add checkpoint cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast

.gitattributes

@@ -270,3 +270,14 @@ checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/che
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-682/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-6820/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-1364/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2046/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2728/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-3410/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-4092/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-4774/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-5456/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-6138/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-682/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-6820/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "v_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_s3_vt_project_a1_ALL_bcast/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ce38e6c8633028cf266ebcfef2434c039c12418d3a5a762ca3da2d905ab91d
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/added_tokens.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/chat_template.jinja

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-1364/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-1364/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "v_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_s3_vt_project_a1_ALL_bcast/checkpoint-1364/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a53ec46a21bcd22fce568330fce9679f8f965388111a778a1ba8539416f469cd
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-1364/added_tokens.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-1364/chat_template.jinja

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-1364/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-1364/tokenizer.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-1364/tokenizer_config.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-1364/trainer_state.json

@@ -0,0 +1,1258 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1364,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01466275659824047,
+      "grad_norm": 3.6663706302642822,
+      "learning_rate": 2.6392961876832847e-06,
+      "loss": 2.4966,
+      "mean_token_accuracy": 0.5401470601558686,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.02932551319648094,
+      "grad_norm": 4.149525165557861,
+      "learning_rate": 5.571847507331378e-06,
+      "loss": 2.4504,
+      "mean_token_accuracy": 0.5461450457572937,
+      "num_tokens": 40815.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.04398826979472141,
+      "grad_norm": 3.468921661376953,
+      "learning_rate": 8.504398826979472e-06,
+      "loss": 2.3747,
+      "mean_token_accuracy": 0.5503004908561706,
+      "num_tokens": 61206.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.05865102639296188,
+      "grad_norm": 1.9510618448257446,
+      "learning_rate": 1.1436950146627567e-05,
+      "loss": 2.0501,
+      "mean_token_accuracy": 0.5706372499465943,
+      "num_tokens": 81686.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07331378299120235,
+      "grad_norm": 1.411676287651062,
+      "learning_rate": 1.4369501466275662e-05,
+      "loss": 1.7601,
+      "mean_token_accuracy": 0.5923529446125031,
+      "num_tokens": 102166.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.08797653958944282,
+      "grad_norm": 1.1375443935394287,
+      "learning_rate": 1.7302052785923756e-05,
+      "loss": 1.5712,
+      "mean_token_accuracy": 0.6036764621734619,
+      "num_tokens": 122646.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.10263929618768329,
+      "grad_norm": 0.9757223725318909,
+      "learning_rate": 2.0234604105571847e-05,
+      "loss": 1.3716,
+      "mean_token_accuracy": 0.6212254881858825,
+      "num_tokens": 143126.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.11730205278592376,
+      "grad_norm": 0.9012596011161804,
+      "learning_rate": 2.3167155425219943e-05,
+      "loss": 1.2133,
+      "mean_token_accuracy": 0.6412255048751831,
+      "num_tokens": 163606.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.13196480938416422,
+      "grad_norm": 1.029589056968689,
+      "learning_rate": 2.6099706744868034e-05,
+      "loss": 1.0462,
+      "mean_token_accuracy": 0.6717647075653076,
+      "num_tokens": 184086.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.1466275659824047,
+      "grad_norm": 1.1074068546295166,
+      "learning_rate": 2.9032258064516133e-05,
+      "loss": 0.9442,
+      "mean_token_accuracy": 0.6842647135257721,
+      "num_tokens": 204566.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.16129032258064516,
+      "grad_norm": 1.2979555130004883,
+      "learning_rate": 3.1964809384164225e-05,
+      "loss": 0.8031,
+      "mean_token_accuracy": 0.7161274492740631,
+      "num_tokens": 225046.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.17595307917888564,
+      "grad_norm": 1.2788987159729004,
+      "learning_rate": 3.489736070381232e-05,
+      "loss": 0.7661,
+      "mean_token_accuracy": 0.7248058915138245,
+      "num_tokens": 245505.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.1906158357771261,
+      "grad_norm": 1.223928689956665,
+      "learning_rate": 3.7829912023460415e-05,
+      "loss": 0.7407,
+      "mean_token_accuracy": 0.7309313714504242,
+      "num_tokens": 265985.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.20527859237536658,
+      "grad_norm": 1.217321515083313,
+      "learning_rate": 4.076246334310851e-05,
+      "loss": 0.7283,
+      "mean_token_accuracy": 0.7320588171482086,
+      "num_tokens": 286465.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.21994134897360704,
+      "grad_norm": 0.8935562968254089,
+      "learning_rate": 4.36950146627566e-05,
+      "loss": 0.6937,
+      "mean_token_accuracy": 0.744705879688263,
+      "num_tokens": 306945.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.23460410557184752,
+      "grad_norm": 0.9931844472885132,
+      "learning_rate": 4.6627565982404694e-05,
+      "loss": 0.693,
+      "mean_token_accuracy": 0.7443526327610016,
+      "num_tokens": 327350.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.24926686217008798,
+      "grad_norm": 0.8610531687736511,
+      "learning_rate": 4.956011730205279e-05,
+      "loss": 0.6883,
+      "mean_token_accuracy": 0.7444378435611725,
+      "num_tokens": 347670.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.26392961876832843,
+      "grad_norm": 0.8810847997665405,
+      "learning_rate": 5.249266862170088e-05,
+      "loss": 0.6677,
+      "mean_token_accuracy": 0.7503921568393708,
+      "num_tokens": 368150.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2785923753665689,
+      "grad_norm": 0.8069462776184082,
+      "learning_rate": 5.542521994134897e-05,
+      "loss": 0.6679,
+      "mean_token_accuracy": 0.7510784268379211,
+      "num_tokens": 388630.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.2932551319648094,
+      "grad_norm": 0.8739913702011108,
+      "learning_rate": 5.8357771260997075e-05,
+      "loss": 0.6677,
+      "mean_token_accuracy": 0.7502941191196442,
+      "num_tokens": 409110.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.30791788856304986,
+      "grad_norm": 0.9066668748855591,
+      "learning_rate": 6.129032258064517e-05,
+      "loss": 0.6721,
+      "mean_token_accuracy": 0.7441666662693024,
+      "num_tokens": 429590.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 0.7986886501312256,
+      "learning_rate": 6.422287390029326e-05,
+      "loss": 0.6588,
+      "mean_token_accuracy": 0.7490686297416687,
+      "num_tokens": 450070.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.33724340175953077,
+      "grad_norm": 0.815414309501648,
+      "learning_rate": 6.715542521994135e-05,
+      "loss": 0.6638,
+      "mean_token_accuracy": 0.7513235330581665,
+      "num_tokens": 470550.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.3519061583577713,
+      "grad_norm": 0.7602818012237549,
+      "learning_rate": 7.008797653958945e-05,
+      "loss": 0.6584,
+      "mean_token_accuracy": 0.7509313762187958,
+      "num_tokens": 491030.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.36656891495601174,
+      "grad_norm": 0.9501712918281555,
+      "learning_rate": 7.302052785923754e-05,
+      "loss": 0.6372,
+      "mean_token_accuracy": 0.7608333349227905,
+      "num_tokens": 511510.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.3812316715542522,
+      "grad_norm": 0.8099446892738342,
+      "learning_rate": 7.595307917888564e-05,
+      "loss": 0.6812,
+      "mean_token_accuracy": 0.7463235318660736,
+      "num_tokens": 531990.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.39589442815249265,
+      "grad_norm": 0.8097174763679504,
+      "learning_rate": 7.888563049853373e-05,
+      "loss": 0.6651,
+      "mean_token_accuracy": 0.7468137264251709,
+      "num_tokens": 552470.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.41055718475073316,
+      "grad_norm": 0.7530633211135864,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 0.6511,
+      "mean_token_accuracy": 0.7538725554943084,
+      "num_tokens": 572950.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.4252199413489736,
+      "grad_norm": 0.660597562789917,
+      "learning_rate": 8.475073313782992e-05,
+      "loss": 0.6479,
+      "mean_token_accuracy": 0.7550000011920929,
+      "num_tokens": 593430.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.4398826979472141,
+      "grad_norm": 0.6961861252784729,
+      "learning_rate": 8.7683284457478e-05,
+      "loss": 0.6587,
+      "mean_token_accuracy": 0.749117660522461,
+      "num_tokens": 613910.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.924081027507782,
+      "learning_rate": 9.06158357771261e-05,
+      "loss": 0.6482,
+      "mean_token_accuracy": 0.7544108033180237,
+      "num_tokens": 634176.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.46920821114369504,
+      "grad_norm": 0.7237821221351624,
+      "learning_rate": 9.35483870967742e-05,
+      "loss": 0.6547,
+      "mean_token_accuracy": 0.7502941012382507,
+      "num_tokens": 654656.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.4838709677419355,
+      "grad_norm": 0.809219479560852,
+      "learning_rate": 9.64809384164223e-05,
+      "loss": 0.6449,
+      "mean_token_accuracy": 0.7552451074123383,
+      "num_tokens": 675136.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.49853372434017595,
+      "grad_norm": 0.6265454888343811,
+      "learning_rate": 9.941348973607039e-05,
+      "loss": 0.6544,
+      "mean_token_accuracy": 0.7504901945590973,
+      "num_tokens": 695616.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5131964809384164,
+      "grad_norm": 0.690653920173645,
+      "learning_rate": 9.999962381348496e-05,
+      "loss": 0.638,
+      "mean_token_accuracy": 0.7574509859085083,
+      "num_tokens": 716096.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5278592375366569,
+      "grad_norm": 0.6082450151443481,
+      "learning_rate": 9.999809556546922e-05,
+      "loss": 0.6469,
+      "mean_token_accuracy": 0.7543627440929412,
+      "num_tokens": 736576.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5425219941348973,
+      "grad_norm": 0.6173468232154846,
+      "learning_rate": 9.999539178019954e-05,
+      "loss": 0.649,
+      "mean_token_accuracy": 0.7521512925624847,
+      "num_tokens": 756812.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5571847507331378,
+      "grad_norm": 0.6369903683662415,
+      "learning_rate": 9.999151252124639e-05,
+      "loss": 0.6501,
+      "mean_token_accuracy": 0.7515686333179474,
+      "num_tokens": 777292.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.5718475073313783,
+      "grad_norm": 0.5715249180793762,
+      "learning_rate": 9.998645787981749e-05,
+      "loss": 0.643,
+      "mean_token_accuracy": 0.7544650256633758,
+      "num_tokens": 797538.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.5865102639296188,
+      "grad_norm": 0.678391695022583,
+      "learning_rate": 9.998022797475572e-05,
+      "loss": 0.6496,
+      "mean_token_accuracy": 0.7516666650772095,
+      "num_tokens": 818018.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6011730205278593,
+      "grad_norm": 0.6235240697860718,
+      "learning_rate": 9.997282295253644e-05,
+      "loss": 0.633,
+      "mean_token_accuracy": 0.7596078515052795,
+      "num_tokens": 838498.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6158357771260997,
+      "grad_norm": 0.5357748866081238,
+      "learning_rate": 9.996424298726381e-05,
+      "loss": 0.6572,
+      "mean_token_accuracy": 0.7510294198989869,
+      "num_tokens": 858978.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.6304985337243402,
+      "grad_norm": 0.6643717288970947,
+      "learning_rate": 9.995448828066693e-05,
+      "loss": 0.6594,
+      "mean_token_accuracy": 0.7500980436801911,
+      "num_tokens": 879458.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.651352047920227,
+      "learning_rate": 9.994355906209492e-05,
+      "loss": 0.654,
+      "mean_token_accuracy": 0.7509803950786591,
+      "num_tokens": 899938.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6598240469208211,
+      "grad_norm": 0.6784325242042542,
+      "learning_rate": 9.993145558851168e-05,
+      "loss": 0.6487,
+      "mean_token_accuracy": 0.7501960813999176,
+      "num_tokens": 920418.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.6744868035190615,
+      "grad_norm": 0.5277068018913269,
+      "learning_rate": 9.991817814448967e-05,
+      "loss": 0.6376,
+      "mean_token_accuracy": 0.75563725233078,
+      "num_tokens": 940898.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.6891495601173021,
+      "grad_norm": 0.5870142579078674,
+      "learning_rate": 9.990372704220345e-05,
+      "loss": 0.6493,
+      "mean_token_accuracy": 0.7515686273574829,
+      "num_tokens": 961378.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7038123167155426,
+      "grad_norm": 0.5757046341896057,
+      "learning_rate": 9.988810262142209e-05,
+      "loss": 0.6502,
+      "mean_token_accuracy": 0.7527043879032135,
+      "num_tokens": 981824.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.718475073313783,
+      "grad_norm": 0.5332264304161072,
+      "learning_rate": 9.987130524950141e-05,
+      "loss": 0.6389,
+      "mean_token_accuracy": 0.7545588254928589,
+      "num_tokens": 1002304.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7331378299120235,
+      "grad_norm": 0.5763241052627563,
+      "learning_rate": 9.985333532137514e-05,
+      "loss": 0.6465,
+      "mean_token_accuracy": 0.7529901921749115,
+      "num_tokens": 1022784.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.7478005865102639,
+      "grad_norm": 0.6235876083374023,
+      "learning_rate": 9.983419325954577e-05,
+      "loss": 0.6391,
+      "mean_token_accuracy": 0.7525490164756775,
+      "num_tokens": 1043264.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.7624633431085044,
+      "grad_norm": 0.6091899275779724,
+      "learning_rate": 9.981387951407462e-05,
+      "loss": 0.6175,
+      "mean_token_accuracy": 0.761715692281723,
+      "num_tokens": 1063744.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.7771260997067448,
+      "grad_norm": 0.6009454131126404,
+      "learning_rate": 9.979239456257113e-05,
+      "loss": 0.6405,
+      "mean_token_accuracy": 0.7544117569923401,
+      "num_tokens": 1084224.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.7917888563049853,
+      "grad_norm": 0.6014620661735535,
+      "learning_rate": 9.976973891018175e-05,
+      "loss": 0.6338,
+      "mean_token_accuracy": 0.7550000011920929,
+      "num_tokens": 1104704.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8064516129032258,
+      "grad_norm": 0.7326117753982544,
+      "learning_rate": 9.974591308957808e-05,
+      "loss": 0.6616,
+      "mean_token_accuracy": 0.743921571969986,
+      "num_tokens": 1125184.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8211143695014663,
+      "grad_norm": 0.6346194744110107,
+      "learning_rate": 9.972091766094424e-05,
+      "loss": 0.6434,
+      "mean_token_accuracy": 0.752892154455185,
+      "num_tokens": 1145664.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8357771260997068,
+      "grad_norm": 0.5967418551445007,
+      "learning_rate": 9.969475321196373e-05,
+      "loss": 0.6385,
+      "mean_token_accuracy": 0.7556862711906434,
+      "num_tokens": 1166144.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8504398826979472,
+      "grad_norm": 0.545911431312561,
+      "learning_rate": 9.966742035780571e-05,
+      "loss": 0.6372,
+      "mean_token_accuracy": 0.7558333277702332,
+      "num_tokens": 1186624.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.8651026392961877,
+      "grad_norm": 0.5666757225990295,
+      "learning_rate": 9.963891974111042e-05,
+      "loss": 0.6404,
+      "mean_token_accuracy": 0.7540686249732971,
+      "num_tokens": 1207104.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.8797653958944281,
+      "grad_norm": 0.5760472416877747,
+      "learning_rate": 9.960925203197408e-05,
+      "loss": 0.6197,
+      "mean_token_accuracy": 0.7618935823440551,
+      "num_tokens": 1227561.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.8944281524926686,
+      "grad_norm": 0.5213801264762878,
+      "learning_rate": 9.957841792793326e-05,
+      "loss": 0.6406,
+      "mean_token_accuracy": 0.7563725531101226,
+      "num_tokens": 1248041.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.5387865304946899,
+      "learning_rate": 9.95464181539483e-05,
+      "loss": 0.6299,
+      "mean_token_accuracy": 0.7593627452850342,
+      "num_tokens": 1268521.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9237536656891495,
+      "grad_norm": 0.5207778811454773,
+      "learning_rate": 9.951325346238638e-05,
+      "loss": 0.6469,
+      "mean_token_accuracy": 0.7524509727954865,
+      "num_tokens": 1289001.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9384164222873901,
+      "grad_norm": 0.6844761967658997,
+      "learning_rate": 9.947892463300381e-05,
+      "loss": 0.6348,
+      "mean_token_accuracy": 0.7599019587039948,
+      "num_tokens": 1309481.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.9530791788856305,
+      "grad_norm": 0.5045949816703796,
+      "learning_rate": 9.944343247292771e-05,
+      "loss": 0.6342,
+      "mean_token_accuracy": 0.7550490260124206,
+      "num_tokens": 1329961.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 0.585598886013031,
+      "learning_rate": 9.940677781663699e-05,
+      "loss": 0.649,
+      "mean_token_accuracy": 0.7502451062202453,
+      "num_tokens": 1350441.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.9824046920821115,
+      "grad_norm": 0.45848599076271057,
+      "learning_rate": 9.936896152594273e-05,
+      "loss": 0.6378,
+      "mean_token_accuracy": 0.7545588195323945,
+      "num_tokens": 1370921.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.9970674486803519,
+      "grad_norm": 0.45816901326179504,
+      "learning_rate": 9.932998448996798e-05,
+      "loss": 0.6306,
+      "mean_token_accuracy": 0.7586764633655548,
+      "num_tokens": 1391401.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.0117302052785924,
+      "grad_norm": 0.5341461300849915,
+      "learning_rate": 9.92898476251268e-05,
+      "loss": 0.6368,
+      "mean_token_accuracy": 0.7575490236282348,
+      "num_tokens": 1410089.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0263929618768328,
+      "grad_norm": 0.7225525379180908,
+      "learning_rate": 9.924855187510274e-05,
+      "loss": 0.6236,
+      "mean_token_accuracy": 0.7612254917621613,
+      "num_tokens": 1430569.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.0410557184750733,
+      "grad_norm": 0.5576125383377075,
+      "learning_rate": 9.920609821082662e-05,
+      "loss": 0.6137,
+      "mean_token_accuracy": 0.765588229894638,
+      "num_tokens": 1451049.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.0557184750733137,
