add checkpoint cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast

.gitattributes

@@ -259,3 +259,14 @@ checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/che
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-681/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-6810/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/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-1364/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-2046/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-2728/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-3410/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-4092/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-4774/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-5456/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-6138/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-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_s2_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_s2_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": [
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2341776fac0501ce594140646c5f53cd58b442dc7908da9cd087c6fc4c1382e3
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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_s2_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_s2_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": [
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-1364/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2399d3f43b74a5eb1df0517dfa1ff607d65e11d6df0fbb5640c8d2667af0dc18
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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_s2_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_s2_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_s2_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_s2_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": 3.478421211242676,
+      "learning_rate": 2.6392961876832847e-06,
+      "loss": 2.49,
+      "mean_token_accuracy": 0.5404902040958405,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.02932551319648094,
+      "grad_norm": 4.437029838562012,
+      "learning_rate": 5.571847507331378e-06,
+      "loss": 2.4861,
+      "mean_token_accuracy": 0.5374019622802735,
+      "num_tokens": 40960.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.04398826979472141,
+      "grad_norm": 3.2707436084747314,
+      "learning_rate": 8.504398826979472e-06,
+      "loss": 2.3345,
+      "mean_token_accuracy": 0.5500490128993988,
+      "num_tokens": 61440.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.05865102639296188,
+      "grad_norm": 1.9522887468338013,
+      "learning_rate": 1.1436950146627567e-05,
+      "loss": 2.0409,
+      "mean_token_accuracy": 0.5806862652301789,
+      "num_tokens": 81920.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07331378299120235,
+      "grad_norm": 1.3734278678894043,
+      "learning_rate": 1.4369501466275662e-05,
+      "loss": 1.7743,
+      "mean_token_accuracy": 0.5944117605686188,
+      "num_tokens": 102400.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.08797653958944282,
+      "grad_norm": 1.124900221824646,
+      "learning_rate": 1.7302052785923756e-05,
+      "loss": 1.5557,
+      "mean_token_accuracy": 0.6044607698917389,
+      "num_tokens": 122880.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.10263929618768329,
+      "grad_norm": 0.8481243848800659,
+      "learning_rate": 2.0234604105571847e-05,
+      "loss": 1.383,
+      "mean_token_accuracy": 0.620245099067688,
+      "num_tokens": 143360.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.11730205278592376,
+      "grad_norm": 0.864518940448761,
+      "learning_rate": 2.3167155425219943e-05,
+      "loss": 1.2221,
+      "mean_token_accuracy": 0.6459313809871674,
+      "num_tokens": 163840.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.13196480938416422,
+      "grad_norm": 0.9745388627052307,
+      "learning_rate": 2.6099706744868034e-05,
+      "loss": 1.0528,
+      "mean_token_accuracy": 0.6676470518112183,
+      "num_tokens": 184320.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.1466275659824047,
+      "grad_norm": 1.1379441022872925,
+      "learning_rate": 2.9032258064516133e-05,
+      "loss": 0.9449,
+      "mean_token_accuracy": 0.6830392181873322,
+      "num_tokens": 204800.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.16129032258064516,
+      "grad_norm": 1.1655960083007812,
+      "learning_rate": 3.1964809384164225e-05,
+      "loss": 0.8282,
+      "mean_token_accuracy": 0.7080882310867309,
+      "num_tokens": 225280.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.17595307917888564,
+      "grad_norm": 1.3215491771697998,
+      "learning_rate": 3.489736070381232e-05,
+      "loss": 0.7662,
+      "mean_token_accuracy": 0.7250490248203277,
+      "num_tokens": 245760.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.1906158357771261,
+      "grad_norm": 1.0598912239074707,
+      "learning_rate": 3.7829912023460415e-05,
+      "loss": 0.7364,
+      "mean_token_accuracy": 0.7327941119670868,
+      "num_tokens": 266240.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.20527859237536658,
+      "grad_norm": 1.122361183166504,
+      "learning_rate": 4.076246334310851e-05,
+      "loss": 0.723,
+      "mean_token_accuracy": 0.7349509775638581,
+      "num_tokens": 286720.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.21994134897360704,
+      "grad_norm": 1.1284314393997192,
+      "learning_rate": 4.36950146627566e-05,
+      "loss": 0.7266,
+      "mean_token_accuracy": 0.7305392146110534,
+      "num_tokens": 307200.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.23460410557184752,
+      "grad_norm": 0.8642133474349976,
+      "learning_rate": 4.6627565982404694e-05,
+      "loss": 0.6996,
+      "mean_token_accuracy": 0.7395318567752838,
+      "num_tokens": 327614.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.24926686217008798,
+      "grad_norm": 0.9549291729927063,
+      "learning_rate": 4.956011730205279e-05,
+      "loss": 0.7056,
+      "mean_token_accuracy": 0.7378431379795074,
+      "num_tokens": 348094.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.26392961876832843,
+      "grad_norm": 0.9989821314811707,
+      "learning_rate": 5.249266862170088e-05,
+      "loss": 0.6685,
+      "mean_token_accuracy": 0.7505882322788239,
+      "num_tokens": 368574.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2785923753665689,
+      "grad_norm": 0.8779164552688599,
+      "learning_rate": 5.542521994134897e-05,
+      "loss": 0.6798,
+      "mean_token_accuracy": 0.7446078479290008,
+      "num_tokens": 389054.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.2932551319648094,
+      "grad_norm": 0.8436822295188904,
+      "learning_rate": 5.8357771260997075e-05,
+      "loss": 0.6859,
+      "mean_token_accuracy": 0.7446078419685364,
+      "num_tokens": 409534.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.30791788856304986,
+      "grad_norm": 0.8713858127593994,
+      "learning_rate": 6.129032258064517e-05,
+      "loss": 0.6535,
+      "mean_token_accuracy": 0.7526268303394318,
+      "num_tokens": 429827.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 0.8723043203353882,
+      "learning_rate": 6.422287390029326e-05,
+      "loss": 0.6523,
+      "mean_token_accuracy": 0.7535784304141998,
+      "num_tokens": 450307.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.33724340175953077,
+      "grad_norm": 0.8272885680198669,
+      "learning_rate": 6.715542521994135e-05,
+      "loss": 0.6609,
+      "mean_token_accuracy": 0.749901968240738,
+      "num_tokens": 470787.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.3519061583577713,
+      "grad_norm": 0.6368948221206665,
+      "learning_rate": 7.008797653958945e-05,
+      "loss": 0.6608,
+      "mean_token_accuracy": 0.7493137300014496,
+      "num_tokens": 491267.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.36656891495601174,
+      "grad_norm": 0.6908038854598999,
+      "learning_rate": 7.302052785923754e-05,
+      "loss": 0.666,
+      "mean_token_accuracy": 0.7473100483417511,
+      "num_tokens": 511627.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.3812316715542522,
+      "grad_norm": 0.6815389394760132,
+      "learning_rate": 7.595307917888564e-05,
+      "loss": 0.6493,
+      "mean_token_accuracy": 0.75220587849617,
+      "num_tokens": 532107.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.39589442815249265,
+      "grad_norm": 0.77500319480896,
+      "learning_rate": 7.888563049853373e-05,
+      "loss": 0.6535,
+      "mean_token_accuracy": 0.7530904829502105,
+      "num_tokens": 552475.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.41055718475073316,
+      "grad_norm": 0.7127943634986877,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 0.6654,
+      "mean_token_accuracy": 0.751323539018631,
+      "num_tokens": 572955.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.4252199413489736,
+      "grad_norm": 0.8289512395858765,
+      "learning_rate": 8.475073313782992e-05,
+      "loss": 0.6518,
+      "mean_token_accuracy": 0.7510293960571289,
+      "num_tokens": 593435.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.4398826979472141,
+      "grad_norm": 0.7434380650520325,
+      "learning_rate": 8.7683284457478e-05,
+      "loss": 0.657,
+      "mean_token_accuracy": 0.7497548878192901,
+      "num_tokens": 613915.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.6814386248588562,
+      "learning_rate": 9.06158357771261e-05,
+      "loss": 0.6413,
+      "mean_token_accuracy": 0.7540686309337616,
+      "num_tokens": 634395.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.46920821114369504,
+      "grad_norm": 0.595894455909729,
+      "learning_rate": 9.35483870967742e-05,
+      "loss": 0.647,
+      "mean_token_accuracy": 0.7533333361148834,
+      "num_tokens": 654875.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.4838709677419355,
+      "grad_norm": 0.5797744989395142,
+      "learning_rate": 9.64809384164223e-05,
+      "loss": 0.6517,
+      "mean_token_accuracy": 0.7517156839370728,
+      "num_tokens": 675355.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.49853372434017595,
+      "grad_norm": 0.6610384583473206,
+      "learning_rate": 9.941348973607039e-05,
+      "loss": 0.6519,
+      "mean_token_accuracy": 0.7513235330581665,
+      "num_tokens": 695835.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5131964809384164,
+      "grad_norm": 0.5836912393569946,
+      "learning_rate": 9.999962381348496e-05,
+      "loss": 0.6615,
+      "mean_token_accuracy": 0.7489215791225433,
+      "num_tokens": 716315.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5278592375366569,
+      "grad_norm": 0.6278303265571594,
+      "learning_rate": 9.999809556546922e-05,
+      "loss": 0.6381,
+      "mean_token_accuracy": 0.756617647409439,
+      "num_tokens": 736795.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5425219941348973,
+      "grad_norm": 0.6376463770866394,
+      "learning_rate": 9.999539178019954e-05,
+      "loss": 0.6509,
+      "mean_token_accuracy": 0.7530082106590271,
+      "num_tokens": 757195.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5571847507331378,
+      "grad_norm": 0.5569787621498108,
+      "learning_rate": 9.999151252124639e-05,
+      "loss": 0.6605,
+      "mean_token_accuracy": 0.7477450966835022,
+      "num_tokens": 777675.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.5718475073313783,
+      "grad_norm": 0.583513617515564,
+      "learning_rate": 9.998645787981749e-05,
+      "loss": 0.6459,
+      "mean_token_accuracy": 0.754313725233078,
+      "num_tokens": 798155.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.5865102639296188,
+      "grad_norm": 0.612436830997467,
+      "learning_rate": 9.998022797475572e-05,
+      "loss": 0.6579,
+      "mean_token_accuracy": 0.7481862723827362,
+      "num_tokens": 818635.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6011730205278593,
+      "grad_norm": 0.5789109468460083,
+      "learning_rate": 9.997282295253644e-05,
+      "loss": 0.6564,
+      "mean_token_accuracy": 0.7513725519180298,
+      "num_tokens": 839115.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6158357771260997,
+      "grad_norm": 0.5940632224082947,
+      "learning_rate": 9.996424298726381e-05,
+      "loss": 0.6365,
+      "mean_token_accuracy": 0.7571078360080719,
+      "num_tokens": 859595.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.6304985337243402,
+      "grad_norm": 0.5033205151557922,
+      "learning_rate": 9.995448828066693e-05,
+      "loss": 0.6286,
+      "mean_token_accuracy": 0.7599019646644593,
+      "num_tokens": 880075.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.6101331114768982,
+      "learning_rate": 9.994355906209492e-05,
+      "loss": 0.6399,
+      "mean_token_accuracy": 0.7571568667888642,
+      "num_tokens": 900555.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6598240469208211,
+      "grad_norm": 0.5758415460586548,
+      "learning_rate": 9.993145558851168e-05,
+      "loss": 0.6368,
+      "mean_token_accuracy": 0.7564705967903137,
+      "num_tokens": 921035.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.6744868035190615,
+      "grad_norm": 0.5409122705459595,
+      "learning_rate": 9.991817814448967e-05,
+      "loss": 0.6516,
+      "mean_token_accuracy": 0.747450977563858,
+      "num_tokens": 941515.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.6891495601173021,
+      "grad_norm": 0.5705657005310059,
+      "learning_rate": 9.990372704220345e-05,
+      "loss": 0.6377,
+      "mean_token_accuracy": 0.7563235342502594,
+      "num_tokens": 961995.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7038123167155426,
+      "grad_norm": 0.4983280599117279,
+      "learning_rate": 9.988810262142209e-05,
+      "loss": 0.6616,
+      "mean_token_accuracy": 0.743039208650589,
+      "num_tokens": 982475.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.718475073313783,
+      "grad_norm": 0.5050950646400452,
+      "learning_rate": 9.987130524950141e-05,
+      "loss": 0.6387,
+      "mean_token_accuracy": 0.7534313797950745,
+      "num_tokens": 1002955.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7331378299120235,
+      "grad_norm": 0.6670287251472473,
+      "learning_rate": 9.985333532137514e-05,
+      "loss": 0.6191,
+      "mean_token_accuracy": 0.7647604286670685,
+      "num_tokens": 1023204.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.7478005865102639,
+      "grad_norm": 0.5413070917129517,
+      "learning_rate": 9.983419325954577e-05,
+      "loss": 0.6416,
+      "mean_token_accuracy": 0.7539705872535706,
+      "num_tokens": 1043684.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.7624633431085044,
+      "grad_norm": 0.5095930099487305,
+      "learning_rate": 9.981387951407462e-05,
+      "loss": 0.6264,
+      "mean_token_accuracy": 0.7603431403636932,
+      "num_tokens": 1064164.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.7771260997067448,
+      "grad_norm": 0.5123670101165771,
+      "learning_rate": 9.979239456257113e-05,
+      "loss": 0.6333,
+      "mean_token_accuracy": 0.7584803879261017,
+      "num_tokens": 1084644.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.7917888563049853,
+      "grad_norm": 0.5062909126281738,
+      "learning_rate": 9.976973891018175e-05,
+      "loss": 0.6345,
+      "mean_token_accuracy": 0.7572302341461181,
+      "num_tokens": 1104872.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8064516129032258,
+      "grad_norm": 0.4592231810092926,
+      "learning_rate": 9.974591308957808e-05,
+      "loss": 0.6504,
+      "mean_token_accuracy": 0.7503150522708892,
+      "num_tokens": 1125162.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8211143695014663,
+      "grad_norm": 0.4416564106941223,
+      "learning_rate": 9.972091766094424e-05,
+      "loss": 0.6426,
+      "mean_token_accuracy": 0.7540196180343628,
+      "num_tokens": 1145642.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8357771260997068,
+      "grad_norm": 0.5509306192398071,
+      "learning_rate": 9.969475321196373e-05,
+      "loss": 0.636,
+      "mean_token_accuracy": 0.7576401591300964,
+      "num_tokens": 1165915.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8504398826979472,
+      "grad_norm": 0.616726279258728,
+      "learning_rate": 9.966742035780571e-05,
+      "loss": 0.6374,
+      "mean_token_accuracy": 0.7540196180343628,
+      "num_tokens": 1186395.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.8651026392961877,
+      "grad_norm": 0.593067467212677,
+      "learning_rate": 9.963891974111042e-05,
+      "loss": 0.6264,
+      "mean_token_accuracy": 0.7561764657497406,
+      "num_tokens": 1206875.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.8797653958944281,
+      "grad_norm": 0.4836729168891907,
+      "learning_rate": 9.960925203197408e-05,
+      "loss": 0.6506,
+      "mean_token_accuracy": 0.7518137276172638,
+      "num_tokens": 1227355.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.8944281524926686,
+      "grad_norm": 0.4806676208972931,
+      "learning_rate": 9.957841792793326e-05,
+      "loss": 0.6339,
+      "mean_token_accuracy": 0.7543627500534058,
+      "num_tokens": 1247835.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.5160490274429321,
+      "learning_rate": 9.95464181539483e-05,
+      "loss": 0.6432,
+      "mean_token_accuracy": 0.7526672542095184,
+      "num_tokens": 1268265.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9237536656891495,
+      "grad_norm": 0.5039036870002747,
+      "learning_rate": 9.951325346238638e-05,
+      "loss": 0.655,
+      "mean_token_accuracy": 0.7470588266849518,
+      "num_tokens": 1288745.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9384164222873901,
+      "grad_norm": 0.5036706924438477,
+      "learning_rate": 9.947892463300381e-05,
+      "loss": 0.6505,
+      "mean_token_accuracy": 0.7505392134189606,
+      "num_tokens": 1309225.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.9530791788856305,
+      "grad_norm": 0.5417743921279907,
+      "learning_rate": 9.944343247292771e-05,
+      "loss": 0.6479,
+      "mean_token_accuracy": 0.7542647004127503,
+      "num_tokens": 1329705.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 0.4578988552093506,
+      "learning_rate": 9.940677781663699e-05,
+      "loss": 0.6161,
+      "mean_token_accuracy": 0.7634804010391235,
+      "num_tokens": 1350185.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.9824046920821115,
+      "grad_norm": 0.48247650265693665,
+      "learning_rate": 9.936896152594273e-05,
+      "loss": 0.6477,
+      "mean_token_accuracy": 0.7534803986549378,
+      "num_tokens": 1370665.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.9970674486803519,
+      "grad_norm": 0.5284174084663391,
+      "learning_rate": 9.932998448996798e-05,
+      "loss": 0.6468,
+      "mean_token_accuracy": 0.7506862759590149,
+      "num_tokens": 1391145.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.0117302052785924,
+      "grad_norm": 0.4927270710468292,
+      "learning_rate": 9.92898476251268e-05,
+      "loss": 0.6284,
+      "mean_token_accuracy": 0.757647055387497,
+      "num_tokens": 1410089.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0263929618768328,
+      "grad_norm": 0.5643373131752014,
+      "learning_rate": 9.924855187510274e-05,
+      "loss": 0.6138,
+      "mean_token_accuracy": 0.7658823609352112,
+      "num_tokens": 1430569.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.0410557184750733,
+      "grad_norm": 0.5678701996803284,
+      "learning_rate": 9.920609821082662e-05,
+      "loss": 0.6254,
+      "mean_token_accuracy": 0.7576960742473602,
+      "num_tokens": 1451049.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.0557184750733137,
+      "grad_norm": 0.5296412110328674,
+      "learning_rate": 9.916248763045375e-05,
+      "loss": 0.6121,
+      "mean_token_accuracy": 0.7641666650772094,
