add checkpoint cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast

.gitattributes

@@ -248,3 +248,14 @@ checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a4_noSys/
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a4_noSys/checkpoint-7510/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a4_noSys/checkpoint-75100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a4_noSys/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-1362/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-2043/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-2724/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-3405/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-4086/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-4767/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-5448/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-6129/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-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_s1_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_s1_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": [
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:594d93fd608e4a77e7b752c3131e5272d2c7b0af51cd70e74dde2e09532091e6
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_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_s1_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_s1_vt_project_a1_ALL_bcast/checkpoint-1362/README.md

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-1362/adapter_config.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-1362/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7496d564643c6425a9f96dfadbeeb73e8c720b3191691fce7281278ceb37195
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-1362/added_tokens.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-1362/chat_template.jinja

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-1362/special_tokens_map.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-1362/tokenizer.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-1362/tokenizer_config.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-1362/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": 1362,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014684287812041116,
+      "grad_norm": 3.9844751358032227,
+      "learning_rate": 2.6392961876832847e-06,
+      "loss": 2.4601,
+      "mean_token_accuracy": 0.5440195977687836,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.02936857562408223,
+      "grad_norm": 3.408750295639038,
+      "learning_rate": 5.571847507331378e-06,
+      "loss": 2.4123,
+      "mean_token_accuracy": 0.5557843208312988,
+      "num_tokens": 40960.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.04405286343612335,
+      "grad_norm": 3.2006149291992188,
+      "learning_rate": 8.504398826979472e-06,
+      "loss": 2.3369,
+      "mean_token_accuracy": 0.5485294103622437,
+      "num_tokens": 61440.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.05873715124816446,
+      "grad_norm": 2.0662899017333984,
+      "learning_rate": 1.1436950146627567e-05,
+      "loss": 2.0808,
+      "mean_token_accuracy": 0.5701960742473602,
+      "num_tokens": 81920.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07342143906020558,
+      "grad_norm": 1.349193811416626,
+      "learning_rate": 1.4369501466275662e-05,
+      "loss": 1.7811,
+      "mean_token_accuracy": 0.5971078455448151,
+      "num_tokens": 102400.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.0881057268722467,
+      "grad_norm": 1.0805939435958862,
+      "learning_rate": 1.7302052785923756e-05,
+      "loss": 1.5636,
+      "mean_token_accuracy": 0.604313725233078,
+      "num_tokens": 122880.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.1027900146842878,
+      "grad_norm": 0.9003157615661621,
+      "learning_rate": 2.0234604105571847e-05,
+      "loss": 1.3844,
+      "mean_token_accuracy": 0.6224509835243225,
+      "num_tokens": 143360.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.11747430249632893,
+      "grad_norm": 0.8923518657684326,
+      "learning_rate": 2.3167155425219943e-05,
+      "loss": 1.2358,
+      "mean_token_accuracy": 0.6361274480819702,
+      "num_tokens": 163840.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.13215859030837004,
+      "grad_norm": 1.0202796459197998,
+      "learning_rate": 2.6099706744868034e-05,
+      "loss": 1.0774,
+      "mean_token_accuracy": 0.6648529529571533,