+      "grad_norm": 0.6563458442687988,
+      "learning_rate": 9.916248763045375e-05,
+      "loss": 0.6239,
+      "mean_token_accuracy": 0.7614491164684296,
+      "num_tokens": 1471384.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.0703812316715542,
+      "grad_norm": 0.5540904998779297,
+      "learning_rate": 9.911772115934042e-05,
+      "loss": 0.6226,
+      "mean_token_accuracy": 0.7628921687602996,
+      "num_tokens": 1491864.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.0850439882697946,
+      "grad_norm": 0.5026265978813171,
+      "learning_rate": 9.907179985001978e-05,
+      "loss": 0.6363,
+      "mean_token_accuracy": 0.7549781084060669,
+      "num_tokens": 1512184.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.099706744868035,
+      "grad_norm": 0.716999351978302,
+      "learning_rate": 9.90247247821772e-05,
+      "loss": 0.6303,
+      "mean_token_accuracy": 0.7568627417087554,
+      "num_tokens": 1532664.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1143695014662756,
+      "grad_norm": 0.4981926381587982,
+      "learning_rate": 9.897649706262473e-05,
+      "loss": 0.619,
+      "mean_token_accuracy": 0.763382351398468,
+      "num_tokens": 1553144.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.129032258064516,
+      "grad_norm": 0.5225701332092285,
+      "learning_rate": 9.892711782527517e-05,
+      "loss": 0.6233,
+      "mean_token_accuracy": 0.761715692281723,
+      "num_tokens": 1573624.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.1436950146627567,
+      "grad_norm": 0.5625816583633423,
+      "learning_rate": 9.887658823111544e-05,
+      "loss": 0.6232,
+      "mean_token_accuracy": 0.7573675394058228,
+      "num_tokens": 1594029.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.1583577712609971,
+      "grad_norm": 0.511184811592102,
+      "learning_rate": 9.882490946817915e-05,
+      "loss": 0.6303,
+      "mean_token_accuracy": 0.7567156851291656,
+      "num_tokens": 1614509.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.1730205278592376,
+      "grad_norm": 0.5488473773002625,
+      "learning_rate": 9.877208275151884e-05,
+      "loss": 0.6185,
+      "mean_token_accuracy": 0.7622549057006835,
+      "num_tokens": 1634989.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.187683284457478,
+      "grad_norm": 0.5918490290641785,
+      "learning_rate": 9.871810932317726e-05,
+      "loss": 0.6175,
+      "mean_token_accuracy": 0.7629630208015442,
+      "num_tokens": 1655225.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2023460410557185,
+      "grad_norm": 0.7483125329017639,
+      "learning_rate": 9.866299045215826e-05,
+      "loss": 0.6203,
+      "mean_token_accuracy": 0.7614705920219421,
+      "num_tokens": 1675705.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.217008797653959,
+      "grad_norm": 0.5696433782577515,
+      "learning_rate": 9.860672743439695e-05,
+      "loss": 0.628,
+      "mean_token_accuracy": 0.7564215719699859,
+      "num_tokens": 1696185.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2316715542521994,
+      "grad_norm": 0.5894884467124939,
+      "learning_rate": 9.854932159272917e-05,
+      "loss": 0.6293,
+      "mean_token_accuracy": 0.7585468471050263,
+      "num_tokens": 1716642.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.2463343108504399,
+      "grad_norm": 0.4901694357395172,
+      "learning_rate": 9.849077427686041e-05,
+      "loss": 0.6139,
+      "mean_token_accuracy": 0.7617156863212585,
+      "num_tokens": 1737122.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.2609970674486803,
+      "grad_norm": 0.5675632357597351,
+      "learning_rate": 9.843108686333417e-05,
+      "loss": 0.6277,
+      "mean_token_accuracy": 0.7617647051811218,
+      "num_tokens": 1757602.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.2756598240469208,
+      "grad_norm": 0.48929065465927124,
+      "learning_rate": 9.837026075549945e-05,
+      "loss": 0.6055,
+      "mean_token_accuracy": 0.7684804022312164,
+      "num_tokens": 1778082.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.5677883625030518,
+      "learning_rate": 9.830829738347782e-05,
+      "loss": 0.6291,
+      "mean_token_accuracy": 0.7578431308269501,
+      "num_tokens": 1798562.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.3049853372434017,
+      "grad_norm": 0.5752457976341248,
+      "learning_rate": 9.82451982041298e-05,
+      "loss": 0.6298,
+      "mean_token_accuracy": 0.7572548925876618,
+      "num_tokens": 1819042.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3196480938416422,
+      "grad_norm": 0.579814612865448,
+      "learning_rate": 9.818096470102067e-05,
+      "loss": 0.613,
+      "mean_token_accuracy": 0.7657352924346924,
+      "num_tokens": 1839522.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.3343108504398826,
+      "grad_norm": 0.5723453164100647,
+      "learning_rate": 9.811559838438542e-05,
+      "loss": 0.6075,
+      "mean_token_accuracy": 0.7673529386520386,
+      "num_tokens": 1860002.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.3489736070381233,
+      "grad_norm": 0.5011471509933472,
+      "learning_rate": 9.804910079109342e-05,
+      "loss": 0.6356,
+      "mean_token_accuracy": 0.7558823525905609,
+      "num_tokens": 1880482.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.5844294428825378,
+      "learning_rate": 9.798147348461218e-05,
+      "loss": 0.6251,
+      "mean_token_accuracy": 0.7588725566864014,
+      "num_tokens": 1900962.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.3782991202346042,
+      "grad_norm": 0.6461315751075745,
+      "learning_rate": 9.791271805497062e-05,
+      "loss": 0.619,
+      "mean_token_accuracy": 0.7632353007793427,
+      "num_tokens": 1921442.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.3929618768328447,
+      "grad_norm": 0.560377836227417,
+      "learning_rate": 9.784283611872169e-05,
+      "loss": 0.6265,
+      "mean_token_accuracy": 0.757421898841858,
+      "num_tokens": 1941888.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4076246334310851,
+      "grad_norm": 0.6241864562034607,
+      "learning_rate": 9.777182931890438e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7597058832645416,
+      "num_tokens": 1962368.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4222873900293256,
+      "grad_norm": 0.5094092488288879,
+      "learning_rate": 9.769969932500502e-05,
+      "loss": 0.6318,
+      "mean_token_accuracy": 0.7576960861682892,
+      "num_tokens": 1982848.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.436950146627566,
+      "grad_norm": 0.5033220052719116,
+      "learning_rate": 9.762644783291812e-05,
+      "loss": 0.6245,
+      "mean_token_accuracy": 0.7599019527435302,
+      "num_tokens": 2003328.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.4516129032258065,
+      "grad_norm": 0.4806479513645172,
+      "learning_rate": 9.755207656490644e-05,
+      "loss": 0.639,
+      "mean_token_accuracy": 0.7538235366344452,
+      "num_tokens": 2023808.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.466275659824047,
+      "grad_norm": 0.5395609140396118,
+      "learning_rate": 9.747658726956048e-05,
+      "loss": 0.6099,
+      "mean_token_accuracy": 0.7634313702583313,
+      "num_tokens": 2044288.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4809384164222874,
+      "grad_norm": 0.5191217660903931,
+      "learning_rate": 9.739998172175744e-05,
+      "loss": 0.605,
+      "mean_token_accuracy": 0.7667647123336792,
+      "num_tokens": 2064768.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.4956011730205279,
+      "grad_norm": 0.49461233615875244,
+      "learning_rate": 9.732226172261943e-05,
+      "loss": 0.6123,
+      "mean_token_accuracy": 0.7655392289161682,
+      "num_tokens": 2085248.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5102639296187683,
+      "grad_norm": 0.5261324048042297,
+      "learning_rate": 9.724342909947114e-05,
+      "loss": 0.6049,
+      "mean_token_accuracy": 0.7624019622802735,
+      "num_tokens": 2105728.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.5249266862170088,
+      "grad_norm": 0.5409830212593079,
+      "learning_rate": 9.716348570579686e-05,
+      "loss": 0.6377,
+      "mean_token_accuracy": 0.7593627452850342,
+      "num_tokens": 2126208.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.5395894428152492,
+      "grad_norm": 0.5728979110717773,
+      "learning_rate": 9.708243342119695e-05,
+      "loss": 0.6054,
+      "mean_token_accuracy": 0.7661274492740631,
+      "num_tokens": 2146688.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.5542521994134897,
+      "grad_norm": 0.5928049683570862,
+      "learning_rate": 9.700027415134358e-05,
+      "loss": 0.6112,
+      "mean_token_accuracy": 0.7631862699985504,
+      "num_tokens": 2167168.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.5689149560117301,
+      "grad_norm": 0.6045894622802734,
+      "learning_rate": 9.691700982793597e-05,
+      "loss": 0.6244,
+      "mean_token_accuracy": 0.7585741996765136,
+      "num_tokens": 2187627.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.5835777126099706,
+      "grad_norm": 0.5053999423980713,
+      "learning_rate": 9.6832642408655e-05,
+      "loss": 0.6094,
+      "mean_token_accuracy": 0.7675980389118194,
+      "num_tokens": 2208107.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.598240469208211,
+      "grad_norm": 0.5727707743644714,
+      "learning_rate": 9.674717387711706e-05,
+      "loss": 0.6263,
+      "mean_token_accuracy": 0.7594117760658264,
+      "num_tokens": 2228587.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 0.5962901711463928,
+      "learning_rate": 9.66606062428276e-05,
+      "loss": 0.6051,
+      "mean_token_accuracy": 0.7674056112766265,
+      "num_tokens": 2248853.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.627565982404692,
+      "grad_norm": 0.5810521245002747,
+      "learning_rate": 9.657294154113368e-05,
+      "loss": 0.6186,
+      "mean_token_accuracy": 0.7595588266849518,
+      "num_tokens": 2269333.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.6422287390029324,
+      "grad_norm": 0.5142710208892822,
+      "learning_rate": 9.648418183317629e-05,
+      "loss": 0.6201,
+      "mean_token_accuracy": 0.7632353007793427,
+      "num_tokens": 2289813.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.6568914956011729,
+      "grad_norm": 0.5239130854606628,
+      "learning_rate": 9.639432920584177e-05,
+      "loss": 0.625,
+      "mean_token_accuracy": 0.7592156827449799,
+      "num_tokens": 2310293.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.6715542521994133,
+      "grad_norm": 0.5248172283172607,
+      "learning_rate": 9.630338577171282e-05,
+      "loss": 0.6347,
+      "mean_token_accuracy": 0.7565686285495759,
+      "num_tokens": 2330773.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.6862170087976538,
+      "grad_norm": 0.6786187887191772,
+      "learning_rate": 9.621135366901874e-05,
+      "loss": 0.626,
+      "mean_token_accuracy": 0.7596078336238861,
+      "num_tokens": 2351253.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7008797653958945,
+      "grad_norm": 0.5295122861862183,
+      "learning_rate": 9.61182350615853e-05,
+      "loss": 0.616,
+      "mean_token_accuracy": 0.7638725519180298,
+      "num_tokens": 2371733.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.715542521994135,
+      "grad_norm": 0.5179807543754578,
+      "learning_rate": 9.60240321387837e-05,
+      "loss": 0.6311,
+      "mean_token_accuracy": 0.756617647409439,
+      "num_tokens": 2392213.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.7302052785923754,
+      "grad_norm": 0.5839389562606812,
+      "learning_rate": 9.592874711547922e-05,
+      "loss": 0.6063,
+      "mean_token_accuracy": 0.765490198135376,
+      "num_tokens": 2412693.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.7448680351906158,
+      "grad_norm": 0.577913761138916,
+      "learning_rate": 9.583238223197906e-05,
+      "loss": 0.6313,
+      "mean_token_accuracy": 0.7565686345100403,
+      "num_tokens": 2433173.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.7595307917888563,
+      "grad_norm": 0.6578575372695923,
+      "learning_rate": 9.573493975397975e-05,
+      "loss": 0.6145,
+      "mean_token_accuracy": 0.7614705860614777,
+      "num_tokens": 2453653.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7741935483870968,
+      "grad_norm": 0.49838587641716003,
+      "learning_rate": 9.56364219725138e-05,
+      "loss": 0.6033,
+      "mean_token_accuracy": 0.7695098042488098,
+      "num_tokens": 2474133.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.7888563049853372,
+      "grad_norm": 0.48799875378608704,
+      "learning_rate": 9.553683120389592e-05,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.764902925491333,
+      "num_tokens": 2494524.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8035190615835777,
+      "grad_norm": 0.5147119164466858,
+      "learning_rate": 9.543616978966842e-05,
+      "loss": 0.6206,
+      "mean_token_accuracy": 0.761617648601532,
+      "num_tokens": 2515004.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.5641414523124695,
+      "learning_rate": 9.53344400965463e-05,
+      "loss": 0.6251,
+      "mean_token_accuracy": 0.7585784316062927,
+      "num_tokens": 2535484.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.8328445747800588,
+      "grad_norm": 0.520799994468689,
+      "learning_rate": 9.523164451636157e-05,
+      "loss": 0.6356,
+      "mean_token_accuracy": 0.7528921604156494,
+      "num_tokens": 2555964.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.8475073313782993,
+      "grad_norm": 0.45843806862831116,
+      "learning_rate": 9.512778546600696e-05,
+      "loss": 0.622,
+      "mean_token_accuracy": 0.7602451145648956,
+      "num_tokens": 2576444.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.8621700879765397,
+      "grad_norm": 0.5162474513053894,
+      "learning_rate": 9.50228653873791e-05,
+      "loss": 0.6065,
+      "mean_token_accuracy": 0.7668967843055725,
+      "num_tokens": 2596690.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.8768328445747802,
+      "grad_norm": 0.5157609581947327,
+      "learning_rate": 9.491688674732123e-05,
+      "loss": 0.5972,
+      "mean_token_accuracy": 0.7700980484485627,
+      "num_tokens": 2617170.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.8914956011730206,
+      "grad_norm": 0.6079277396202087,
+      "learning_rate": 9.480985203756501e-05,
+      "loss": 0.6334,
+      "mean_token_accuracy": 0.7560294091701507,
+      "num_tokens": 2637650.0,
+      "step": 1290
+    },
+    {
+      "epoch": 1.906158357771261,
+      "grad_norm": 0.5813050270080566,
+      "learning_rate": 9.470176377467206e-05,
+      "loss": 0.6206,
+      "mean_token_accuracy": 0.7631862759590149,
+      "num_tokens": 2658130.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.9208211143695015,
+      "grad_norm": 0.6724423170089722,
+      "learning_rate": 9.45926244999748e-05,
+      "loss": 0.6218,
+      "mean_token_accuracy": 0.7615686237812043,
+      "num_tokens": 2678610.0,
+      "step": 1310
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 0.5010402798652649,
+      "learning_rate": 9.44824367795166e-05,
+      "loss": 0.6077,
+      "mean_token_accuracy": 0.7619117617607116,
+      "num_tokens": 2699090.0,
+      "step": 1320
+    },
+    {
+      "epoch": 1.9501466275659824,
+      "grad_norm": 0.45624953508377075,
+      "learning_rate": 9.437120320399158e-05,
+      "loss": 0.6154,
+      "mean_token_accuracy": 0.7637745201587677,
+      "num_tokens": 2719570.0,
+      "step": 1330
+    },
+    {
+      "epoch": 1.964809384164223,
+      "grad_norm": 0.5894467830657959,
+      "learning_rate": 9.425892638868356e-05,
+      "loss": 0.6061,
+      "mean_token_accuracy": 0.7665196061134338,
+      "num_tokens": 2740050.0,
+      "step": 1340
+    },
+    {
+      "epoch": 1.9794721407624634,
+      "grad_norm": 0.4616512656211853,
+      "learning_rate": 9.414560897340468e-05,
+      "loss": 0.6355,
+      "mean_token_accuracy": 0.7558333337306976,
+      "num_tokens": 2760530.0,
+      "step": 1350
+    },
+    {
+      "epoch": 1.9941348973607038,
+      "grad_norm": 0.5391420125961304,
+      "learning_rate": 9.403125362243328e-05,
+      "loss": 0.6169,
+      "mean_token_accuracy": 0.7617647111415863,
+      "num_tokens": 2781010.0,
+      "step": 1360
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6820,
+  "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": 1.1869529768932147e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-1364/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e72e8fc2bceab0c8efcfc23f671d1d30f1f51aa52ae8d9a80ad818c207cbfc
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2046/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2046/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "v_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_s3_vt_project_a1_ALL_bcast/checkpoint-2046/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b720a64356bdfbd1d41607807f3a5525e351c45284cdf2c172458102773abe52
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2046/added_tokens.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2046/chat_template.jinja

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2046/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2046/tokenizer.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2046/tokenizer_config.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2046/trainer_state.json

@@ -0,0 +1,1870 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2046,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01466275659824047,
+      "grad_norm": 3.6663706302642822,
+      "learning_rate": 2.6392961876832847e-06,
+      "loss": 2.4966,
+      "mean_token_accuracy": 0.5401470601558686,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.02932551319648094,
+      "grad_norm": 4.149525165557861,
+      "learning_rate": 5.571847507331378e-06,
+      "loss": 2.4504,
+      "mean_token_accuracy": 0.5461450457572937,
+      "num_tokens": 40815.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.04398826979472141,
+      "grad_norm": 3.468921661376953,
+      "learning_rate": 8.504398826979472e-06,
+      "loss": 2.3747,
+      "mean_token_accuracy": 0.5503004908561706,
+      "num_tokens": 61206.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.05865102639296188,
+      "grad_norm": 1.9510618448257446,
+      "learning_rate": 1.1436950146627567e-05,
+      "loss": 2.0501,
+      "mean_token_accuracy": 0.5706372499465943,
+      "num_tokens": 81686.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07331378299120235,
+      "grad_norm": 1.411676287651062,
+      "learning_rate": 1.4369501466275662e-05,
+      "loss": 1.7601,
+      "mean_token_accuracy": 0.5923529446125031,
+      "num_tokens": 102166.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.08797653958944282,
+      "grad_norm": 1.1375443935394287,
+      "learning_rate": 1.7302052785923756e-05,
+      "loss": 1.5712,
+      "mean_token_accuracy": 0.6036764621734619,
+      "num_tokens": 122646.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.10263929618768329,
+      "grad_norm": 0.9757223725318909,
+      "learning_rate": 2.0234604105571847e-05,
+      "loss": 1.3716,
+      "mean_token_accuracy": 0.6212254881858825,
+      "num_tokens": 143126.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.11730205278592376,
+      "grad_norm": 0.9012596011161804,
+      "learning_rate": 2.3167155425219943e-05,
+      "loss": 1.2133,
+      "mean_token_accuracy": 0.6412255048751831,
+      "num_tokens": 163606.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.13196480938416422,
+      "grad_norm": 1.029589056968689,
+      "learning_rate": 2.6099706744868034e-05,
+      "loss": 1.0462,
+      "mean_token_accuracy": 0.6717647075653076,
+      "num_tokens": 184086.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.1466275659824047,
+      "grad_norm": 1.1074068546295166,
+      "learning_rate": 2.9032258064516133e-05,
+      "loss": 0.9442,
+      "mean_token_accuracy": 0.6842647135257721,
+      "num_tokens": 204566.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.16129032258064516,
