      "loss": 0.5533,
+      "mean_token_accuracy": 0.7850490152835846,
+      "num_tokens": 5170500.0,
+      "step": 2530
+    },
+    {
+      "epoch": 3.919753086419753,
+      "grad_norm": 0.8158549070358276,
+      "learning_rate": 7.131574295900221e-05,
+      "loss": 0.566,
+      "mean_token_accuracy": 0.7858333349227905,
+      "num_tokens": 5190980.0,
+      "step": 2540
+    },
+    {
+      "epoch": 3.935185185185185,
+      "grad_norm": 0.8107885718345642,
+      "learning_rate": 7.108465046595336e-05,
+      "loss": 0.5589,
+      "mean_token_accuracy": 0.7826470673084259,
+      "num_tokens": 5211460.0,
+      "step": 2550
+    },
+    {
+      "epoch": 3.950617283950617,
+      "grad_norm": 0.8853438496589661,
+      "learning_rate": 7.085300885198846e-05,
+      "loss": 0.5431,
+      "mean_token_accuracy": 0.7922549068927764,
+      "num_tokens": 5231940.0,
+      "step": 2560
+    },
+    {
+      "epoch": 3.9660493827160495,
+      "grad_norm": 0.8967506289482117,
+      "learning_rate": 7.062082414989684e-05,
+      "loss": 0.5637,
+      "mean_token_accuracy": 0.7829411745071411,
+      "num_tokens": 5252420.0,
+      "step": 2570
+    },
+    {
+      "epoch": 3.9814814814814814,
+      "grad_norm": 0.7501311898231506,
+      "learning_rate": 7.03881024066119e-05,
+      "loss": 0.5534,
+      "mean_token_accuracy": 0.7878431379795074,
+      "num_tokens": 5272900.0,
+      "step": 2580
+    },
+    {
+      "epoch": 3.996913580246914,
+      "grad_norm": 0.9286791682243347,
+      "learning_rate": 7.015484968305348e-05,
+      "loss": 0.5597,
+      "mean_token_accuracy": 0.7838725447654724,
+      "num_tokens": 5293380.0,
+      "step": 2590
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6553741097450256,
+      "eval_mean_token_accuracy": 0.7550579616001674,
+      "eval_num_tokens": 5295940.0,
+      "eval_runtime": 3.2428,
+      "eval_samples_per_second": 84.187,
+      "eval_steps_per_second": 10.793,
+      "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_s2_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:a6ae2e45c24ad2de3ad1c1a2451eabb81c07194ae1361d646cc4fc0918792a0e
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "o_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_s2_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3240/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bf9ad04f99daa912f273d26a900f46bf1f6d7115ab87b5616e3b5cf5be6a680
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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_s2_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_s2_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