+      "num_tokens": 184320.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.14684287812041116,
+      "grad_norm": 1.149533748626709,
+      "learning_rate": 2.9032258064516133e-05,
+      "loss": 0.9291,
+      "mean_token_accuracy": 0.6854411721229553,
+      "num_tokens": 204800.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.16152716593245228,
+      "grad_norm": 1.153542160987854,
+      "learning_rate": 3.1964809384164225e-05,
+      "loss": 0.8269,
+      "mean_token_accuracy": 0.709852933883667,
+      "num_tokens": 225280.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.1762114537444934,
+      "grad_norm": 1.2031893730163574,
+      "learning_rate": 3.489736070381232e-05,
+      "loss": 0.7872,
+      "mean_token_accuracy": 0.7195098102092743,
+      "num_tokens": 245760.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.19089574155653452,
+      "grad_norm": 1.1650404930114746,
+      "learning_rate": 3.7829912023460415e-05,
+      "loss": 0.7448,
+      "mean_token_accuracy": 0.7316666603088379,
+      "num_tokens": 266240.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.2055800293685756,
+      "grad_norm": 1.1167842149734497,
+      "learning_rate": 4.076246334310851e-05,
+      "loss": 0.7018,
+      "mean_token_accuracy": 0.7435784280300141,
+      "num_tokens": 286720.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.22026431718061673,
+      "grad_norm": 1.1387581825256348,
+      "learning_rate": 4.36950146627566e-05,
+      "loss": 0.6919,
+      "mean_token_accuracy": 0.7467156887054444,
+      "num_tokens": 307200.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.23494860499265785,
+      "grad_norm": 1.0053479671478271,
+      "learning_rate": 4.6627565982404694e-05,
+      "loss": 0.7028,
+      "mean_token_accuracy": 0.7395588219165802,
+      "num_tokens": 327680.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.24963289280469897,
+      "grad_norm": 0.9742514491081238,
+      "learning_rate": 4.956011730205279e-05,
+      "loss": 0.6858,
+      "mean_token_accuracy": 0.745686274766922,
+      "num_tokens": 348160.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.2643171806167401,
+      "grad_norm": 0.8818563222885132,
+      "learning_rate": 5.249266862170088e-05,
+      "loss": 0.6913,
+      "mean_token_accuracy": 0.7424509763717652,
+      "num_tokens": 368640.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2790014684287812,
+      "grad_norm": 0.8835548162460327,
+      "learning_rate": 5.542521994134897e-05,
+      "loss": 0.6767,
+      "mean_token_accuracy": 0.7474999964237213,
+      "num_tokens": 389120.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.2936857562408223,
+      "grad_norm": 0.8910827040672302,
+      "learning_rate": 5.8357771260997075e-05,
+      "loss": 0.6789,
+      "mean_token_accuracy": 0.7434803903102875,
+      "num_tokens": 409600.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.30837004405286345,
+      "grad_norm": 0.9448742866516113,
+      "learning_rate": 6.129032258064517e-05,
+      "loss": 0.6637,
+      "mean_token_accuracy": 0.7499999940395355,
+      "num_tokens": 430080.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.32305433186490456,
+      "grad_norm": 0.7906215190887451,
+      "learning_rate": 6.422287390029326e-05,
+      "loss": 0.6593,
+      "mean_token_accuracy": 0.7529411673545837,
+      "num_tokens": 450560.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.3377386196769457,
+      "grad_norm": 0.854017436504364,
+      "learning_rate": 6.715542521994135e-05,
+      "loss": 0.6682,
+      "mean_token_accuracy": 0.7474509835243225,
+      "num_tokens": 471040.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.3524229074889868,
+      "grad_norm": 0.7827669978141785,
+      "learning_rate": 7.008797653958945e-05,
+      "loss": 0.6857,
+      "mean_token_accuracy": 0.741813725233078,
+      "num_tokens": 491520.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.3671071953010279,
+      "grad_norm": 0.7865115404129028,
+      "learning_rate": 7.302052785923754e-05,
+      "loss": 0.657,
+      "mean_token_accuracy": 0.7524509787559509,
+      "num_tokens": 512000.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.38179148311306904,
+      "grad_norm": 0.7960774302482605,
+      "learning_rate": 7.595307917888564e-05,
+      "loss": 0.6569,
+      "mean_token_accuracy": 0.752205890417099,
+      "num_tokens": 532480.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.3964757709251101,