+      "grad_norm": 1.2979555130004883,
+      "learning_rate": 3.1964809384164225e-05,
+      "loss": 0.8031,
+      "mean_token_accuracy": 0.7161274492740631,
+      "num_tokens": 225046.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.17595307917888564,
+      "grad_norm": 1.2788987159729004,
+      "learning_rate": 3.489736070381232e-05,
+      "loss": 0.7661,
+      "mean_token_accuracy": 0.7248058915138245,
+      "num_tokens": 245505.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.1906158357771261,
+      "grad_norm": 1.223928689956665,
+      "learning_rate": 3.7829912023460415e-05,
+      "loss": 0.7407,
+      "mean_token_accuracy": 0.7309313714504242,
+      "num_tokens": 265985.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.20527859237536658,
+      "grad_norm": 1.217321515083313,
+      "learning_rate": 4.076246334310851e-05,
+      "loss": 0.7283,
+      "mean_token_accuracy": 0.7320588171482086,
+      "num_tokens": 286465.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.21994134897360704,
+      "grad_norm": 0.8935562968254089,
+      "learning_rate": 4.36950146627566e-05,
+      "loss": 0.6937,
+      "mean_token_accuracy": 0.744705879688263,
+      "num_tokens": 306945.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.23460410557184752,
+      "grad_norm": 0.9931844472885132,
+      "learning_rate": 4.6627565982404694e-05,
+      "loss": 0.693,
+      "mean_token_accuracy": 0.7443526327610016,
+      "num_tokens": 327350.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.24926686217008798,
+      "grad_norm": 0.8610531687736511,
+      "learning_rate": 4.956011730205279e-05,
+      "loss": 0.6883,
+      "mean_token_accuracy": 0.7444378435611725,
+      "num_tokens": 347670.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.26392961876832843,
+      "grad_norm": 0.8810847997665405,
+      "learning_rate": 5.249266862170088e-05,
+      "loss": 0.6677,
+      "mean_token_accuracy": 0.7503921568393708,
+      "num_tokens": 368150.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2785923753665689,
+      "grad_norm": 0.8069462776184082,
+      "learning_rate": 5.542521994134897e-05,
+      "loss": 0.6679,
+      "mean_token_accuracy": 0.7510784268379211,
+      "num_tokens": 388630.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.2932551319648094,
+      "grad_norm": 0.8739913702011108,
+      "learning_rate": 5.8357771260997075e-05,
+      "loss": 0.6677,
+      "mean_token_accuracy": 0.7502941191196442,
+      "num_tokens": 409110.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.30791788856304986,
+      "grad_norm": 0.9066668748855591,
+      "learning_rate": 6.129032258064517e-05,
+      "loss": 0.6721,
+      "mean_token_accuracy": 0.7441666662693024,
+      "num_tokens": 429590.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 0.7986886501312256,
+      "learning_rate": 6.422287390029326e-05,
+      "loss": 0.6588,
+      "mean_token_accuracy": 0.7490686297416687,
+      "num_tokens": 450070.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.33724340175953077,
+      "grad_norm": 0.815414309501648,
+      "learning_rate": 6.715542521994135e-05,
+      "loss": 0.6638,
+      "mean_token_accuracy": 0.7513235330581665,
+      "num_tokens": 470550.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.3519061583577713,
+      "grad_norm": 0.7602818012237549,
+      "learning_rate": 7.008797653958945e-05,
+      "loss": 0.6584,
+      "mean_token_accuracy": 0.7509313762187958,
+      "num_tokens": 491030.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.36656891495601174,
+      "grad_norm": 0.9501712918281555,
+      "learning_rate": 7.302052785923754e-05,
+      "loss": 0.6372,
+      "mean_token_accuracy": 0.7608333349227905,
+      "num_tokens": 511510.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.3812316715542522,
+      "grad_norm": 0.8099446892738342,
+      "learning_rate": 7.595307917888564e-05,
+      "loss": 0.6812,
+      "mean_token_accuracy": 0.7463235318660736,
+      "num_tokens": 531990.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.39589442815249265,
+      "grad_norm": 0.8097174763679504,
+      "learning_rate": 7.888563049853373e-05,
+      "loss": 0.6651,
+      "mean_token_accuracy": 0.7468137264251709,
+      "num_tokens": 552470.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.41055718475073316,
+      "grad_norm": 0.7530633211135864,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 0.6511,
+      "mean_token_accuracy": 0.7538725554943084,
+      "num_tokens": 572950.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.4252199413489736,
+      "grad_norm": 0.660597562789917,
+      "learning_rate": 8.475073313782992e-05,
+      "loss": 0.6479,
+      "mean_token_accuracy": 0.7550000011920929,
+      "num_tokens": 593430.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.4398826979472141,
+      "grad_norm": 0.6961861252784729,
+      "learning_rate": 8.7683284457478e-05,
+      "loss": 0.6587,
+      "mean_token_accuracy": 0.749117660522461,
+      "num_tokens": 613910.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.924081027507782,
+      "learning_rate": 9.06158357771261e-05,
+      "loss": 0.6482,
+      "mean_token_accuracy": 0.7544108033180237,
+      "num_tokens": 634176.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.46920821114369504,
+      "grad_norm": 0.7237821221351624,
+      "learning_rate": 9.35483870967742e-05,
+      "loss": 0.6547,
+      "mean_token_accuracy": 0.7502941012382507,
+      "num_tokens": 654656.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.4838709677419355,
+      "grad_norm": 0.809219479560852,
+      "learning_rate": 9.64809384164223e-05,
+      "loss": 0.6449,
+      "mean_token_accuracy": 0.7552451074123383,
+      "num_tokens": 675136.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.49853372434017595,
+      "grad_norm": 0.6265454888343811,
+      "learning_rate": 9.941348973607039e-05,
+      "loss": 0.6544,
+      "mean_token_accuracy": 0.7504901945590973,
+      "num_tokens": 695616.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5131964809384164,
+      "grad_norm": 0.690653920173645,
+      "learning_rate": 9.999962381348496e-05,
+      "loss": 0.638,
+      "mean_token_accuracy": 0.7574509859085083,
+      "num_tokens": 716096.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5278592375366569,
+      "grad_norm": 0.6082450151443481,
+      "learning_rate": 9.999809556546922e-05,
+      "loss": 0.6469,
+      "mean_token_accuracy": 0.7543627440929412,
+      "num_tokens": 736576.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5425219941348973,
+      "grad_norm": 0.6173468232154846,
+      "learning_rate": 9.999539178019954e-05,
+      "loss": 0.649,
+      "mean_token_accuracy": 0.7521512925624847,
+      "num_tokens": 756812.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5571847507331378,
+      "grad_norm": 0.6369903683662415,
+      "learning_rate": 9.999151252124639e-05,
+      "loss": 0.6501,
+      "mean_token_accuracy": 0.7515686333179474,
+      "num_tokens": 777292.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.5718475073313783,
+      "grad_norm": 0.5715249180793762,
+      "learning_rate": 9.998645787981749e-05,
+      "loss": 0.643,
+      "mean_token_accuracy": 0.7544650256633758,
+      "num_tokens": 797538.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.5865102639296188,
+      "grad_norm": 0.678391695022583,
+      "learning_rate": 9.998022797475572e-05,
+      "loss": 0.6496,
+      "mean_token_accuracy": 0.7516666650772095,
+      "num_tokens": 818018.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6011730205278593,
+      "grad_norm": 0.6235240697860718,
+      "learning_rate": 9.997282295253644e-05,
+      "loss": 0.633,
+      "mean_token_accuracy": 0.7596078515052795,
+      "num_tokens": 838498.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6158357771260997,
+      "grad_norm": 0.5357748866081238,
+      "learning_rate": 9.996424298726381e-05,
+      "loss": 0.6572,
+      "mean_token_accuracy": 0.7510294198989869,
+      "num_tokens": 858978.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.6304985337243402,
+      "grad_norm": 0.6643717288970947,
+      "learning_rate": 9.995448828066693e-05,
+      "loss": 0.6594,
+      "mean_token_accuracy": 0.7500980436801911,
+      "num_tokens": 879458.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.651352047920227,
+      "learning_rate": 9.994355906209492e-05,
+      "loss": 0.654,
+      "mean_token_accuracy": 0.7509803950786591,
+      "num_tokens": 899938.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6598240469208211,
+      "grad_norm": 0.6784325242042542,
+      "learning_rate": 9.993145558851168e-05,
+      "loss": 0.6487,
+      "mean_token_accuracy": 0.7501960813999176,
+      "num_tokens": 920418.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.6744868035190615,
+      "grad_norm": 0.5277068018913269,
+      "learning_rate": 9.991817814448967e-05,
+      "loss": 0.6376,
+      "mean_token_accuracy": 0.75563725233078,
+      "num_tokens": 940898.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.6891495601173021,
+      "grad_norm": 0.5870142579078674,
+      "learning_rate": 9.990372704220345e-05,
+      "loss": 0.6493,
+      "mean_token_accuracy": 0.7515686273574829,
+      "num_tokens": 961378.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7038123167155426,
+      "grad_norm": 0.5757046341896057,
+      "learning_rate": 9.988810262142209e-05,
+      "loss": 0.6502,
+      "mean_token_accuracy": 0.7527043879032135,
+      "num_tokens": 981824.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.718475073313783,
+      "grad_norm": 0.5332264304161072,
+      "learning_rate": 9.987130524950141e-05,
+      "loss": 0.6389,
+      "mean_token_accuracy": 0.7545588254928589,
+      "num_tokens": 1002304.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7331378299120235,
+      "grad_norm": 0.5763241052627563,
+      "learning_rate": 9.985333532137514e-05,
+      "loss": 0.6465,
+      "mean_token_accuracy": 0.7529901921749115,
+      "num_tokens": 1022784.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.7478005865102639,
+      "grad_norm": 0.6235876083374023,
+      "learning_rate": 9.983419325954577e-05,
+      "loss": 0.6391,
+      "mean_token_accuracy": 0.7525490164756775,
+      "num_tokens": 1043264.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.7624633431085044,
+      "grad_norm": 0.6091899275779724,
+      "learning_rate": 9.981387951407462e-05,
+      "loss": 0.6175,
+      "mean_token_accuracy": 0.761715692281723,
+      "num_tokens": 1063744.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.7771260997067448,
+      "grad_norm": 0.6009454131126404,
+      "learning_rate": 9.979239456257113e-05,
+      "loss": 0.6405,
+      "mean_token_accuracy": 0.7544117569923401,
+      "num_tokens": 1084224.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.7917888563049853,
+      "grad_norm": 0.6014620661735535,
+      "learning_rate": 9.976973891018175e-05,
+      "loss": 0.6338,
+      "mean_token_accuracy": 0.7550000011920929,
+      "num_tokens": 1104704.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8064516129032258,
+      "grad_norm": 0.7326117753982544,
+      "learning_rate": 9.974591308957808e-05,
+      "loss": 0.6616,
+      "mean_token_accuracy": 0.743921571969986,
+      "num_tokens": 1125184.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8211143695014663,
+      "grad_norm": 0.6346194744110107,
+      "learning_rate": 9.972091766094424e-05,
+      "loss": 0.6434,
+      "mean_token_accuracy": 0.752892154455185,
+      "num_tokens": 1145664.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8357771260997068,
+      "grad_norm": 0.5967418551445007,
+      "learning_rate": 9.969475321196373e-05,
+      "loss": 0.6385,
+      "mean_token_accuracy": 0.7556862711906434,
+      "num_tokens": 1166144.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8504398826979472,
+      "grad_norm": 0.545911431312561,
+      "learning_rate": 9.966742035780571e-05,
+      "loss": 0.6372,
+      "mean_token_accuracy": 0.7558333277702332,
+      "num_tokens": 1186624.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.8651026392961877,
+      "grad_norm": 0.5666757225990295,
+      "learning_rate": 9.963891974111042e-05,
+      "loss": 0.6404,
+      "mean_token_accuracy": 0.7540686249732971,
+      "num_tokens": 1207104.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.8797653958944281,
+      "grad_norm": 0.5760472416877747,
+      "learning_rate": 9.960925203197408e-05,
+      "loss": 0.6197,
+      "mean_token_accuracy": 0.7618935823440551,
+      "num_tokens": 1227561.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.8944281524926686,
+      "grad_norm": 0.5213801264762878,
+      "learning_rate": 9.957841792793326e-05,
+      "loss": 0.6406,
+      "mean_token_accuracy": 0.7563725531101226,
+      "num_tokens": 1248041.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.5387865304946899,
+      "learning_rate": 9.95464181539483e-05,
+      "loss": 0.6299,
+      "mean_token_accuracy": 0.7593627452850342,
+      "num_tokens": 1268521.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9237536656891495,
+      "grad_norm": 0.5207778811454773,
+      "learning_rate": 9.951325346238638e-05,
+      "loss": 0.6469,
+      "mean_token_accuracy": 0.7524509727954865,
+      "num_tokens": 1289001.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9384164222873901,
+      "grad_norm": 0.6844761967658997,
+      "learning_rate": 9.947892463300381e-05,
+      "loss": 0.6348,
+      "mean_token_accuracy": 0.7599019587039948,
+      "num_tokens": 1309481.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.9530791788856305,
+      "grad_norm": 0.5045949816703796,
+      "learning_rate": 9.944343247292771e-05,
+      "loss": 0.6342,
+      "mean_token_accuracy": 0.7550490260124206,
+      "num_tokens": 1329961.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 0.585598886013031,
+      "learning_rate": 9.940677781663699e-05,
+      "loss": 0.649,
+      "mean_token_accuracy": 0.7502451062202453,
+      "num_tokens": 1350441.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.9824046920821115,
+      "grad_norm": 0.45848599076271057,
+      "learning_rate": 9.936896152594273e-05,
+      "loss": 0.6378,
+      "mean_token_accuracy": 0.7545588195323945,
+      "num_tokens": 1370921.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.9970674486803519,
+      "grad_norm": 0.45816901326179504,
+      "learning_rate": 9.932998448996798e-05,
+      "loss": 0.6306,
+      "mean_token_accuracy": 0.7586764633655548,
+      "num_tokens": 1391401.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.0117302052785924,
+      "grad_norm": 0.5341461300849915,
+      "learning_rate": 9.92898476251268e-05,
+      "loss": 0.6368,
+      "mean_token_accuracy": 0.7575490236282348,
+      "num_tokens": 1410089.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0263929618768328,
+      "grad_norm": 0.7225525379180908,
+      "learning_rate": 9.924855187510274e-05,
+      "loss": 0.6236,
+      "mean_token_accuracy": 0.7612254917621613,
+      "num_tokens": 1430569.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.0410557184750733,
+      "grad_norm": 0.5576125383377075,
+      "learning_rate": 9.920609821082662e-05,
+      "loss": 0.6137,
+      "mean_token_accuracy": 0.765588229894638,
+      "num_tokens": 1451049.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.0557184750733137,
+      "grad_norm": 0.6563458442687988,
+      "learning_rate": 9.916248763045375e-05,
+      "loss": 0.6239,
+      "mean_token_accuracy": 0.7614491164684296,
+      "num_tokens": 1471384.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.0703812316715542,
+      "grad_norm": 0.5540904998779297,
+      "learning_rate": 9.911772115934042e-05,
+      "loss": 0.6226,
+      "mean_token_accuracy": 0.7628921687602996,
+      "num_tokens": 1491864.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.0850439882697946,
+      "grad_norm": 0.5026265978813171,
+      "learning_rate": 9.907179985001978e-05,
+      "loss": 0.6363,
+      "mean_token_accuracy": 0.7549781084060669,
+      "num_tokens": 1512184.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.099706744868035,
+      "grad_norm": 0.716999351978302,
+      "learning_rate": 9.90247247821772e-05,
+      "loss": 0.6303,
+      "mean_token_accuracy": 0.7568627417087554,
+      "num_tokens": 1532664.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1143695014662756,
+      "grad_norm": 0.4981926381587982,
+      "learning_rate": 9.897649706262473e-05,
+      "loss": 0.619,
+      "mean_token_accuracy": 0.763382351398468,
+      "num_tokens": 1553144.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.129032258064516,
+      "grad_norm": 0.5225701332092285,
+      "learning_rate": 9.892711782527517e-05,
+      "loss": 0.6233,
+      "mean_token_accuracy": 0.761715692281723,
+      "num_tokens": 1573624.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.1436950146627567,
+      "grad_norm": 0.5625816583633423,
+      "learning_rate": 9.887658823111544e-05,
+      "loss": 0.6232,
+      "mean_token_accuracy": 0.7573675394058228,
+      "num_tokens": 1594029.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.1583577712609971,
+      "grad_norm": 0.511184811592102,
+      "learning_rate": 9.882490946817915e-05,
+      "loss": 0.6303,
+      "mean_token_accuracy": 0.7567156851291656,
+      "num_tokens": 1614509.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.1730205278592376,
+      "grad_norm": 0.5488473773002625,
+      "learning_rate": 9.877208275151884e-05,
+      "loss": 0.6185,
+      "mean_token_accuracy": 0.7622549057006835,
+      "num_tokens": 1634989.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.187683284457478,
+      "grad_norm": 0.5918490290641785,
+      "learning_rate": 9.871810932317726e-05,
+      "loss": 0.6175,
+      "mean_token_accuracy": 0.7629630208015442,
+      "num_tokens": 1655225.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2023460410557185,
+      "grad_norm": 0.7483125329017639,
+      "learning_rate": 9.866299045215826e-05,
+      "loss": 0.6203,
+      "mean_token_accuracy": 0.7614705920219421,
+      "num_tokens": 1675705.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.217008797653959,
+      "grad_norm": 0.5696433782577515,
+      "learning_rate": 9.860672743439695e-05,
+      "loss": 0.628,
+      "mean_token_accuracy": 0.7564215719699859,
+      "num_tokens": 1696185.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2316715542521994,
+      "grad_norm": 0.5894884467124939,
+      "learning_rate": 9.854932159272917e-05,
+      "loss": 0.6293,
+      "mean_token_accuracy": 0.7585468471050263,
+      "num_tokens": 1716642.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.2463343108504399,
+      "grad_norm": 0.4901694357395172,
+      "learning_rate": 9.849077427686041e-05,
+      "loss": 0.6139,
+      "mean_token_accuracy": 0.7617156863212585,
+      "num_tokens": 1737122.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.2609970674486803,
+      "grad_norm": 0.5675632357597351,
+      "learning_rate": 9.843108686333417e-05,
+      "loss": 0.6277,
+      "mean_token_accuracy": 0.7617647051811218,
+      "num_tokens": 1757602.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.2756598240469208,
+      "grad_norm": 0.48929065465927124,
+      "learning_rate": 9.837026075549945e-05,
+      "loss": 0.6055,
+      "mean_token_accuracy": 0.7684804022312164,
+      "num_tokens": 1778082.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.5677883625030518,
+      "learning_rate": 9.830829738347782e-05,
+      "loss": 0.6291,
+      "mean_token_accuracy": 0.7578431308269501,
+      "num_tokens": 1798562.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.3049853372434017,
+      "grad_norm": 0.5752457976341248,
+      "learning_rate": 9.82451982041298e-05,
+      "loss": 0.6298,
+      "mean_token_accuracy": 0.7572548925876618,
+      "num_tokens": 1819042.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3196480938416422,
+      "grad_norm": 0.579814612865448,
+      "learning_rate": 9.818096470102067e-05,
+      "loss": 0.613,
+      "mean_token_accuracy": 0.7657352924346924,