+      "num_tokens": 1471529.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.0703812316715542,
+      "grad_norm": 0.5680798292160034,
+      "learning_rate": 9.911772115934042e-05,
+      "loss": 0.6128,
+      "mean_token_accuracy": 0.766274505853653,
+      "num_tokens": 1492009.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.0850439882697946,
+      "grad_norm": 0.4596232771873474,
+      "learning_rate": 9.907179985001978e-05,
+      "loss": 0.6255,
+      "mean_token_accuracy": 0.7588051378726959,
+      "num_tokens": 1512369.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.099706744868035,
+      "grad_norm": 0.6007994413375854,
+      "learning_rate": 9.90247247821772e-05,
+      "loss": 0.6153,
+      "mean_token_accuracy": 0.7644117712974549,
+      "num_tokens": 1532849.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1143695014662756,
+      "grad_norm": 0.5747436881065369,
+      "learning_rate": 9.897649706262473e-05,
+      "loss": 0.6173,
+      "mean_token_accuracy": 0.763137263059616,
+      "num_tokens": 1553329.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.129032258064516,
+      "grad_norm": 0.46429798007011414,
+      "learning_rate": 9.892711782527517e-05,
+      "loss": 0.6342,
+      "mean_token_accuracy": 0.7545098066329956,
+      "num_tokens": 1573809.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.1436950146627567,
+      "grad_norm": 0.5654335618019104,
+      "learning_rate": 9.887658823111544e-05,
+      "loss": 0.635,
+      "mean_token_accuracy": 0.7538235247135162,
+      "num_tokens": 1594289.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.1583577712609971,
+      "grad_norm": 0.5111511945724487,
+      "learning_rate": 9.882490946817915e-05,
+      "loss": 0.6325,
+      "mean_token_accuracy": 0.7592646956443787,
+      "num_tokens": 1614769.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.1730205278592376,
+      "grad_norm": 0.5609337091445923,
+      "learning_rate": 9.877208275151884e-05,
+      "loss": 0.6053,
+      "mean_token_accuracy": 0.7668137192726135,
+      "num_tokens": 1635249.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.187683284457478,
+      "grad_norm": 0.6170390248298645,
+      "learning_rate": 9.871810932317726e-05,
+      "loss": 0.6271,
+      "mean_token_accuracy": 0.7599417567253113,
+      "num_tokens": 1655522.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2023460410557185,
+      "grad_norm": 0.6282625198364258,
+      "learning_rate": 9.866299045215826e-05,
+      "loss": 0.6179,
+      "mean_token_accuracy": 0.7623039245605469,
+      "num_tokens": 1676002.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.217008797653959,
+      "grad_norm": 0.5284767746925354,
+      "learning_rate": 9.860672743439695e-05,
+      "loss": 0.6296,
+      "mean_token_accuracy": 0.7596568644046784,
+      "num_tokens": 1696482.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2316715542521994,
+      "grad_norm": 0.5899022817611694,
+      "learning_rate": 9.854932159272917e-05,
+      "loss": 0.6134,
+      "mean_token_accuracy": 0.7627948582172394,
+      "num_tokens": 1716912.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.2463343108504399,
+      "grad_norm": 0.60678631067276,
+      "learning_rate": 9.849077427686041e-05,
+      "loss": 0.6224,
+      "mean_token_accuracy": 0.7598529517650604,
+      "num_tokens": 1737392.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.2609970674486803,
+      "grad_norm": 0.5868576169013977,
+      "learning_rate": 9.843108686333417e-05,
+      "loss": 0.6199,
+      "mean_token_accuracy": 0.7617156803607941,
+      "num_tokens": 1757872.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.2756598240469208,
+      "grad_norm": 0.6662725210189819,
+      "learning_rate": 9.837026075549945e-05,
+      "loss": 0.6134,
+      "mean_token_accuracy": 0.7634313762187958,
+      "num_tokens": 1778352.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.6636219620704651,
+      "learning_rate": 9.830829738347782e-05,
+      "loss": 0.6301,
+      "mean_token_accuracy": 0.7577941298484803,
+      "num_tokens": 1798832.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.3049853372434017,
+      "grad_norm": 0.498141884803772,
+      "learning_rate": 9.82451982041298e-05,
+      "loss": 0.6372,
+      "mean_token_accuracy": 0.7548039197921753,
+      "num_tokens": 1819312.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3196480938416422,
+      "grad_norm": 0.5891352295875549,
+      "learning_rate": 9.818096470102067e-05,
+      "loss": 0.6289,
+      "mean_token_accuracy": 0.7583333313465118,
+      "num_tokens": 1839792.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.3343108504398826,
+      "grad_norm": 0.5640554428100586,
+      "learning_rate": 9.811559838438542e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7626470625400543,
+      "num_tokens": 1860272.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.3489736070381233,
+      "grad_norm": 0.7103374600410461,
+      "learning_rate": 9.804910079109342e-05,
+      "loss": 0.6176,
+      "mean_token_accuracy": 0.7616600275039673,
+      "num_tokens": 1880420.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.6304973363876343,
+      "learning_rate": 9.798147348461218e-05,
+      "loss": 0.6011,
+      "mean_token_accuracy": 0.7669014155864715,
+      "num_tokens": 1900713.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.3782991202346042,
+      "grad_norm": 0.4847545623779297,
+      "learning_rate": 9.791271805497062e-05,
+      "loss": 0.6328,
+      "mean_token_accuracy": 0.7561274468898773,
+      "num_tokens": 1921193.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.3929618768328447,
+      "grad_norm": 0.6657376885414124,
+      "learning_rate": 9.784283611872169e-05,
+      "loss": 0.6144,
+      "mean_token_accuracy": 0.7649019598960877,
+      "num_tokens": 1941673.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4076246334310851,
+      "grad_norm": 0.581245481967926,
+      "learning_rate": 9.777182931890438e-05,
+      "loss": 0.623,
+      "mean_token_accuracy": 0.7615196108818054,
+      "num_tokens": 1962153.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4222873900293256,
+      "grad_norm": 0.4939914643764496,
+      "learning_rate": 9.769969932500502e-05,
+      "loss": 0.6315,
+      "mean_token_accuracy": 0.7568137228488923,
+      "num_tokens": 1982633.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.436950146627566,
+      "grad_norm": 0.5039688944816589,
+      "learning_rate": 9.762644783291812e-05,
+      "loss": 0.6042,
+      "mean_token_accuracy": 0.7705392241477966,
+      "num_tokens": 2003113.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.4516129032258065,
+      "grad_norm": 0.5869693756103516,
+      "learning_rate": 9.755207656490644e-05,
+      "loss": 0.6063,
+      "mean_token_accuracy": 0.765588229894638,
+      "num_tokens": 2023593.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.466275659824047,
+      "grad_norm": 0.5763869285583496,
+      "learning_rate": 9.747658726956048e-05,
+      "loss": 0.6345,
+      "mean_token_accuracy": 0.7569607853889465,
+      "num_tokens": 2044073.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4809384164222874,
+      "grad_norm": 0.5597388744354248,
+      "learning_rate": 9.739998172175744e-05,
+      "loss": 0.6271,
+      "mean_token_accuracy": 0.7582843244075775,
+      "num_tokens": 2064553.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.4956011730205279,
+      "grad_norm": 0.5474197268486023,
+      "learning_rate": 9.732226172261943e-05,
+      "loss": 0.621,
+      "mean_token_accuracy": 0.7624509751796722,
+      "num_tokens": 2085033.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5102639296187683,
+      "grad_norm": 0.5269312262535095,
+      "learning_rate": 9.724342909947114e-05,
+      "loss": 0.6227,
+      "mean_token_accuracy": 0.7598717212677002,
+      "num_tokens": 2105447.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.5249266862170088,
+      "grad_norm": 0.4974181354045868,
+      "learning_rate": 9.716348570579686e-05,
+      "loss": 0.6086,
+      "mean_token_accuracy": 0.7698944330215454,
+      "num_tokens": 2125815.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.5395894428152492,
+      "grad_norm": 0.5832821726799011,
+      "learning_rate": 9.708243342119695e-05,
+      "loss": 0.6301,
+      "mean_token_accuracy": 0.7575490176677704,
+      "num_tokens": 2146295.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.5542521994134897,
+      "grad_norm": 0.49198174476623535,
+      "learning_rate": 9.700027415134358e-05,
+      "loss": 0.6135,
+      "mean_token_accuracy": 0.7628921508789063,
+      "num_tokens": 2166775.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.5689149560117301,
+      "grad_norm": 0.43694180250167847,
+      "learning_rate": 9.691700982793597e-05,
+      "loss": 0.6243,
+      "mean_token_accuracy": 0.7612254858016968,
+      "num_tokens": 2187255.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.5835777126099706,
+      "grad_norm": 0.5030059814453125,
+      "learning_rate": 9.6832642408655e-05,
+      "loss": 0.6154,
+      "mean_token_accuracy": 0.7645588338375091,
+      "num_tokens": 2207735.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.598240469208211,
+      "grad_norm": 0.5831127166748047,
+      "learning_rate": 9.674717387711706e-05,
+      "loss": 0.6032,
+      "mean_token_accuracy": 0.7698039233684539,
+      "num_tokens": 2228215.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 0.5647640824317932,
+      "learning_rate": 9.66606062428276e-05,
+      "loss": 0.6553,
+      "mean_token_accuracy": 0.7468942880630494,
+      "num_tokens": 2248464.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.627565982404692,
+      "grad_norm": 0.5415534377098083,
+      "learning_rate": 9.657294154113368e-05,
+      "loss": 0.6164,
+      "mean_token_accuracy": 0.761519604921341,
+      "num_tokens": 2268944.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.6422287390029324,
+      "grad_norm": 0.6378477215766907,
+      "learning_rate": 9.648418183317629e-05,
+      "loss": 0.6192,
+      "mean_token_accuracy": 0.7626470625400543,
+      "num_tokens": 2289424.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.6568914956011729,
+      "grad_norm": 0.5039816498756409,
+      "learning_rate": 9.639432920584177e-05,
+      "loss": 0.6186,
+      "mean_token_accuracy": 0.7617647111415863,
+      "num_tokens": 2309904.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.6715542521994133,
+      "grad_norm": 0.545703649520874,
+      "learning_rate": 9.630338577171282e-05,
+      "loss": 0.6358,
+      "mean_token_accuracy": 0.7567647159099579,
+      "num_tokens": 2330384.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.6862170087976538,
+      "grad_norm": 0.5335627198219299,
+      "learning_rate": 9.621135366901874e-05,
+      "loss": 0.6168,
+      "mean_token_accuracy": 0.7622058987617493,
+      "num_tokens": 2350864.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7008797653958945,
+      "grad_norm": 0.5737611055374146,
+      "learning_rate": 9.61182350615853e-05,
+      "loss": 0.6088,
+      "mean_token_accuracy": 0.7669607877731324,
+      "num_tokens": 2371344.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.715542521994135,
+      "grad_norm": 0.5467628240585327,
+      "learning_rate": 9.60240321387837e-05,
+      "loss": 0.6355,
+      "mean_token_accuracy": 0.7537745118141175,
+      "num_tokens": 2391824.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.7302052785923754,
+      "grad_norm": 0.47698599100112915,
+      "learning_rate": 9.592874711547922e-05,
+      "loss": 0.6157,
+      "mean_token_accuracy": 0.7636764705181122,
+      "num_tokens": 2412304.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.7448680351906158,
+      "grad_norm": 0.5102219581604004,
+      "learning_rate": 9.583238223197906e-05,
+      "loss": 0.6037,
+      "mean_token_accuracy": 0.7686274528503418,
+      "num_tokens": 2432784.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.7595307917888563,
+      "grad_norm": 0.5764709115028381,
+      "learning_rate": 9.573493975397975e-05,
+      "loss": 0.6321,
+      "mean_token_accuracy": 0.7561274468898773,
+      "num_tokens": 2453264.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7741935483870968,
+      "grad_norm": 0.5202457904815674,
+      "learning_rate": 9.56364219725138e-05,
+      "loss": 0.6399,
+      "mean_token_accuracy": 0.7505392134189606,
+      "num_tokens": 2473744.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.7888563049853372,
+      "grad_norm": 0.5214654803276062,
+      "learning_rate": 9.553683120389592e-05,
+      "loss": 0.6161,
+      "mean_token_accuracy": 0.7630882322788238,
+      "num_tokens": 2494224.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8035190615835777,
+      "grad_norm": 0.5128310322761536,
+      "learning_rate": 9.543616978966842e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7627941191196441,
+      "num_tokens": 2514704.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.5823948383331299,
+      "learning_rate": 9.53344400965463e-05,
+      "loss": 0.6354,
+      "mean_token_accuracy": 0.756078428030014,
+      "num_tokens": 2535184.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.8328445747800588,
+      "grad_norm": 0.568189799785614,
+      "learning_rate": 9.523164451636157e-05,
+      "loss": 0.6168,
+      "mean_token_accuracy": 0.7599999964237213,
+      "num_tokens": 2555664.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.8475073313782993,
+      "grad_norm": 0.5598325133323669,
+      "learning_rate": 9.512778546600696e-05,
+      "loss": 0.6292,
+      "mean_token_accuracy": 0.75686274766922,
+      "num_tokens": 2576144.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.8621700879765397,
+      "grad_norm": 0.5429131388664246,
+      "learning_rate": 9.50228653873791e-05,
+      "loss": 0.6283,
+      "mean_token_accuracy": 0.7598039209842682,
+      "num_tokens": 2596624.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.8768328445747802,
+      "grad_norm": 0.4898570775985718,
+      "learning_rate": 9.491688674732123e-05,
+      "loss": 0.6406,
+      "mean_token_accuracy": 0.7537254869937897,
+      "num_tokens": 2617104.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.8914956011730206,
+      "grad_norm": 0.5072643756866455,
+      "learning_rate": 9.480985203756501e-05,
+      "loss": 0.6288,
+      "mean_token_accuracy": 0.7583333313465118,
+      "num_tokens": 2637584.0,
+      "step": 1290
+    },
+    {
+      "epoch": 1.906158357771261,
+      "grad_norm": 0.5450229048728943,
+      "learning_rate": 9.470176377467206e-05,
+      "loss": 0.6135,
+      "mean_token_accuracy": 0.7631862699985504,
+      "num_tokens": 2658064.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.9208211143695015,
+      "grad_norm": 0.5232940912246704,
+      "learning_rate": 9.45926244999748e-05,
+      "loss": 0.6196,
+      "mean_token_accuracy": 0.7628431499004364,
+      "num_tokens": 2678544.0,
+      "step": 1310
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 0.5383533239364624,
+      "learning_rate": 9.44824367795166e-05,
+      "loss": 0.6046,
+      "mean_token_accuracy": 0.7665885031223297,
+      "num_tokens": 2698834.0,
+      "step": 1320
+    },
+    {
+      "epoch": 1.9501466275659824,
+      "grad_norm": 0.4725590944290161,
+      "learning_rate": 9.437120320399158e-05,
+      "loss": 0.6297,
+      "mean_token_accuracy": 0.7592157006263733,
+      "num_tokens": 2719314.0,
+      "step": 1330
+    },
+    {
+      "epoch": 1.964809384164223,
+      "grad_norm": 0.48085474967956543,
+      "learning_rate": 9.425892638868356e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7608333349227905,
+      "num_tokens": 2739794.0,
+      "step": 1340
+    },
+    {
+      "epoch": 1.9794721407624634,
+      "grad_norm": 0.5690534710884094,
+      "learning_rate": 9.414560897340468e-05,
+      "loss": 0.6349,
+      "mean_token_accuracy": 0.75343137383461,
+      "num_tokens": 2760274.0,
+      "step": 1350
+    },
+    {
+      "epoch": 1.9941348973607038,
+      "grad_norm": 0.5363736152648926,
+      "learning_rate": 9.403125362243328e-05,
+      "loss": 0.6124,
+      "mean_token_accuracy": 0.7653431355953216,
+      "num_tokens": 2780754.0,
+      "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": 1.187170806398976e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-1364/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4734d6626d9f4e5de52d260e514c2c8d854a75e2ff6292ebf0fe2fce39775fa5
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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": [
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-2046/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5583cc4fdd312640e5f64442a2be0b4de6062a4e134e3436ff3c2ac5b9d04772
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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_s2_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_s2_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_s2_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_s2_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": 3.478421211242676,
+      "learning_rate": 2.6392961876832847e-06,
+      "loss": 2.49,
+      "mean_token_accuracy": 0.5404902040958405,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.02932551319648094,
+      "grad_norm": 4.437029838562012,
+      "learning_rate": 5.571847507331378e-06,
+      "loss": 2.4861,
+      "mean_token_accuracy": 0.5374019622802735,
+      "num_tokens": 40960.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.04398826979472141,
+      "grad_norm": 3.2707436084747314,
+      "learning_rate": 8.504398826979472e-06,
+      "loss": 2.3345,
+      "mean_token_accuracy": 0.5500490128993988,
+      "num_tokens": 61440.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.05865102639296188,
+      "grad_norm": 1.9522887468338013,
+      "learning_rate": 1.1436950146627567e-05,
+      "loss": 2.0409,
+      "mean_token_accuracy": 0.5806862652301789,
+      "num_tokens": 81920.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07331378299120235,
+      "grad_norm": 1.3734278678894043,
+      "learning_rate": 1.4369501466275662e-05,
+      "loss": 1.7743,
+      "mean_token_accuracy": 0.5944117605686188,
+      "num_tokens": 102400.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.08797653958944282,
+      "grad_norm": 1.124900221824646,
+      "learning_rate": 1.7302052785923756e-05,
+      "loss": 1.5557,
+      "mean_token_accuracy": 0.6044607698917389,
+      "num_tokens": 122880.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.10263929618768329,
+      "grad_norm": 0.8481243848800659,
+      "learning_rate": 2.0234604105571847e-05,
+      "loss": 1.383,
+      "mean_token_accuracy": 0.620245099067688,
+      "num_tokens": 143360.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.11730205278592376,
+      "grad_norm": 0.864518940448761,
+      "learning_rate": 2.3167155425219943e-05,
+      "loss": 1.2221,
+      "mean_token_accuracy": 0.6459313809871674,
+      "num_tokens": 163840.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.13196480938416422,
+      "grad_norm": 0.9745388627052307,
+      "learning_rate": 2.6099706744868034e-05,
+      "loss": 1.0528,
+      "mean_token_accuracy": 0.6676470518112183,
+      "num_tokens": 184320.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.1466275659824047,
+      "grad_norm": 1.1379441022872925,
+      "learning_rate": 2.9032258064516133e-05,
+      "loss": 0.9449,
+      "mean_token_accuracy": 0.6830392181873322,
+      "num_tokens": 204800.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.16129032258064516,
+      "grad_norm": 1.1655960083007812,
+      "learning_rate": 3.1964809384164225e-05,
+      "loss": 0.8282,
+      "mean_token_accuracy": 0.7080882310867309,
+      "num_tokens": 225280.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.17595307917888564,
+      "grad_norm": 1.3215491771697998,
+      "learning_rate": 3.489736070381232e-05,
+      "loss": 0.7662,