+      "grad_norm": 0.7246135473251343,
+      "learning_rate": 7.888563049853373e-05,
+      "loss": 0.6506,
+      "mean_token_accuracy": 0.7553921639919281,
+      "num_tokens": 552960.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.4111600587371512,
+      "grad_norm": 0.6880009770393372,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 0.6617,
+      "mean_token_accuracy": 0.7480882346630097,
+      "num_tokens": 573440.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.42584434654919234,
+      "grad_norm": 0.7460880279541016,
+      "learning_rate": 8.475073313782992e-05,
+      "loss": 0.641,
+      "mean_token_accuracy": 0.7563235282897949,
+      "num_tokens": 593920.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.44052863436123346,
+      "grad_norm": 0.6125314831733704,
+      "learning_rate": 8.7683284457478e-05,
+      "loss": 0.662,
+      "mean_token_accuracy": 0.7470588207244873,
+      "num_tokens": 614400.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.4552129221732746,
+      "grad_norm": 0.8595872521400452,
+      "learning_rate": 9.06158357771261e-05,
+      "loss": 0.6428,
+      "mean_token_accuracy": 0.753333330154419,
+      "num_tokens": 634880.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.4698972099853157,
+      "grad_norm": 0.7512183785438538,
+      "learning_rate": 9.35483870967742e-05,
+      "loss": 0.6474,
+      "mean_token_accuracy": 0.7549509763717651,
+      "num_tokens": 655360.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.4845814977973568,
+      "grad_norm": 0.5831340551376343,
+      "learning_rate": 9.64809384164223e-05,
+      "loss": 0.6484,
+      "mean_token_accuracy": 0.7540196001529693,
+      "num_tokens": 675840.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.49926578560939794,
+      "grad_norm": 0.7933578491210938,
+      "learning_rate": 9.941348973607039e-05,
+      "loss": 0.6486,
+      "mean_token_accuracy": 0.7517647087574005,
+      "num_tokens": 696320.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5139500734214391,
+      "grad_norm": 0.5593725442886353,
+      "learning_rate": 9.99996226495437e-05,
+      "loss": 0.6685,
+      "mean_token_accuracy": 0.7433085501194,
+      "num_tokens": 716778.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5286343612334802,
+      "grad_norm": 0.8261681795120239,
+      "learning_rate": 9.999808967307669e-05,
+      "loss": 0.6481,
+      "mean_token_accuracy": 0.7506862759590149,
+      "num_tokens": 737258.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5433186490455213,
+      "grad_norm": 0.5749596953392029,
+      "learning_rate": 9.999537752232195e-05,
+      "loss": 0.6569,
+      "mean_token_accuracy": 0.749117648601532,
+      "num_tokens": 757738.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5580029368575624,
+      "grad_norm": 0.7790083885192871,
+      "learning_rate": 9.999148626124389e-05,
+      "loss": 0.6498,
+      "mean_token_accuracy": 0.7523039162158967,
+      "num_tokens": 778218.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.5726872246696035,
+      "grad_norm": 0.5859090685844421,
+      "learning_rate": 9.998641598161553e-05,
+      "loss": 0.6519,
+      "mean_token_accuracy": 0.7507352948188781,
+      "num_tokens": 798698.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.5873715124816447,
+      "grad_norm": 0.5902988910675049,
+      "learning_rate": 9.998016680301629e-05,
+      "loss": 0.6371,
+      "mean_token_accuracy": 0.7570588231086731,
+      "num_tokens": 819178.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6020558002936858,
+      "grad_norm": 0.5497356653213501,
+      "learning_rate": 9.997273887282922e-05,
+      "loss": 0.645,
+      "mean_token_accuracy": 0.7509313642978668,
+      "num_tokens": 839658.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6167400881057269,
+      "grad_norm": 0.6334931254386902,
+      "learning_rate": 9.996413236623751e-05,
+      "loss": 0.6551,
+      "mean_token_accuracy": 0.7505392134189606,
+      "num_tokens": 860138.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.631424375917768,
+      "grad_norm": 0.6489232778549194,
+      "learning_rate": 9.995434748622034e-05,
+      "loss": 0.6561,
+      "mean_token_accuracy": 0.751323527097702,
+      "num_tokens": 880618.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6461086637298091,
+      "grad_norm": 0.5434768795967102,