+      "num_tokens": 1839522.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.3343108504398826,
+      "grad_norm": 0.5723453164100647,
+      "learning_rate": 9.811559838438542e-05,
+      "loss": 0.6075,
+      "mean_token_accuracy": 0.7673529386520386,
+      "num_tokens": 1860002.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.3489736070381233,
+      "grad_norm": 0.5011471509933472,
+      "learning_rate": 9.804910079109342e-05,
+      "loss": 0.6356,
+      "mean_token_accuracy": 0.7558823525905609,
+      "num_tokens": 1880482.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.5844294428825378,
+      "learning_rate": 9.798147348461218e-05,
+      "loss": 0.6251,
+      "mean_token_accuracy": 0.7588725566864014,
+      "num_tokens": 1900962.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.3782991202346042,
+      "grad_norm": 0.6461315751075745,
+      "learning_rate": 9.791271805497062e-05,
+      "loss": 0.619,
+      "mean_token_accuracy": 0.7632353007793427,
+      "num_tokens": 1921442.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.3929618768328447,
+      "grad_norm": 0.560377836227417,
+      "learning_rate": 9.784283611872169e-05,
+      "loss": 0.6265,
+      "mean_token_accuracy": 0.757421898841858,
+      "num_tokens": 1941888.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4076246334310851,
+      "grad_norm": 0.6241864562034607,
+      "learning_rate": 9.777182931890438e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7597058832645416,
+      "num_tokens": 1962368.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4222873900293256,
+      "grad_norm": 0.5094092488288879,
+      "learning_rate": 9.769969932500502e-05,
+      "loss": 0.6318,
+      "mean_token_accuracy": 0.7576960861682892,
+      "num_tokens": 1982848.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.436950146627566,
+      "grad_norm": 0.5033220052719116,
+      "learning_rate": 9.762644783291812e-05,
+      "loss": 0.6245,
+      "mean_token_accuracy": 0.7599019527435302,
+      "num_tokens": 2003328.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.4516129032258065,
+      "grad_norm": 0.4806479513645172,
+      "learning_rate": 9.755207656490644e-05,
+      "loss": 0.639,
+      "mean_token_accuracy": 0.7538235366344452,
+      "num_tokens": 2023808.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.466275659824047,
+      "grad_norm": 0.5395609140396118,
+      "learning_rate": 9.747658726956048e-05,
+      "loss": 0.6099,
+      "mean_token_accuracy": 0.7634313702583313,
+      "num_tokens": 2044288.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4809384164222874,
+      "grad_norm": 0.5191217660903931,
+      "learning_rate": 9.739998172175744e-05,
+      "loss": 0.605,
+      "mean_token_accuracy": 0.7667647123336792,
+      "num_tokens": 2064768.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.4956011730205279,
+      "grad_norm": 0.49461233615875244,
+      "learning_rate": 9.732226172261943e-05,
+      "loss": 0.6123,
+      "mean_token_accuracy": 0.7655392289161682,
+      "num_tokens": 2085248.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5102639296187683,
+      "grad_norm": 0.5261324048042297,
+      "learning_rate": 9.724342909947114e-05,
+      "loss": 0.6049,
+      "mean_token_accuracy": 0.7624019622802735,
+      "num_tokens": 2105728.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.5249266862170088,
+      "grad_norm": 0.5409830212593079,
+      "learning_rate": 9.716348570579686e-05,
+      "loss": 0.6377,
+      "mean_token_accuracy": 0.7593627452850342,
+      "num_tokens": 2126208.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.5395894428152492,
+      "grad_norm": 0.5728979110717773,
+      "learning_rate": 9.708243342119695e-05,
+      "loss": 0.6054,
+      "mean_token_accuracy": 0.7661274492740631,
+      "num_tokens": 2146688.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.5542521994134897,
+      "grad_norm": 0.5928049683570862,
+      "learning_rate": 9.700027415134358e-05,
+      "loss": 0.6112,
+      "mean_token_accuracy": 0.7631862699985504,
+      "num_tokens": 2167168.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.5689149560117301,
+      "grad_norm": 0.6045894622802734,
+      "learning_rate": 9.691700982793597e-05,
+      "loss": 0.6244,
+      "mean_token_accuracy": 0.7585741996765136,
+      "num_tokens": 2187627.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.5835777126099706,
+      "grad_norm": 0.5053999423980713,
+      "learning_rate": 9.6832642408655e-05,
+      "loss": 0.6094,
+      "mean_token_accuracy": 0.7675980389118194,
+      "num_tokens": 2208107.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.598240469208211,
+      "grad_norm": 0.5727707743644714,
+      "learning_rate": 9.674717387711706e-05,
+      "loss": 0.6263,
+      "mean_token_accuracy": 0.7594117760658264,
+      "num_tokens": 2228587.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 0.5962901711463928,
+      "learning_rate": 9.66606062428276e-05,
+      "loss": 0.6051,
+      "mean_token_accuracy": 0.7674056112766265,
+      "num_tokens": 2248853.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.627565982404692,
+      "grad_norm": 0.5810521245002747,
+      "learning_rate": 9.657294154113368e-05,
+      "loss": 0.6186,
+      "mean_token_accuracy": 0.7595588266849518,
+      "num_tokens": 2269333.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.6422287390029324,
+      "grad_norm": 0.5142710208892822,
+      "learning_rate": 9.648418183317629e-05,
+      "loss": 0.6201,
+      "mean_token_accuracy": 0.7632353007793427,
+      "num_tokens": 2289813.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.6568914956011729,
+      "grad_norm": 0.5239130854606628,
+      "learning_rate": 9.639432920584177e-05,
+      "loss": 0.625,
+      "mean_token_accuracy": 0.7592156827449799,
+      "num_tokens": 2310293.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.6715542521994133,
+      "grad_norm": 0.5248172283172607,
+      "learning_rate": 9.630338577171282e-05,
+      "loss": 0.6347,
+      "mean_token_accuracy": 0.7565686285495759,
+      "num_tokens": 2330773.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.6862170087976538,
+      "grad_norm": 0.6786187887191772,
+      "learning_rate": 9.621135366901874e-05,
+      "loss": 0.626,
+      "mean_token_accuracy": 0.7596078336238861,
+      "num_tokens": 2351253.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7008797653958945,
+      "grad_norm": 0.5295122861862183,
+      "learning_rate": 9.61182350615853e-05,
+      "loss": 0.616,
+      "mean_token_accuracy": 0.7638725519180298,
+      "num_tokens": 2371733.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.715542521994135,
+      "grad_norm": 0.5179807543754578,
+      "learning_rate": 9.60240321387837e-05,
+      "loss": 0.6311,
+      "mean_token_accuracy": 0.756617647409439,
+      "num_tokens": 2392213.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.7302052785923754,
+      "grad_norm": 0.5839389562606812,
+      "learning_rate": 9.592874711547922e-05,
+      "loss": 0.6063,
+      "mean_token_accuracy": 0.765490198135376,
+      "num_tokens": 2412693.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.7448680351906158,
+      "grad_norm": 0.577913761138916,
+      "learning_rate": 9.583238223197906e-05,
+      "loss": 0.6313,
+      "mean_token_accuracy": 0.7565686345100403,
+      "num_tokens": 2433173.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.7595307917888563,
+      "grad_norm": 0.6578575372695923,
+      "learning_rate": 9.573493975397975e-05,
+      "loss": 0.6145,
+      "mean_token_accuracy": 0.7614705860614777,
+      "num_tokens": 2453653.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7741935483870968,
+      "grad_norm": 0.49838587641716003,
+      "learning_rate": 9.56364219725138e-05,
+      "loss": 0.6033,
+      "mean_token_accuracy": 0.7695098042488098,
+      "num_tokens": 2474133.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.7888563049853372,
+      "grad_norm": 0.48799875378608704,
+      "learning_rate": 9.553683120389592e-05,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.764902925491333,
+      "num_tokens": 2494524.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8035190615835777,
+      "grad_norm": 0.5147119164466858,
+      "learning_rate": 9.543616978966842e-05,
+      "loss": 0.6206,
+      "mean_token_accuracy": 0.761617648601532,
+      "num_tokens": 2515004.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.5641414523124695,
+      "learning_rate": 9.53344400965463e-05,
+      "loss": 0.6251,
+      "mean_token_accuracy": 0.7585784316062927,
+      "num_tokens": 2535484.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.8328445747800588,
+      "grad_norm": 0.520799994468689,
+      "learning_rate": 9.523164451636157e-05,
+      "loss": 0.6356,
+      "mean_token_accuracy": 0.7528921604156494,
+      "num_tokens": 2555964.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.8475073313782993,
+      "grad_norm": 0.45843806862831116,
+      "learning_rate": 9.512778546600696e-05,
+      "loss": 0.622,
+      "mean_token_accuracy": 0.7602451145648956,
+      "num_tokens": 2576444.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.8621700879765397,
+      "grad_norm": 0.5162474513053894,
+      "learning_rate": 9.50228653873791e-05,
+      "loss": 0.6065,
+      "mean_token_accuracy": 0.7668967843055725,
+      "num_tokens": 2596690.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.8768328445747802,
+      "grad_norm": 0.5157609581947327,
+      "learning_rate": 9.491688674732123e-05,
+      "loss": 0.5972,
+      "mean_token_accuracy": 0.7700980484485627,
+      "num_tokens": 2617170.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.8914956011730206,
+      "grad_norm": 0.6079277396202087,
+      "learning_rate": 9.480985203756501e-05,
+      "loss": 0.6334,
+      "mean_token_accuracy": 0.7560294091701507,
+      "num_tokens": 2637650.0,
+      "step": 1290
+    },
+    {
+      "epoch": 1.906158357771261,
+      "grad_norm": 0.5813050270080566,
+      "learning_rate": 9.470176377467206e-05,
+      "loss": 0.6206,
+      "mean_token_accuracy": 0.7631862759590149,
+      "num_tokens": 2658130.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.9208211143695015,
+      "grad_norm": 0.6724423170089722,
+      "learning_rate": 9.45926244999748e-05,
+      "loss": 0.6218,
+      "mean_token_accuracy": 0.7615686237812043,
+      "num_tokens": 2678610.0,
+      "step": 1310
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 0.5010402798652649,
+      "learning_rate": 9.44824367795166e-05,
+      "loss": 0.6077,
+      "mean_token_accuracy": 0.7619117617607116,
+      "num_tokens": 2699090.0,
+      "step": 1320
+    },
+    {
+      "epoch": 1.9501466275659824,
+      "grad_norm": 0.45624953508377075,
+      "learning_rate": 9.437120320399158e-05,
+      "loss": 0.6154,
+      "mean_token_accuracy": 0.7637745201587677,
+      "num_tokens": 2719570.0,
+      "step": 1330
+    },
+    {
+      "epoch": 1.964809384164223,
+      "grad_norm": 0.5894467830657959,
+      "learning_rate": 9.425892638868356e-05,
+      "loss": 0.6061,
+      "mean_token_accuracy": 0.7665196061134338,
+      "num_tokens": 2740050.0,
+      "step": 1340
+    },
+    {
+      "epoch": 1.9794721407624634,
+      "grad_norm": 0.4616512656211853,
+      "learning_rate": 9.414560897340468e-05,
+      "loss": 0.6355,
+      "mean_token_accuracy": 0.7558333337306976,
+      "num_tokens": 2760530.0,
+      "step": 1350
+    },
+    {
+      "epoch": 1.9941348973607038,
+      "grad_norm": 0.5391420125961304,
+      "learning_rate": 9.403125362243328e-05,
+      "loss": 0.6169,
+      "mean_token_accuracy": 0.7617647111415863,
+      "num_tokens": 2781010.0,
+      "step": 1360
+    },
+    {
+      "epoch": 2.0087976539589443,
+      "grad_norm": 0.705719530582428,
+      "learning_rate": 9.39158630244513e-05,
+      "loss": 0.6214,
+      "mean_token_accuracy": 0.7583823561668396,
+      "num_tokens": 2799698.0,
+      "step": 1370
+    },
+    {
+      "epoch": 2.0234604105571847,
+      "grad_norm": 0.6386483311653137,
+      "learning_rate": 9.379943989248096e-05,
+      "loss": 0.5938,
+      "mean_token_accuracy": 0.7719317078590393,
+      "num_tokens": 2820144.0,
+      "step": 1380
+    },
+    {
+      "epoch": 2.038123167155425,
+      "grad_norm": 0.6188822388648987,
+      "learning_rate": 9.368198696382115e-05,
+      "loss": 0.5943,
+      "mean_token_accuracy": 0.7689215660095214,
+      "num_tokens": 2840624.0,
+      "step": 1390
+    },
+    {
+      "epoch": 2.0527859237536656,
+      "grad_norm": 0.5979672074317932,
+      "learning_rate": 9.356350699998288e-05,
+      "loss": 0.5803,
+      "mean_token_accuracy": 0.7749509871006012,
+      "num_tokens": 2861104.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.067448680351906,
+      "grad_norm": 0.6713985204696655,
+      "learning_rate": 9.344400278662448e-05,
+      "loss": 0.5903,
+      "mean_token_accuracy": 0.7725980401039123,
+      "num_tokens": 2881584.0,
+      "step": 1410
+    },
+    {
+      "epoch": 2.0821114369501466,
+      "grad_norm": 0.7570429444313049,
+      "learning_rate": 9.332347713348608e-05,
+      "loss": 0.5889,
+      "mean_token_accuracy": 0.7715686380863189,
+      "num_tokens": 2902064.0,
+      "step": 1420
+    },
+    {
+      "epoch": 2.096774193548387,
+      "grad_norm": 0.6166312098503113,
+      "learning_rate": 9.320193287432353e-05,
+      "loss": 0.5843,
+      "mean_token_accuracy": 0.7747058868408203,
+      "num_tokens": 2922544.0,
+      "step": 1430
+    },
+    {
+      "epoch": 2.1114369501466275,
+      "grad_norm": 0.6174513101577759,
+      "learning_rate": 9.307937286684173e-05,
+      "loss": 0.5931,
+      "mean_token_accuracy": 0.7726470589637756,
+      "num_tokens": 2943024.0,
+      "step": 1440
+    },
+    {
+      "epoch": 2.126099706744868,
+      "grad_norm": 0.5643057227134705,
+      "learning_rate": 9.295579999262756e-05,
+      "loss": 0.6074,
+      "mean_token_accuracy": 0.7670098125934601,
+      "num_tokens": 2963504.0,
+      "step": 1450
+    },
+    {
+      "epoch": 2.1407624633431084,
+      "grad_norm": 0.5920215249061584,
+      "learning_rate": 9.283121715708202e-05,
+      "loss": 0.5974,
+      "mean_token_accuracy": 0.7697058737277984,
+      "num_tokens": 2983984.0,
+      "step": 1460
+    },
+    {
+      "epoch": 2.155425219941349,
+      "grad_norm": 0.6717423796653748,
+      "learning_rate": 9.270562728935197e-05,
+      "loss": 0.5829,
+      "mean_token_accuracy": 0.7775569915771484,
+      "num_tokens": 3004220.0,
+      "step": 1470
+    },
+    {
+      "epoch": 2.1700879765395893,
+      "grad_norm": 0.5588908791542053,
+      "learning_rate": 9.257903334226124e-05,
+      "loss": 0.6012,
+      "mean_token_accuracy": 0.7698039233684539,
+      "num_tokens": 3024700.0,
+      "step": 1480
+    },
+    {
+      "epoch": 2.1847507331378297,
+      "grad_norm": 0.6039055585861206,
+      "learning_rate": 9.24514382922412e-05,
+      "loss": 0.5958,
+      "mean_token_accuracy": 0.7707352995872497,
+      "num_tokens": 3045180.0,
+      "step": 1490
+    },
+    {
+      "epoch": 2.19941348973607,
+      "grad_norm": 0.8095436692237854,
+      "learning_rate": 9.232284513926085e-05,
+      "loss": 0.5761,
+      "mean_token_accuracy": 0.7764215707778931,
+      "num_tokens": 3065660.0,
+      "step": 1500
+    },
+    {
+      "epoch": 2.2140762463343107,
+      "grad_norm": 0.6638913154602051,
+      "learning_rate": 9.219325690675615e-05,
+      "loss": 0.5903,
+      "mean_token_accuracy": 0.7721568584442139,
+      "num_tokens": 3086140.0,
+      "step": 1510
+    },
+    {
+      "epoch": 2.228739002932551,
+      "grad_norm": 0.6669881939888,
+      "learning_rate": 9.206267664155907e-05,
+      "loss": 0.6103,
+      "mean_token_accuracy": 0.7656372547149658,
+      "num_tokens": 3106620.0,
+      "step": 1520
+    },
+    {
+      "epoch": 2.2434017595307916,
+      "grad_norm": 0.8208006620407104,
+      "learning_rate": 9.193110741382585e-05,
+      "loss": 0.5946,
+      "mean_token_accuracy": 0.7709803879261017,
+      "num_tokens": 3127100.0,
+      "step": 1530
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 0.7447239756584167,
+      "learning_rate": 9.179855231696491e-05,
+      "loss": 0.5982,
+      "mean_token_accuracy": 0.7691666722297669,
+      "num_tokens": 3147580.0,
+      "step": 1540
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.5061095356941223,
+      "learning_rate": 9.166501446756405e-05,
+      "loss": 0.5993,
+      "mean_token_accuracy": 0.7696078479290008,
+      "num_tokens": 3168060.0,
+      "step": 1550
+    },
+    {
+      "epoch": 2.2873900293255134,
+      "grad_norm": 0.7621920704841614,
+      "learning_rate": 9.153049700531718e-05,
+      "loss": 0.5849,
+      "mean_token_accuracy": 0.7756862759590148,
+      "num_tokens": 3188540.0,
+      "step": 1560
+    },
+    {
+      "epoch": 2.302052785923754,
+      "grad_norm": 0.6623703837394714,
+      "learning_rate": 9.139500309295053e-05,
+      "loss": 0.5867,
+      "mean_token_accuracy": 0.7735294103622437,
+      "num_tokens": 3209020.0,
+      "step": 1570
+    },
+    {
+      "epoch": 2.3167155425219943,
+      "grad_norm": 0.6104727387428284,
+      "learning_rate": 9.125853591614828e-05,
+      "loss": 0.6113,
+      "mean_token_accuracy": 0.765147066116333,
+      "num_tokens": 3229500.0,
+      "step": 1580
+    },
+    {
+      "epoch": 2.3313782991202348,
+      "grad_norm": 0.7286109924316406,
+      "learning_rate": 9.112109868347763e-05,
+      "loss": 0.5994,
+      "mean_token_accuracy": 0.7715686142444611,
+      "num_tokens": 3249980.0,
+      "step": 1590
+    },
+    {
+      "epoch": 2.346041055718475,
+      "grad_norm": 0.6333359479904175,
+      "learning_rate": 9.098269462631341e-05,
+      "loss": 0.6052,
+      "mean_token_accuracy": 0.7670098125934601,
+      "num_tokens": 3270460.0,
+      "step": 1600
+    },
+    {
+      "epoch": 2.3607038123167157,
+      "grad_norm": 0.5577898621559143,
+      "learning_rate": 9.084332699876208e-05,
+      "loss": 0.6007,
+      "mean_token_accuracy": 0.7678921639919281,
+      "num_tokens": 3290940.0,
+      "step": 1610
+    },
+    {
+      "epoch": 2.375366568914956,
+      "grad_norm": 0.6581786870956421,
+      "learning_rate": 9.07029990775852e-05,
+      "loss": 0.596,
+      "mean_token_accuracy": 0.7687745034694672,
+      "num_tokens": 3311420.0,
+      "step": 1620
+    },
+    {
+      "epoch": 2.3900293255131966,
+      "grad_norm": 0.7705698013305664,
+      "learning_rate": 9.056171416212243e-05,
+      "loss": 0.5902,
+      "mean_token_accuracy": 0.7741009593009949,
+      "num_tokens": 3331595.0,
+      "step": 1630
+    },
+    {
+      "epoch": 2.404692082111437,
+      "grad_norm": 0.5370859503746033,
+      "learning_rate": 9.041947557421391e-05,
+      "loss": 0.5994,
+      "mean_token_accuracy": 0.768921560049057,
+      "num_tokens": 3352075.0,
+      "step": 1640
+    },
+    {
+      "epoch": 2.4193548387096775,
+      "grad_norm": 0.6219416856765747,
+      "learning_rate": 9.02762866581222e-05,
+      "loss": 0.5898,
+      "mean_token_accuracy": 0.7736274540424347,
+      "num_tokens": 3372555.0,
+      "step": 1650
+    },
+    {
+      "epoch": 2.434017595307918,
+      "grad_norm": 0.6901549100875854,
+      "learning_rate": 9.013215078045363e-05,
+      "loss": 0.5848,
+      "mean_token_accuracy": 0.7751470625400543,
+      "num_tokens": 3393035.0,
+      "step": 1660
+    },
+    {
+      "epoch": 2.4486803519061584,
+      "grad_norm": 0.6291585564613342,
+      "learning_rate": 8.998707133007918e-05,
+      "loss": 0.5884,
+      "mean_token_accuracy": 0.7722058892250061,
+      "num_tokens": 3413515.0,
+      "step": 1670
+    },
+    {
+      "epoch": 2.463343108504399,
+      "grad_norm": 0.7224541306495667,
+      "learning_rate": 8.984105171805472e-05,
+      "loss": 0.5911,
+      "mean_token_accuracy": 0.7755882441997528,
+      "num_tokens": 3433995.0,
+      "step": 1680
+    },
+    {
+      "epoch": 2.4780058651026393,
+      "grad_norm": 0.7153178453445435,
+      "learning_rate": 8.969409537754092e-05,
+      "loss": 0.5805,
+      "mean_token_accuracy": 0.7749509990215302,