+      "mean_token_accuracy": 0.7250490248203277,
+      "num_tokens": 245760.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.1906158357771261,
+      "grad_norm": 1.0598912239074707,
+      "learning_rate": 3.7829912023460415e-05,
+      "loss": 0.7364,
+      "mean_token_accuracy": 0.7327941119670868,
+      "num_tokens": 266240.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.20527859237536658,
+      "grad_norm": 1.122361183166504,
+      "learning_rate": 4.076246334310851e-05,
+      "loss": 0.723,
+      "mean_token_accuracy": 0.7349509775638581,
+      "num_tokens": 286720.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.21994134897360704,
+      "grad_norm": 1.1284314393997192,
+      "learning_rate": 4.36950146627566e-05,
+      "loss": 0.7266,
+      "mean_token_accuracy": 0.7305392146110534,
+      "num_tokens": 307200.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.23460410557184752,
+      "grad_norm": 0.8642133474349976,
+      "learning_rate": 4.6627565982404694e-05,
+      "loss": 0.6996,
+      "mean_token_accuracy": 0.7395318567752838,
+      "num_tokens": 327614.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.24926686217008798,
+      "grad_norm": 0.9549291729927063,
+      "learning_rate": 4.956011730205279e-05,
+      "loss": 0.7056,
+      "mean_token_accuracy": 0.7378431379795074,
+      "num_tokens": 348094.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.26392961876832843,
+      "grad_norm": 0.9989821314811707,
+      "learning_rate": 5.249266862170088e-05,
+      "loss": 0.6685,
+      "mean_token_accuracy": 0.7505882322788239,
+      "num_tokens": 368574.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2785923753665689,
+      "grad_norm": 0.8779164552688599,
+      "learning_rate": 5.542521994134897e-05,
+      "loss": 0.6798,
+      "mean_token_accuracy": 0.7446078479290008,
+      "num_tokens": 389054.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.2932551319648094,
+      "grad_norm": 0.8436822295188904,
+      "learning_rate": 5.8357771260997075e-05,
+      "loss": 0.6859,
+      "mean_token_accuracy": 0.7446078419685364,
+      "num_tokens": 409534.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.30791788856304986,
+      "grad_norm": 0.8713858127593994,
+      "learning_rate": 6.129032258064517e-05,
+      "loss": 0.6535,
+      "mean_token_accuracy": 0.7526268303394318,
+      "num_tokens": 429827.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 0.8723043203353882,
+      "learning_rate": 6.422287390029326e-05,
+      "loss": 0.6523,
+      "mean_token_accuracy": 0.7535784304141998,
+      "num_tokens": 450307.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.33724340175953077,
+      "grad_norm": 0.8272885680198669,
+      "learning_rate": 6.715542521994135e-05,
+      "loss": 0.6609,
+      "mean_token_accuracy": 0.749901968240738,
+      "num_tokens": 470787.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.3519061583577713,
+      "grad_norm": 0.6368948221206665,
+      "learning_rate": 7.008797653958945e-05,
+      "loss": 0.6608,
+      "mean_token_accuracy": 0.7493137300014496,
+      "num_tokens": 491267.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.36656891495601174,
+      "grad_norm": 0.6908038854598999,
+      "learning_rate": 7.302052785923754e-05,
+      "loss": 0.666,
+      "mean_token_accuracy": 0.7473100483417511,
+      "num_tokens": 511627.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.3812316715542522,
+      "grad_norm": 0.6815389394760132,
+      "learning_rate": 7.595307917888564e-05,
+      "loss": 0.6493,
+      "mean_token_accuracy": 0.75220587849617,
+      "num_tokens": 532107.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.39589442815249265,
+      "grad_norm": 0.77500319480896,
+      "learning_rate": 7.888563049853373e-05,
+      "loss": 0.6535,
+      "mean_token_accuracy": 0.7530904829502105,
+      "num_tokens": 552475.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.41055718475073316,
+      "grad_norm": 0.7127943634986877,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 0.6654,
+      "mean_token_accuracy": 0.751323539018631,
+      "num_tokens": 572955.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.4252199413489736,
+      "grad_norm": 0.8289512395858765,
+      "learning_rate": 8.475073313782992e-05,
+      "loss": 0.6518,
+      "mean_token_accuracy": 0.7510293960571289,
+      "num_tokens": 593435.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.4398826979472141,
+      "grad_norm": 0.7434380650520325,
+      "learning_rate": 8.7683284457478e-05,
+      "loss": 0.657,
+      "mean_token_accuracy": 0.7497548878192901,
+      "num_tokens": 613915.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.6814386248588562,
+      "learning_rate": 9.06158357771261e-05,
+      "loss": 0.6413,
+      "mean_token_accuracy": 0.7540686309337616,
+      "num_tokens": 634395.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.46920821114369504,
+      "grad_norm": 0.595894455909729,
+      "learning_rate": 9.35483870967742e-05,
+      "loss": 0.647,
+      "mean_token_accuracy": 0.7533333361148834,
+      "num_tokens": 654875.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.4838709677419355,
+      "grad_norm": 0.5797744989395142,
+      "learning_rate": 9.64809384164223e-05,
+      "loss": 0.6517,
+      "mean_token_accuracy": 0.7517156839370728,
+      "num_tokens": 675355.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.49853372434017595,
+      "grad_norm": 0.6610384583473206,
+      "learning_rate": 9.941348973607039e-05,
+      "loss": 0.6519,
+      "mean_token_accuracy": 0.7513235330581665,
+      "num_tokens": 695835.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5131964809384164,
+      "grad_norm": 0.5836912393569946,
+      "learning_rate": 9.999962381348496e-05,
+      "loss": 0.6615,
+      "mean_token_accuracy": 0.7489215791225433,
+      "num_tokens": 716315.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5278592375366569,
+      "grad_norm": 0.6278303265571594,
+      "learning_rate": 9.999809556546922e-05,
+      "loss": 0.6381,
+      "mean_token_accuracy": 0.756617647409439,
+      "num_tokens": 736795.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5425219941348973,
+      "grad_norm": 0.6376463770866394,
+      "learning_rate": 9.999539178019954e-05,
+      "loss": 0.6509,
+      "mean_token_accuracy": 0.7530082106590271,
+      "num_tokens": 757195.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5571847507331378,
+      "grad_norm": 0.5569787621498108,
+      "learning_rate": 9.999151252124639e-05,
+      "loss": 0.6605,
+      "mean_token_accuracy": 0.7477450966835022,
+      "num_tokens": 777675.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.5718475073313783,
+      "grad_norm": 0.583513617515564,
+      "learning_rate": 9.998645787981749e-05,
+      "loss": 0.6459,
+      "mean_token_accuracy": 0.754313725233078,
+      "num_tokens": 798155.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.5865102639296188,
+      "grad_norm": 0.612436830997467,
+      "learning_rate": 9.998022797475572e-05,
+      "loss": 0.6579,
+      "mean_token_accuracy": 0.7481862723827362,
+      "num_tokens": 818635.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6011730205278593,
+      "grad_norm": 0.5789109468460083,
+      "learning_rate": 9.997282295253644e-05,
+      "loss": 0.6564,
+      "mean_token_accuracy": 0.7513725519180298,
+      "num_tokens": 839115.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6158357771260997,
+      "grad_norm": 0.5940632224082947,
+      "learning_rate": 9.996424298726381e-05,
+      "loss": 0.6365,
+      "mean_token_accuracy": 0.7571078360080719,
+      "num_tokens": 859595.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.6304985337243402,
+      "grad_norm": 0.5033205151557922,
+      "learning_rate": 9.995448828066693e-05,
+      "loss": 0.6286,
+      "mean_token_accuracy": 0.7599019646644593,
+      "num_tokens": 880075.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.6101331114768982,
+      "learning_rate": 9.994355906209492e-05,
+      "loss": 0.6399,
+      "mean_token_accuracy": 0.7571568667888642,
+      "num_tokens": 900555.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6598240469208211,
+      "grad_norm": 0.5758415460586548,
+      "learning_rate": 9.993145558851168e-05,
+      "loss": 0.6368,
+      "mean_token_accuracy": 0.7564705967903137,
+      "num_tokens": 921035.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.6744868035190615,
+      "grad_norm": 0.5409122705459595,
+      "learning_rate": 9.991817814448967e-05,
+      "loss": 0.6516,
+      "mean_token_accuracy": 0.747450977563858,
+      "num_tokens": 941515.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.6891495601173021,
+      "grad_norm": 0.5705657005310059,
+      "learning_rate": 9.990372704220345e-05,
+      "loss": 0.6377,
+      "mean_token_accuracy": 0.7563235342502594,
+      "num_tokens": 961995.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7038123167155426,
+      "grad_norm": 0.4983280599117279,
+      "learning_rate": 9.988810262142209e-05,
+      "loss": 0.6616,
+      "mean_token_accuracy": 0.743039208650589,
+      "num_tokens": 982475.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.718475073313783,
+      "grad_norm": 0.5050950646400452,
+      "learning_rate": 9.987130524950141e-05,
+      "loss": 0.6387,
+      "mean_token_accuracy": 0.7534313797950745,
+      "num_tokens": 1002955.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7331378299120235,
+      "grad_norm": 0.6670287251472473,
+      "learning_rate": 9.985333532137514e-05,
+      "loss": 0.6191,
+      "mean_token_accuracy": 0.7647604286670685,
+      "num_tokens": 1023204.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.7478005865102639,
+      "grad_norm": 0.5413070917129517,
+      "learning_rate": 9.983419325954577e-05,
+      "loss": 0.6416,
+      "mean_token_accuracy": 0.7539705872535706,
+      "num_tokens": 1043684.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.7624633431085044,
+      "grad_norm": 0.5095930099487305,
+      "learning_rate": 9.981387951407462e-05,
+      "loss": 0.6264,
+      "mean_token_accuracy": 0.7603431403636932,
+      "num_tokens": 1064164.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.7771260997067448,
+      "grad_norm": 0.5123670101165771,
+      "learning_rate": 9.979239456257113e-05,
+      "loss": 0.6333,
+      "mean_token_accuracy": 0.7584803879261017,
+      "num_tokens": 1084644.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.7917888563049853,
+      "grad_norm": 0.5062909126281738,
+      "learning_rate": 9.976973891018175e-05,
+      "loss": 0.6345,
+      "mean_token_accuracy": 0.7572302341461181,
+      "num_tokens": 1104872.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8064516129032258,
+      "grad_norm": 0.4592231810092926,
+      "learning_rate": 9.974591308957808e-05,
+      "loss": 0.6504,
+      "mean_token_accuracy": 0.7503150522708892,
+      "num_tokens": 1125162.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8211143695014663,
+      "grad_norm": 0.4416564106941223,
+      "learning_rate": 9.972091766094424e-05,
+      "loss": 0.6426,
+      "mean_token_accuracy": 0.7540196180343628,
+      "num_tokens": 1145642.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8357771260997068,
+      "grad_norm": 0.5509306192398071,
+      "learning_rate": 9.969475321196373e-05,
+      "loss": 0.636,
+      "mean_token_accuracy": 0.7576401591300964,
+      "num_tokens": 1165915.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8504398826979472,
+      "grad_norm": 0.616726279258728,
+      "learning_rate": 9.966742035780571e-05,
+      "loss": 0.6374,
+      "mean_token_accuracy": 0.7540196180343628,
+      "num_tokens": 1186395.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.8651026392961877,
+      "grad_norm": 0.593067467212677,
+      "learning_rate": 9.963891974111042e-05,
+      "loss": 0.6264,
+      "mean_token_accuracy": 0.7561764657497406,
+      "num_tokens": 1206875.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.8797653958944281,
+      "grad_norm": 0.4836729168891907,
+      "learning_rate": 9.960925203197408e-05,
+      "loss": 0.6506,
+      "mean_token_accuracy": 0.7518137276172638,
+      "num_tokens": 1227355.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.8944281524926686,
+      "grad_norm": 0.4806676208972931,
+      "learning_rate": 9.957841792793326e-05,
+      "loss": 0.6339,
+      "mean_token_accuracy": 0.7543627500534058,
+      "num_tokens": 1247835.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.5160490274429321,
+      "learning_rate": 9.95464181539483e-05,
+      "loss": 0.6432,
+      "mean_token_accuracy": 0.7526672542095184,
+      "num_tokens": 1268265.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9237536656891495,
+      "grad_norm": 0.5039036870002747,
+      "learning_rate": 9.951325346238638e-05,
+      "loss": 0.655,
+      "mean_token_accuracy": 0.7470588266849518,
+      "num_tokens": 1288745.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9384164222873901,
+      "grad_norm": 0.5036706924438477,
+      "learning_rate": 9.947892463300381e-05,
+      "loss": 0.6505,
+      "mean_token_accuracy": 0.7505392134189606,
+      "num_tokens": 1309225.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.9530791788856305,
+      "grad_norm": 0.5417743921279907,
+      "learning_rate": 9.944343247292771e-05,
+      "loss": 0.6479,
+      "mean_token_accuracy": 0.7542647004127503,
+      "num_tokens": 1329705.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 0.4578988552093506,
+      "learning_rate": 9.940677781663699e-05,
+      "loss": 0.6161,
+      "mean_token_accuracy": 0.7634804010391235,
+      "num_tokens": 1350185.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.9824046920821115,
+      "grad_norm": 0.48247650265693665,
+      "learning_rate": 9.936896152594273e-05,
+      "loss": 0.6477,
+      "mean_token_accuracy": 0.7534803986549378,
+      "num_tokens": 1370665.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.9970674486803519,
+      "grad_norm": 0.5284174084663391,
+      "learning_rate": 9.932998448996798e-05,
+      "loss": 0.6468,
+      "mean_token_accuracy": 0.7506862759590149,
+      "num_tokens": 1391145.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.0117302052785924,
+      "grad_norm": 0.4927270710468292,
+      "learning_rate": 9.92898476251268e-05,
+      "loss": 0.6284,
+      "mean_token_accuracy": 0.757647055387497,
+      "num_tokens": 1410089.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0263929618768328,
+      "grad_norm": 0.5643373131752014,
+      "learning_rate": 9.924855187510274e-05,
+      "loss": 0.6138,
+      "mean_token_accuracy": 0.7658823609352112,
+      "num_tokens": 1430569.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.0410557184750733,
+      "grad_norm": 0.5678701996803284,
+      "learning_rate": 9.920609821082662e-05,
+      "loss": 0.6254,
+      "mean_token_accuracy": 0.7576960742473602,
+      "num_tokens": 1451049.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.0557184750733137,
+      "grad_norm": 0.5296412110328674,
+      "learning_rate": 9.916248763045375e-05,
+      "loss": 0.6121,
+      "mean_token_accuracy": 0.7641666650772094,
+      "num_tokens": 1471529.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.0703812316715542,
+      "grad_norm": 0.5680798292160034,
+      "learning_rate": 9.911772115934042e-05,
+      "loss": 0.6128,
+      "mean_token_accuracy": 0.766274505853653,
+      "num_tokens": 1492009.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.0850439882697946,
+      "grad_norm": 0.4596232771873474,
+      "learning_rate": 9.907179985001978e-05,
+      "loss": 0.6255,
+      "mean_token_accuracy": 0.7588051378726959,
+      "num_tokens": 1512369.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.099706744868035,
+      "grad_norm": 0.6007994413375854,
+      "learning_rate": 9.90247247821772e-05,
+      "loss": 0.6153,
+      "mean_token_accuracy": 0.7644117712974549,
+      "num_tokens": 1532849.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1143695014662756,
+      "grad_norm": 0.5747436881065369,
+      "learning_rate": 9.897649706262473e-05,
+      "loss": 0.6173,
+      "mean_token_accuracy": 0.763137263059616,
+      "num_tokens": 1553329.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.129032258064516,
+      "grad_norm": 0.46429798007011414,
+      "learning_rate": 9.892711782527517e-05,
+      "loss": 0.6342,
+      "mean_token_accuracy": 0.7545098066329956,
+      "num_tokens": 1573809.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.1436950146627567,
+      "grad_norm": 0.5654335618019104,
+      "learning_rate": 9.887658823111544e-05,
+      "loss": 0.635,
+      "mean_token_accuracy": 0.7538235247135162,
+      "num_tokens": 1594289.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.1583577712609971,
+      "grad_norm": 0.5111511945724487,
+      "learning_rate": 9.882490946817915e-05,
+      "loss": 0.6325,
+      "mean_token_accuracy": 0.7592646956443787,
+      "num_tokens": 1614769.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.1730205278592376,
+      "grad_norm": 0.5609337091445923,
+      "learning_rate": 9.877208275151884e-05,
+      "loss": 0.6053,
+      "mean_token_accuracy": 0.7668137192726135,
+      "num_tokens": 1635249.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.187683284457478,
+      "grad_norm": 0.6170390248298645,
+      "learning_rate": 9.871810932317726e-05,
+      "loss": 0.6271,
+      "mean_token_accuracy": 0.7599417567253113,
+      "num_tokens": 1655522.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2023460410557185,
+      "grad_norm": 0.6282625198364258,
+      "learning_rate": 9.866299045215826e-05,
+      "loss": 0.6179,
+      "mean_token_accuracy": 0.7623039245605469,
+      "num_tokens": 1676002.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.217008797653959,
+      "grad_norm": 0.5284767746925354,
+      "learning_rate": 9.860672743439695e-05,
+      "loss": 0.6296,
+      "mean_token_accuracy": 0.7596568644046784,
+      "num_tokens": 1696482.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2316715542521994,
+      "grad_norm": 0.5899022817611694,
+      "learning_rate": 9.854932159272917e-05,
+      "loss": 0.6134,
+      "mean_token_accuracy": 0.7627948582172394,
+      "num_tokens": 1716912.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.2463343108504399,
+      "grad_norm": 0.60678631067276,
+      "learning_rate": 9.849077427686041e-05,
+      "loss": 0.6224,
+      "mean_token_accuracy": 0.7598529517650604,
+      "num_tokens": 1737392.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.2609970674486803,
+      "grad_norm": 0.5868576169013977,
+      "learning_rate": 9.843108686333417e-05,
+      "loss": 0.6199,
+      "mean_token_accuracy": 0.7617156803607941,
+      "num_tokens": 1757872.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.2756598240469208,
+      "grad_norm": 0.6662725210189819,
+      "learning_rate": 9.837026075549945e-05,
+      "loss": 0.6134,
+      "mean_token_accuracy": 0.7634313762187958,
+      "num_tokens": 1778352.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.6636219620704651,
+      "learning_rate": 9.830829738347782e-05,
+      "loss": 0.6301,
+      "mean_token_accuracy": 0.7577941298484803,
+      "num_tokens": 1798832.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.3049853372434017,
+      "grad_norm": 0.498141884803772,
+      "learning_rate": 9.82451982041298e-05,
+      "loss": 0.6372,
+      "mean_token_accuracy": 0.7548039197921753,
+      "num_tokens": 1819312.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3196480938416422,
+      "grad_norm": 0.5891352295875549,
+      "learning_rate": 9.818096470102067e-05,
+      "loss": 0.6289,
+      "mean_token_accuracy": 0.7583333313465118,
+      "num_tokens": 1839792.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.3343108504398826,
+      "grad_norm": 0.5640554428100586,
+      "learning_rate": 9.811559838438542e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7626470625400543,