+      "learning_rate": 9.994338446354809e-05,
+      "loss": 0.6433,
+      "mean_token_accuracy": 0.7540266394615174,
+      "num_tokens": 901066.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6607929515418502,
+      "grad_norm": 0.5775740146636963,
+      "learning_rate": 9.993124355677692e-05,
+      "loss": 0.6448,
+      "mean_token_accuracy": 0.7538183212280274,
+      "num_tokens": 921389.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.6754772393538914,
+      "grad_norm": 0.4898783564567566,
+      "learning_rate": 9.99179250522427e-05,
+      "loss": 0.6371,
+      "mean_token_accuracy": 0.7541666686534881,
+      "num_tokens": 941869.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.6901615271659325,
+      "grad_norm": 0.53432297706604,
+      "learning_rate": 9.990342926405419e-05,
+      "loss": 0.6399,
+      "mean_token_accuracy": 0.7554790556430817,
+      "num_tokens": 962250.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7048458149779736,
+      "grad_norm": 0.5491565465927124,
+      "learning_rate": 9.988775653408564e-05,
+      "loss": 0.6432,
+      "mean_token_accuracy": 0.7505809485912323,
+      "num_tokens": 982609.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.7195301027900147,
+      "grad_norm": 0.6353980302810669,
+      "learning_rate": 9.987090723196881e-05,
+      "loss": 0.6411,
+      "mean_token_accuracy": 0.7574509799480438,
+      "num_tokens": 1003089.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7342143906020558,
+      "grad_norm": 0.4572882056236267,
+      "learning_rate": 9.985288175508413e-05,
+      "loss": 0.6317,
+      "mean_token_accuracy": 0.7595588326454162,
+      "num_tokens": 1023569.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.748898678414097,
+      "grad_norm": 0.579796552658081,
+      "learning_rate": 9.983368052855143e-05,
+      "loss": 0.6463,
+      "mean_token_accuracy": 0.7553976953029633,
+      "num_tokens": 1043972.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.7635829662261381,
+      "grad_norm": 0.6805964112281799,
+      "learning_rate": 9.981330400521987e-05,
+      "loss": 0.6219,
+      "mean_token_accuracy": 0.7632352948188782,
+      "num_tokens": 1064452.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.7782672540381792,
+      "grad_norm": 0.4945206642150879,
+      "learning_rate": 9.979175266565725e-05,
+      "loss": 0.6408,
+      "mean_token_accuracy": 0.7531372547149658,
+      "num_tokens": 1084932.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.7929515418502202,
+      "grad_norm": 0.7035859227180481,
+      "learning_rate": 9.97690270181387e-05,
+      "loss": 0.6156,
+      "mean_token_accuracy": 0.7650490283966065,
+      "num_tokens": 1105412.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8076358296622613,
+      "grad_norm": 0.4683134853839874,
+      "learning_rate": 9.97451275986347e-05,
+      "loss": 0.6467,
+      "mean_token_accuracy": 0.7550490260124206,
+      "num_tokens": 1125892.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8223201174743024,
+      "grad_norm": 0.6907538771629333,
+      "learning_rate": 9.972005497079838e-05,
+      "loss": 0.6378,
+      "mean_token_accuracy": 0.7559075593948364,
+      "num_tokens": 1146250.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8370044052863436,
+      "grad_norm": 0.45830196142196655,
+      "learning_rate": 9.96938097259523e-05,
+      "loss": 0.6442,
+      "mean_token_accuracy": 0.7528921604156494,
+      "num_tokens": 1166730.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8516886930983847,
+      "grad_norm": 0.5164074301719666,
+      "learning_rate": 9.966639248307447e-05,
+      "loss": 0.6338,
+      "mean_token_accuracy": 0.7568260788917541,
+      "num_tokens": 1187017.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.8663729809104258,
+      "grad_norm": 0.5325213670730591,
+      "learning_rate": 9.963780388878377e-05,
+      "loss": 0.6408,
+      "mean_token_accuracy": 0.7529411792755127,
+      "num_tokens": 1207497.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.8810572687224669,
+      "grad_norm": 0.5315613746643066,
+      "learning_rate": 9.960804461732463e-05,
+      "loss": 0.6428,
+      "mean_token_accuracy": 0.7546401798725129,
+      "num_tokens": 1227817.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.895741556534508,
+      "grad_norm": 0.5416283011436462,
+      "learning_rate": 9.957711537055126e-05,
+      "loss": 0.629,