+      "num_tokens": 3454475.0,
+      "step": 1690
+    },
+    {
+      "epoch": 2.4926686217008798,
+      "grad_norm": 0.6772195100784302,
+      "learning_rate": 8.95462057637224e-05,
+      "loss": 0.5894,
+      "mean_token_accuracy": 0.7743137359619141,
+      "num_tokens": 3474955.0,
+      "step": 1700
+    },
+    {
+      "epoch": 2.5073313782991202,
+      "grad_norm": 0.7709519267082214,
+      "learning_rate": 8.939738635372664e-05,
+      "loss": 0.5908,
+      "mean_token_accuracy": 0.7723039329051972,
+      "num_tokens": 3495435.0,
+      "step": 1710
+    },
+    {
+      "epoch": 2.5219941348973607,
+      "grad_norm": 0.6761429905891418,
+      "learning_rate": 8.924764064654212e-05,
+      "loss": 0.6223,
+      "mean_token_accuracy": 0.761617648601532,
+      "num_tokens": 3515915.0,
+      "step": 1720
+    },
+    {
+      "epoch": 2.536656891495601,
+      "grad_norm": 0.5991116166114807,
+      "learning_rate": 8.909697216293609e-05,
+      "loss": 0.5899,
+      "mean_token_accuracy": 0.7736764788627625,
+      "num_tokens": 3536395.0,
+      "step": 1730
+    },
+    {
+      "epoch": 2.5513196480938416,
+      "grad_norm": 0.7265383005142212,
+      "learning_rate": 8.894538444537177e-05,
+      "loss": 0.5966,
+      "mean_token_accuracy": 0.7698986232280731,
+      "num_tokens": 3556786.0,
+      "step": 1740
+    },
+    {
+      "epoch": 2.565982404692082,
+      "grad_norm": 0.7882624268531799,
+      "learning_rate": 8.87928810579251e-05,
+      "loss": 0.5898,
+      "mean_token_accuracy": 0.7731645762920379,
+      "num_tokens": 3577191.0,
+      "step": 1750
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 0.657804548740387,
+      "learning_rate": 8.863946558620094e-05,
+      "loss": 0.5928,
+      "mean_token_accuracy": 0.7701545894145966,
+      "num_tokens": 3597648.0,
+      "step": 1760
+    },
+    {
+      "epoch": 2.595307917888563,
+      "grad_norm": 0.6528093814849854,
+      "learning_rate": 8.84851416372487e-05,
+      "loss": 0.5988,
+      "mean_token_accuracy": 0.7719607830047608,
+      "num_tokens": 3618128.0,
+      "step": 1770
+    },
+    {
+      "epoch": 2.6099706744868034,
+      "grad_norm": 0.7075777649879456,
+      "learning_rate": 8.832991283947762e-05,
+      "loss": 0.5846,
+      "mean_token_accuracy": 0.7754901945590973,
+      "num_tokens": 3638608.0,
+      "step": 1780
+    },
+    {
+      "epoch": 2.624633431085044,
+      "grad_norm": 0.581615686416626,
+      "learning_rate": 8.81737828425714e-05,
+      "loss": 0.5878,
+      "mean_token_accuracy": 0.7726470470428467,
+      "num_tokens": 3659088.0,
+      "step": 1790
+    },
+    {
+      "epoch": 2.6392961876832843,
+      "grad_norm": 0.6932193636894226,
+      "learning_rate": 8.80167553174024e-05,
+      "loss": 0.6062,
+      "mean_token_accuracy": 0.7654902040958405,
+      "num_tokens": 3679568.0,
+      "step": 1800
+    },
+    {
+      "epoch": 2.653958944281525,
+      "grad_norm": 0.6022186875343323,
+      "learning_rate": 8.785883395594541e-05,
+      "loss": 0.5876,
+      "mean_token_accuracy": 0.7725980460643769,
+      "num_tokens": 3700048.0,
+      "step": 1810
+    },
+    {
+      "epoch": 2.6686217008797652,
+      "grad_norm": 0.8625696897506714,
+      "learning_rate": 8.770002247119064e-05,
+      "loss": 0.6065,
+      "mean_token_accuracy": 0.7678162634372712,
+      "num_tokens": 3720294.0,
+      "step": 1820
+    },
+    {
+      "epoch": 2.6832844574780057,
+      "grad_norm": 0.8375098705291748,
+      "learning_rate": 8.754032459705672e-05,
+      "loss": 0.6033,
+      "mean_token_accuracy": 0.7681929707527161,
+      "num_tokens": 3740560.0,
+      "step": 1830
+    },
+    {
+      "epoch": 2.6979472140762466,
+      "grad_norm": 0.6922727823257446,
+      "learning_rate": 8.737974408830263e-05,
+      "loss": 0.582,
+      "mean_token_accuracy": 0.7738213419914246,
+      "num_tokens": 3761019.0,
+      "step": 1840
+    },
+    {
+      "epoch": 2.712609970674487,
+      "grad_norm": 0.6475608348846436,
+      "learning_rate": 8.721828472043958e-05,
+      "loss": 0.5846,
+      "mean_token_accuracy": 0.7751960813999176,
+      "num_tokens": 3781499.0,
+      "step": 1850
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.6575704216957092,
+      "learning_rate": 8.705595028964222e-05,
+      "loss": 0.5858,
+      "mean_token_accuracy": 0.7764705955982208,
+      "num_tokens": 3801979.0,
+      "step": 1860
+    },
+    {
+      "epoch": 2.741935483870968,
+      "grad_norm": 0.6429558396339417,
+      "learning_rate": 8.689274461265935e-05,
+      "loss": 0.6056,
+      "mean_token_accuracy": 0.7670588254928589,
+      "num_tokens": 3822459.0,
+      "step": 1870
+    },
+    {
+      "epoch": 2.7565982404692084,
+      "grad_norm": 0.6039347052574158,
+      "learning_rate": 8.672867152672416e-05,
+      "loss": 0.622,
+      "mean_token_accuracy": 0.7584313750267029,
+      "num_tokens": 3842939.0,
+      "step": 1880
+    },
+    {
+      "epoch": 2.771260997067449,
+      "grad_norm": 0.6779440641403198,
+      "learning_rate": 8.656373488946409e-05,
+      "loss": 0.6011,
+      "mean_token_accuracy": 0.7695097923278809,
+      "num_tokens": 3863419.0,
+      "step": 1890
+    },
+    {
+      "epoch": 2.7859237536656893,
+      "grad_norm": 0.6504889726638794,
+      "learning_rate": 8.639793857881011e-05,
+      "loss": 0.5816,
+      "mean_token_accuracy": 0.7756372570991517,
+      "num_tokens": 3883899.0,
+      "step": 1900
+    },
+    {
+      "epoch": 2.80058651026393,
+      "grad_norm": 0.6093726754188538,
+      "learning_rate": 8.623128649290544e-05,
+      "loss": 0.6111,
+      "mean_token_accuracy": 0.7643137216567993,
+      "num_tokens": 3904379.0,
+      "step": 1910
+    },
+    {
+      "epoch": 2.8152492668621703,
+      "grad_norm": 0.6347564458847046,
+      "learning_rate": 8.606378255001408e-05,
+      "loss": 0.5897,
+      "mean_token_accuracy": 0.7719607889652252,
+      "num_tokens": 3924859.0,
+      "step": 1920
+    },
+    {
+      "epoch": 2.8299120234604107,
+      "grad_norm": 0.6521418690681458,
+      "learning_rate": 8.58954306884285e-05,
+      "loss": 0.5948,
+      "mean_token_accuracy": 0.7706372559070587,
+      "num_tokens": 3945339.0,
+      "step": 1930
+    },
+    {
+      "epoch": 2.844574780058651,
+      "grad_norm": 0.55730140209198,
+      "learning_rate": 8.572623486637719e-05,
+      "loss": 0.5945,
+      "mean_token_accuracy": 0.7713235318660736,
+      "num_tokens": 3965819.0,
+      "step": 1940
+    },
+    {
+      "epoch": 2.8592375366568916,
+      "grad_norm": 0.7235424518585205,
+      "learning_rate": 8.555619906193147e-05,
+      "loss": 0.6023,
+      "mean_token_accuracy": 0.7676470577716827,
+      "num_tokens": 3986299.0,
+      "step": 1950
+    },
+    {
+      "epoch": 2.873900293255132,
+      "grad_norm": 0.8976076245307922,
+      "learning_rate": 8.538532727291211e-05,
+      "loss": 0.5887,
+      "mean_token_accuracy": 0.7734313786029816,
+      "num_tokens": 4006779.0,
+      "step": 1960
+    },
+    {
+      "epoch": 2.8885630498533725,
+      "grad_norm": 0.49708253145217896,
+      "learning_rate": 8.521362351679517e-05,
+      "loss": 0.5842,
+      "mean_token_accuracy": 0.7723039209842681,
+      "num_tokens": 4027259.0,
+      "step": 1970
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 0.7013171315193176,
+      "learning_rate": 8.504109183061768e-05,
+      "loss": 0.5676,
+      "mean_token_accuracy": 0.7804902017116546,
+      "num_tokens": 4047739.0,
+      "step": 1980
+    },
+    {
+      "epoch": 2.9178885630498534,
+      "grad_norm": 0.687017023563385,
+      "learning_rate": 8.486773627088263e-05,
+      "loss": 0.5997,
+      "mean_token_accuracy": 0.7691176414489747,
+      "num_tokens": 4068219.0,
+      "step": 1990
+    },
+    {
+      "epoch": 2.932551319648094,
+      "grad_norm": 0.6752710342407227,
+      "learning_rate": 8.469356091346361e-05,
+      "loss": 0.6194,
+      "mean_token_accuracy": 0.7596078395843506,
+      "num_tokens": 4088699.0,
+      "step": 2000
+    },
+    {
+      "epoch": 2.9472140762463344,
+      "grad_norm": 0.5824620723724365,
+      "learning_rate": 8.451856985350906e-05,
+      "loss": 0.5815,
+      "mean_token_accuracy": 0.7760294139385223,
+      "num_tokens": 4109179.0,
+      "step": 2010
+    },
+    {
+      "epoch": 2.961876832844575,
+      "grad_norm": 0.6335878968238831,
+      "learning_rate": 8.434276720534588e-05,
+      "loss": 0.5657,
+      "mean_token_accuracy": 0.7812745153903962,
+      "num_tokens": 4129659.0,
+      "step": 2020
+    },
+    {
+      "epoch": 2.9765395894428153,
+      "grad_norm": 0.5174537301063538,
+      "learning_rate": 8.416615710238277e-05,
+      "loss": 0.5933,
+      "mean_token_accuracy": 0.7704901993274689,
+      "num_tokens": 4150139.0,
+      "step": 2030
+    },
+    {
+      "epoch": 2.9912023460410557,
+      "grad_norm": 0.56158047914505,
+      "learning_rate": 8.398874369701297e-05,
+      "loss": 0.6054,
+      "mean_token_accuracy": 0.7657352983951569,
+      "num_tokens": 4170619.0,
+      "step": 2040
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6820,
+  "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": 1.780429465339822e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2046/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e72e8fc2bceab0c8efcfc23f671d1d30f1f51aa52ae8d9a80ad818c207cbfc
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2728/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2728/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "v_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_s3_vt_project_a1_ALL_bcast/checkpoint-2728/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4164b0bd445ffb08a600f5a015a5ec5214e6da493e344d990f8b11c9cfd417cf
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2728/added_tokens.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2728/chat_template.jinja

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2728/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2728/tokenizer.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2728/tokenizer_config.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2728/trainer_state.json

@@ -0,0 +1,2482 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2728,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01466275659824047,
+      "grad_norm": 3.6663706302642822,
+      "learning_rate": 2.6392961876832847e-06,
+      "loss": 2.4966,
+      "mean_token_accuracy": 0.5401470601558686,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.02932551319648094,
+      "grad_norm": 4.149525165557861,
+      "learning_rate": 5.571847507331378e-06,
+      "loss": 2.4504,
+      "mean_token_accuracy": 0.5461450457572937,
+      "num_tokens": 40815.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.04398826979472141,
+      "grad_norm": 3.468921661376953,
+      "learning_rate": 8.504398826979472e-06,
+      "loss": 2.3747,
+      "mean_token_accuracy": 0.5503004908561706,
+      "num_tokens": 61206.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.05865102639296188,
+      "grad_norm": 1.9510618448257446,
+      "learning_rate": 1.1436950146627567e-05,
+      "loss": 2.0501,
+      "mean_token_accuracy": 0.5706372499465943,
+      "num_tokens": 81686.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07331378299120235,
+      "grad_norm": 1.411676287651062,
+      "learning_rate": 1.4369501466275662e-05,
+      "loss": 1.7601,
+      "mean_token_accuracy": 0.5923529446125031,
+      "num_tokens": 102166.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.08797653958944282,
+      "grad_norm": 1.1375443935394287,
+      "learning_rate": 1.7302052785923756e-05,
+      "loss": 1.5712,
+      "mean_token_accuracy": 0.6036764621734619,
+      "num_tokens": 122646.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.10263929618768329,
+      "grad_norm": 0.9757223725318909,
+      "learning_rate": 2.0234604105571847e-05,
+      "loss": 1.3716,
+      "mean_token_accuracy": 0.6212254881858825,
+      "num_tokens": 143126.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.11730205278592376,
+      "grad_norm": 0.9012596011161804,
+      "learning_rate": 2.3167155425219943e-05,
+      "loss": 1.2133,
+      "mean_token_accuracy": 0.6412255048751831,
+      "num_tokens": 163606.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.13196480938416422,
+      "grad_norm": 1.029589056968689,
+      "learning_rate": 2.6099706744868034e-05,
+      "loss": 1.0462,
+      "mean_token_accuracy": 0.6717647075653076,
+      "num_tokens": 184086.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.1466275659824047,
+      "grad_norm": 1.1074068546295166,
+      "learning_rate": 2.9032258064516133e-05,
+      "loss": 0.9442,
+      "mean_token_accuracy": 0.6842647135257721,
+      "num_tokens": 204566.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.16129032258064516,
+      "grad_norm": 1.2979555130004883,
+      "learning_rate": 3.1964809384164225e-05,
+      "loss": 0.8031,
+      "mean_token_accuracy": 0.7161274492740631,
+      "num_tokens": 225046.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.17595307917888564,
+      "grad_norm": 1.2788987159729004,
+      "learning_rate": 3.489736070381232e-05,
+      "loss": 0.7661,
+      "mean_token_accuracy": 0.7248058915138245,
+      "num_tokens": 245505.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.1906158357771261,
+      "grad_norm": 1.223928689956665,
+      "learning_rate": 3.7829912023460415e-05,
+      "loss": 0.7407,
+      "mean_token_accuracy": 0.7309313714504242,
+      "num_tokens": 265985.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.20527859237536658,
+      "grad_norm": 1.217321515083313,
+      "learning_rate": 4.076246334310851e-05,
+      "loss": 0.7283,
+      "mean_token_accuracy": 0.7320588171482086,
+      "num_tokens": 286465.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.21994134897360704,
+      "grad_norm": 0.8935562968254089,
+      "learning_rate": 4.36950146627566e-05,
+      "loss": 0.6937,
+      "mean_token_accuracy": 0.744705879688263,
+      "num_tokens": 306945.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.23460410557184752,
+      "grad_norm": 0.9931844472885132,
+      "learning_rate": 4.6627565982404694e-05,
+      "loss": 0.693,
+      "mean_token_accuracy": 0.7443526327610016,
+      "num_tokens": 327350.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.24926686217008798,
+      "grad_norm": 0.8610531687736511,
+      "learning_rate": 4.956011730205279e-05,
+      "loss": 0.6883,
+      "mean_token_accuracy": 0.7444378435611725,
+      "num_tokens": 347670.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.26392961876832843,
+      "grad_norm": 0.8810847997665405,
+      "learning_rate": 5.249266862170088e-05,
+      "loss": 0.6677,
+      "mean_token_accuracy": 0.7503921568393708,
+      "num_tokens": 368150.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2785923753665689,
+      "grad_norm": 0.8069462776184082,
+      "learning_rate": 5.542521994134897e-05,
+      "loss": 0.6679,
+      "mean_token_accuracy": 0.7510784268379211,
+      "num_tokens": 388630.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.2932551319648094,
+      "grad_norm": 0.8739913702011108,
+      "learning_rate": 5.8357771260997075e-05,
+      "loss": 0.6677,
+      "mean_token_accuracy": 0.7502941191196442,
+      "num_tokens": 409110.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.30791788856304986,
+      "grad_norm": 0.9066668748855591,
+      "learning_rate": 6.129032258064517e-05,
+      "loss": 0.6721,
+      "mean_token_accuracy": 0.7441666662693024,
+      "num_tokens": 429590.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 0.7986886501312256,
+      "learning_rate": 6.422287390029326e-05,
+      "loss": 0.6588,
+      "mean_token_accuracy": 0.7490686297416687,
+      "num_tokens": 450070.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.33724340175953077,
+      "grad_norm": 0.815414309501648,
+      "learning_rate": 6.715542521994135e-05,
+      "loss": 0.6638,
+      "mean_token_accuracy": 0.7513235330581665,
+      "num_tokens": 470550.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.3519061583577713,
+      "grad_norm": 0.7602818012237549,
+      "learning_rate": 7.008797653958945e-05,
+      "loss": 0.6584,
+      "mean_token_accuracy": 0.7509313762187958,
+      "num_tokens": 491030.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.36656891495601174,
+      "grad_norm": 0.9501712918281555,
+      "learning_rate": 7.302052785923754e-05,
+      "loss": 0.6372,
+      "mean_token_accuracy": 0.7608333349227905,
+      "num_tokens": 511510.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.3812316715542522,
+      "grad_norm": 0.8099446892738342,
+      "learning_rate": 7.595307917888564e-05,
+      "loss": 0.6812,
+      "mean_token_accuracy": 0.7463235318660736,
+      "num_tokens": 531990.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.39589442815249265,
+      "grad_norm": 0.8097174763679504,
+      "learning_rate": 7.888563049853373e-05,
+      "loss": 0.6651,
+      "mean_token_accuracy": 0.7468137264251709,
+      "num_tokens": 552470.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.41055718475073316,
+      "grad_norm": 0.7530633211135864,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 0.6511,
+      "mean_token_accuracy": 0.7538725554943084,
+      "num_tokens": 572950.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.4252199413489736,
+      "grad_norm": 0.660597562789917,
+      "learning_rate": 8.475073313782992e-05,
+      "loss": 0.6479,
+      "mean_token_accuracy": 0.7550000011920929,
+      "num_tokens": 593430.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.4398826979472141,
+      "grad_norm": 0.6961861252784729,
+      "learning_rate": 8.7683284457478e-05,
+      "loss": 0.6587,
+      "mean_token_accuracy": 0.749117660522461,
+      "num_tokens": 613910.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.924081027507782,
+      "learning_rate": 9.06158357771261e-05,
+      "loss": 0.6482,
+      "mean_token_accuracy": 0.7544108033180237,
+      "num_tokens": 634176.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.46920821114369504,
+      "grad_norm": 0.7237821221351624,
+      "learning_rate": 9.35483870967742e-05,
+      "loss": 0.6547,
+      "mean_token_accuracy": 0.7502941012382507,
+      "num_tokens": 654656.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.4838709677419355,
+      "grad_norm": 0.809219479560852,
+      "learning_rate": 9.64809384164223e-05,
+      "loss": 0.6449,
+      "mean_token_accuracy": 0.7552451074123383,
+      "num_tokens": 675136.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.49853372434017595,
+      "grad_norm": 0.6265454888343811,
+      "learning_rate": 9.941348973607039e-05,
+      "loss": 0.6544,
+      "mean_token_accuracy": 0.7504901945590973,
+      "num_tokens": 695616.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5131964809384164,
+      "grad_norm": 0.690653920173645,
+      "learning_rate": 9.999962381348496e-05,
+      "loss": 0.638,
+      "mean_token_accuracy": 0.7574509859085083,
+      "num_tokens": 716096.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5278592375366569,
+      "grad_norm": 0.6082450151443481,
+      "learning_rate": 9.999809556546922e-05,
+      "loss": 0.6469,
+      "mean_token_accuracy": 0.7543627440929412,
+      "num_tokens": 736576.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5425219941348973,
+      "grad_norm": 0.6173468232154846,
+      "learning_rate": 9.999539178019954e-05,
+      "loss": 0.649,
+      "mean_token_accuracy": 0.7521512925624847,
+      "num_tokens": 756812.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5571847507331378,
+      "grad_norm": 0.6369903683662415,
+      "learning_rate": 9.999151252124639e-05,
+      "loss": 0.6501,
+      "mean_token_accuracy": 0.7515686333179474,
+      "num_tokens": 777292.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.5718475073313783,
+      "grad_norm": 0.5715249180793762,
+      "learning_rate": 9.998645787981749e-05,
+      "loss": 0.643,
+      "mean_token_accuracy": 0.7544650256633758,
+      "num_tokens": 797538.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.5865102639296188,
+      "grad_norm": 0.678391695022583,