+      "num_tokens": 1860272.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.3489736070381233,
+      "grad_norm": 0.7103374600410461,
+      "learning_rate": 9.804910079109342e-05,
+      "loss": 0.6176,
+      "mean_token_accuracy": 0.7616600275039673,
+      "num_tokens": 1880420.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.6304973363876343,
+      "learning_rate": 9.798147348461218e-05,
+      "loss": 0.6011,
+      "mean_token_accuracy": 0.7669014155864715,
+      "num_tokens": 1900713.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.3782991202346042,
+      "grad_norm": 0.4847545623779297,
+      "learning_rate": 9.791271805497062e-05,
+      "loss": 0.6328,
+      "mean_token_accuracy": 0.7561274468898773,
+      "num_tokens": 1921193.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.3929618768328447,
+      "grad_norm": 0.6657376885414124,
+      "learning_rate": 9.784283611872169e-05,
+      "loss": 0.6144,
+      "mean_token_accuracy": 0.7649019598960877,
+      "num_tokens": 1941673.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4076246334310851,
+      "grad_norm": 0.581245481967926,
+      "learning_rate": 9.777182931890438e-05,
+      "loss": 0.623,
+      "mean_token_accuracy": 0.7615196108818054,
+      "num_tokens": 1962153.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4222873900293256,
+      "grad_norm": 0.4939914643764496,
+      "learning_rate": 9.769969932500502e-05,
+      "loss": 0.6315,
+      "mean_token_accuracy": 0.7568137228488923,
+      "num_tokens": 1982633.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.436950146627566,
+      "grad_norm": 0.5039688944816589,
+      "learning_rate": 9.762644783291812e-05,
+      "loss": 0.6042,
+      "mean_token_accuracy": 0.7705392241477966,
+      "num_tokens": 2003113.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.4516129032258065,
+      "grad_norm": 0.5869693756103516,
+      "learning_rate": 9.755207656490644e-05,
+      "loss": 0.6063,
+      "mean_token_accuracy": 0.765588229894638,
+      "num_tokens": 2023593.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.466275659824047,
+      "grad_norm": 0.5763869285583496,
+      "learning_rate": 9.747658726956048e-05,
+      "loss": 0.6345,
+      "mean_token_accuracy": 0.7569607853889465,
+      "num_tokens": 2044073.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4809384164222874,
+      "grad_norm": 0.5597388744354248,
+      "learning_rate": 9.739998172175744e-05,
+      "loss": 0.6271,
+      "mean_token_accuracy": 0.7582843244075775,
+      "num_tokens": 2064553.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.4956011730205279,
+      "grad_norm": 0.5474197268486023,
+      "learning_rate": 9.732226172261943e-05,
+      "loss": 0.621,
+      "mean_token_accuracy": 0.7624509751796722,
+      "num_tokens": 2085033.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5102639296187683,
+      "grad_norm": 0.5269312262535095,
+      "learning_rate": 9.724342909947114e-05,
+      "loss": 0.6227,
+      "mean_token_accuracy": 0.7598717212677002,
+      "num_tokens": 2105447.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.5249266862170088,
+      "grad_norm": 0.4974181354045868,
+      "learning_rate": 9.716348570579686e-05,
+      "loss": 0.6086,
+      "mean_token_accuracy": 0.7698944330215454,
+      "num_tokens": 2125815.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.5395894428152492,
+      "grad_norm": 0.5832821726799011,
+      "learning_rate": 9.708243342119695e-05,
+      "loss": 0.6301,
+      "mean_token_accuracy": 0.7575490176677704,
+      "num_tokens": 2146295.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.5542521994134897,
+      "grad_norm": 0.49198174476623535,
+      "learning_rate": 9.700027415134358e-05,
+      "loss": 0.6135,
+      "mean_token_accuracy": 0.7628921508789063,
+      "num_tokens": 2166775.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.5689149560117301,
+      "grad_norm": 0.43694180250167847,
+      "learning_rate": 9.691700982793597e-05,
+      "loss": 0.6243,
+      "mean_token_accuracy": 0.7612254858016968,
+      "num_tokens": 2187255.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.5835777126099706,
+      "grad_norm": 0.5030059814453125,
+      "learning_rate": 9.6832642408655e-05,
+      "loss": 0.6154,
+      "mean_token_accuracy": 0.7645588338375091,
+      "num_tokens": 2207735.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.598240469208211,
+      "grad_norm": 0.5831127166748047,
+      "learning_rate": 9.674717387711706e-05,
+      "loss": 0.6032,
+      "mean_token_accuracy": 0.7698039233684539,
+      "num_tokens": 2228215.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 0.5647640824317932,
+      "learning_rate": 9.66606062428276e-05,
+      "loss": 0.6553,
+      "mean_token_accuracy": 0.7468942880630494,
+      "num_tokens": 2248464.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.627565982404692,
+      "grad_norm": 0.5415534377098083,
+      "learning_rate": 9.657294154113368e-05,
+      "loss": 0.6164,
+      "mean_token_accuracy": 0.761519604921341,
+      "num_tokens": 2268944.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.6422287390029324,
+      "grad_norm": 0.6378477215766907,
+      "learning_rate": 9.648418183317629e-05,
+      "loss": 0.6192,
+      "mean_token_accuracy": 0.7626470625400543,
+      "num_tokens": 2289424.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.6568914956011729,
+      "grad_norm": 0.5039816498756409,
+      "learning_rate": 9.639432920584177e-05,
+      "loss": 0.6186,
+      "mean_token_accuracy": 0.7617647111415863,
+      "num_tokens": 2309904.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.6715542521994133,
+      "grad_norm": 0.545703649520874,
+      "learning_rate": 9.630338577171282e-05,
+      "loss": 0.6358,
+      "mean_token_accuracy": 0.7567647159099579,
+      "num_tokens": 2330384.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.6862170087976538,
+      "grad_norm": 0.5335627198219299,
+      "learning_rate": 9.621135366901874e-05,
+      "loss": 0.6168,
+      "mean_token_accuracy": 0.7622058987617493,
+      "num_tokens": 2350864.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7008797653958945,
+      "grad_norm": 0.5737611055374146,
+      "learning_rate": 9.61182350615853e-05,
+      "loss": 0.6088,
+      "mean_token_accuracy": 0.7669607877731324,
+      "num_tokens": 2371344.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.715542521994135,
+      "grad_norm": 0.5467628240585327,
+      "learning_rate": 9.60240321387837e-05,
+      "loss": 0.6355,
+      "mean_token_accuracy": 0.7537745118141175,
+      "num_tokens": 2391824.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.7302052785923754,
+      "grad_norm": 0.47698599100112915,
+      "learning_rate": 9.592874711547922e-05,
+      "loss": 0.6157,
+      "mean_token_accuracy": 0.7636764705181122,
+      "num_tokens": 2412304.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.7448680351906158,
+      "grad_norm": 0.5102219581604004,
+      "learning_rate": 9.583238223197906e-05,
+      "loss": 0.6037,
+      "mean_token_accuracy": 0.7686274528503418,
+      "num_tokens": 2432784.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.7595307917888563,
+      "grad_norm": 0.5764709115028381,
+      "learning_rate": 9.573493975397975e-05,
+      "loss": 0.6321,
+      "mean_token_accuracy": 0.7561274468898773,
+      "num_tokens": 2453264.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7741935483870968,
+      "grad_norm": 0.5202457904815674,
+      "learning_rate": 9.56364219725138e-05,
+      "loss": 0.6399,
+      "mean_token_accuracy": 0.7505392134189606,
+      "num_tokens": 2473744.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.7888563049853372,
+      "grad_norm": 0.5214654803276062,
+      "learning_rate": 9.553683120389592e-05,
+      "loss": 0.6161,
+      "mean_token_accuracy": 0.7630882322788238,
+      "num_tokens": 2494224.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8035190615835777,
+      "grad_norm": 0.5128310322761536,
+      "learning_rate": 9.543616978966842e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7627941191196441,
+      "num_tokens": 2514704.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.5823948383331299,
+      "learning_rate": 9.53344400965463e-05,
+      "loss": 0.6354,
+      "mean_token_accuracy": 0.756078428030014,
+      "num_tokens": 2535184.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.8328445747800588,
+      "grad_norm": 0.568189799785614,
+      "learning_rate": 9.523164451636157e-05,
+      "loss": 0.6168,
+      "mean_token_accuracy": 0.7599999964237213,
+      "num_tokens": 2555664.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.8475073313782993,
+      "grad_norm": 0.5598325133323669,
+      "learning_rate": 9.512778546600696e-05,
+      "loss": 0.6292,
+      "mean_token_accuracy": 0.75686274766922,
+      "num_tokens": 2576144.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.8621700879765397,
+      "grad_norm": 0.5429131388664246,
+      "learning_rate": 9.50228653873791e-05,
+      "loss": 0.6283,
+      "mean_token_accuracy": 0.7598039209842682,
+      "num_tokens": 2596624.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.8768328445747802,
+      "grad_norm": 0.4898570775985718,
+      "learning_rate": 9.491688674732123e-05,
+      "loss": 0.6406,
+      "mean_token_accuracy": 0.7537254869937897,
+      "num_tokens": 2617104.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.8914956011730206,
+      "grad_norm": 0.5072643756866455,
+      "learning_rate": 9.480985203756501e-05,
+      "loss": 0.6288,
+      "mean_token_accuracy": 0.7583333313465118,
+      "num_tokens": 2637584.0,
+      "step": 1290
+    },
+    {
+      "epoch": 1.906158357771261,
+      "grad_norm": 0.5450229048728943,
+      "learning_rate": 9.470176377467206e-05,
+      "loss": 0.6135,
+      "mean_token_accuracy": 0.7631862699985504,
+      "num_tokens": 2658064.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.9208211143695015,
+      "grad_norm": 0.5232940912246704,
+      "learning_rate": 9.45926244999748e-05,
+      "loss": 0.6196,
+      "mean_token_accuracy": 0.7628431499004364,
+      "num_tokens": 2678544.0,
+      "step": 1310
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 0.5383533239364624,
+      "learning_rate": 9.44824367795166e-05,
+      "loss": 0.6046,
+      "mean_token_accuracy": 0.7665885031223297,
+      "num_tokens": 2698834.0,
+      "step": 1320
+    },
+    {
+      "epoch": 1.9501466275659824,
+      "grad_norm": 0.4725590944290161,
+      "learning_rate": 9.437120320399158e-05,
+      "loss": 0.6297,
+      "mean_token_accuracy": 0.7592157006263733,
+      "num_tokens": 2719314.0,
+      "step": 1330
+    },
+    {
+      "epoch": 1.964809384164223,
+      "grad_norm": 0.48085474967956543,
+      "learning_rate": 9.425892638868356e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7608333349227905,
+      "num_tokens": 2739794.0,
+      "step": 1340
+    },
+    {
+      "epoch": 1.9794721407624634,
+      "grad_norm": 0.5690534710884094,
+      "learning_rate": 9.414560897340468e-05,
+      "loss": 0.6349,
+      "mean_token_accuracy": 0.75343137383461,
+      "num_tokens": 2760274.0,
+      "step": 1350
+    },
+    {
+      "epoch": 1.9941348973607038,
+      "grad_norm": 0.5363736152648926,
+      "learning_rate": 9.403125362243328e-05,
+      "loss": 0.6124,
+      "mean_token_accuracy": 0.7653431355953216,
+      "num_tokens": 2780754.0,
+      "step": 1360
+    },
+    {
+      "epoch": 2.0087976539589443,
+      "grad_norm": 0.544509768486023,
+      "learning_rate": 9.39158630244513e-05,
+      "loss": 0.6031,
+      "mean_token_accuracy": 0.7673039197921753,
+      "num_tokens": 2799698.0,
+      "step": 1370
+    },
+    {
+      "epoch": 2.0234604105571847,
+      "grad_norm": 0.6539320945739746,
+      "learning_rate": 9.379943989248096e-05,
+      "loss": 0.5932,
+      "mean_token_accuracy": 0.7711764693260192,
+      "num_tokens": 2820178.0,
+      "step": 1380
+    },
+    {
+      "epoch": 2.038123167155425,
+      "grad_norm": 0.7973995208740234,
+      "learning_rate": 9.368198696382115e-05,
+      "loss": 0.5895,
+      "mean_token_accuracy": 0.7704901933670044,
+      "num_tokens": 2840658.0,
+      "step": 1390
+    },
+    {
+      "epoch": 2.0527859237536656,
+      "grad_norm": 0.5431190133094788,
+      "learning_rate": 9.356350699998288e-05,
+      "loss": 0.5823,
+      "mean_token_accuracy": 0.7777450978755951,
+      "num_tokens": 2861138.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.067448680351906,
+      "grad_norm": 0.6147369742393494,
+      "learning_rate": 9.344400278662448e-05,
+      "loss": 0.5854,
+      "mean_token_accuracy": 0.7753921627998352,
+      "num_tokens": 2881618.0,
+      "step": 1410
+    },
+    {
+      "epoch": 2.0821114369501466,
+      "grad_norm": 0.6121999025344849,
+      "learning_rate": 9.332347713348608e-05,
+      "loss": 0.5973,
+      "mean_token_accuracy": 0.7709803938865661,
+      "num_tokens": 2902098.0,
+      "step": 1420
+    },
+    {
+      "epoch": 2.096774193548387,
+      "grad_norm": 0.7150356769561768,
+      "learning_rate": 9.320193287432353e-05,
+      "loss": 0.592,
+      "mean_token_accuracy": 0.7744117677211761,
+      "num_tokens": 2922578.0,
+      "step": 1430
+    },
+    {
+      "epoch": 2.1114369501466275,
+      "grad_norm": 0.6568698287010193,
+      "learning_rate": 9.307937286684173e-05,
+      "loss": 0.6013,
+      "mean_token_accuracy": 0.7699509859085083,
+      "num_tokens": 2943058.0,
+      "step": 1440
+    },
+    {
+      "epoch": 2.126099706744868,
+      "grad_norm": 0.6842476725578308,
+      "learning_rate": 9.295579999262756e-05,
+      "loss": 0.5836,
+      "mean_token_accuracy": 0.776862746477127,
+      "num_tokens": 2963538.0,
+      "step": 1450
+    },
+    {
+      "epoch": 2.1407624633431084,
+      "grad_norm": 0.7466417551040649,
+      "learning_rate": 9.283121715708202e-05,
+      "loss": 0.5931,
+      "mean_token_accuracy": 0.7705392241477966,
+      "num_tokens": 2984018.0,
+      "step": 1460
+    },
+    {
+      "epoch": 2.155425219941349,
+      "grad_norm": 0.6118063926696777,
+      "learning_rate": 9.270562728935197e-05,
+      "loss": 0.6063,
+      "mean_token_accuracy": 0.7664917647838593,
+      "num_tokens": 3004171.0,
+      "step": 1470
+    },
+    {
+      "epoch": 2.1700879765395893,
+      "grad_norm": 0.6150789260864258,
+      "learning_rate": 9.257903334226124e-05,
+      "loss": 0.5848,
+      "mean_token_accuracy": 0.7761870443820953,
+      "num_tokens": 3024539.0,
+      "step": 1480
+    },
+    {
+      "epoch": 2.1847507331378297,
+      "grad_norm": 0.6299267411231995,
+      "learning_rate": 9.24514382922412e-05,
+      "loss": 0.5817,
+      "mean_token_accuracy": 0.774215692281723,
+      "num_tokens": 3045019.0,
+      "step": 1490
+    },
+    {
+      "epoch": 2.19941348973607,
+      "grad_norm": 0.6822914481163025,
+      "learning_rate": 9.232284513926085e-05,
+      "loss": 0.5752,
+      "mean_token_accuracy": 0.7771973431110382,
+      "num_tokens": 3065312.0,
+      "step": 1500
+    },
+    {
+      "epoch": 2.2140762463343107,
+      "grad_norm": 0.6228194832801819,
+      "learning_rate": 9.219325690675615e-05,
+      "loss": 0.6104,
+      "mean_token_accuracy": 0.7640686273574829,
+      "num_tokens": 3085792.0,
+      "step": 1510
+    },
+    {
+      "epoch": 2.228739002932551,
+      "grad_norm": 0.6606581211090088,
+      "learning_rate": 9.206267664155907e-05,
+      "loss": 0.6004,
+      "mean_token_accuracy": 0.7706372559070587,
+      "num_tokens": 3106272.0,
+      "step": 1520
+    },
+    {
+      "epoch": 2.2434017595307916,
+      "grad_norm": 0.6690000295639038,
+      "learning_rate": 9.193110741382585e-05,
+      "loss": 0.6004,
+      "mean_token_accuracy": 0.770147055387497,
+      "num_tokens": 3126752.0,
+      "step": 1530
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 0.495844304561615,
+      "learning_rate": 9.179855231696491e-05,
+      "loss": 0.5804,
+      "mean_token_accuracy": 0.7760294198989868,
+      "num_tokens": 3147232.0,
+      "step": 1540
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.6850236654281616,
+      "learning_rate": 9.166501446756405e-05,
+      "loss": 0.5987,
+      "mean_token_accuracy": 0.7694117665290833,
+      "num_tokens": 3167712.0,
+      "step": 1550
+    },
+    {
+      "epoch": 2.2873900293255134,
+      "grad_norm": 0.6291906237602234,
+      "learning_rate": 9.153049700531718e-05,
+      "loss": 0.6047,
+      "mean_token_accuracy": 0.769803935289383,
+      "num_tokens": 3188192.0,
+      "step": 1560
+    },
+    {
+      "epoch": 2.302052785923754,
+      "grad_norm": 0.5397360324859619,
+      "learning_rate": 9.139500309295053e-05,
+      "loss": 0.5845,
+      "mean_token_accuracy": 0.7725980460643769,
+      "num_tokens": 3208672.0,
+      "step": 1570
+    },
+    {
+      "epoch": 2.3167155425219943,
+      "grad_norm": 0.5473708510398865,
+      "learning_rate": 9.125853591614828e-05,
+      "loss": 0.6019,
+      "mean_token_accuracy": 0.7681862771511078,
+      "num_tokens": 3229152.0,
+      "step": 1580
+    },
+    {
+      "epoch": 2.3313782991202348,
+      "grad_norm": 0.6557981371879578,
+      "learning_rate": 9.112109868347763e-05,
+      "loss": 0.6003,
+      "mean_token_accuracy": 0.7697058916091919,
+      "num_tokens": 3249632.0,
+      "step": 1590
+    },
+    {
+      "epoch": 2.346041055718475,
+      "grad_norm": 0.583633303642273,
+      "learning_rate": 9.098269462631341e-05,
+      "loss": 0.6045,
+      "mean_token_accuracy": 0.7686714708805085,
+      "num_tokens": 3270032.0,
+      "step": 1600
+    },
+    {
+      "epoch": 2.3607038123167157,
+      "grad_norm": 0.6261008381843567,
+      "learning_rate": 9.084332699876208e-05,
+      "loss": 0.5885,
+      "mean_token_accuracy": 0.77156862616539,
+      "num_tokens": 3290512.0,
+      "step": 1610
+    },
+    {
+      "epoch": 2.375366568914956,
+      "grad_norm": 0.7260749340057373,
+      "learning_rate": 9.07029990775852e-05,
+      "loss": 0.5971,
+      "mean_token_accuracy": 0.7704411804676056,
+      "num_tokens": 3310992.0,
+      "step": 1620
+    },
+    {
+      "epoch": 2.3900293255131966,
+      "grad_norm": 0.6833462715148926,
+      "learning_rate": 9.056171416212243e-05,
+      "loss": 0.5866,
+      "mean_token_accuracy": 0.7733333289623261,
+      "num_tokens": 3331472.0,
+      "step": 1630
+    },
+    {
+      "epoch": 2.404692082111437,
+      "grad_norm": 0.7324588894844055,
+      "learning_rate": 9.041947557421391e-05,
+      "loss": 0.5809,
+      "mean_token_accuracy": 0.7767156839370728,
+      "num_tokens": 3351952.0,
+      "step": 1640
+    },
+    {
+      "epoch": 2.4193548387096775,
+      "grad_norm": 0.5573662519454956,
+      "learning_rate": 9.02762866581222e-05,
+      "loss": 0.6028,
+      "mean_token_accuracy": 0.7668627440929413,
+      "num_tokens": 3372432.0,
+      "step": 1650
+    },
+    {
+      "epoch": 2.434017595307918,
+      "grad_norm": 0.825465202331543,
+      "learning_rate": 9.013215078045363e-05,
+      "loss": 0.6014,
+      "mean_token_accuracy": 0.7658333301544189,
+      "num_tokens": 3392912.0,
+      "step": 1660
+    },
+    {
+      "epoch": 2.4486803519061584,
+      "grad_norm": 0.6437454223632812,
+      "learning_rate": 8.998707133007918e-05,
+      "loss": 0.6047,
+      "mean_token_accuracy": 0.7664215743541718,
+      "num_tokens": 3413392.0,
+      "step": 1670
+    },
+    {
+      "epoch": 2.463343108504399,
+      "grad_norm": 0.6310515999794006,
+      "learning_rate": 8.984105171805472e-05,
+      "loss": 0.5842,
+      "mean_token_accuracy": 0.7743137300014495,
+      "num_tokens": 3433872.0,
+      "step": 1680
+    },
+    {
+      "epoch": 2.4780058651026393,
+      "grad_norm": 0.641413152217865,
+      "learning_rate": 8.969409537754092e-05,
+      "loss": 0.5971,
+      "mean_token_accuracy": 0.7689705848693847,
+      "num_tokens": 3454352.0,
+      "step": 1690
+    },
+    {
+      "epoch": 2.4926686217008798,
+      "grad_norm": 0.6254575252532959,
+      "learning_rate": 8.95462057637224e-05,
+      "loss": 0.601,
+      "mean_token_accuracy": 0.7684313714504242,
+      "num_tokens": 3474832.0,
+      "step": 1700
+    },
+    {
+      "epoch": 2.5073313782991202,
+      "grad_norm": 0.5509727597236633,
+      "learning_rate": 8.939738635372664e-05,
+      "loss": 0.6032,
+      "mean_token_accuracy": 0.7683777451515198,
+      "num_tokens": 3495060.0,
+      "step": 1710
+    },
+    {
+      "epoch": 2.5219941348973607,
+      "grad_norm": 0.6135575175285339,
+      "learning_rate": 8.924764064654212e-05,
+      "loss": 0.595,
+      "mean_token_accuracy": 0.7695098042488098,
+      "num_tokens": 3515540.0,
+      "step": 1720
+    },
+    {
+      "epoch": 2.536656891495601,
+      "grad_norm": 0.5865819454193115,
+      "learning_rate": 8.909697216293609e-05,
+      "loss": 0.604,
+      "mean_token_accuracy": 0.7670098066329956,
+      "num_tokens": 3536020.0,
+      "step": 1730
+    },
+    {
+      "epoch": 2.5513196480938416,
+      "grad_norm": 0.6289553046226501,
+      "learning_rate": 8.894538444537177e-05,
+      "loss": 0.588,
+      "mean_token_accuracy": 0.7727451026439667,
+      "num_tokens": 3556500.0,
+      "step": 1740
+    },
+    {
+      "epoch": 2.565982404692082,
+      "grad_norm": 0.5837467908859253,
+      "learning_rate": 8.87928810579251e-05,
+      "loss": 0.5908,
+      "mean_token_accuracy": 0.7722666919231415,
+      "num_tokens": 3576749.0,
+      "step": 1750
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 0.7653214931488037,
+      "learning_rate": 8.863946558620094e-05,
+      "loss": 0.6068,
+      "mean_token_accuracy": 0.7670588195323944,
+      "num_tokens": 3597229.0,
+      "step": 1760
+    },
+    {
+      "epoch": 2.595307917888563,
+      "grad_norm": 0.5600757002830505,
+      "learning_rate": 8.84851416372487e-05,
+      "loss": 0.5964,
+      "mean_token_accuracy": 0.7708823502063751,
+      "num_tokens": 3617709.0,
+      "step": 1770
+    },
+    {
+      "epoch": 2.6099706744868034,
+      "grad_norm": 0.615788996219635,
+      "learning_rate": 8.832991283947762e-05,
+      "loss": 0.6216,
+      "mean_token_accuracy": 0.761176460981369,
+      "num_tokens": 3638189.0,
+      "step": 1780
+    },
+    {
+      "epoch": 2.624633431085044,
+      "grad_norm": 0.574803352355957,
+      "learning_rate": 8.81737828425714e-05,
+      "loss": 0.5768,
+      "mean_token_accuracy": 0.7758823573589325,
+      "num_tokens": 3658669.0,
+      "step": 1790
+    },
+    {
+      "epoch": 2.6392961876832843,
+      "grad_norm": 0.7114520072937012,
+      "learning_rate": 8.80167553174024e-05,
+      "loss": 0.5926,
+      "mean_token_accuracy": 0.7726960778236389,
+      "num_tokens": 3679149.0,
+      "step": 1800
+    },
+    {
+      "epoch": 2.653958944281525,
+      "grad_norm": 0.5663362145423889,
+      "learning_rate": 8.785883395594541e-05,
+      "loss": 0.5794,
+      "mean_token_accuracy": 0.7743627488613128,
+      "num_tokens": 3699629.0,
+      "step": 1810
+    },
+    {
+      "epoch": 2.6686217008797652,
+      "grad_norm": 0.6680328249931335,
+      "learning_rate": 8.770002247119064e-05,
+      "loss": 0.6057,
+      "mean_token_accuracy": 0.7669117748737335,
+      "num_tokens": 3720109.0,
+      "step": 1820
+    },
+    {
+      "epoch": 2.6832844574780057,
+      "grad_norm": 0.6905878186225891,
+      "learning_rate": 8.754032459705672e-05,
+      "loss": 0.6001,
+      "mean_token_accuracy": 0.7686764895915985,
+      "num_tokens": 3740589.0,
+      "step": 1830
+    },
+    {
+      "epoch": 2.6979472140762466,
+      "grad_norm": 0.5783908367156982,
+      "learning_rate": 8.737974408830263e-05,
+      "loss": 0.6037,
+      "mean_token_accuracy": 0.7703921616077423,
+      "num_tokens": 3761069.0,
+      "step": 1840
+    },
+    {
+      "epoch": 2.712609970674487,
+      "grad_norm": 0.7091444730758667,
+      "learning_rate": 8.721828472043958e-05,
+      "loss": 0.5801,
+      "mean_token_accuracy": 0.777009803056717,
+      "num_tokens": 3781549.0,
+      "step": 1850
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.6419853568077087,
+      "learning_rate": 8.705595028964222e-05,
+      "loss": 0.592,
+      "mean_token_accuracy": 0.7715686321258545,
+      "num_tokens": 3802029.0,
+      "step": 1860
+    },
+    {
+      "epoch": 2.741935483870968,
+      "grad_norm": 0.6625768542289734,
+      "learning_rate": 8.689274461265935e-05,
+      "loss": 0.5984,
+      "mean_token_accuracy": 0.7693137288093567,
+      "num_tokens": 3822509.0,
+      "step": 1870
+    },
+    {
+      "epoch": 2.7565982404692084,
+      "grad_norm": 0.6934528350830078,
+      "learning_rate": 8.672867152672416e-05,
+      "loss": 0.5871,
+      "mean_token_accuracy": 0.7757352948188782,
+      "num_tokens": 3842989.0,
+      "step": 1880
+    },
+    {
+      "epoch": 2.771260997067449,
+      "grad_norm": 0.570747435092926,
+      "learning_rate": 8.656373488946409e-05,
+      "loss": 0.5777,
+      "mean_token_accuracy": 0.7777941226959229,
+      "num_tokens": 3863469.0,
+      "step": 1890
+    },
+    {
+      "epoch": 2.7859237536656893,
+      "grad_norm": 0.5088850855827332,
+      "learning_rate": 8.639793857881011e-05,
+      "loss": 0.5912,
+      "mean_token_accuracy": 0.7703921675682068,
+      "num_tokens": 3883949.0,
+      "step": 1900
+    },
+    {
+      "epoch": 2.80058651026393,
+      "grad_norm": 0.7125044465065002,
+      "learning_rate": 8.623128649290544e-05,
+      "loss": 0.6006,
+      "mean_token_accuracy": 0.7711764693260192,
+      "num_tokens": 3904429.0,
+      "step": 1910
+    },
+    {
+      "epoch": 2.8152492668621703,
+      "grad_norm": 0.707624614238739,
+      "learning_rate": 8.606378255001408e-05,
+      "loss": 0.5983,
+      "mean_token_accuracy": 0.7694117724895477,
+      "num_tokens": 3924909.0,
+      "step": 1920
+    },
+    {
+      "epoch": 2.8299120234604107,
+      "grad_norm": 0.6317010521888733,
+      "learning_rate": 8.58954306884285e-05,
+      "loss": 0.6064,
+      "mean_token_accuracy": 0.7670129835605621,
+      "num_tokens": 3945199.0,
+      "step": 1930
+    },
+    {
+      "epoch": 2.844574780058651,
+      "grad_norm": 0.6072015166282654,
+      "learning_rate": 8.572623486637719e-05,
+      "loss": 0.5982,
+      "mean_token_accuracy": 0.7714847445487976,
+      "num_tokens": 3965613.0,
+      "step": 1940
+    },
+    {
+      "epoch": 2.8592375366568916,
+      "grad_norm": 0.6589727997779846,
+      "learning_rate": 8.555619906193147e-05,
+      "loss": 0.5861,
+      "mean_token_accuracy": 0.7741666734218597,
+      "num_tokens": 3986093.0,
+      "step": 1950
+    },
+    {
+      "epoch": 2.873900293255132,
+      "grad_norm": 0.676544189453125,
+      "learning_rate": 8.538532727291211e-05,
+      "loss": 0.5995,
+      "mean_token_accuracy": 0.7698529422283172,
+      "num_tokens": 4006573.0,
+      "step": 1960
+    },
+    {
+      "epoch": 2.8885630498533725,
+      "grad_norm": 0.7198004126548767,
+      "learning_rate": 8.521362351679517e-05,
+      "loss": 0.6057,
+      "mean_token_accuracy": 0.7672058820724488,
+      "num_tokens": 4027053.0,
+      "step": 1970
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 0.6745808124542236,
+      "learning_rate": 8.504109183061768e-05,
+      "loss": 0.5961,
+      "mean_token_accuracy": 0.7691176533699036,
+      "num_tokens": 4047533.0,
+      "step": 1980
+    },
+    {
+      "epoch": 2.9178885630498534,
+      "grad_norm": 0.5883781909942627,
+      "learning_rate": 8.486773627088263e-05,
+      "loss": 0.5881,
+      "mean_token_accuracy": 0.7735294163227081,
+      "num_tokens": 4068013.0,
+      "step": 1990
+    },
+    {
+      "epoch": 2.932551319648094,
+      "grad_norm": 0.6510045528411865,
+      "learning_rate": 8.469356091346361e-05,
+      "loss": 0.6149,
+      "mean_token_accuracy": 0.7622058868408204,
+      "num_tokens": 4088493.0,
+      "step": 2000
+    },
+    {
+      "epoch": 2.9472140762463344,
+      "grad_norm": 0.6162061095237732,
+      "learning_rate": 8.451856985350906e-05,
+      "loss": 0.6064,
+      "mean_token_accuracy": 0.765656465291977,
+      "num_tokens": 4108923.0,
+      "step": 2010
+    },
+    {
+      "epoch": 2.961876832844575,
+      "grad_norm": 0.7037227153778076,
+      "learning_rate": 8.434276720534588e-05,
+      "loss": 0.5993,
+      "mean_token_accuracy": 0.7701960802078247,
+      "num_tokens": 4129403.0,
+      "step": 2020
+    },
+    {
+      "epoch": 2.9765395894428153,
+      "grad_norm": 0.6391721963882446,
+      "learning_rate": 8.416615710238277e-05,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.7682352960109711,
+      "num_tokens": 4149883.0,
+      "step": 2030
+    },
+    {
+      "epoch": 2.9912023460410557,
+      "grad_norm": 0.5743676424026489,
+      "learning_rate": 8.398874369701297e-05,
+      "loss": 0.6044,
+      "mean_token_accuracy": 0.7700980484485627,
+      "num_tokens": 4170363.0,
+      "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": 1.780756209598464e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-2046/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4734d6626d9f4e5de52d260e514c2c8d854a75e2ff6292ebf0fe2fce39775fa5
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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": [
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-2728/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69ea82a4081f8ae6f04b8aff255a25e2d2e778ec413bd21010d988e106b7e7c5
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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_s2_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_s2_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_s2_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_s2_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": 3.478421211242676,
+      "learning_rate": 2.6392961876832847e-06,
+      "loss": 2.49,
+      "mean_token_accuracy": 0.5404902040958405,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.02932551319648094,
+      "grad_norm": 4.437029838562012,
+      "learning_rate": 5.571847507331378e-06,
+      "loss": 2.4861,
+      "mean_token_accuracy": 0.5374019622802735,
+      "num_tokens": 40960.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.04398826979472141,
+      "grad_norm": 3.2707436084747314,
+      "learning_rate": 8.504398826979472e-06,
+      "loss": 2.3345,
+      "mean_token_accuracy": 0.5500490128993988,
+      "num_tokens": 61440.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.05865102639296188,
+      "grad_norm": 1.9522887468338013,
+      "learning_rate": 1.1436950146627567e-05,
+      "loss": 2.0409,
+      "mean_token_accuracy": 0.5806862652301789,
+      "num_tokens": 81920.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07331378299120235,
+      "grad_norm": 1.3734278678894043,
+      "learning_rate": 1.4369501466275662e-05,
+      "loss": 1.7743,
+      "mean_token_accuracy": 0.5944117605686188,
+      "num_tokens": 102400.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.08797653958944282,
+      "grad_norm": 1.124900221824646,
+      "learning_rate": 1.7302052785923756e-05,
+      "loss": 1.5557,
+      "mean_token_accuracy": 0.6044607698917389,
+      "num_tokens": 122880.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.10263929618768329,
+      "grad_norm": 0.8481243848800659,
+      "learning_rate": 2.0234604105571847e-05,
+      "loss": 1.383,
+      "mean_token_accuracy": 0.620245099067688,
+      "num_tokens": 143360.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.11730205278592376,
+      "grad_norm": 0.864518940448761,
+      "learning_rate": 2.3167155425219943e-05,
+      "loss": 1.2221,
+      "mean_token_accuracy": 0.6459313809871674,
+      "num_tokens": 163840.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.13196480938416422,
+      "grad_norm": 0.9745388627052307,
+      "learning_rate": 2.6099706744868034e-05,
+      "loss": 1.0528,
+      "mean_token_accuracy": 0.6676470518112183,
+      "num_tokens": 184320.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.1466275659824047,
+      "grad_norm": 1.1379441022872925,
+      "learning_rate": 2.9032258064516133e-05,
+      "loss": 0.9449,
+      "mean_token_accuracy": 0.6830392181873322,
+      "num_tokens": 204800.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.16129032258064516,
+      "grad_norm": 1.1655960083007812,
+      "learning_rate": 3.1964809384164225e-05,
+      "loss": 0.8282,
+      "mean_token_accuracy": 0.7080882310867309,
+      "num_tokens": 225280.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.17595307917888564,
+      "grad_norm": 1.3215491771697998,
+      "learning_rate": 3.489736070381232e-05,
+      "loss": 0.7662,
+      "mean_token_accuracy": 0.7250490248203277,
+      "num_tokens": 245760.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.1906158357771261,
+      "grad_norm": 1.0598912239074707,
+      "learning_rate": 3.7829912023460415e-05,
+      "loss": 0.7364,
+      "mean_token_accuracy": 0.7327941119670868,
+      "num_tokens": 266240.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.20527859237536658,
+      "grad_norm": 1.122361183166504,
+      "learning_rate": 4.076246334310851e-05,
+      "loss": 0.723,
+      "mean_token_accuracy": 0.7349509775638581,
+      "num_tokens": 286720.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.21994134897360704,
+      "grad_norm": 1.1284314393997192,
+      "learning_rate": 4.36950146627566e-05,
+      "loss": 0.7266,
+      "mean_token_accuracy": 0.7305392146110534,
+      "num_tokens": 307200.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.23460410557184752,
+      "grad_norm": 0.8642133474349976,
+      "learning_rate": 4.6627565982404694e-05,
+      "loss": 0.6996,
+      "mean_token_accuracy": 0.7395318567752838,
+      "num_tokens": 327614.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.24926686217008798,
+      "grad_norm": 0.9549291729927063,
+      "learning_rate": 4.956011730205279e-05,
+      "loss": 0.7056,
+      "mean_token_accuracy": 0.7378431379795074,
+      "num_tokens": 348094.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.26392961876832843,
+      "grad_norm": 0.9989821314811707,
+      "learning_rate": 5.249266862170088e-05,
+      "loss": 0.6685,
+      "mean_token_accuracy": 0.7505882322788239,
+      "num_tokens": 368574.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2785923753665689,
+      "grad_norm": 0.8779164552688599,
+      "learning_rate": 5.542521994134897e-05,
+      "loss": 0.6798,
+      "mean_token_accuracy": 0.7446078479290008,
+      "num_tokens": 389054.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.2932551319648094,
+      "grad_norm": 0.8436822295188904,
+      "learning_rate": 5.8357771260997075e-05,
+      "loss": 0.6859,
+      "mean_token_accuracy": 0.7446078419685364,
+      "num_tokens": 409534.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.30791788856304986,
+      "grad_norm": 0.8713858127593994,
+      "learning_rate": 6.129032258064517e-05,
+      "loss": 0.6535,
+      "mean_token_accuracy": 0.7526268303394318,
+      "num_tokens": 429827.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 0.8723043203353882,
+      "learning_rate": 6.422287390029326e-05,
+      "loss": 0.6523,
+      "mean_token_accuracy": 0.7535784304141998,
+      "num_tokens": 450307.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.33724340175953077,
+      "grad_norm": 0.8272885680198669,
+      "learning_rate": 6.715542521994135e-05,
+      "loss": 0.6609,
+      "mean_token_accuracy": 0.749901968240738,
+      "num_tokens": 470787.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.3519061583577713,
+      "grad_norm": 0.6368948221206665,
+      "learning_rate": 7.008797653958945e-05,
+      "loss": 0.6608,
+      "mean_token_accuracy": 0.7493137300014496,
+      "num_tokens": 491267.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.36656891495601174,
+      "grad_norm": 0.6908038854598999,
+      "learning_rate": 7.302052785923754e-05,
+      "loss": 0.666,
+      "mean_token_accuracy": 0.7473100483417511,
+      "num_tokens": 511627.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.3812316715542522,
+      "grad_norm": 0.6815389394760132,
+      "learning_rate": 7.595307917888564e-05,
+      "loss": 0.6493,
+      "mean_token_accuracy": 0.75220587849617,
+      "num_tokens": 532107.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.39589442815249265,
+      "grad_norm": 0.77500319480896,
+      "learning_rate": 7.888563049853373e-05,
+      "loss": 0.6535,
+      "mean_token_accuracy": 0.7530904829502105,
+      "num_tokens": 552475.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.41055718475073316,
+      "grad_norm": 0.7127943634986877,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 0.6654,
+      "mean_token_accuracy": 0.751323539018631,
+      "num_tokens": 572955.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.4252199413489736,
+      "grad_norm": 0.8289512395858765,
+      "learning_rate": 8.475073313782992e-05,
+      "loss": 0.6518,
+      "mean_token_accuracy": 0.7510293960571289,
+      "num_tokens": 593435.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.4398826979472141,
+      "grad_norm": 0.7434380650520325,
+      "learning_rate": 8.7683284457478e-05,
+      "loss": 0.657,
+      "mean_token_accuracy": 0.7497548878192901,
+      "num_tokens": 613915.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.6814386248588562,
+      "learning_rate": 9.06158357771261e-05,
+      "loss": 0.6413,
+      "mean_token_accuracy": 0.7540686309337616,
+      "num_tokens": 634395.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.46920821114369504,
+      "grad_norm": 0.595894455909729,
+      "learning_rate": 9.35483870967742e-05,
+      "loss": 0.647,
+      "mean_token_accuracy": 0.7533333361148834,
+      "num_tokens": 654875.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.4838709677419355,
+      "grad_norm": 0.5797744989395142,
+      "learning_rate": 9.64809384164223e-05,
+      "loss": 0.6517,
+      "mean_token_accuracy": 0.7517156839370728,
+      "num_tokens": 675355.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.49853372434017595,
+      "grad_norm": 0.6610384583473206,
+      "learning_rate": 9.941348973607039e-05,
+      "loss": 0.6519,
+      "mean_token_accuracy": 0.7513235330581665,
+      "num_tokens": 695835.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5131964809384164,
+      "grad_norm": 0.5836912393569946,
+      "learning_rate": 9.999962381348496e-05,
+      "loss": 0.6615,
+      "mean_token_accuracy": 0.7489215791225433,
+      "num_tokens": 716315.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5278592375366569,
+      "grad_norm": 0.6278303265571594,
+      "learning_rate": 9.999809556546922e-05,
+      "loss": 0.6381,
+      "mean_token_accuracy": 0.756617647409439,
+      "num_tokens": 736795.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5425219941348973,
+      "grad_norm": 0.6376463770866394,
+      "learning_rate": 9.999539178019954e-05,
+      "loss": 0.6509,
+      "mean_token_accuracy": 0.7530082106590271,
+      "num_tokens": 757195.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5571847507331378,
+      "grad_norm": 0.5569787621498108,
+      "learning_rate": 9.999151252124639e-05,
+      "loss": 0.6605,
+      "mean_token_accuracy": 0.7477450966835022,
+      "num_tokens": 777675.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.5718475073313783,
+      "grad_norm": 0.583513617515564,
+      "learning_rate": 9.998645787981749e-05,
+      "loss": 0.6459,
+      "mean_token_accuracy": 0.754313725233078,
+      "num_tokens": 798155.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.5865102639296188,
+      "grad_norm": 0.612436830997467,
+      "learning_rate": 9.998022797475572e-05,
+      "loss": 0.6579,
+      "mean_token_accuracy": 0.7481862723827362,
+      "num_tokens": 818635.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6011730205278593,
+      "grad_norm": 0.5789109468460083,
+      "learning_rate": 9.997282295253644e-05,
+      "loss": 0.6564,