+      "learning_rate": 9.998022797475572e-05,
+      "loss": 0.6496,
+      "mean_token_accuracy": 0.7516666650772095,
+      "num_tokens": 818018.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6011730205278593,
+      "grad_norm": 0.6235240697860718,
+      "learning_rate": 9.997282295253644e-05,
+      "loss": 0.633,
+      "mean_token_accuracy": 0.7596078515052795,
+      "num_tokens": 838498.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6158357771260997,
+      "grad_norm": 0.5357748866081238,
+      "learning_rate": 9.996424298726381e-05,
+      "loss": 0.6572,
+      "mean_token_accuracy": 0.7510294198989869,
+      "num_tokens": 858978.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.6304985337243402,
+      "grad_norm": 0.6643717288970947,
+      "learning_rate": 9.995448828066693e-05,
+      "loss": 0.6594,
+      "mean_token_accuracy": 0.7500980436801911,
+      "num_tokens": 879458.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.651352047920227,
+      "learning_rate": 9.994355906209492e-05,
+      "loss": 0.654,
+      "mean_token_accuracy": 0.7509803950786591,
+      "num_tokens": 899938.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6598240469208211,
+      "grad_norm": 0.6784325242042542,
+      "learning_rate": 9.993145558851168e-05,
+      "loss": 0.6487,
+      "mean_token_accuracy": 0.7501960813999176,
+      "num_tokens": 920418.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.6744868035190615,
+      "grad_norm": 0.5277068018913269,
+      "learning_rate": 9.991817814448967e-05,
+      "loss": 0.6376,
+      "mean_token_accuracy": 0.75563725233078,
+      "num_tokens": 940898.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.6891495601173021,
+      "grad_norm": 0.5870142579078674,
+      "learning_rate": 9.990372704220345e-05,
+      "loss": 0.6493,
+      "mean_token_accuracy": 0.7515686273574829,
+      "num_tokens": 961378.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7038123167155426,
+      "grad_norm": 0.5757046341896057,
+      "learning_rate": 9.988810262142209e-05,
+      "loss": 0.6502,
+      "mean_token_accuracy": 0.7527043879032135,
+      "num_tokens": 981824.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.718475073313783,
+      "grad_norm": 0.5332264304161072,
+      "learning_rate": 9.987130524950141e-05,
+      "loss": 0.6389,
+      "mean_token_accuracy": 0.7545588254928589,
+      "num_tokens": 1002304.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7331378299120235,
+      "grad_norm": 0.5763241052627563,
+      "learning_rate": 9.985333532137514e-05,
+      "loss": 0.6465,
+      "mean_token_accuracy": 0.7529901921749115,
+      "num_tokens": 1022784.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.7478005865102639,
+      "grad_norm": 0.6235876083374023,
+      "learning_rate": 9.983419325954577e-05,
+      "loss": 0.6391,
+      "mean_token_accuracy": 0.7525490164756775,
+      "num_tokens": 1043264.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.7624633431085044,
+      "grad_norm": 0.6091899275779724,
+      "learning_rate": 9.981387951407462e-05,
+      "loss": 0.6175,
+      "mean_token_accuracy": 0.761715692281723,
+      "num_tokens": 1063744.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.7771260997067448,
+      "grad_norm": 0.6009454131126404,
+      "learning_rate": 9.979239456257113e-05,
+      "loss": 0.6405,
+      "mean_token_accuracy": 0.7544117569923401,
+      "num_tokens": 1084224.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.7917888563049853,
+      "grad_norm": 0.6014620661735535,
+      "learning_rate": 9.976973891018175e-05,
+      "loss": 0.6338,
+      "mean_token_accuracy": 0.7550000011920929,
+      "num_tokens": 1104704.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8064516129032258,
+      "grad_norm": 0.7326117753982544,
+      "learning_rate": 9.974591308957808e-05,
+      "loss": 0.6616,
+      "mean_token_accuracy": 0.743921571969986,
+      "num_tokens": 1125184.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8211143695014663,
+      "grad_norm": 0.6346194744110107,
+      "learning_rate": 9.972091766094424e-05,
+      "loss": 0.6434,
+      "mean_token_accuracy": 0.752892154455185,
+      "num_tokens": 1145664.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8357771260997068,
+      "grad_norm": 0.5967418551445007,
+      "learning_rate": 9.969475321196373e-05,
+      "loss": 0.6385,
+      "mean_token_accuracy": 0.7556862711906434,
+      "num_tokens": 1166144.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8504398826979472,
+      "grad_norm": 0.545911431312561,
+      "learning_rate": 9.966742035780571e-05,
+      "loss": 0.6372,
+      "mean_token_accuracy": 0.7558333277702332,
+      "num_tokens": 1186624.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.8651026392961877,
+      "grad_norm": 0.5666757225990295,
+      "learning_rate": 9.963891974111042e-05,
+      "loss": 0.6404,
+      "mean_token_accuracy": 0.7540686249732971,
+      "num_tokens": 1207104.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.8797653958944281,
+      "grad_norm": 0.5760472416877747,
+      "learning_rate": 9.960925203197408e-05,
+      "loss": 0.6197,
+      "mean_token_accuracy": 0.7618935823440551,
+      "num_tokens": 1227561.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.8944281524926686,
+      "grad_norm": 0.5213801264762878,
+      "learning_rate": 9.957841792793326e-05,
+      "loss": 0.6406,
+      "mean_token_accuracy": 0.7563725531101226,
+      "num_tokens": 1248041.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.5387865304946899,
+      "learning_rate": 9.95464181539483e-05,
+      "loss": 0.6299,
+      "mean_token_accuracy": 0.7593627452850342,
+      "num_tokens": 1268521.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9237536656891495,
+      "grad_norm": 0.5207778811454773,
+      "learning_rate": 9.951325346238638e-05,
+      "loss": 0.6469,
+      "mean_token_accuracy": 0.7524509727954865,
+      "num_tokens": 1289001.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9384164222873901,
+      "grad_norm": 0.6844761967658997,
+      "learning_rate": 9.947892463300381e-05,
+      "loss": 0.6348,
+      "mean_token_accuracy": 0.7599019587039948,
+      "num_tokens": 1309481.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.9530791788856305,
+      "grad_norm": 0.5045949816703796,
+      "learning_rate": 9.944343247292771e-05,
+      "loss": 0.6342,
+      "mean_token_accuracy": 0.7550490260124206,
+      "num_tokens": 1329961.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 0.585598886013031,
+      "learning_rate": 9.940677781663699e-05,
+      "loss": 0.649,
+      "mean_token_accuracy": 0.7502451062202453,
+      "num_tokens": 1350441.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.9824046920821115,
+      "grad_norm": 0.45848599076271057,
+      "learning_rate": 9.936896152594273e-05,
+      "loss": 0.6378,
+      "mean_token_accuracy": 0.7545588195323945,
+      "num_tokens": 1370921.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.9970674486803519,
+      "grad_norm": 0.45816901326179504,
+      "learning_rate": 9.932998448996798e-05,
+      "loss": 0.6306,
+      "mean_token_accuracy": 0.7586764633655548,
+      "num_tokens": 1391401.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.0117302052785924,
+      "grad_norm": 0.5341461300849915,
+      "learning_rate": 9.92898476251268e-05,
+      "loss": 0.6368,
+      "mean_token_accuracy": 0.7575490236282348,
+      "num_tokens": 1410089.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0263929618768328,
+      "grad_norm": 0.7225525379180908,
+      "learning_rate": 9.924855187510274e-05,
+      "loss": 0.6236,
+      "mean_token_accuracy": 0.7612254917621613,
+      "num_tokens": 1430569.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.0410557184750733,
+      "grad_norm": 0.5576125383377075,
+      "learning_rate": 9.920609821082662e-05,
+      "loss": 0.6137,
+      "mean_token_accuracy": 0.765588229894638,
+      "num_tokens": 1451049.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.0557184750733137,
+      "grad_norm": 0.6563458442687988,
+      "learning_rate": 9.916248763045375e-05,
+      "loss": 0.6239,
+      "mean_token_accuracy": 0.7614491164684296,
+      "num_tokens": 1471384.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.0703812316715542,
+      "grad_norm": 0.5540904998779297,
+      "learning_rate": 9.911772115934042e-05,
+      "loss": 0.6226,
+      "mean_token_accuracy": 0.7628921687602996,
+      "num_tokens": 1491864.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.0850439882697946,
+      "grad_norm": 0.5026265978813171,
+      "learning_rate": 9.907179985001978e-05,
+      "loss": 0.6363,
+      "mean_token_accuracy": 0.7549781084060669,
+      "num_tokens": 1512184.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.099706744868035,
+      "grad_norm": 0.716999351978302,
+      "learning_rate": 9.90247247821772e-05,
+      "loss": 0.6303,
+      "mean_token_accuracy": 0.7568627417087554,
+      "num_tokens": 1532664.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1143695014662756,
+      "grad_norm": 0.4981926381587982,
+      "learning_rate": 9.897649706262473e-05,
+      "loss": 0.619,
+      "mean_token_accuracy": 0.763382351398468,
+      "num_tokens": 1553144.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.129032258064516,
+      "grad_norm": 0.5225701332092285,
+      "learning_rate": 9.892711782527517e-05,
+      "loss": 0.6233,
+      "mean_token_accuracy": 0.761715692281723,
+      "num_tokens": 1573624.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.1436950146627567,
+      "grad_norm": 0.5625816583633423,
+      "learning_rate": 9.887658823111544e-05,
+      "loss": 0.6232,
+      "mean_token_accuracy": 0.7573675394058228,
+      "num_tokens": 1594029.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.1583577712609971,
+      "grad_norm": 0.511184811592102,
+      "learning_rate": 9.882490946817915e-05,
+      "loss": 0.6303,
+      "mean_token_accuracy": 0.7567156851291656,
+      "num_tokens": 1614509.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.1730205278592376,
+      "grad_norm": 0.5488473773002625,
+      "learning_rate": 9.877208275151884e-05,
+      "loss": 0.6185,
+      "mean_token_accuracy": 0.7622549057006835,
+      "num_tokens": 1634989.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.187683284457478,
+      "grad_norm": 0.5918490290641785,
+      "learning_rate": 9.871810932317726e-05,
+      "loss": 0.6175,
+      "mean_token_accuracy": 0.7629630208015442,
+      "num_tokens": 1655225.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2023460410557185,
+      "grad_norm": 0.7483125329017639,
+      "learning_rate": 9.866299045215826e-05,
+      "loss": 0.6203,
+      "mean_token_accuracy": 0.7614705920219421,
+      "num_tokens": 1675705.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.217008797653959,
+      "grad_norm": 0.5696433782577515,
+      "learning_rate": 9.860672743439695e-05,
+      "loss": 0.628,
+      "mean_token_accuracy": 0.7564215719699859,
+      "num_tokens": 1696185.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2316715542521994,
+      "grad_norm": 0.5894884467124939,
+      "learning_rate": 9.854932159272917e-05,
+      "loss": 0.6293,
+      "mean_token_accuracy": 0.7585468471050263,
+      "num_tokens": 1716642.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.2463343108504399,
+      "grad_norm": 0.4901694357395172,
+      "learning_rate": 9.849077427686041e-05,
+      "loss": 0.6139,
+      "mean_token_accuracy": 0.7617156863212585,
+      "num_tokens": 1737122.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.2609970674486803,
+      "grad_norm": 0.5675632357597351,
+      "learning_rate": 9.843108686333417e-05,
+      "loss": 0.6277,
+      "mean_token_accuracy": 0.7617647051811218,
+      "num_tokens": 1757602.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.2756598240469208,
+      "grad_norm": 0.48929065465927124,
+      "learning_rate": 9.837026075549945e-05,
+      "loss": 0.6055,
+      "mean_token_accuracy": 0.7684804022312164,
+      "num_tokens": 1778082.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.5677883625030518,
+      "learning_rate": 9.830829738347782e-05,
+      "loss": 0.6291,
+      "mean_token_accuracy": 0.7578431308269501,
+      "num_tokens": 1798562.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.3049853372434017,
+      "grad_norm": 0.5752457976341248,
+      "learning_rate": 9.82451982041298e-05,
+      "loss": 0.6298,
+      "mean_token_accuracy": 0.7572548925876618,
+      "num_tokens": 1819042.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3196480938416422,
+      "grad_norm": 0.579814612865448,
+      "learning_rate": 9.818096470102067e-05,
+      "loss": 0.613,
+      "mean_token_accuracy": 0.7657352924346924,
+      "num_tokens": 1839522.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.3343108504398826,
+      "grad_norm": 0.5723453164100647,
+      "learning_rate": 9.811559838438542e-05,
+      "loss": 0.6075,
+      "mean_token_accuracy": 0.7673529386520386,
+      "num_tokens": 1860002.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.3489736070381233,
+      "grad_norm": 0.5011471509933472,
+      "learning_rate": 9.804910079109342e-05,
+      "loss": 0.6356,
+      "mean_token_accuracy": 0.7558823525905609,
+      "num_tokens": 1880482.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.5844294428825378,
+      "learning_rate": 9.798147348461218e-05,
+      "loss": 0.6251,
+      "mean_token_accuracy": 0.7588725566864014,
+      "num_tokens": 1900962.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.3782991202346042,
+      "grad_norm": 0.6461315751075745,
+      "learning_rate": 9.791271805497062e-05,
+      "loss": 0.619,
+      "mean_token_accuracy": 0.7632353007793427,
+      "num_tokens": 1921442.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.3929618768328447,
+      "grad_norm": 0.560377836227417,
+      "learning_rate": 9.784283611872169e-05,
+      "loss": 0.6265,
+      "mean_token_accuracy": 0.757421898841858,
+      "num_tokens": 1941888.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4076246334310851,
+      "grad_norm": 0.6241864562034607,
+      "learning_rate": 9.777182931890438e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7597058832645416,
+      "num_tokens": 1962368.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4222873900293256,
+      "grad_norm": 0.5094092488288879,
+      "learning_rate": 9.769969932500502e-05,
+      "loss": 0.6318,
+      "mean_token_accuracy": 0.7576960861682892,
+      "num_tokens": 1982848.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.436950146627566,
+      "grad_norm": 0.5033220052719116,
+      "learning_rate": 9.762644783291812e-05,
+      "loss": 0.6245,
+      "mean_token_accuracy": 0.7599019527435302,
+      "num_tokens": 2003328.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.4516129032258065,
+      "grad_norm": 0.4806479513645172,
+      "learning_rate": 9.755207656490644e-05,
+      "loss": 0.639,
+      "mean_token_accuracy": 0.7538235366344452,
+      "num_tokens": 2023808.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.466275659824047,
+      "grad_norm": 0.5395609140396118,
+      "learning_rate": 9.747658726956048e-05,
+      "loss": 0.6099,
+      "mean_token_accuracy": 0.7634313702583313,
+      "num_tokens": 2044288.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4809384164222874,
+      "grad_norm": 0.5191217660903931,
+      "learning_rate": 9.739998172175744e-05,
+      "loss": 0.605,
+      "mean_token_accuracy": 0.7667647123336792,
+      "num_tokens": 2064768.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.4956011730205279,
+      "grad_norm": 0.49461233615875244,
+      "learning_rate": 9.732226172261943e-05,
+      "loss": 0.6123,
+      "mean_token_accuracy": 0.7655392289161682,
+      "num_tokens": 2085248.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5102639296187683,
+      "grad_norm": 0.5261324048042297,
+      "learning_rate": 9.724342909947114e-05,
+      "loss": 0.6049,
+      "mean_token_accuracy": 0.7624019622802735,
+      "num_tokens": 2105728.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.5249266862170088,
+      "grad_norm": 0.5409830212593079,
+      "learning_rate": 9.716348570579686e-05,
+      "loss": 0.6377,
+      "mean_token_accuracy": 0.7593627452850342,
+      "num_tokens": 2126208.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.5395894428152492,
+      "grad_norm": 0.5728979110717773,
+      "learning_rate": 9.708243342119695e-05,
+      "loss": 0.6054,
+      "mean_token_accuracy": 0.7661274492740631,
+      "num_tokens": 2146688.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.5542521994134897,
+      "grad_norm": 0.5928049683570862,
+      "learning_rate": 9.700027415134358e-05,
+      "loss": 0.6112,
+      "mean_token_accuracy": 0.7631862699985504,
+      "num_tokens": 2167168.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.5689149560117301,
+      "grad_norm": 0.6045894622802734,
+      "learning_rate": 9.691700982793597e-05,
+      "loss": 0.6244,
+      "mean_token_accuracy": 0.7585741996765136,
+      "num_tokens": 2187627.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.5835777126099706,
+      "grad_norm": 0.5053999423980713,
+      "learning_rate": 9.6832642408655e-05,
+      "loss": 0.6094,
+      "mean_token_accuracy": 0.7675980389118194,
+      "num_tokens": 2208107.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.598240469208211,
+      "grad_norm": 0.5727707743644714,
+      "learning_rate": 9.674717387711706e-05,
+      "loss": 0.6263,
+      "mean_token_accuracy": 0.7594117760658264,
+      "num_tokens": 2228587.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 0.5962901711463928,
+      "learning_rate": 9.66606062428276e-05,
+      "loss": 0.6051,
+      "mean_token_accuracy": 0.7674056112766265,
+      "num_tokens": 2248853.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.627565982404692,
+      "grad_norm": 0.5810521245002747,
+      "learning_rate": 9.657294154113368e-05,
+      "loss": 0.6186,
+      "mean_token_accuracy": 0.7595588266849518,
+      "num_tokens": 2269333.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.6422287390029324,
+      "grad_norm": 0.5142710208892822,
+      "learning_rate": 9.648418183317629e-05,
+      "loss": 0.6201,
+      "mean_token_accuracy": 0.7632353007793427,
+      "num_tokens": 2289813.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.6568914956011729,
+      "grad_norm": 0.5239130854606628,
+      "learning_rate": 9.639432920584177e-05,
+      "loss": 0.625,
+      "mean_token_accuracy": 0.7592156827449799,
+      "num_tokens": 2310293.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.6715542521994133,
+      "grad_norm": 0.5248172283172607,
+      "learning_rate": 9.630338577171282e-05,
+      "loss": 0.6347,
+      "mean_token_accuracy": 0.7565686285495759,
+      "num_tokens": 2330773.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.6862170087976538,
+      "grad_norm": 0.6786187887191772,
+      "learning_rate": 9.621135366901874e-05,
+      "loss": 0.626,
+      "mean_token_accuracy": 0.7596078336238861,
+      "num_tokens": 2351253.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7008797653958945,
+      "grad_norm": 0.5295122861862183,
+      "learning_rate": 9.61182350615853e-05,
+      "loss": 0.616,
+      "mean_token_accuracy": 0.7638725519180298,
+      "num_tokens": 2371733.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.715542521994135,
+      "grad_norm": 0.5179807543754578,
+      "learning_rate": 9.60240321387837e-05,
+      "loss": 0.6311,
+      "mean_token_accuracy": 0.756617647409439,
+      "num_tokens": 2392213.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.7302052785923754,
+      "grad_norm": 0.5839389562606812,
+      "learning_rate": 9.592874711547922e-05,
+      "loss": 0.6063,
+      "mean_token_accuracy": 0.765490198135376,
+      "num_tokens": 2412693.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.7448680351906158,
+      "grad_norm": 0.577913761138916,
+      "learning_rate": 9.583238223197906e-05,
+      "loss": 0.6313,
+      "mean_token_accuracy": 0.7565686345100403,