+      "mean_token_accuracy": 0.7513725519180298,
+      "num_tokens": 839115.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6158357771260997,
+      "grad_norm": 0.5940632224082947,
+      "learning_rate": 9.996424298726381e-05,
+      "loss": 0.6365,
+      "mean_token_accuracy": 0.7571078360080719,
+      "num_tokens": 859595.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.6304985337243402,
+      "grad_norm": 0.5033205151557922,
+      "learning_rate": 9.995448828066693e-05,
+      "loss": 0.6286,
+      "mean_token_accuracy": 0.7599019646644593,
+      "num_tokens": 880075.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 0.6101331114768982,
+      "learning_rate": 9.994355906209492e-05,
+      "loss": 0.6399,
+      "mean_token_accuracy": 0.7571568667888642,
+      "num_tokens": 900555.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6598240469208211,
+      "grad_norm": 0.5758415460586548,
+      "learning_rate": 9.993145558851168e-05,
+      "loss": 0.6368,
+      "mean_token_accuracy": 0.7564705967903137,
+      "num_tokens": 921035.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.6744868035190615,
+      "grad_norm": 0.5409122705459595,
+      "learning_rate": 9.991817814448967e-05,
+      "loss": 0.6516,
+      "mean_token_accuracy": 0.747450977563858,
+      "num_tokens": 941515.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.6891495601173021,
+      "grad_norm": 0.5705657005310059,
+      "learning_rate": 9.990372704220345e-05,
+      "loss": 0.6377,
+      "mean_token_accuracy": 0.7563235342502594,
+      "num_tokens": 961995.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7038123167155426,
+      "grad_norm": 0.4983280599117279,
+      "learning_rate": 9.988810262142209e-05,
+      "loss": 0.6616,
+      "mean_token_accuracy": 0.743039208650589,
+      "num_tokens": 982475.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.718475073313783,
+      "grad_norm": 0.5050950646400452,
+      "learning_rate": 9.987130524950141e-05,
+      "loss": 0.6387,
+      "mean_token_accuracy": 0.7534313797950745,
+      "num_tokens": 1002955.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7331378299120235,
+      "grad_norm": 0.6670287251472473,
+      "learning_rate": 9.985333532137514e-05,
+      "loss": 0.6191,
+      "mean_token_accuracy": 0.7647604286670685,
+      "num_tokens": 1023204.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.7478005865102639,
+      "grad_norm": 0.5413070917129517,
+      "learning_rate": 9.983419325954577e-05,
+      "loss": 0.6416,
+      "mean_token_accuracy": 0.7539705872535706,
+      "num_tokens": 1043684.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.7624633431085044,
+      "grad_norm": 0.5095930099487305,
+      "learning_rate": 9.981387951407462e-05,
+      "loss": 0.6264,
+      "mean_token_accuracy": 0.7603431403636932,
+      "num_tokens": 1064164.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.7771260997067448,
+      "grad_norm": 0.5123670101165771,
+      "learning_rate": 9.979239456257113e-05,
+      "loss": 0.6333,
+      "mean_token_accuracy": 0.7584803879261017,
+      "num_tokens": 1084644.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.7917888563049853,
+      "grad_norm": 0.5062909126281738,
+      "learning_rate": 9.976973891018175e-05,
+      "loss": 0.6345,
+      "mean_token_accuracy": 0.7572302341461181,
+      "num_tokens": 1104872.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8064516129032258,
+      "grad_norm": 0.4592231810092926,
+      "learning_rate": 9.974591308957808e-05,
+      "loss": 0.6504,
+      "mean_token_accuracy": 0.7503150522708892,
+      "num_tokens": 1125162.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8211143695014663,
+      "grad_norm": 0.4416564106941223,
+      "learning_rate": 9.972091766094424e-05,
+      "loss": 0.6426,
+      "mean_token_accuracy": 0.7540196180343628,
+      "num_tokens": 1145642.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8357771260997068,
+      "grad_norm": 0.5509306192398071,
+      "learning_rate": 9.969475321196373e-05,
+      "loss": 0.636,
+      "mean_token_accuracy": 0.7576401591300964,
+      "num_tokens": 1165915.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8504398826979472,
+      "grad_norm": 0.616726279258728,
+      "learning_rate": 9.966742035780571e-05,
+      "loss": 0.6374,
+      "mean_token_accuracy": 0.7540196180343628,
+      "num_tokens": 1186395.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.8651026392961877,
+      "grad_norm": 0.593067467212677,
+      "learning_rate": 9.963891974111042e-05,
+      "loss": 0.6264,
+      "mean_token_accuracy": 0.7561764657497406,
+      "num_tokens": 1206875.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.8797653958944281,
+      "grad_norm": 0.4836729168891907,
+      "learning_rate": 9.960925203197408e-05,
+      "loss": 0.6506,
+      "mean_token_accuracy": 0.7518137276172638,
+      "num_tokens": 1227355.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.8944281524926686,
+      "grad_norm": 0.4806676208972931,
+      "learning_rate": 9.957841792793326e-05,
+      "loss": 0.6339,
+      "mean_token_accuracy": 0.7543627500534058,
+      "num_tokens": 1247835.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.5160490274429321,
+      "learning_rate": 9.95464181539483e-05,
+      "loss": 0.6432,
+      "mean_token_accuracy": 0.7526672542095184,
+      "num_tokens": 1268265.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9237536656891495,
+      "grad_norm": 0.5039036870002747,
+      "learning_rate": 9.951325346238638e-05,
+      "loss": 0.655,
+      "mean_token_accuracy": 0.7470588266849518,
+      "num_tokens": 1288745.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9384164222873901,
+      "grad_norm": 0.5036706924438477,
+      "learning_rate": 9.947892463300381e-05,
+      "loss": 0.6505,
+      "mean_token_accuracy": 0.7505392134189606,
+      "num_tokens": 1309225.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.9530791788856305,
+      "grad_norm": 0.5417743921279907,
+      "learning_rate": 9.944343247292771e-05,
+      "loss": 0.6479,
+      "mean_token_accuracy": 0.7542647004127503,
+      "num_tokens": 1329705.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 0.4578988552093506,
+      "learning_rate": 9.940677781663699e-05,
+      "loss": 0.6161,
+      "mean_token_accuracy": 0.7634804010391235,
+      "num_tokens": 1350185.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.9824046920821115,
+      "grad_norm": 0.48247650265693665,
+      "learning_rate": 9.936896152594273e-05,
+      "loss": 0.6477,
+      "mean_token_accuracy": 0.7534803986549378,
+      "num_tokens": 1370665.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.9970674486803519,
+      "grad_norm": 0.5284174084663391,
+      "learning_rate": 9.932998448996798e-05,
+      "loss": 0.6468,
+      "mean_token_accuracy": 0.7506862759590149,
+      "num_tokens": 1391145.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.0117302052785924,
+      "grad_norm": 0.4927270710468292,
+      "learning_rate": 9.92898476251268e-05,
+      "loss": 0.6284,
+      "mean_token_accuracy": 0.757647055387497,
+      "num_tokens": 1410089.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0263929618768328,
+      "grad_norm": 0.5643373131752014,
+      "learning_rate": 9.924855187510274e-05,
+      "loss": 0.6138,
+      "mean_token_accuracy": 0.7658823609352112,
+      "num_tokens": 1430569.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.0410557184750733,
+      "grad_norm": 0.5678701996803284,
+      "learning_rate": 9.920609821082662e-05,
+      "loss": 0.6254,
+      "mean_token_accuracy": 0.7576960742473602,
+      "num_tokens": 1451049.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.0557184750733137,
+      "grad_norm": 0.5296412110328674,
+      "learning_rate": 9.916248763045375e-05,
+      "loss": 0.6121,
+      "mean_token_accuracy": 0.7641666650772094,
+      "num_tokens": 1471529.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.0703812316715542,
+      "grad_norm": 0.5680798292160034,
+      "learning_rate": 9.911772115934042e-05,
+      "loss": 0.6128,
+      "mean_token_accuracy": 0.766274505853653,
+      "num_tokens": 1492009.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.0850439882697946,
+      "grad_norm": 0.4596232771873474,
+      "learning_rate": 9.907179985001978e-05,
+      "loss": 0.6255,
+      "mean_token_accuracy": 0.7588051378726959,
+      "num_tokens": 1512369.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.099706744868035,
+      "grad_norm": 0.6007994413375854,
+      "learning_rate": 9.90247247821772e-05,
+      "loss": 0.6153,
+      "mean_token_accuracy": 0.7644117712974549,
+      "num_tokens": 1532849.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1143695014662756,
+      "grad_norm": 0.5747436881065369,
+      "learning_rate": 9.897649706262473e-05,
+      "loss": 0.6173,
+      "mean_token_accuracy": 0.763137263059616,
+      "num_tokens": 1553329.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.129032258064516,
+      "grad_norm": 0.46429798007011414,
+      "learning_rate": 9.892711782527517e-05,
+      "loss": 0.6342,
+      "mean_token_accuracy": 0.7545098066329956,
+      "num_tokens": 1573809.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.1436950146627567,
+      "grad_norm": 0.5654335618019104,
+      "learning_rate": 9.887658823111544e-05,
+      "loss": 0.635,
+      "mean_token_accuracy": 0.7538235247135162,
+      "num_tokens": 1594289.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.1583577712609971,
+      "grad_norm": 0.5111511945724487,
+      "learning_rate": 9.882490946817915e-05,
+      "loss": 0.6325,
+      "mean_token_accuracy": 0.7592646956443787,
+      "num_tokens": 1614769.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.1730205278592376,
+      "grad_norm": 0.5609337091445923,
+      "learning_rate": 9.877208275151884e-05,
+      "loss": 0.6053,
+      "mean_token_accuracy": 0.7668137192726135,
+      "num_tokens": 1635249.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.187683284457478,
+      "grad_norm": 0.6170390248298645,
+      "learning_rate": 9.871810932317726e-05,
+      "loss": 0.6271,
+      "mean_token_accuracy": 0.7599417567253113,
+      "num_tokens": 1655522.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2023460410557185,
+      "grad_norm": 0.6282625198364258,
+      "learning_rate": 9.866299045215826e-05,
+      "loss": 0.6179,
+      "mean_token_accuracy": 0.7623039245605469,
+      "num_tokens": 1676002.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.217008797653959,
+      "grad_norm": 0.5284767746925354,
+      "learning_rate": 9.860672743439695e-05,
+      "loss": 0.6296,
+      "mean_token_accuracy": 0.7596568644046784,
+      "num_tokens": 1696482.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2316715542521994,
+      "grad_norm": 0.5899022817611694,
+      "learning_rate": 9.854932159272917e-05,
+      "loss": 0.6134,
+      "mean_token_accuracy": 0.7627948582172394,
+      "num_tokens": 1716912.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.2463343108504399,
+      "grad_norm": 0.60678631067276,
+      "learning_rate": 9.849077427686041e-05,
+      "loss": 0.6224,
+      "mean_token_accuracy": 0.7598529517650604,
+      "num_tokens": 1737392.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.2609970674486803,
+      "grad_norm": 0.5868576169013977,
+      "learning_rate": 9.843108686333417e-05,
+      "loss": 0.6199,
+      "mean_token_accuracy": 0.7617156803607941,
+      "num_tokens": 1757872.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.2756598240469208,
+      "grad_norm": 0.6662725210189819,
+      "learning_rate": 9.837026075549945e-05,
+      "loss": 0.6134,
+      "mean_token_accuracy": 0.7634313762187958,
+      "num_tokens": 1778352.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.6636219620704651,
+      "learning_rate": 9.830829738347782e-05,
+      "loss": 0.6301,
+      "mean_token_accuracy": 0.7577941298484803,
+      "num_tokens": 1798832.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.3049853372434017,
+      "grad_norm": 0.498141884803772,
+      "learning_rate": 9.82451982041298e-05,
+      "loss": 0.6372,
+      "mean_token_accuracy": 0.7548039197921753,
+      "num_tokens": 1819312.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3196480938416422,
+      "grad_norm": 0.5891352295875549,
+      "learning_rate": 9.818096470102067e-05,
+      "loss": 0.6289,
+      "mean_token_accuracy": 0.7583333313465118,
+      "num_tokens": 1839792.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.3343108504398826,
+      "grad_norm": 0.5640554428100586,
+      "learning_rate": 9.811559838438542e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7626470625400543,
+      "num_tokens": 1860272.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.3489736070381233,
+      "grad_norm": 0.7103374600410461,
+      "learning_rate": 9.804910079109342e-05,
+      "loss": 0.6176,
+      "mean_token_accuracy": 0.7616600275039673,
+      "num_tokens": 1880420.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.6304973363876343,
+      "learning_rate": 9.798147348461218e-05,
+      "loss": 0.6011,
+      "mean_token_accuracy": 0.7669014155864715,
+      "num_tokens": 1900713.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.3782991202346042,
+      "grad_norm": 0.4847545623779297,
+      "learning_rate": 9.791271805497062e-05,
+      "loss": 0.6328,
+      "mean_token_accuracy": 0.7561274468898773,
+      "num_tokens": 1921193.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.3929618768328447,
+      "grad_norm": 0.6657376885414124,
+      "learning_rate": 9.784283611872169e-05,
+      "loss": 0.6144,
+      "mean_token_accuracy": 0.7649019598960877,
+      "num_tokens": 1941673.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4076246334310851,
+      "grad_norm": 0.581245481967926,
+      "learning_rate": 9.777182931890438e-05,
+      "loss": 0.623,
+      "mean_token_accuracy": 0.7615196108818054,
+      "num_tokens": 1962153.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4222873900293256,
+      "grad_norm": 0.4939914643764496,
+      "learning_rate": 9.769969932500502e-05,
+      "loss": 0.6315,
+      "mean_token_accuracy": 0.7568137228488923,
+      "num_tokens": 1982633.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.436950146627566,
+      "grad_norm": 0.5039688944816589,
+      "learning_rate": 9.762644783291812e-05,
+      "loss": 0.6042,
+      "mean_token_accuracy": 0.7705392241477966,
+      "num_tokens": 2003113.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.4516129032258065,
+      "grad_norm": 0.5869693756103516,
+      "learning_rate": 9.755207656490644e-05,
+      "loss": 0.6063,
+      "mean_token_accuracy": 0.765588229894638,
+      "num_tokens": 2023593.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.466275659824047,
+      "grad_norm": 0.5763869285583496,
+      "learning_rate": 9.747658726956048e-05,
+      "loss": 0.6345,
+      "mean_token_accuracy": 0.7569607853889465,
+      "num_tokens": 2044073.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4809384164222874,
+      "grad_norm": 0.5597388744354248,
+      "learning_rate": 9.739998172175744e-05,
+      "loss": 0.6271,
+      "mean_token_accuracy": 0.7582843244075775,
+      "num_tokens": 2064553.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.4956011730205279,
+      "grad_norm": 0.5474197268486023,
+      "learning_rate": 9.732226172261943e-05,
+      "loss": 0.621,
+      "mean_token_accuracy": 0.7624509751796722,
+      "num_tokens": 2085033.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5102639296187683,
+      "grad_norm": 0.5269312262535095,
+      "learning_rate": 9.724342909947114e-05,
+      "loss": 0.6227,
+      "mean_token_accuracy": 0.7598717212677002,
+      "num_tokens": 2105447.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.5249266862170088,
+      "grad_norm": 0.4974181354045868,
+      "learning_rate": 9.716348570579686e-05,
+      "loss": 0.6086,
+      "mean_token_accuracy": 0.7698944330215454,
+      "num_tokens": 2125815.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.5395894428152492,
+      "grad_norm": 0.5832821726799011,
+      "learning_rate": 9.708243342119695e-05,
+      "loss": 0.6301,
+      "mean_token_accuracy": 0.7575490176677704,
+      "num_tokens": 2146295.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.5542521994134897,
+      "grad_norm": 0.49198174476623535,
+      "learning_rate": 9.700027415134358e-05,
+      "loss": 0.6135,
+      "mean_token_accuracy": 0.7628921508789063,
+      "num_tokens": 2166775.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.5689149560117301,
+      "grad_norm": 0.43694180250167847,
+      "learning_rate": 9.691700982793597e-05,
+      "loss": 0.6243,
+      "mean_token_accuracy": 0.7612254858016968,
+      "num_tokens": 2187255.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.5835777126099706,
+      "grad_norm": 0.5030059814453125,
+      "learning_rate": 9.6832642408655e-05,
+      "loss": 0.6154,
+      "mean_token_accuracy": 0.7645588338375091,
+      "num_tokens": 2207735.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.598240469208211,
+      "grad_norm": 0.5831127166748047,
+      "learning_rate": 9.674717387711706e-05,
+      "loss": 0.6032,
+      "mean_token_accuracy": 0.7698039233684539,
+      "num_tokens": 2228215.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 0.5647640824317932,
+      "learning_rate": 9.66606062428276e-05,
+      "loss": 0.6553,
+      "mean_token_accuracy": 0.7468942880630494,
+      "num_tokens": 2248464.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.627565982404692,
+      "grad_norm": 0.5415534377098083,
+      "learning_rate": 9.657294154113368e-05,
+      "loss": 0.6164,
+      "mean_token_accuracy": 0.761519604921341,
+      "num_tokens": 2268944.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.6422287390029324,
+      "grad_norm": 0.6378477215766907,
+      "learning_rate": 9.648418183317629e-05,
+      "loss": 0.6192,
+      "mean_token_accuracy": 0.7626470625400543,
+      "num_tokens": 2289424.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.6568914956011729,
+      "grad_norm": 0.5039816498756409,
+      "learning_rate": 9.639432920584177e-05,
+      "loss": 0.6186,
+      "mean_token_accuracy": 0.7617647111415863,
+      "num_tokens": 2309904.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.6715542521994133,
+      "grad_norm": 0.545703649520874,
+      "learning_rate": 9.630338577171282e-05,
+      "loss": 0.6358,
+      "mean_token_accuracy": 0.7567647159099579,
+      "num_tokens": 2330384.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.6862170087976538,
+      "grad_norm": 0.5335627198219299,
+      "learning_rate": 9.621135366901874e-05,
+      "loss": 0.6168,
+      "mean_token_accuracy": 0.7622058987617493,
+      "num_tokens": 2350864.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7008797653958945,
+      "grad_norm": 0.5737611055374146,
+      "learning_rate": 9.61182350615853e-05,
+      "loss": 0.6088,
+      "mean_token_accuracy": 0.7669607877731324,
+      "num_tokens": 2371344.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.715542521994135,
+      "grad_norm": 0.5467628240585327,
+      "learning_rate": 9.60240321387837e-05,
+      "loss": 0.6355,
+      "mean_token_accuracy": 0.7537745118141175,
+      "num_tokens": 2391824.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.7302052785923754,
+      "grad_norm": 0.47698599100112915,
+      "learning_rate": 9.592874711547922e-05,
+      "loss": 0.6157,
+      "mean_token_accuracy": 0.7636764705181122,
+      "num_tokens": 2412304.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.7448680351906158,
+      "grad_norm": 0.5102219581604004,
+      "learning_rate": 9.583238223197906e-05,
+      "loss": 0.6037,
+      "mean_token_accuracy": 0.7686274528503418,
+      "num_tokens": 2432784.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.7595307917888563,
+      "grad_norm": 0.5764709115028381,
+      "learning_rate": 9.573493975397975e-05,