+      "num_tokens": 2433173.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.7595307917888563,
+      "grad_norm": 0.6578575372695923,
+      "learning_rate": 9.573493975397975e-05,
+      "loss": 0.6145,
+      "mean_token_accuracy": 0.7614705860614777,
+      "num_tokens": 2453653.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7741935483870968,
+      "grad_norm": 0.49838587641716003,
+      "learning_rate": 9.56364219725138e-05,
+      "loss": 0.6033,
+      "mean_token_accuracy": 0.7695098042488098,
+      "num_tokens": 2474133.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.7888563049853372,
+      "grad_norm": 0.48799875378608704,
+      "learning_rate": 9.553683120389592e-05,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.764902925491333,
+      "num_tokens": 2494524.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8035190615835777,
+      "grad_norm": 0.5147119164466858,
+      "learning_rate": 9.543616978966842e-05,
+      "loss": 0.6206,
+      "mean_token_accuracy": 0.761617648601532,
+      "num_tokens": 2515004.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.5641414523124695,
+      "learning_rate": 9.53344400965463e-05,
+      "loss": 0.6251,
+      "mean_token_accuracy": 0.7585784316062927,
+      "num_tokens": 2535484.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.8328445747800588,
+      "grad_norm": 0.520799994468689,
+      "learning_rate": 9.523164451636157e-05,
+      "loss": 0.6356,
+      "mean_token_accuracy": 0.7528921604156494,
+      "num_tokens": 2555964.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.8475073313782993,
+      "grad_norm": 0.45843806862831116,
+      "learning_rate": 9.512778546600696e-05,
+      "loss": 0.622,
+      "mean_token_accuracy": 0.7602451145648956,
+      "num_tokens": 2576444.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.8621700879765397,
+      "grad_norm": 0.5162474513053894,
+      "learning_rate": 9.50228653873791e-05,
+      "loss": 0.6065,
+      "mean_token_accuracy": 0.7668967843055725,
+      "num_tokens": 2596690.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.8768328445747802,
+      "grad_norm": 0.5157609581947327,
+      "learning_rate": 9.491688674732123e-05,
+      "loss": 0.5972,
+      "mean_token_accuracy": 0.7700980484485627,
+      "num_tokens": 2617170.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.8914956011730206,
+      "grad_norm": 0.6079277396202087,
+      "learning_rate": 9.480985203756501e-05,
+      "loss": 0.6334,
+      "mean_token_accuracy": 0.7560294091701507,
+      "num_tokens": 2637650.0,
+      "step": 1290
+    },
+    {
+      "epoch": 1.906158357771261,
+      "grad_norm": 0.5813050270080566,
+      "learning_rate": 9.470176377467206e-05,
+      "loss": 0.6206,
+      "mean_token_accuracy": 0.7631862759590149,
+      "num_tokens": 2658130.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.9208211143695015,
+      "grad_norm": 0.6724423170089722,
+      "learning_rate": 9.45926244999748e-05,
+      "loss": 0.6218,
+      "mean_token_accuracy": 0.7615686237812043,
+      "num_tokens": 2678610.0,
+      "step": 1310
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 0.5010402798652649,
+      "learning_rate": 9.44824367795166e-05,
+      "loss": 0.6077,
+      "mean_token_accuracy": 0.7619117617607116,
+      "num_tokens": 2699090.0,
+      "step": 1320
+    },
+    {
+      "epoch": 1.9501466275659824,
+      "grad_norm": 0.45624953508377075,
+      "learning_rate": 9.437120320399158e-05,
+      "loss": 0.6154,
+      "mean_token_accuracy": 0.7637745201587677,
+      "num_tokens": 2719570.0,
+      "step": 1330
+    },
+    {
+      "epoch": 1.964809384164223,
+      "grad_norm": 0.5894467830657959,
+      "learning_rate": 9.425892638868356e-05,
+      "loss": 0.6061,
+      "mean_token_accuracy": 0.7665196061134338,
+      "num_tokens": 2740050.0,
+      "step": 1340
+    },
+    {
+      "epoch": 1.9794721407624634,
+      "grad_norm": 0.4616512656211853,
+      "learning_rate": 9.414560897340468e-05,
+      "loss": 0.6355,
+      "mean_token_accuracy": 0.7558333337306976,
+      "num_tokens": 2760530.0,
+      "step": 1350
+    },
+    {
+      "epoch": 1.9941348973607038,
+      "grad_norm": 0.5391420125961304,
+      "learning_rate": 9.403125362243328e-05,
+      "loss": 0.6169,
+      "mean_token_accuracy": 0.7617647111415863,
+      "num_tokens": 2781010.0,
+      "step": 1360
+    },
+    {
+      "epoch": 2.0087976539589443,
+      "grad_norm": 0.705719530582428,
+      "learning_rate": 9.39158630244513e-05,
+      "loss": 0.6214,
+      "mean_token_accuracy": 0.7583823561668396,
+      "num_tokens": 2799698.0,
+      "step": 1370
+    },
+    {
+      "epoch": 2.0234604105571847,
+      "grad_norm": 0.6386483311653137,
+      "learning_rate": 9.379943989248096e-05,
+      "loss": 0.5938,
+      "mean_token_accuracy": 0.7719317078590393,
+      "num_tokens": 2820144.0,
+      "step": 1380
+    },
+    {
+      "epoch": 2.038123167155425,
+      "grad_norm": 0.6188822388648987,
+      "learning_rate": 9.368198696382115e-05,
+      "loss": 0.5943,
+      "mean_token_accuracy": 0.7689215660095214,
+      "num_tokens": 2840624.0,
+      "step": 1390
+    },
+    {
+      "epoch": 2.0527859237536656,
+      "grad_norm": 0.5979672074317932,
+      "learning_rate": 9.356350699998288e-05,
+      "loss": 0.5803,
+      "mean_token_accuracy": 0.7749509871006012,
+      "num_tokens": 2861104.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.067448680351906,
+      "grad_norm": 0.6713985204696655,
+      "learning_rate": 9.344400278662448e-05,
+      "loss": 0.5903,
+      "mean_token_accuracy": 0.7725980401039123,
+      "num_tokens": 2881584.0,
+      "step": 1410
+    },
+    {
+      "epoch": 2.0821114369501466,
+      "grad_norm": 0.7570429444313049,
+      "learning_rate": 9.332347713348608e-05,
+      "loss": 0.5889,
+      "mean_token_accuracy": 0.7715686380863189,
+      "num_tokens": 2902064.0,
+      "step": 1420
+    },
+    {
+      "epoch": 2.096774193548387,
+      "grad_norm": 0.6166312098503113,
+      "learning_rate": 9.320193287432353e-05,
+      "loss": 0.5843,
+      "mean_token_accuracy": 0.7747058868408203,
+      "num_tokens": 2922544.0,
+      "step": 1430
+    },
+    {
+      "epoch": 2.1114369501466275,
+      "grad_norm": 0.6174513101577759,
+      "learning_rate": 9.307937286684173e-05,
+      "loss": 0.5931,
+      "mean_token_accuracy": 0.7726470589637756,
+      "num_tokens": 2943024.0,
+      "step": 1440
+    },
+    {
+      "epoch": 2.126099706744868,
+      "grad_norm": 0.5643057227134705,
+      "learning_rate": 9.295579999262756e-05,
+      "loss": 0.6074,
+      "mean_token_accuracy": 0.7670098125934601,
+      "num_tokens": 2963504.0,
+      "step": 1450
+    },
+    {
+      "epoch": 2.1407624633431084,
+      "grad_norm": 0.5920215249061584,
+      "learning_rate": 9.283121715708202e-05,
+      "loss": 0.5974,
+      "mean_token_accuracy": 0.7697058737277984,
+      "num_tokens": 2983984.0,
+      "step": 1460
+    },
+    {
+      "epoch": 2.155425219941349,
+      "grad_norm": 0.6717423796653748,
+      "learning_rate": 9.270562728935197e-05,
+      "loss": 0.5829,
+      "mean_token_accuracy": 0.7775569915771484,
+      "num_tokens": 3004220.0,
+      "step": 1470
+    },
+    {
+      "epoch": 2.1700879765395893,
+      "grad_norm": 0.5588908791542053,
+      "learning_rate": 9.257903334226124e-05,
+      "loss": 0.6012,
+      "mean_token_accuracy": 0.7698039233684539,
+      "num_tokens": 3024700.0,
+      "step": 1480
+    },
+    {
+      "epoch": 2.1847507331378297,
+      "grad_norm": 0.6039055585861206,
+      "learning_rate": 9.24514382922412e-05,
+      "loss": 0.5958,
+      "mean_token_accuracy": 0.7707352995872497,
+      "num_tokens": 3045180.0,
+      "step": 1490
+    },
+    {
+      "epoch": 2.19941348973607,
+      "grad_norm": 0.8095436692237854,
+      "learning_rate": 9.232284513926085e-05,
+      "loss": 0.5761,
+      "mean_token_accuracy": 0.7764215707778931,
+      "num_tokens": 3065660.0,
+      "step": 1500
+    },
+    {
+      "epoch": 2.2140762463343107,
+      "grad_norm": 0.6638913154602051,
+      "learning_rate": 9.219325690675615e-05,
+      "loss": 0.5903,
+      "mean_token_accuracy": 0.7721568584442139,
+      "num_tokens": 3086140.0,
+      "step": 1510
+    },
+    {
+      "epoch": 2.228739002932551,
+      "grad_norm": 0.6669881939888,
+      "learning_rate": 9.206267664155907e-05,
+      "loss": 0.6103,
+      "mean_token_accuracy": 0.7656372547149658,
+      "num_tokens": 3106620.0,
+      "step": 1520
+    },
+    {
+      "epoch": 2.2434017595307916,
+      "grad_norm": 0.8208006620407104,
+      "learning_rate": 9.193110741382585e-05,
+      "loss": 0.5946,
+      "mean_token_accuracy": 0.7709803879261017,
+      "num_tokens": 3127100.0,
+      "step": 1530
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 0.7447239756584167,
+      "learning_rate": 9.179855231696491e-05,
+      "loss": 0.5982,
+      "mean_token_accuracy": 0.7691666722297669,
+      "num_tokens": 3147580.0,
+      "step": 1540
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.5061095356941223,
+      "learning_rate": 9.166501446756405e-05,
+      "loss": 0.5993,
+      "mean_token_accuracy": 0.7696078479290008,
+      "num_tokens": 3168060.0,
+      "step": 1550
+    },
+    {
+      "epoch": 2.2873900293255134,
+      "grad_norm": 0.7621920704841614,
+      "learning_rate": 9.153049700531718e-05,
+      "loss": 0.5849,
+      "mean_token_accuracy": 0.7756862759590148,
+      "num_tokens": 3188540.0,
+      "step": 1560
+    },
+    {
+      "epoch": 2.302052785923754,
+      "grad_norm": 0.6623703837394714,
+      "learning_rate": 9.139500309295053e-05,
+      "loss": 0.5867,
+      "mean_token_accuracy": 0.7735294103622437,
+      "num_tokens": 3209020.0,
+      "step": 1570
+    },
+    {
+      "epoch": 2.3167155425219943,
+      "grad_norm": 0.6104727387428284,
+      "learning_rate": 9.125853591614828e-05,
+      "loss": 0.6113,
+      "mean_token_accuracy": 0.765147066116333,
+      "num_tokens": 3229500.0,
+      "step": 1580
+    },
+    {
+      "epoch": 2.3313782991202348,
+      "grad_norm": 0.7286109924316406,
+      "learning_rate": 9.112109868347763e-05,
+      "loss": 0.5994,
+      "mean_token_accuracy": 0.7715686142444611,
+      "num_tokens": 3249980.0,
+      "step": 1590
+    },
+    {
+      "epoch": 2.346041055718475,
+      "grad_norm": 0.6333359479904175,
+      "learning_rate": 9.098269462631341e-05,
+      "loss": 0.6052,
+      "mean_token_accuracy": 0.7670098125934601,
+      "num_tokens": 3270460.0,
+      "step": 1600
+    },
+    {
+      "epoch": 2.3607038123167157,
+      "grad_norm": 0.5577898621559143,
+      "learning_rate": 9.084332699876208e-05,
+      "loss": 0.6007,
+      "mean_token_accuracy": 0.7678921639919281,
+      "num_tokens": 3290940.0,
+      "step": 1610
+    },
+    {
+      "epoch": 2.375366568914956,
+      "grad_norm": 0.6581786870956421,
+      "learning_rate": 9.07029990775852e-05,
+      "loss": 0.596,
+      "mean_token_accuracy": 0.7687745034694672,
+      "num_tokens": 3311420.0,
+      "step": 1620
+    },
+    {
+      "epoch": 2.3900293255131966,
+      "grad_norm": 0.7705698013305664,
+      "learning_rate": 9.056171416212243e-05,
+      "loss": 0.5902,
+      "mean_token_accuracy": 0.7741009593009949,
+      "num_tokens": 3331595.0,
+      "step": 1630
+    },
+    {
+      "epoch": 2.404692082111437,
+      "grad_norm": 0.5370859503746033,
+      "learning_rate": 9.041947557421391e-05,
+      "loss": 0.5994,
+      "mean_token_accuracy": 0.768921560049057,
+      "num_tokens": 3352075.0,
+      "step": 1640
+    },
+    {
+      "epoch": 2.4193548387096775,
+      "grad_norm": 0.6219416856765747,
+      "learning_rate": 9.02762866581222e-05,
+      "loss": 0.5898,
+      "mean_token_accuracy": 0.7736274540424347,
+      "num_tokens": 3372555.0,
+      "step": 1650
+    },
+    {
+      "epoch": 2.434017595307918,
+      "grad_norm": 0.6901549100875854,
+      "learning_rate": 9.013215078045363e-05,
+      "loss": 0.5848,
+      "mean_token_accuracy": 0.7751470625400543,
+      "num_tokens": 3393035.0,
+      "step": 1660
+    },
+    {
+      "epoch": 2.4486803519061584,
+      "grad_norm": 0.6291585564613342,
+      "learning_rate": 8.998707133007918e-05,
+      "loss": 0.5884,
+      "mean_token_accuracy": 0.7722058892250061,
+      "num_tokens": 3413515.0,
+      "step": 1670
+    },
+    {
+      "epoch": 2.463343108504399,
+      "grad_norm": 0.7224541306495667,
+      "learning_rate": 8.984105171805472e-05,
+      "loss": 0.5911,
+      "mean_token_accuracy": 0.7755882441997528,
+      "num_tokens": 3433995.0,
+      "step": 1680
+    },
+    {
+      "epoch": 2.4780058651026393,
+      "grad_norm": 0.7153178453445435,
+      "learning_rate": 8.969409537754092e-05,
+      "loss": 0.5805,
+      "mean_token_accuracy": 0.7749509990215302,
+      "num_tokens": 3454475.0,
+      "step": 1690
+    },
+    {
+      "epoch": 2.4926686217008798,
+      "grad_norm": 0.6772195100784302,
+      "learning_rate": 8.95462057637224e-05,
+      "loss": 0.5894,
+      "mean_token_accuracy": 0.7743137359619141,
+      "num_tokens": 3474955.0,
+      "step": 1700
+    },
+    {
+      "epoch": 2.5073313782991202,
+      "grad_norm": 0.7709519267082214,
+      "learning_rate": 8.939738635372664e-05,
+      "loss": 0.5908,
+      "mean_token_accuracy": 0.7723039329051972,
+      "num_tokens": 3495435.0,
+      "step": 1710
+    },
+    {
+      "epoch": 2.5219941348973607,
+      "grad_norm": 0.6761429905891418,
+      "learning_rate": 8.924764064654212e-05,
+      "loss": 0.6223,
+      "mean_token_accuracy": 0.761617648601532,
+      "num_tokens": 3515915.0,
+      "step": 1720
+    },
+    {
+      "epoch": 2.536656891495601,
+      "grad_norm": 0.5991116166114807,
+      "learning_rate": 8.909697216293609e-05,
+      "loss": 0.5899,
+      "mean_token_accuracy": 0.7736764788627625,
+      "num_tokens": 3536395.0,
+      "step": 1730
+    },
+    {
+      "epoch": 2.5513196480938416,
+      "grad_norm": 0.7265383005142212,
+      "learning_rate": 8.894538444537177e-05,
+      "loss": 0.5966,
+      "mean_token_accuracy": 0.7698986232280731,
+      "num_tokens": 3556786.0,
+      "step": 1740
+    },
+    {
+      "epoch": 2.565982404692082,
+      "grad_norm": 0.7882624268531799,
+      "learning_rate": 8.87928810579251e-05,
+      "loss": 0.5898,
+      "mean_token_accuracy": 0.7731645762920379,
+      "num_tokens": 3577191.0,
+      "step": 1750
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 0.657804548740387,
+      "learning_rate": 8.863946558620094e-05,
+      "loss": 0.5928,
+      "mean_token_accuracy": 0.7701545894145966,
+      "num_tokens": 3597648.0,
+      "step": 1760
+    },
+    {
+      "epoch": 2.595307917888563,
+      "grad_norm": 0.6528093814849854,
+      "learning_rate": 8.84851416372487e-05,
+      "loss": 0.5988,
+      "mean_token_accuracy": 0.7719607830047608,
+      "num_tokens": 3618128.0,
+      "step": 1770
+    },
+    {
+      "epoch": 2.6099706744868034,
+      "grad_norm": 0.7075777649879456,
+      "learning_rate": 8.832991283947762e-05,
+      "loss": 0.5846,
+      "mean_token_accuracy": 0.7754901945590973,
+      "num_tokens": 3638608.0,
+      "step": 1780
+    },
+    {
+      "epoch": 2.624633431085044,
+      "grad_norm": 0.581615686416626,
+      "learning_rate": 8.81737828425714e-05,
+      "loss": 0.5878,
+      "mean_token_accuracy": 0.7726470470428467,
+      "num_tokens": 3659088.0,
+      "step": 1790
+    },
+    {
+      "epoch": 2.6392961876832843,
+      "grad_norm": 0.6932193636894226,
+      "learning_rate": 8.80167553174024e-05,
+      "loss": 0.6062,
+      "mean_token_accuracy": 0.7654902040958405,
+      "num_tokens": 3679568.0,
+      "step": 1800
+    },
+    {
+      "epoch": 2.653958944281525,
+      "grad_norm": 0.6022186875343323,
+      "learning_rate": 8.785883395594541e-05,
+      "loss": 0.5876,
+      "mean_token_accuracy": 0.7725980460643769,
+      "num_tokens": 3700048.0,
+      "step": 1810
+    },
+    {
+      "epoch": 2.6686217008797652,
+      "grad_norm": 0.8625696897506714,
+      "learning_rate": 8.770002247119064e-05,
+      "loss": 0.6065,
+      "mean_token_accuracy": 0.7678162634372712,
+      "num_tokens": 3720294.0,
+      "step": 1820
+    },
+    {
+      "epoch": 2.6832844574780057,
+      "grad_norm": 0.8375098705291748,
+      "learning_rate": 8.754032459705672e-05,
+      "loss": 0.6033,
+      "mean_token_accuracy": 0.7681929707527161,
+      "num_tokens": 3740560.0,
+      "step": 1830
+    },
+    {
+      "epoch": 2.6979472140762466,
+      "grad_norm": 0.6922727823257446,
+      "learning_rate": 8.737974408830263e-05,
+      "loss": 0.582,
+      "mean_token_accuracy": 0.7738213419914246,
+      "num_tokens": 3761019.0,
+      "step": 1840
+    },
+    {
+      "epoch": 2.712609970674487,
+      "grad_norm": 0.6475608348846436,
+      "learning_rate": 8.721828472043958e-05,
+      "loss": 0.5846,
+      "mean_token_accuracy": 0.7751960813999176,
+      "num_tokens": 3781499.0,
+      "step": 1850
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.6575704216957092,
+      "learning_rate": 8.705595028964222e-05,
+      "loss": 0.5858,
+      "mean_token_accuracy": 0.7764705955982208,
+      "num_tokens": 3801979.0,
+      "step": 1860
+    },
+    {
+      "epoch": 2.741935483870968,
+      "grad_norm": 0.6429558396339417,
+      "learning_rate": 8.689274461265935e-05,
+      "loss": 0.6056,
+      "mean_token_accuracy": 0.7670588254928589,
+      "num_tokens": 3822459.0,
+      "step": 1870
+    },
+    {
+      "epoch": 2.7565982404692084,
+      "grad_norm": 0.6039347052574158,
+      "learning_rate": 8.672867152672416e-05,
+      "loss": 0.622,
+      "mean_token_accuracy": 0.7584313750267029,
+      "num_tokens": 3842939.0,
+      "step": 1880
+    },
+    {
+      "epoch": 2.771260997067449,
+      "grad_norm": 0.6779440641403198,
+      "learning_rate": 8.656373488946409e-05,
+      "loss": 0.6011,
+      "mean_token_accuracy": 0.7695097923278809,
+      "num_tokens": 3863419.0,
+      "step": 1890
+    },
+    {
+      "epoch": 2.7859237536656893,
+      "grad_norm": 0.6504889726638794,
+      "learning_rate": 8.639793857881011e-05,
+      "loss": 0.5816,
+      "mean_token_accuracy": 0.7756372570991517,
+      "num_tokens": 3883899.0,
+      "step": 1900
+    },
+    {
+      "epoch": 2.80058651026393,
+      "grad_norm": 0.6093726754188538,
+      "learning_rate": 8.623128649290544e-05,
+      "loss": 0.6111,
+      "mean_token_accuracy": 0.7643137216567993,
+      "num_tokens": 3904379.0,
+      "step": 1910
+    },
+    {
+      "epoch": 2.8152492668621703,
+      "grad_norm": 0.6347564458847046,
+      "learning_rate": 8.606378255001408e-05,
+      "loss": 0.5897,
+      "mean_token_accuracy": 0.7719607889652252,
+      "num_tokens": 3924859.0,
+      "step": 1920
+    },
+    {
+      "epoch": 2.8299120234604107,
+      "grad_norm": 0.6521418690681458,
+      "learning_rate": 8.58954306884285e-05,
+      "loss": 0.5948,
+      "mean_token_accuracy": 0.7706372559070587,
+      "num_tokens": 3945339.0,
+      "step": 1930
+    },
+    {
+      "epoch": 2.844574780058651,
+      "grad_norm": 0.55730140209198,
+      "learning_rate": 8.572623486637719e-05,
+      "loss": 0.5945,
+      "mean_token_accuracy": 0.7713235318660736,
+      "num_tokens": 3965819.0,
+      "step": 1940
+    },
+    {
+      "epoch": 2.8592375366568916,
+      "grad_norm": 0.7235424518585205,
+      "learning_rate": 8.555619906193147e-05,
+      "loss": 0.6023,
+      "mean_token_accuracy": 0.7676470577716827,
+      "num_tokens": 3986299.0,
+      "step": 1950
+    },
+    {
+      "epoch": 2.873900293255132,
+      "grad_norm": 0.8976076245307922,
+      "learning_rate": 8.538532727291211e-05,
+      "loss": 0.5887,
+      "mean_token_accuracy": 0.7734313786029816,
+      "num_tokens": 4006779.0,
+      "step": 1960
+    },
+    {
+      "epoch": 2.8885630498533725,
+      "grad_norm": 0.49708253145217896,
+      "learning_rate": 8.521362351679517e-05,
+      "loss": 0.5842,
+      "mean_token_accuracy": 0.7723039209842681,
+      "num_tokens": 4027259.0,
+      "step": 1970
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 0.7013171315193176,
+      "learning_rate": 8.504109183061768e-05,
+      "loss": 0.5676,
+      "mean_token_accuracy": 0.7804902017116546,