+      "loss": 0.6321,
+      "mean_token_accuracy": 0.7561274468898773,
+      "num_tokens": 2453264.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7741935483870968,
+      "grad_norm": 0.5202457904815674,
+      "learning_rate": 9.56364219725138e-05,
+      "loss": 0.6399,
+      "mean_token_accuracy": 0.7505392134189606,
+      "num_tokens": 2473744.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.7888563049853372,
+      "grad_norm": 0.5214654803276062,
+      "learning_rate": 9.553683120389592e-05,
+      "loss": 0.6161,
+      "mean_token_accuracy": 0.7630882322788238,
+      "num_tokens": 2494224.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8035190615835777,
+      "grad_norm": 0.5128310322761536,
+      "learning_rate": 9.543616978966842e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7627941191196441,
+      "num_tokens": 2514704.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.5823948383331299,
+      "learning_rate": 9.53344400965463e-05,
+      "loss": 0.6354,
+      "mean_token_accuracy": 0.756078428030014,
+      "num_tokens": 2535184.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.8328445747800588,
+      "grad_norm": 0.568189799785614,
+      "learning_rate": 9.523164451636157e-05,
+      "loss": 0.6168,
+      "mean_token_accuracy": 0.7599999964237213,
+      "num_tokens": 2555664.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.8475073313782993,
+      "grad_norm": 0.5598325133323669,
+      "learning_rate": 9.512778546600696e-05,
+      "loss": 0.6292,
+      "mean_token_accuracy": 0.75686274766922,
+      "num_tokens": 2576144.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.8621700879765397,
+      "grad_norm": 0.5429131388664246,
+      "learning_rate": 9.50228653873791e-05,
+      "loss": 0.6283,
+      "mean_token_accuracy": 0.7598039209842682,
+      "num_tokens": 2596624.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.8768328445747802,
+      "grad_norm": 0.4898570775985718,
+      "learning_rate": 9.491688674732123e-05,
+      "loss": 0.6406,
+      "mean_token_accuracy": 0.7537254869937897,
+      "num_tokens": 2617104.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.8914956011730206,
+      "grad_norm": 0.5072643756866455,
+      "learning_rate": 9.480985203756501e-05,
+      "loss": 0.6288,
+      "mean_token_accuracy": 0.7583333313465118,
+      "num_tokens": 2637584.0,
+      "step": 1290
+    },
+    {
+      "epoch": 1.906158357771261,
+      "grad_norm": 0.5450229048728943,
+      "learning_rate": 9.470176377467206e-05,
+      "loss": 0.6135,
+      "mean_token_accuracy": 0.7631862699985504,
+      "num_tokens": 2658064.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.9208211143695015,
+      "grad_norm": 0.5232940912246704,
+      "learning_rate": 9.45926244999748e-05,
+      "loss": 0.6196,
+      "mean_token_accuracy": 0.7628431499004364,
+      "num_tokens": 2678544.0,
+      "step": 1310
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 0.5383533239364624,
+      "learning_rate": 9.44824367795166e-05,
+      "loss": 0.6046,
+      "mean_token_accuracy": 0.7665885031223297,
+      "num_tokens": 2698834.0,
+      "step": 1320
+    },
+    {
+      "epoch": 1.9501466275659824,
+      "grad_norm": 0.4725590944290161,
+      "learning_rate": 9.437120320399158e-05,
+      "loss": 0.6297,
+      "mean_token_accuracy": 0.7592157006263733,
+      "num_tokens": 2719314.0,
+      "step": 1330
+    },
+    {
+      "epoch": 1.964809384164223,
+      "grad_norm": 0.48085474967956543,
+      "learning_rate": 9.425892638868356e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7608333349227905,
+      "num_tokens": 2739794.0,
+      "step": 1340
+    },
+    {
+      "epoch": 1.9794721407624634,
+      "grad_norm": 0.5690534710884094,
+      "learning_rate": 9.414560897340468e-05,
+      "loss": 0.6349,
+      "mean_token_accuracy": 0.75343137383461,
+      "num_tokens": 2760274.0,
+      "step": 1350
+    },
+    {
+      "epoch": 1.9941348973607038,
+      "grad_norm": 0.5363736152648926,
+      "learning_rate": 9.403125362243328e-05,
+      "loss": 0.6124,
+      "mean_token_accuracy": 0.7653431355953216,
+      "num_tokens": 2780754.0,
+      "step": 1360
+    },
+    {
+      "epoch": 2.0087976539589443,
+      "grad_norm": 0.544509768486023,
+      "learning_rate": 9.39158630244513e-05,
+      "loss": 0.6031,
+      "mean_token_accuracy": 0.7673039197921753,
+      "num_tokens": 2799698.0,
+      "step": 1370
+    },
+    {
+      "epoch": 2.0234604105571847,
+      "grad_norm": 0.6539320945739746,
+      "learning_rate": 9.379943989248096e-05,
+      "loss": 0.5932,
+      "mean_token_accuracy": 0.7711764693260192,
+      "num_tokens": 2820178.0,
+      "step": 1380
+    },
+    {
+      "epoch": 2.038123167155425,
+      "grad_norm": 0.7973995208740234,
+      "learning_rate": 9.368198696382115e-05,
+      "loss": 0.5895,
+      "mean_token_accuracy": 0.7704901933670044,
+      "num_tokens": 2840658.0,
+      "step": 1390
+    },
+    {
+      "epoch": 2.0527859237536656,
+      "grad_norm": 0.5431190133094788,
+      "learning_rate": 9.356350699998288e-05,
+      "loss": 0.5823,
+      "mean_token_accuracy": 0.7777450978755951,
+      "num_tokens": 2861138.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.067448680351906,
+      "grad_norm": 0.6147369742393494,
+      "learning_rate": 9.344400278662448e-05,
+      "loss": 0.5854,
+      "mean_token_accuracy": 0.7753921627998352,
+      "num_tokens": 2881618.0,
+      "step": 1410
+    },
+    {
+      "epoch": 2.0821114369501466,
+      "grad_norm": 0.6121999025344849,
+      "learning_rate": 9.332347713348608e-05,
+      "loss": 0.5973,
+      "mean_token_accuracy": 0.7709803938865661,
+      "num_tokens": 2902098.0,
+      "step": 1420
+    },
+    {
+      "epoch": 2.096774193548387,
+      "grad_norm": 0.7150356769561768,
+      "learning_rate": 9.320193287432353e-05,
+      "loss": 0.592,
+      "mean_token_accuracy": 0.7744117677211761,
+      "num_tokens": 2922578.0,
+      "step": 1430
+    },
+    {
+      "epoch": 2.1114369501466275,
+      "grad_norm": 0.6568698287010193,
+      "learning_rate": 9.307937286684173e-05,
+      "loss": 0.6013,
+      "mean_token_accuracy": 0.7699509859085083,
+      "num_tokens": 2943058.0,
+      "step": 1440
+    },
+    {
+      "epoch": 2.126099706744868,
+      "grad_norm": 0.6842476725578308,
+      "learning_rate": 9.295579999262756e-05,
+      "loss": 0.5836,
+      "mean_token_accuracy": 0.776862746477127,
+      "num_tokens": 2963538.0,
+      "step": 1450
+    },
+    {
+      "epoch": 2.1407624633431084,
+      "grad_norm": 0.7466417551040649,
+      "learning_rate": 9.283121715708202e-05,
+      "loss": 0.5931,
+      "mean_token_accuracy": 0.7705392241477966,
+      "num_tokens": 2984018.0,
+      "step": 1460
+    },
+    {
+      "epoch": 2.155425219941349,
+      "grad_norm": 0.6118063926696777,
+      "learning_rate": 9.270562728935197e-05,
+      "loss": 0.6063,
+      "mean_token_accuracy": 0.7664917647838593,
+      "num_tokens": 3004171.0,
+      "step": 1470
+    },
+    {
+      "epoch": 2.1700879765395893,
+      "grad_norm": 0.6150789260864258,
+      "learning_rate": 9.257903334226124e-05,
+      "loss": 0.5848,
+      "mean_token_accuracy": 0.7761870443820953,
+      "num_tokens": 3024539.0,
+      "step": 1480
+    },
+    {
+      "epoch": 2.1847507331378297,
+      "grad_norm": 0.6299267411231995,
+      "learning_rate": 9.24514382922412e-05,
+      "loss": 0.5817,
+      "mean_token_accuracy": 0.774215692281723,
+      "num_tokens": 3045019.0,
+      "step": 1490
+    },
+    {
+      "epoch": 2.19941348973607,
+      "grad_norm": 0.6822914481163025,
+      "learning_rate": 9.232284513926085e-05,
+      "loss": 0.5752,
+      "mean_token_accuracy": 0.7771973431110382,
+      "num_tokens": 3065312.0,
+      "step": 1500
+    },
+    {
+      "epoch": 2.2140762463343107,
+      "grad_norm": 0.6228194832801819,
+      "learning_rate": 9.219325690675615e-05,
+      "loss": 0.6104,
+      "mean_token_accuracy": 0.7640686273574829,
+      "num_tokens": 3085792.0,
+      "step": 1510
+    },
+    {
+      "epoch": 2.228739002932551,
+      "grad_norm": 0.6606581211090088,
+      "learning_rate": 9.206267664155907e-05,
+      "loss": 0.6004,
+      "mean_token_accuracy": 0.7706372559070587,
+      "num_tokens": 3106272.0,
+      "step": 1520
+    },
+    {
+      "epoch": 2.2434017595307916,
+      "grad_norm": 0.6690000295639038,
+      "learning_rate": 9.193110741382585e-05,
+      "loss": 0.6004,
+      "mean_token_accuracy": 0.770147055387497,
+      "num_tokens": 3126752.0,
+      "step": 1530
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 0.495844304561615,
+      "learning_rate": 9.179855231696491e-05,
+      "loss": 0.5804,
+      "mean_token_accuracy": 0.7760294198989868,
+      "num_tokens": 3147232.0,
+      "step": 1540
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.6850236654281616,
+      "learning_rate": 9.166501446756405e-05,
+      "loss": 0.5987,
+      "mean_token_accuracy": 0.7694117665290833,
+      "num_tokens": 3167712.0,
+      "step": 1550
+    },
+    {
+      "epoch": 2.2873900293255134,
+      "grad_norm": 0.6291906237602234,
+      "learning_rate": 9.153049700531718e-05,
+      "loss": 0.6047,
+      "mean_token_accuracy": 0.769803935289383,
+      "num_tokens": 3188192.0,
+      "step": 1560
+    },
+    {
+      "epoch": 2.302052785923754,
+      "grad_norm": 0.5397360324859619,
+      "learning_rate": 9.139500309295053e-05,
+      "loss": 0.5845,
+      "mean_token_accuracy": 0.7725980460643769,
+      "num_tokens": 3208672.0,
+      "step": 1570
+    },
+    {
+      "epoch": 2.3167155425219943,
+      "grad_norm": 0.5473708510398865,
+      "learning_rate": 9.125853591614828e-05,
+      "loss": 0.6019,
+      "mean_token_accuracy": 0.7681862771511078,
+      "num_tokens": 3229152.0,
+      "step": 1580
+    },
+    {
+      "epoch": 2.3313782991202348,
+      "grad_norm": 0.6557981371879578,
+      "learning_rate": 9.112109868347763e-05,
+      "loss": 0.6003,
+      "mean_token_accuracy": 0.7697058916091919,
+      "num_tokens": 3249632.0,
+      "step": 1590
+    },
+    {
+      "epoch": 2.346041055718475,
+      "grad_norm": 0.583633303642273,
+      "learning_rate": 9.098269462631341e-05,
+      "loss": 0.6045,
+      "mean_token_accuracy": 0.7686714708805085,
+      "num_tokens": 3270032.0,
+      "step": 1600
+    },
+    {
+      "epoch": 2.3607038123167157,
+      "grad_norm": 0.6261008381843567,
+      "learning_rate": 9.084332699876208e-05,
+      "loss": 0.5885,
+      "mean_token_accuracy": 0.77156862616539,
+      "num_tokens": 3290512.0,
+      "step": 1610
+    },
+    {
+      "epoch": 2.375366568914956,
+      "grad_norm": 0.7260749340057373,
+      "learning_rate": 9.07029990775852e-05,
+      "loss": 0.5971,
+      "mean_token_accuracy": 0.7704411804676056,
+      "num_tokens": 3310992.0,
+      "step": 1620
+    },
+    {
+      "epoch": 2.3900293255131966,
+      "grad_norm": 0.6833462715148926,
+      "learning_rate": 9.056171416212243e-05,
+      "loss": 0.5866,
+      "mean_token_accuracy": 0.7733333289623261,
+      "num_tokens": 3331472.0,
+      "step": 1630
+    },
+    {
+      "epoch": 2.404692082111437,
+      "grad_norm": 0.7324588894844055,
+      "learning_rate": 9.041947557421391e-05,
+      "loss": 0.5809,
+      "mean_token_accuracy": 0.7767156839370728,
+      "num_tokens": 3351952.0,
+      "step": 1640
+    },
+    {
+      "epoch": 2.4193548387096775,
+      "grad_norm": 0.5573662519454956,
+      "learning_rate": 9.02762866581222e-05,
+      "loss": 0.6028,
+      "mean_token_accuracy": 0.7668627440929413,
+      "num_tokens": 3372432.0,
+      "step": 1650
+    },
+    {
+      "epoch": 2.434017595307918,
+      "grad_norm": 0.825465202331543,
+      "learning_rate": 9.013215078045363e-05,
+      "loss": 0.6014,
+      "mean_token_accuracy": 0.7658333301544189,
+      "num_tokens": 3392912.0,
+      "step": 1660
+    },
+    {
+      "epoch": 2.4486803519061584,
+      "grad_norm": 0.6437454223632812,
+      "learning_rate": 8.998707133007918e-05,
+      "loss": 0.6047,
+      "mean_token_accuracy": 0.7664215743541718,
+      "num_tokens": 3413392.0,
+      "step": 1670
+    },
+    {
+      "epoch": 2.463343108504399,
+      "grad_norm": 0.6310515999794006,
+      "learning_rate": 8.984105171805472e-05,
+      "loss": 0.5842,
+      "mean_token_accuracy": 0.7743137300014495,
+      "num_tokens": 3433872.0,
+      "step": 1680
+    },
+    {
+      "epoch": 2.4780058651026393,
+      "grad_norm": 0.641413152217865,
+      "learning_rate": 8.969409537754092e-05,
+      "loss": 0.5971,
+      "mean_token_accuracy": 0.7689705848693847,
+      "num_tokens": 3454352.0,
+      "step": 1690
+    },
+    {
+      "epoch": 2.4926686217008798,
+      "grad_norm": 0.6254575252532959,
+      "learning_rate": 8.95462057637224e-05,
+      "loss": 0.601,
+      "mean_token_accuracy": 0.7684313714504242,
+      "num_tokens": 3474832.0,
+      "step": 1700
+    },
+    {
+      "epoch": 2.5073313782991202,
+      "grad_norm": 0.5509727597236633,
+      "learning_rate": 8.939738635372664e-05,
+      "loss": 0.6032,
+      "mean_token_accuracy": 0.7683777451515198,
+      "num_tokens": 3495060.0,
+      "step": 1710
+    },
+    {
+      "epoch": 2.5219941348973607,
+      "grad_norm": 0.6135575175285339,
+      "learning_rate": 8.924764064654212e-05,
+      "loss": 0.595,
+      "mean_token_accuracy": 0.7695098042488098,
+      "num_tokens": 3515540.0,
+      "step": 1720
+    },
+    {
+      "epoch": 2.536656891495601,
+      "grad_norm": 0.5865819454193115,
+      "learning_rate": 8.909697216293609e-05,
+      "loss": 0.604,
+      "mean_token_accuracy": 0.7670098066329956,
+      "num_tokens": 3536020.0,
+      "step": 1730
+    },
+    {
+      "epoch": 2.5513196480938416,
+      "grad_norm": 0.6289553046226501,
+      "learning_rate": 8.894538444537177e-05,
+      "loss": 0.588,
+      "mean_token_accuracy": 0.7727451026439667,
+      "num_tokens": 3556500.0,
+      "step": 1740
+    },
+    {
+      "epoch": 2.565982404692082,
+      "grad_norm": 0.5837467908859253,
+      "learning_rate": 8.87928810579251e-05,
+      "loss": 0.5908,
+      "mean_token_accuracy": 0.7722666919231415,
+      "num_tokens": 3576749.0,
+      "step": 1750
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 0.7653214931488037,
+      "learning_rate": 8.863946558620094e-05,
+      "loss": 0.6068,
+      "mean_token_accuracy": 0.7670588195323944,
+      "num_tokens": 3597229.0,
+      "step": 1760
+    },
+    {
+      "epoch": 2.595307917888563,
+      "grad_norm": 0.5600757002830505,
+      "learning_rate": 8.84851416372487e-05,
+      "loss": 0.5964,
+      "mean_token_accuracy": 0.7708823502063751,
+      "num_tokens": 3617709.0,
+      "step": 1770
+    },
+    {
+      "epoch": 2.6099706744868034,
+      "grad_norm": 0.615788996219635,
+      "learning_rate": 8.832991283947762e-05,
+      "loss": 0.6216,
+      "mean_token_accuracy": 0.761176460981369,
+      "num_tokens": 3638189.0,
+      "step": 1780
+    },
+    {
+      "epoch": 2.624633431085044,
+      "grad_norm": 0.574803352355957,
+      "learning_rate": 8.81737828425714e-05,
+      "loss": 0.5768,
+      "mean_token_accuracy": 0.7758823573589325,
+      "num_tokens": 3658669.0,
+      "step": 1790
+    },
+    {
+      "epoch": 2.6392961876832843,
+      "grad_norm": 0.7114520072937012,
+      "learning_rate": 8.80167553174024e-05,
+      "loss": 0.5926,
+      "mean_token_accuracy": 0.7726960778236389,
+      "num_tokens": 3679149.0,
+      "step": 1800
+    },
+    {
+      "epoch": 2.653958944281525,
+      "grad_norm": 0.5663362145423889,
+      "learning_rate": 8.785883395594541e-05,
+      "loss": 0.5794,
+      "mean_token_accuracy": 0.7743627488613128,
+      "num_tokens": 3699629.0,
+      "step": 1810
+    },
+    {
+      "epoch": 2.6686217008797652,
+      "grad_norm": 0.6680328249931335,
+      "learning_rate": 8.770002247119064e-05,
+      "loss": 0.6057,
+      "mean_token_accuracy": 0.7669117748737335,
+      "num_tokens": 3720109.0,
+      "step": 1820
+    },
+    {
+      "epoch": 2.6832844574780057,
+      "grad_norm": 0.6905878186225891,
+      "learning_rate": 8.754032459705672e-05,
+      "loss": 0.6001,
+      "mean_token_accuracy": 0.7686764895915985,
+      "num_tokens": 3740589.0,
+      "step": 1830
+    },
+    {
+      "epoch": 2.6979472140762466,
+      "grad_norm": 0.5783908367156982,
+      "learning_rate": 8.737974408830263e-05,
+      "loss": 0.6037,
+      "mean_token_accuracy": 0.7703921616077423,
+      "num_tokens": 3761069.0,
+      "step": 1840
+    },
+    {
+      "epoch": 2.712609970674487,
+      "grad_norm": 0.7091444730758667,
+      "learning_rate": 8.721828472043958e-05,
+      "loss": 0.5801,
+      "mean_token_accuracy": 0.777009803056717,
+      "num_tokens": 3781549.0,
+      "step": 1850
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.6419853568077087,
+      "learning_rate": 8.705595028964222e-05,
+      "loss": 0.592,
+      "mean_token_accuracy": 0.7715686321258545,
+      "num_tokens": 3802029.0,
+      "step": 1860
+    },
+    {
+      "epoch": 2.741935483870968,
+      "grad_norm": 0.6625768542289734,
+      "learning_rate": 8.689274461265935e-05,
+      "loss": 0.5984,
+      "mean_token_accuracy": 0.7693137288093567,
+      "num_tokens": 3822509.0,
+      "step": 1870
+    },
+    {
+      "epoch": 2.7565982404692084,
+      "grad_norm": 0.6934528350830078,
+      "learning_rate": 8.672867152672416e-05,
+      "loss": 0.5871,
+      "mean_token_accuracy": 0.7757352948188782,
+      "num_tokens": 3842989.0,
+      "step": 1880
+    },
+    {
+      "epoch": 2.771260997067449,
+      "grad_norm": 0.570747435092926,
+      "learning_rate": 8.656373488946409e-05,
+      "loss": 0.5777,
+      "mean_token_accuracy": 0.7777941226959229,
+      "num_tokens": 3863469.0,
+      "step": 1890
+    },
+    {
+      "epoch": 2.7859237536656893,
+      "grad_norm": 0.5088850855827332,
+      "learning_rate": 8.639793857881011e-05,
+      "loss": 0.5912,
+      "mean_token_accuracy": 0.7703921675682068,
+      "num_tokens": 3883949.0,
+      "step": 1900
+    },
+    {
+      "epoch": 2.80058651026393,
+      "grad_norm": 0.7125044465065002,
+      "learning_rate": 8.623128649290544e-05,
+      "loss": 0.6006,
+      "mean_token_accuracy": 0.7711764693260192,
+      "num_tokens": 3904429.0,
+      "step": 1910
+    },
+    {
+      "epoch": 2.8152492668621703,
+      "grad_norm": 0.707624614238739,
+      "learning_rate": 8.606378255001408e-05,
+      "loss": 0.5983,
+      "mean_token_accuracy": 0.7694117724895477,
+      "num_tokens": 3924909.0,
+      "step": 1920
+    },
+    {
+      "epoch": 2.8299120234604107,
+      "grad_norm": 0.6317010521888733,
+      "learning_rate": 8.58954306884285e-05,
+      "loss": 0.6064,
+      "mean_token_accuracy": 0.7670129835605621,
+      "num_tokens": 3945199.0,
+      "step": 1930
+    },
+    {
+      "epoch": 2.844574780058651,
+      "grad_norm": 0.6072015166282654,
+      "learning_rate": 8.572623486637719e-05,
+      "loss": 0.5982,
+      "mean_token_accuracy": 0.7714847445487976,
+      "num_tokens": 3965613.0,
+      "step": 1940
+    },
+    {
+      "epoch": 2.8592375366568916,
+      "grad_norm": 0.6589727997779846,
+      "learning_rate": 8.555619906193147e-05,
+      "loss": 0.5861,
+      "mean_token_accuracy": 0.7741666734218597,
+      "num_tokens": 3986093.0,
+      "step": 1950
+    },
+    {
+      "epoch": 2.873900293255132,
+      "grad_norm": 0.676544189453125,
+      "learning_rate": 8.538532727291211e-05,
+      "loss": 0.5995,
+      "mean_token_accuracy": 0.7698529422283172,
+      "num_tokens": 4006573.0,
+      "step": 1960
+    },
+    {
+      "epoch": 2.8885630498533725,
+      "grad_norm": 0.7198004126548767,
+      "learning_rate": 8.521362351679517e-05,
+      "loss": 0.6057,
+      "mean_token_accuracy": 0.7672058820724488,
+      "num_tokens": 4027053.0,
+      "step": 1970
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 0.6745808124542236,
+      "learning_rate": 8.504109183061768e-05,
+      "loss": 0.5961,