+      "num_tokens": 4047739.0,
+      "step": 1980
+    },
+    {
+      "epoch": 2.9178885630498534,
+      "grad_norm": 0.687017023563385,
+      "learning_rate": 8.486773627088263e-05,
+      "loss": 0.5997,
+      "mean_token_accuracy": 0.7691176414489747,
+      "num_tokens": 4068219.0,
+      "step": 1990
+    },
+    {
+      "epoch": 2.932551319648094,
+      "grad_norm": 0.6752710342407227,
+      "learning_rate": 8.469356091346361e-05,
+      "loss": 0.6194,
+      "mean_token_accuracy": 0.7596078395843506,
+      "num_tokens": 4088699.0,
+      "step": 2000
+    },
+    {
+      "epoch": 2.9472140762463344,
+      "grad_norm": 0.5824620723724365,
+      "learning_rate": 8.451856985350906e-05,
+      "loss": 0.5815,
+      "mean_token_accuracy": 0.7760294139385223,
+      "num_tokens": 4109179.0,
+      "step": 2010
+    },
+    {
+      "epoch": 2.961876832844575,
+      "grad_norm": 0.6335878968238831,
+      "learning_rate": 8.434276720534588e-05,
+      "loss": 0.5657,
+      "mean_token_accuracy": 0.7812745153903962,
+      "num_tokens": 4129659.0,
+      "step": 2020
+    },
+    {
+      "epoch": 2.9765395894428153,
+      "grad_norm": 0.5174537301063538,
+      "learning_rate": 8.416615710238277e-05,
+      "loss": 0.5933,
+      "mean_token_accuracy": 0.7704901993274689,
+      "num_tokens": 4150139.0,
+      "step": 2030
+    },
+    {
+      "epoch": 2.9912023460410557,
+      "grad_norm": 0.56158047914505,
+      "learning_rate": 8.398874369701297e-05,
+      "loss": 0.6054,
+      "mean_token_accuracy": 0.7657352983951569,
+      "num_tokens": 4170619.0,
+      "step": 2040
+    },
+    {
+      "epoch": 3.005865102639296,
+      "grad_norm": 0.6061378121376038,
+      "learning_rate": 8.381053116051672e-05,
+      "loss": 0.5873,
+      "mean_token_accuracy": 0.7740196049213409,
+      "num_tokens": 4189307.0,
+      "step": 2050
+    },
+    {
+      "epoch": 3.0205278592375366,
+      "grad_norm": 0.766022801399231,
+      "learning_rate": 8.363152368296312e-05,
+      "loss": 0.5419,
+      "mean_token_accuracy": 0.7925980389118195,
+      "num_tokens": 4209787.0,
+      "step": 2060
+    },
+    {
+      "epoch": 3.035190615835777,
+      "grad_norm": 0.6952306032180786,
+      "learning_rate": 8.345172547311165e-05,
+      "loss": 0.5677,
+      "mean_token_accuracy": 0.7813725531101227,
+      "num_tokens": 4230267.0,
+      "step": 2070
+    },
+    {
+      "epoch": 3.0498533724340176,
+      "grad_norm": 0.7040441036224365,
+      "learning_rate": 8.327114075831322e-05,
+      "loss": 0.5728,
+      "mean_token_accuracy": 0.7811764657497406,
+      "num_tokens": 4250747.0,
+      "step": 2080
+    },
+    {
+      "epoch": 3.064516129032258,
+      "grad_norm": 0.9368137121200562,
+      "learning_rate": 8.308977378441072e-05,
+      "loss": 0.5686,
+      "mean_token_accuracy": 0.7805882334709168,
+      "num_tokens": 4271227.0,
+      "step": 2090
+    },
+    {
+      "epoch": 3.0791788856304985,
+      "grad_norm": 0.8406084775924683,
+      "learning_rate": 8.290762881563925e-05,
+      "loss": 0.546,
+      "mean_token_accuracy": 0.7900044798851014,
+      "num_tokens": 4291463.0,
+      "step": 2100
+    },
+    {
+      "epoch": 3.093841642228739,
+      "grad_norm": 0.7071312069892883,
+      "learning_rate": 8.272471013452589e-05,
+      "loss": 0.5515,
+      "mean_token_accuracy": 0.7887254893779755,
+      "num_tokens": 4311943.0,
+      "step": 2110
+    },
+    {
+      "epoch": 3.1085043988269794,
+      "grad_norm": 0.7741420269012451,
+      "learning_rate": 8.254102204178891e-05,
+      "loss": 0.5424,
+      "mean_token_accuracy": 0.7915686309337616,
+      "num_tokens": 4332423.0,
+      "step": 2120
+    },
+    {
+      "epoch": 3.12316715542522,
+      "grad_norm": 0.7695740461349487,
+      "learning_rate": 8.235656885623673e-05,
+      "loss": 0.5555,
+      "mean_token_accuracy": 0.788382351398468,
+      "num_tokens": 4352903.0,
+      "step": 2130
+    },
+    {
+      "epoch": 3.1378299120234603,
+      "grad_norm": 0.8262962698936462,
+      "learning_rate": 8.217135491466636e-05,
+      "loss": 0.5341,
+      "mean_token_accuracy": 0.7942156910896301,
+      "num_tokens": 4373383.0,
+      "step": 2140
+    },
+    {
+      "epoch": 3.1524926686217007,
+      "grad_norm": 0.6974924206733704,
+      "learning_rate": 8.198538457176142e-05,
+      "loss": 0.5625,
+      "mean_token_accuracy": 0.7792647063732148,
+      "num_tokens": 4393863.0,
+      "step": 2150
+    },
+    {
+      "epoch": 3.167155425219941,
+      "grad_norm": 0.7380699515342712,
+      "learning_rate": 8.17986621999898e-05,
+      "loss": 0.5443,
+      "mean_token_accuracy": 0.7889705836772919,
+      "num_tokens": 4414343.0,
+      "step": 2160
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "grad_norm": 0.7039031386375427,
+      "learning_rate": 8.161119218950078e-05,
+      "loss": 0.5641,
+      "mean_token_accuracy": 0.7828431308269501,
+      "num_tokens": 4434823.0,
+      "step": 2170
+    },
+    {
+      "epoch": 3.196480938416422,
+      "grad_norm": 0.652038037776947,
+      "learning_rate": 8.142297894802184e-05,
+      "loss": 0.5573,
+      "mean_token_accuracy": 0.7855392217636108,
+      "num_tokens": 4455303.0,
+      "step": 2180
+    },
+    {
+      "epoch": 3.2111436950146626,
+      "grad_norm": 0.686612606048584,
+      "learning_rate": 8.123402690075514e-05,
+      "loss": 0.563,
+      "mean_token_accuracy": 0.7828921496868133,
+      "num_tokens": 4475783.0,
+      "step": 2190
+    },
+    {
+      "epoch": 3.225806451612903,
+      "grad_norm": 0.6992233991622925,
+      "learning_rate": 8.104434049027327e-05,
+      "loss": 0.57,
+      "mean_token_accuracy": 0.7814772367477417,
+      "num_tokens": 4496229.0,
+      "step": 2200
+    },
+    {
+      "epoch": 3.2404692082111435,
+      "grad_norm": 0.8781445622444153,
+      "learning_rate": 8.085392417641493e-05,
+      "loss": 0.5311,
+      "mean_token_accuracy": 0.7932843148708344,
+      "num_tokens": 4516709.0,
+      "step": 2210
+    },
+    {
+      "epoch": 3.255131964809384,
+      "grad_norm": 0.9201792478561401,
+      "learning_rate": 8.066278243618008e-05,
+      "loss": 0.5638,
+      "mean_token_accuracy": 0.7814483523368836,
+      "num_tokens": 4536830.0,
+      "step": 2220
+    },
+    {
+      "epoch": 3.2697947214076244,
+      "grad_norm": 0.859659731388092,
+      "learning_rate": 8.047091976362459e-05,
+      "loss": 0.5722,
+      "mean_token_accuracy": 0.7801470577716827,
+      "num_tokens": 4557310.0,
+      "step": 2230
+    },
+    {
+      "epoch": 3.2844574780058653,
+      "grad_norm": 0.7493177652359009,
+      "learning_rate": 8.02783406697547e-05,
+      "loss": 0.5622,
+      "mean_token_accuracy": 0.7836764693260193,
+      "num_tokens": 4577790.0,
+      "step": 2240
+    },
+    {
+      "epoch": 3.2991202346041058,
+      "grad_norm": 1.052527666091919,
+      "learning_rate": 8.008504968242083e-05,
+      "loss": 0.547,
+      "mean_token_accuracy": 0.7868137240409852,
+      "num_tokens": 4598270.0,
+      "step": 2250
+    },
+    {
+      "epoch": 3.313782991202346,
+      "grad_norm": 0.7455736398696899,
+      "learning_rate": 7.989105134621122e-05,
+      "loss": 0.5432,
+      "mean_token_accuracy": 0.7905392169952392,
+      "num_tokens": 4618750.0,
+      "step": 2260
+    },
+    {
+      "epoch": 3.3284457478005867,
+      "grad_norm": 0.9125356674194336,
+      "learning_rate": 7.969635022234501e-05,
+      "loss": 0.5416,
+      "mean_token_accuracy": 0.7914705872535706,
+      "num_tokens": 4639230.0,
+      "step": 2270
+    },
+    {
+      "epoch": 3.343108504398827,
+      "grad_norm": 0.9040418267250061,
+      "learning_rate": 7.950095088856508e-05,
+      "loss": 0.5597,
+      "mean_token_accuracy": 0.7813235342502594,
+      "num_tokens": 4659710.0,
+      "step": 2280
+    },
+    {
+      "epoch": 3.3577712609970676,
+      "grad_norm": 0.9419428706169128,
+      "learning_rate": 7.930485793903031e-05,
+      "loss": 0.5681,
+      "mean_token_accuracy": 0.7789705932140351,
+      "num_tokens": 4680190.0,
+      "step": 2290
+    },
+    {
+      "epoch": 3.372434017595308,
+      "grad_norm": 0.9829403758049011,
+      "learning_rate": 7.910807598420767e-05,
+      "loss": 0.5583,
+      "mean_token_accuracy": 0.7852941155433655,
+      "num_tokens": 4700670.0,
+      "step": 2300
+    },
+    {
+      "epoch": 3.3870967741935485,
+      "grad_norm": 0.8162914514541626,
+      "learning_rate": 7.891060965076375e-05,
+      "loss": 0.5644,
+      "mean_token_accuracy": 0.7829901933670044,
+      "num_tokens": 4721150.0,
+      "step": 2310
+    },
+    {
+      "epoch": 3.401759530791789,
+      "grad_norm": 0.730269193649292,
+      "learning_rate": 7.871246358145605e-05,
+      "loss": 0.5685,
+      "mean_token_accuracy": 0.7820588231086731,
+      "num_tokens": 4741630.0,
+      "step": 2320
+    },
+    {
+      "epoch": 3.4164222873900294,
+      "grad_norm": 0.8207823634147644,
+      "learning_rate": 7.851364243502369e-05,
+      "loss": 0.577,
+      "mean_token_accuracy": 0.7796078443527221,
+      "num_tokens": 4762110.0,
+      "step": 2330
+    },
+    {
+      "epoch": 3.43108504398827,
+      "grad_norm": 0.9779303073883057,
+      "learning_rate": 7.831415088607801e-05,
+      "loss": 0.5637,
+      "mean_token_accuracy": 0.784852933883667,
+      "num_tokens": 4782590.0,
+      "step": 2340
+    },
+    {
+      "epoch": 3.4457478005865103,
+      "grad_norm": 0.8204278945922852,
+      "learning_rate": 7.811399362499267e-05,
+      "loss": 0.5525,
+      "mean_token_accuracy": 0.7868196904659271,
+      "num_tokens": 4803049.0,
+      "step": 2350
+    },
+    {
+      "epoch": 3.4604105571847508,
+      "grad_norm": 0.7875622510910034,
+      "learning_rate": 7.791317535779318e-05,
+      "loss": 0.5567,
+      "mean_token_accuracy": 0.7877857744693756,
+      "num_tokens": 4823369.0,
+      "step": 2360
+    },
+    {
+      "epoch": 3.4750733137829912,
+      "grad_norm": 0.6897715926170349,
+      "learning_rate": 7.771170080604652e-05,
+      "loss": 0.5531,
+      "mean_token_accuracy": 0.7874509811401367,
+      "num_tokens": 4843849.0,
+      "step": 2370
+    },
+    {
+      "epoch": 3.4897360703812317,
+      "grad_norm": 0.9699828624725342,
+      "learning_rate": 7.750957470674996e-05,
+      "loss": 0.5672,
+      "mean_token_accuracy": 0.780980396270752,
+      "num_tokens": 4864329.0,
+      "step": 2380
+    },
+    {
+      "epoch": 3.504398826979472,
+      "grad_norm": 0.7897684574127197,
+      "learning_rate": 7.730680181221963e-05,
+      "loss": 0.5615,
+      "mean_token_accuracy": 0.7850490272045135,
+      "num_tokens": 4884809.0,
+      "step": 2390
+    },
+    {
+      "epoch": 3.5190615835777126,
+      "grad_norm": 0.7306972146034241,
+      "learning_rate": 7.710338688997901e-05,
+      "loss": 0.5632,
+      "mean_token_accuracy": 0.7850980520248413,
+      "num_tokens": 4905289.0,
+      "step": 2400
+    },
+    {
+      "epoch": 3.533724340175953,
+      "grad_norm": 0.8678225874900818,
+      "learning_rate": 7.689933472264661e-05,
+      "loss": 0.565,
+      "mean_token_accuracy": 0.7843137264251709,
+      "num_tokens": 4925769.0,
+      "step": 2410
+    },
+    {
+      "epoch": 3.5483870967741935,
+      "grad_norm": 0.8993431329727173,
+      "learning_rate": 7.669465010782369e-05,
+      "loss": 0.5584,
+      "mean_token_accuracy": 0.7872548997402191,
+      "num_tokens": 4946249.0,
+      "step": 2420
+    },
+    {
+      "epoch": 3.563049853372434,
+      "grad_norm": 0.9338233470916748,
+      "learning_rate": 7.648933785798133e-05,
+      "loss": 0.5716,
+      "mean_token_accuracy": 0.7816176414489746,
+      "num_tokens": 4966729.0,
+      "step": 2430
+    },
+    {
+      "epoch": 3.5777126099706744,
+      "grad_norm": 0.780002236366272,
+      "learning_rate": 7.628340280034736e-05,
+      "loss": 0.5619,
+      "mean_token_accuracy": 0.7822058916091919,
+      "num_tokens": 4987209.0,
+      "step": 2440
+    },
+    {
+      "epoch": 3.592375366568915,
+      "grad_norm": 0.8452161550521851,
+      "learning_rate": 7.607684977679283e-05,
+      "loss": 0.5757,
+      "mean_token_accuracy": 0.7790196120738984,
+      "num_tokens": 5007689.0,
+      "step": 2450
+    },
+    {
+      "epoch": 3.6070381231671553,
+      "grad_norm": 0.8637092113494873,
+      "learning_rate": 7.586968364371823e-05,
+      "loss": 0.5759,
+      "mean_token_accuracy": 0.7815196096897126,
+      "num_tokens": 5028169.0,
+      "step": 2460
+    },
+    {
+      "epoch": 3.621700879765396,
+      "grad_norm": 0.7940127849578857,
+      "learning_rate": 7.56619092719392e-05,
+      "loss": 0.5672,
+      "mean_token_accuracy": 0.7823529422283173,
+      "num_tokens": 5048649.0,
+      "step": 2470
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 0.7398171424865723,
+      "learning_rate": 7.545353154657211e-05,
+      "loss": 0.5562,
+      "mean_token_accuracy": 0.784382963180542,
+      "num_tokens": 5069106.0,
+      "step": 2480
+    },
+    {
+      "epoch": 3.6510263929618767,
+      "grad_norm": 0.7265703082084656,
+      "learning_rate": 7.524455536691915e-05,
+      "loss": 0.5611,
+      "mean_token_accuracy": 0.7842304110527039,
+      "num_tokens": 5089497.0,
+      "step": 2490
+    },
+    {
+      "epoch": 3.665689149560117,
+      "grad_norm": 0.7777828574180603,
+      "learning_rate": 7.503498564635312e-05,
+      "loss": 0.5677,
+      "mean_token_accuracy": 0.783529418706894,
+      "num_tokens": 5109977.0,
+      "step": 2500
+    },
+    {
+      "epoch": 3.6803519061583576,
+      "grad_norm": 0.7887988090515137,
+      "learning_rate": 7.482482731220202e-05,
+      "loss": 0.5709,
+      "mean_token_accuracy": 0.7828431367874146,
+      "num_tokens": 5130457.0,
+      "step": 2510
+    },
+    {
+      "epoch": 3.6950146627565985,
+      "grad_norm": 0.8695141673088074,
+      "learning_rate": 7.461408530563303e-05,
+      "loss": 0.571,
+      "mean_token_accuracy": 0.7798529386520385,
+      "num_tokens": 5150937.0,
+      "step": 2520
+    },
+    {
+      "epoch": 3.709677419354839,
+      "grad_norm": 0.9031780958175659,
+      "learning_rate": 7.44027645815365e-05,
+      "loss": 0.5631,
+      "mean_token_accuracy": 0.7856862843036652,
+      "num_tokens": 5171417.0,
+      "step": 2530
+    },
+    {
+      "epoch": 3.7243401759530794,
+      "grad_norm": 0.8435536026954651,
+      "learning_rate": 7.419087010840933e-05,
+      "loss": 0.5638,
+      "mean_token_accuracy": 0.782843142747879,
+      "num_tokens": 5191897.0,
+      "step": 2540
+    },
+    {
+      "epoch": 3.73900293255132,
+      "grad_norm": 0.917770504951477,
+      "learning_rate": 7.397840686823823e-05,
+      "loss": 0.5641,
+      "mean_token_accuracy": 0.7801470756530762,
+      "num_tokens": 5212377.0,
+      "step": 2550
+    },
+    {
+      "epoch": 3.7536656891495603,
+      "grad_norm": 0.9334399104118347,
+      "learning_rate": 7.376537985638254e-05,
+      "loss": 0.5691,
+      "mean_token_accuracy": 0.7804411768913269,
+      "num_tokens": 5232857.0,
+      "step": 2560
+    },
+    {
+      "epoch": 3.768328445747801,
+      "grad_norm": 0.8330138325691223,
+      "learning_rate": 7.35517940814568e-05,
+      "loss": 0.5776,
+      "mean_token_accuracy": 0.7804901957511902,
+      "num_tokens": 5253337.0,
+      "step": 2570
+    },
+    {
+      "epoch": 3.7829912023460412,
+      "grad_norm": 0.6732172966003418,
+      "learning_rate": 7.333765456521299e-05,
+      "loss": 0.553,
+      "mean_token_accuracy": 0.7866176486015319,
+      "num_tokens": 5273817.0,
+      "step": 2580
+    },
+    {
+      "epoch": 3.7976539589442817,
+      "grad_norm": 0.8446711301803589,
+      "learning_rate": 7.312296634242246e-05,
+      "loss": 0.573,
+      "mean_token_accuracy": 0.7800000011920929,
+      "num_tokens": 5294297.0,
+      "step": 2590
+    },
+    {
+      "epoch": 3.812316715542522,
+      "grad_norm": 0.9171662926673889,
+      "learning_rate": 7.290773446075754e-05,
+      "loss": 0.5571,
+      "mean_token_accuracy": 0.7859803915023804,
+      "num_tokens": 5314777.0,
+      "step": 2600
+    },
+    {
+      "epoch": 3.8269794721407626,
+      "grad_norm": 0.7296270728111267,
+      "learning_rate": 7.269196398067287e-05,
+      "loss": 0.5603,
+      "mean_token_accuracy": 0.7824988842010498,
+      "num_tokens": 5335182.0,
+      "step": 2610
+    },
+    {
+      "epoch": 3.841642228739003,
+      "grad_norm": 0.6045035719871521,
+      "learning_rate": 7.247565997528646e-05,
+      "loss": 0.5554,
+      "mean_token_accuracy": 0.7868627488613129,
+      "num_tokens": 5355662.0,
+      "step": 2620
+    },
+    {
+      "epoch": 3.8563049853372435,
+      "grad_norm": 0.8061227798461914,
+      "learning_rate": 7.225882753026033e-05,
+      "loss": 0.5658,
+      "mean_token_accuracy": 0.782500010728836,
+      "num_tokens": 5376142.0,
+      "step": 2630
+    },
+    {
+      "epoch": 3.870967741935484,
+      "grad_norm": 0.8307713270187378,
+      "learning_rate": 7.204147174368097e-05,
+      "loss": 0.5564,
+      "mean_token_accuracy": 0.7862254917621613,
+      "num_tokens": 5396622.0,
+      "step": 2640
+    },
+    {
+      "epoch": 3.8856304985337244,
+      "grad_norm": 0.8681085705757141,
+      "learning_rate": 7.182359772593955e-05,
+      "loss": 0.5652,
+      "mean_token_accuracy": 0.7826470553874969,
+      "num_tokens": 5417102.0,
+      "step": 2650
+    },
+    {
+      "epoch": 3.900293255131965,
+      "grad_norm": 0.7953760623931885,
+      "learning_rate": 7.160521059961169e-05,
+      "loss": 0.5608,
+      "mean_token_accuracy": 0.7843627452850341,
+      "num_tokens": 5437582.0,
+      "step": 2660
+    },
+    {
+      "epoch": 3.9149560117302054,
+      "grad_norm": 0.8679683208465576,
+      "learning_rate": 7.138631549933698e-05,
+      "loss": 0.5403,
+      "mean_token_accuracy": 0.7930882334709167,
+      "num_tokens": 5458062.0,
+      "step": 2670
+    },
+    {
+      "epoch": 3.929618768328446,
+      "grad_norm": 0.7938868999481201,
+      "learning_rate": 7.116691757169837e-05,
+      "loss": 0.5635,
+      "mean_token_accuracy": 0.7834803879261016,
+      "num_tokens": 5478542.0,
+      "step": 2680
+    },
+    {
+      "epoch": 3.9442815249266863,
+      "grad_norm": 0.8288176655769348,
+      "learning_rate": 7.094702197510108e-05,
+      "loss": 0.5524,
+      "mean_token_accuracy": 0.7859803974628449,
+      "num_tokens": 5499022.0,
+      "step": 2690
+    },
+    {
+      "epoch": 3.9589442815249267,
+      "grad_norm": 0.9484570622444153,
+      "learning_rate": 7.072663387965134e-05,
+      "loss": 0.5369,
+      "mean_token_accuracy": 0.7931239128112793,
+      "num_tokens": 5519268.0,
+      "step": 2700
+    },
+    {
+      "epoch": 3.973607038123167,
+      "grad_norm": 0.8716885447502136,
+      "learning_rate": 7.050575846703484e-05,
+      "loss": 0.5515,
+      "mean_token_accuracy": 0.7868137419223785,
+      "num_tokens": 5539748.0,
+      "step": 2710
+    },
+    {
+      "epoch": 3.9882697947214076,
+      "grad_norm": 0.6836452484130859,
+      "learning_rate": 7.028440093039493e-05,
+      "loss": 0.5543,
+      "mean_token_accuracy": 0.7861274480819702,
+      "num_tokens": 5560228.0,
+      "step": 2720
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6820,
+  "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": 2.3739059537864294e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2728/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e72e8fc2bceab0c8efcfc23f671d1d30f1f51aa52ae8d9a80ad818c207cbfc
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-3410/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-3410/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "v_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_s3_vt_project_a1_ALL_bcast/checkpoint-3410/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df9261a7ff6310ea4626b2aeda5544d35564429b75f5bb3a5d6f62edd111c33
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-3410/added_tokens.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-3410/chat_template.jinja

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-3410/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-3410/tokenizer.json

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