+      "mean_token_accuracy": 0.7691176533699036,
+      "num_tokens": 4047533.0,
+      "step": 1980
+    },
+    {
+      "epoch": 2.9178885630498534,
+      "grad_norm": 0.5883781909942627,
+      "learning_rate": 8.486773627088263e-05,
+      "loss": 0.5881,
+      "mean_token_accuracy": 0.7735294163227081,
+      "num_tokens": 4068013.0,
+      "step": 1990
+    },
+    {
+      "epoch": 2.932551319648094,
+      "grad_norm": 0.6510045528411865,
+      "learning_rate": 8.469356091346361e-05,
+      "loss": 0.6149,
+      "mean_token_accuracy": 0.7622058868408204,
+      "num_tokens": 4088493.0,
+      "step": 2000
+    },
+    {
+      "epoch": 2.9472140762463344,
+      "grad_norm": 0.6162061095237732,
+      "learning_rate": 8.451856985350906e-05,
+      "loss": 0.6064,
+      "mean_token_accuracy": 0.765656465291977,
+      "num_tokens": 4108923.0,
+      "step": 2010
+    },
+    {
+      "epoch": 2.961876832844575,
+      "grad_norm": 0.7037227153778076,
+      "learning_rate": 8.434276720534588e-05,
+      "loss": 0.5993,
+      "mean_token_accuracy": 0.7701960802078247,
+      "num_tokens": 4129403.0,
+      "step": 2020
+    },
+    {
+      "epoch": 2.9765395894428153,
+      "grad_norm": 0.6391721963882446,
+      "learning_rate": 8.416615710238277e-05,
+      "loss": 0.6005,
+      "mean_token_accuracy": 0.7682352960109711,
+      "num_tokens": 4149883.0,
+      "step": 2030
+    },
+    {
+      "epoch": 2.9912023460410557,
+      "grad_norm": 0.5743676424026489,
+      "learning_rate": 8.398874369701297e-05,
+      "loss": 0.6044,
+      "mean_token_accuracy": 0.7700980484485627,
+      "num_tokens": 4170363.0,
+      "step": 2040
+    },
+    {
+      "epoch": 3.005865102639296,
+      "grad_norm": 0.6292133927345276,
+      "learning_rate": 8.381053116051672e-05,
+      "loss": 0.5874,
+      "mean_token_accuracy": 0.7730392098426819,
+      "num_tokens": 4189307.0,
+      "step": 2050
+    },
+    {
+      "epoch": 3.0205278592375366,
+      "grad_norm": 0.7218403220176697,
+      "learning_rate": 8.363152368296312e-05,
+      "loss": 0.5669,
+      "mean_token_accuracy": 0.7835784316062927,
+      "num_tokens": 4209787.0,
+      "step": 2060
+    },
+    {
+      "epoch": 3.035190615835777,
+      "grad_norm": 0.5877867937088013,
+      "learning_rate": 8.345172547311165e-05,
+      "loss": 0.5594,
+      "mean_token_accuracy": 0.7853638231754303,
+      "num_tokens": 4230217.0,
+      "step": 2070
+    },
+    {
+      "epoch": 3.0498533724340176,
+      "grad_norm": 0.7881086468696594,
+      "learning_rate": 8.327114075831322e-05,
+      "loss": 0.5706,
+      "mean_token_accuracy": 0.7824086725711823,
+      "num_tokens": 4250585.0,
+      "step": 2080
+    },
+    {
+      "epoch": 3.064516129032258,
+      "grad_norm": 0.7770957946777344,
+      "learning_rate": 8.308977378441072e-05,
+      "loss": 0.5521,
+      "mean_token_accuracy": 0.7870588302612305,
+      "num_tokens": 4271065.0,
+      "step": 2090
+    },
+    {
+      "epoch": 3.0791788856304985,
+      "grad_norm": 0.7066412568092346,
+      "learning_rate": 8.290762881563925e-05,
+      "loss": 0.5637,
+      "mean_token_accuracy": 0.7850000023841858,
+      "num_tokens": 4291545.0,
+      "step": 2100
+    },
+    {
+      "epoch": 3.093841642228739,
+      "grad_norm": 0.8342577815055847,
+      "learning_rate": 8.272471013452589e-05,
+      "loss": 0.544,
+      "mean_token_accuracy": 0.7900490164756775,
+      "num_tokens": 4312025.0,
+      "step": 2110
+    },
+    {
+      "epoch": 3.1085043988269794,
+      "grad_norm": 0.8545389175415039,
+      "learning_rate": 8.254102204178891e-05,
+      "loss": 0.5696,
+      "mean_token_accuracy": 0.7814215660095215,
+      "num_tokens": 4332505.0,
+      "step": 2120
+    },
+    {
+      "epoch": 3.12316715542522,
+      "grad_norm": 0.7944217920303345,
+      "learning_rate": 8.235656885623673e-05,
+      "loss": 0.5629,
+      "mean_token_accuracy": 0.7832352995872498,
+      "num_tokens": 4352985.0,
+      "step": 2130
+    },
+    {
+      "epoch": 3.1378299120234603,
+      "grad_norm": 0.8933734893798828,
+      "learning_rate": 8.217135491466636e-05,
+      "loss": 0.5565,
+      "mean_token_accuracy": 0.7854902029037476,
+      "num_tokens": 4373465.0,
+      "step": 2140
+    },
+    {
+      "epoch": 3.1524926686217007,
+      "grad_norm": 0.9214743971824646,
+      "learning_rate": 8.198538457176142e-05,
+      "loss": 0.5619,
+      "mean_token_accuracy": 0.785735297203064,
+      "num_tokens": 4393945.0,
+      "step": 2150
+    },
+    {
+      "epoch": 3.167155425219941,
+      "grad_norm": 0.7290875315666199,
+      "learning_rate": 8.17986621999898e-05,
+      "loss": 0.5627,
+      "mean_token_accuracy": 0.7828921675682068,
+      "num_tokens": 4414425.0,
+      "step": 2160
+    },
+    {
+      "epoch": 3.1818181818181817,
+      "grad_norm": 0.9044493436813354,
+      "learning_rate": 8.161119218950078e-05,
+      "loss": 0.567,
+      "mean_token_accuracy": 0.782745099067688,
+      "num_tokens": 4434905.0,
+      "step": 2170
+    },
+    {
+      "epoch": 3.196480938416422,
+      "grad_norm": 0.7789188027381897,
+      "learning_rate": 8.142297894802184e-05,
+      "loss": 0.5432,
+      "mean_token_accuracy": 0.7916666626930237,
+      "num_tokens": 4455385.0,
+      "step": 2180
+    },
+    {
+      "epoch": 3.2111436950146626,
+      "grad_norm": 0.8108877539634705,
+      "learning_rate": 8.123402690075514e-05,
+      "loss": 0.5732,
+      "mean_token_accuracy": 0.7794117629528046,
+      "num_tokens": 4475865.0,
+      "step": 2190
+    },
+    {
+      "epoch": 3.225806451612903,
+      "grad_norm": 0.8983103036880493,
+      "learning_rate": 8.104434049027327e-05,
+      "loss": 0.5689,
+      "mean_token_accuracy": 0.7813602983951569,
+      "num_tokens": 4496225.0,
+      "step": 2200
+    },
+    {
+      "epoch": 3.2404692082111435,
+      "grad_norm": 0.9456232786178589,
+      "learning_rate": 8.085392417641493e-05,
+      "loss": 0.5432,
+      "mean_token_accuracy": 0.7895588219165802,
+      "num_tokens": 4516705.0,
+      "step": 2210
+    },
+    {
+      "epoch": 3.255131964809384,
+      "grad_norm": 1.0749609470367432,
+      "learning_rate": 8.066278243618008e-05,
+      "loss": 0.5701,
+      "mean_token_accuracy": 0.7805392265319824,
+      "num_tokens": 4537185.0,
+      "step": 2220
+    },
+    {
+      "epoch": 3.2697947214076244,
+      "grad_norm": 0.7756474018096924,
+      "learning_rate": 8.047091976362459e-05,
+      "loss": 0.554,
+      "mean_token_accuracy": 0.7881602823734284,
+      "num_tokens": 4557413.0,
+      "step": 2230
+    },
+    {
+      "epoch": 3.2844574780058653,
+      "grad_norm": 0.7649694681167603,
+      "learning_rate": 8.02783406697547e-05,
+      "loss": 0.5759,
+      "mean_token_accuracy": 0.7800490260124207,
+      "num_tokens": 4577893.0,
+      "step": 2240
+    },
+    {
+      "epoch": 3.2991202346041058,
+      "grad_norm": 0.694879949092865,
+      "learning_rate": 8.008504968242083e-05,
+      "loss": 0.5544,
+      "mean_token_accuracy": 0.7855392217636108,
+      "num_tokens": 4598373.0,
+      "step": 2250
+    },
+    {
+      "epoch": 3.313782991202346,
+      "grad_norm": 0.6860668063163757,
+      "learning_rate": 7.989105134621122e-05,
+      "loss": 0.5503,
+      "mean_token_accuracy": 0.7881372570991516,
+      "num_tokens": 4618853.0,
+      "step": 2260
+    },
+    {
+      "epoch": 3.3284457478005867,
+      "grad_norm": 0.7908605337142944,
+      "learning_rate": 7.969635022234501e-05,
+      "loss": 0.559,
+      "mean_token_accuracy": 0.7852414846420288,
+      "num_tokens": 4639126.0,
+      "step": 2270
+    },
+    {
+      "epoch": 3.343108504398827,
+      "grad_norm": 0.7057257294654846,
+      "learning_rate": 7.950095088856508e-05,
+      "loss": 0.5566,
+      "mean_token_accuracy": 0.7858823537826538,
+      "num_tokens": 4659606.0,
+      "step": 2280
+    },
+    {
+      "epoch": 3.3577712609970676,
+      "grad_norm": 0.736119270324707,
+      "learning_rate": 7.930485793903031e-05,
+      "loss": 0.5432,
+      "mean_token_accuracy": 0.7909313797950744,
+      "num_tokens": 4680086.0,
+      "step": 2290
+    },
+    {
+      "epoch": 3.372434017595308,
+      "grad_norm": 0.7554038166999817,
+      "learning_rate": 7.910807598420767e-05,
+      "loss": 0.5535,
+      "mean_token_accuracy": 0.7869117617607116,
+      "num_tokens": 4700566.0,
+      "step": 2300
+    },
+    {
+      "epoch": 3.3870967741935485,
+      "grad_norm": 0.6825692653656006,
+      "learning_rate": 7.891060965076375e-05,
+      "loss": 0.5626,
+      "mean_token_accuracy": 0.7843627512454987,
+      "num_tokens": 4721046.0,
+      "step": 2310
+    },
+    {
+      "epoch": 3.401759530791789,
+      "grad_norm": 0.8772905468940735,
+      "learning_rate": 7.871246358145605e-05,
+      "loss": 0.5689,
+      "mean_token_accuracy": 0.7812254905700684,
+      "num_tokens": 4741526.0,
+      "step": 2320
+    },
+    {
+      "epoch": 3.4164222873900294,
+      "grad_norm": 0.7459845542907715,
+      "learning_rate": 7.851364243502369e-05,
+      "loss": 0.5733,
+      "mean_token_accuracy": 0.7820588290691376,
+      "num_tokens": 4762006.0,
+      "step": 2330
+    },
+    {
+      "epoch": 3.43108504398827,
+      "grad_norm": 0.7376842498779297,
+      "learning_rate": 7.831415088607801e-05,
+      "loss": 0.5663,
+      "mean_token_accuracy": 0.7830882430076599,
+      "num_tokens": 4782486.0,
+      "step": 2340
+    },
+    {
+      "epoch": 3.4457478005865103,
+      "grad_norm": 0.7503150701522827,
+      "learning_rate": 7.811399362499267e-05,
+      "loss": 0.5448,
+      "mean_token_accuracy": 0.7920588314533233,
+      "num_tokens": 4802966.0,
+      "step": 2350
+    },
+    {
+      "epoch": 3.4604105571847508,
+      "grad_norm": 0.7918108701705933,
+      "learning_rate": 7.791317535779318e-05,
+      "loss": 0.5711,
+      "mean_token_accuracy": 0.7794607877731323,
+      "num_tokens": 4823446.0,
+      "step": 2360
+    },
+    {
+      "epoch": 3.4750733137829912,
+      "grad_norm": 0.7009081840515137,
+      "learning_rate": 7.771170080604652e-05,
+      "loss": 0.5564,
+      "mean_token_accuracy": 0.7876960813999176,
+      "num_tokens": 4843926.0,
+      "step": 2370
+    },
+    {
+      "epoch": 3.4897360703812317,
+      "grad_norm": 0.8529141545295715,
+      "learning_rate": 7.750957470674996e-05,
+      "loss": 0.554,
+      "mean_token_accuracy": 0.7859313666820527,
+      "num_tokens": 4864406.0,
+      "step": 2380
+    },
+    {
+      "epoch": 3.504398826979472,
+      "grad_norm": 0.8747164011001587,
+      "learning_rate": 7.730680181221963e-05,
+      "loss": 0.5599,
+      "mean_token_accuracy": 0.7838725566864013,
+      "num_tokens": 4884886.0,
+      "step": 2390
+    },
+    {
+      "epoch": 3.5190615835777126,
+      "grad_norm": 0.9171078205108643,
+      "learning_rate": 7.710338688997901e-05,
+      "loss": 0.5678,
+      "mean_token_accuracy": 0.7790196120738984,
+      "num_tokens": 4905366.0,
+      "step": 2400
+    },
+    {
+      "epoch": 3.533724340175953,
+      "grad_norm": 0.7325013875961304,
+      "learning_rate": 7.689933472264661e-05,
+      "loss": 0.5482,
+      "mean_token_accuracy": 0.7890164613723755,
+      "num_tokens": 4925659.0,
+      "step": 2410
+    },
+    {
+      "epoch": 3.5483870967741935,
+      "grad_norm": 0.7751185297966003,
+      "learning_rate": 7.669465010782369e-05,
+      "loss": 0.5653,
+      "mean_token_accuracy": 0.7840696752071381,
+      "num_tokens": 4946073.0,
+      "step": 2420
+    },
+    {
+      "epoch": 3.563049853372434,
+      "grad_norm": 0.8070659637451172,
+      "learning_rate": 7.648933785798133e-05,
+      "loss": 0.5653,
+      "mean_token_accuracy": 0.7836764693260193,
+      "num_tokens": 4966553.0,
+      "step": 2430
+    },
+    {
+      "epoch": 3.5777126099706744,
+      "grad_norm": 0.8361178040504456,
+      "learning_rate": 7.628340280034736e-05,
+      "loss": 0.5636,
+      "mean_token_accuracy": 0.7812254846096038,
+      "num_tokens": 4987033.0,
+      "step": 2440
+    },
+    {
+      "epoch": 3.592375366568915,
+      "grad_norm": 0.6866549849510193,
+      "learning_rate": 7.607684977679283e-05,
+      "loss": 0.5622,
+      "mean_token_accuracy": 0.7831862807273865,
+      "num_tokens": 5007513.0,
+      "step": 2450
+    },
+    {
+      "epoch": 3.6070381231671553,
+      "grad_norm": 0.851594865322113,
+      "learning_rate": 7.586968364371823e-05,
+      "loss": 0.54,
+      "mean_token_accuracy": 0.7919117689132691,
+      "num_tokens": 5027993.0,
+      "step": 2460
+    },
+    {
+      "epoch": 3.621700879765396,
+      "grad_norm": 0.8111262917518616,
+      "learning_rate": 7.56619092719392e-05,
+      "loss": 0.5589,
+      "mean_token_accuracy": 0.7877941131591797,
+      "num_tokens": 5048473.0,
+      "step": 2470
+    },
+    {
+      "epoch": 3.6363636363636362,
+      "grad_norm": 0.9650378823280334,
+      "learning_rate": 7.545353154657211e-05,
+      "loss": 0.5689,
+      "mean_token_accuracy": 0.7816176474094391,
+      "num_tokens": 5068953.0,
+      "step": 2480
+    },
+    {
+      "epoch": 3.6510263929618767,
+      "grad_norm": 1.074792504310608,
+      "learning_rate": 7.524455536691915e-05,
+      "loss": 0.5784,
+      "mean_token_accuracy": 0.7783733367919922,
+      "num_tokens": 5089202.0,
+      "step": 2490
+    },
+    {
+      "epoch": 3.665689149560117,
+      "grad_norm": 0.8097825050354004,
+      "learning_rate": 7.503498564635312e-05,
+      "loss": 0.5659,
+      "mean_token_accuracy": 0.7803921580314637,
+      "num_tokens": 5109682.0,
+      "step": 2500
+    },
+    {
+      "epoch": 3.6803519061583576,
+      "grad_norm": 0.6955359578132629,
+      "learning_rate": 7.482482731220202e-05,
+      "loss": 0.5921,
+      "mean_token_accuracy": 0.7721568584442139,
+      "num_tokens": 5130162.0,
+      "step": 2510
+    },
+    {
+      "epoch": 3.6950146627565985,
+      "grad_norm": 0.794173002243042,
+      "learning_rate": 7.461408530563303e-05,
+      "loss": 0.5518,
+      "mean_token_accuracy": 0.7884313702583313,
+      "num_tokens": 5150642.0,
+      "step": 2520
+    },
+    {
+      "epoch": 3.709677419354839,
+      "grad_norm": 0.8053852319717407,
+      "learning_rate": 7.44027645815365e-05,
+      "loss": 0.5657,
+      "mean_token_accuracy": 0.7833823502063751,
+      "num_tokens": 5171122.0,
+      "step": 2530
+    },
+    {
+      "epoch": 3.7243401759530794,
+      "grad_norm": 0.7356454730033875,
+      "learning_rate": 7.419087010840933e-05,
+      "loss": 0.5563,
+      "mean_token_accuracy": 0.7868627488613129,
+      "num_tokens": 5191602.0,
+      "step": 2540
+    },
+    {
+      "epoch": 3.73900293255132,
+      "grad_norm": 0.7777561545372009,
+      "learning_rate": 7.397840686823823e-05,
+      "loss": 0.5737,
+      "mean_token_accuracy": 0.7809313714504242,
+      "num_tokens": 5212082.0,
+      "step": 2550
+    },
+    {
+      "epoch": 3.7536656891495603,
+      "grad_norm": 0.8399965167045593,
+      "learning_rate": 7.376537985638254e-05,
+      "loss": 0.5921,
+      "mean_token_accuracy": 0.7739215731620789,
+      "num_tokens": 5232562.0,
+      "step": 2560
+    },
+    {
+      "epoch": 3.768328445747801,
+      "grad_norm": 0.7420411705970764,
+      "learning_rate": 7.35517940814568e-05,
+      "loss": 0.5561,
+      "mean_token_accuracy": 0.7847549021244049,
+      "num_tokens": 5253042.0,
+      "step": 2570
+    },
+    {
+      "epoch": 3.7829912023460412,
+      "grad_norm": 0.8343306183815002,
+      "learning_rate": 7.333765456521299e-05,
+      "loss": 0.5623,
+      "mean_token_accuracy": 0.7810294091701507,
+      "num_tokens": 5273522.0,
+      "step": 2580
+    },
+    {
+      "epoch": 3.7976539589442817,
+      "grad_norm": 0.8203510046005249,
+      "learning_rate": 7.312296634242246e-05,
+      "loss": 0.5641,
+      "mean_token_accuracy": 0.7849820017814636,
+      "num_tokens": 5293922.0,
+      "step": 2590
+    },
+    {
+      "epoch": 3.812316715542522,
+      "grad_norm": 0.8383901119232178,
+      "learning_rate": 7.290773446075754e-05,
+      "loss": 0.557,
+      "mean_token_accuracy": 0.7848039269447327,
+      "num_tokens": 5314402.0,
+      "step": 2600
+    },
+    {
+      "epoch": 3.8269794721407626,
+      "grad_norm": 0.7239795923233032,
+      "learning_rate": 7.269196398067287e-05,
+      "loss": 0.5625,
+      "mean_token_accuracy": 0.7849509716033936,
+      "num_tokens": 5334882.0,
+      "step": 2610
+    },
+    {
+      "epoch": 3.841642228739003,
+      "grad_norm": 0.7140374183654785,
+      "learning_rate": 7.247565997528646e-05,
+      "loss": 0.5558,
+      "mean_token_accuracy": 0.7874019622802735,
+      "num_tokens": 5355362.0,
+      "step": 2620
+    },
+    {
+      "epoch": 3.8563049853372435,
+      "grad_norm": 0.8675426840782166,
+      "learning_rate": 7.225882753026033e-05,
+      "loss": 0.5637,
+      "mean_token_accuracy": 0.7815657079219818,
+      "num_tokens": 5375652.0,
+      "step": 2630
+    },
+    {
+      "epoch": 3.870967741935484,
+      "grad_norm": 0.9986236095428467,
+      "learning_rate": 7.204147174368097e-05,
+      "loss": 0.5705,
+      "mean_token_accuracy": 0.7812745034694671,
+      "num_tokens": 5396132.0,
+      "step": 2640
+    },
+    {
+      "epoch": 3.8856304985337244,
+      "grad_norm": 0.7778323292732239,
+      "learning_rate": 7.182359772593955e-05,
+      "loss": 0.5806,
+      "mean_token_accuracy": 0.7780392169952393,
+      "num_tokens": 5416612.0,
+      "step": 2650
+    },
+    {
+      "epoch": 3.900293255131965,
+      "grad_norm": 0.8607691526412964,
+      "learning_rate": 7.160521059961169e-05,
+      "loss": 0.5466,
+      "mean_token_accuracy": 0.790833342075348,
+      "num_tokens": 5437092.0,
+      "step": 2660
+    },
+    {
+      "epoch": 3.9149560117302054,
+      "grad_norm": 0.7039009928703308,
+      "learning_rate": 7.138631549933698e-05,
+      "loss": 0.5633,
+      "mean_token_accuracy": 0.7830882430076599,
+      "num_tokens": 5457572.0,
+      "step": 2670
+    },
+    {
+      "epoch": 3.929618768328446,
+      "grad_norm": 0.8310902118682861,
+      "learning_rate": 7.116691757169837e-05,
+      "loss": 0.5486,
+      "mean_token_accuracy": 0.788823527097702,
+      "num_tokens": 5478052.0,
+      "step": 2680
+    },
+    {
+      "epoch": 3.9442815249266863,
+      "grad_norm": 0.7563566565513611,
+      "learning_rate": 7.094702197510108e-05,
+      "loss": 0.5773,
+      "mean_token_accuracy": 0.7763725519180298,
+      "num_tokens": 5498532.0,
+      "step": 2690
+    },
+    {
+      "epoch": 3.9589442815249267,
+      "grad_norm": 0.7671879529953003,
+      "learning_rate": 7.072663387965134e-05,
+      "loss": 0.5737,
+      "mean_token_accuracy": 0.7802941143512726,
+      "num_tokens": 5519012.0,
+      "step": 2700
+    },
+    {
+      "epoch": 3.973607038123167,
+      "grad_norm": 0.7739540338516235,
+      "learning_rate": 7.050575846703484e-05,
+      "loss": 0.5517,
+      "mean_token_accuracy": 0.7894117653369903,
+      "num_tokens": 5539492.0,
+      "step": 2710
+    },
+    {
+      "epoch": 3.9882697947214076,
+      "grad_norm": 0.781837522983551,
+      "learning_rate": 7.028440093039493e-05,
+      "loss": 0.5552,
+      "mean_token_accuracy": 0.7865196108818054,
+      "num_tokens": 5559972.0,
+      "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": 2.374341612797952e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-2728/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4734d6626d9f4e5de52d260e514c2c8d854a75e2ff6292ebf0fe2fce39775fa5
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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": [
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-3410/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d44386a3cb922665613778e903f7f417c044b3e4a07d18fc6ee0a6f0eab09cd2
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_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_s2_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_s2_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_s2_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