+      "mean_token_accuracy": 0.7575490176677704,
+      "num_tokens": 1248297.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9104258443465492,
+      "grad_norm": 0.5316348671913147,
+      "learning_rate": 9.954501687791093e-05,
+      "loss": 0.6296,
+      "mean_token_accuracy": 0.7591666758060456,
+      "num_tokens": 1268777.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9251101321585903,
+      "grad_norm": 0.4492694139480591,
+      "learning_rate": 9.951174989642695e-05,
+      "loss": 0.6361,
+      "mean_token_accuracy": 0.7559313774108887,
+      "num_tokens": 1289257.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9397944199706314,
+      "grad_norm": 0.48100170493125916,
+      "learning_rate": 9.947731521068067e-05,
+      "loss": 0.6507,
+      "mean_token_accuracy": 0.7501960873603821,
+      "num_tokens": 1309737.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.9544787077826725,
+      "grad_norm": 0.4680826663970947,
+      "learning_rate": 9.944171363279305e-05,
+      "loss": 0.611,
+      "mean_token_accuracy": 0.7656862795352936,
+      "num_tokens": 1330217.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.9691629955947136,
+      "grad_norm": 0.5119115114212036,
+      "learning_rate": 9.940494600240544e-05,
+      "loss": 0.6283,
+      "mean_token_accuracy": 0.7572058737277985,
+      "num_tokens": 1350697.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.9838472834067548,
+      "grad_norm": 0.5171290040016174,
+      "learning_rate": 9.936701318665988e-05,
+      "loss": 0.6331,
+      "mean_token_accuracy": 0.7570098042488098,
+      "num_tokens": 1371177.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.9985315712187959,
+      "grad_norm": 0.48826828598976135,
+      "learning_rate": 9.932791608017857e-05,
+      "loss": 0.6237,
+      "mean_token_accuracy": 0.7597549021244049,
+      "num_tokens": 1391657.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.013215859030837,
+      "grad_norm": 0.6590768098831177,
+      "learning_rate": 9.92876556050428e-05,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.7640686333179474,
+      "num_tokens": 1412137.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0279001468428781,
+      "grad_norm": 0.5727214217185974,
+      "learning_rate": 9.924623271077116e-05,
+      "loss": 0.6321,
+      "mean_token_accuracy": 0.758725494146347,
+      "num_tokens": 1432617.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.0425844346549193,
+      "grad_norm": 0.6612036824226379,
+      "learning_rate": 9.920364837429726e-05,
+      "loss": 0.624,
+      "mean_token_accuracy": 0.7604901969432831,
+      "num_tokens": 1453097.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.0572687224669604,
+      "grad_norm": 0.5342158675193787,
+      "learning_rate": 9.915990359994654e-05,
+      "loss": 0.6083,
+      "mean_token_accuracy": 0.7637745201587677,
+      "num_tokens": 1473577.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.0719530102790014,
+      "grad_norm": 0.5662015676498413,
+      "learning_rate": 9.911499941941265e-05,
+      "loss": 0.6117,
+      "mean_token_accuracy": 0.7661274611949921,
+      "num_tokens": 1494057.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.0866372980910426,
+      "grad_norm": 0.5665001273155212,
+      "learning_rate": 9.90689368917332e-05,
+      "loss": 0.6106,
+      "mean_token_accuracy": 0.7660784244537353,
+      "num_tokens": 1514537.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.1013215859030836,
+      "grad_norm": 0.5586121678352356,
+      "learning_rate": 9.902171710326464e-05,
+      "loss": 0.6174,
+      "mean_token_accuracy": 0.7632494688034057,
+      "num_tokens": 1534940.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1160058737151248,
+      "grad_norm": 0.6175503134727478,
+      "learning_rate": 9.897334116765674e-05,
+      "loss": 0.6362,
+      "mean_token_accuracy": 0.755294120311737,
+      "num_tokens": 1555420.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.1306901615271658,
+      "grad_norm": 0.5187695026397705,
+      "learning_rate": 9.892381022582627e-05,
+      "loss": 0.6112,
+      "mean_token_accuracy": 0.7644117712974549,
+      "num_tokens": 1575900.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.145374449339207,
+      "grad_norm": 0.64495849609375,
+      "learning_rate": 9.88731254459301e-05,
+      "loss": 0.6286,
+      "mean_token_accuracy": 0.759852945804596,
+      "num_tokens": 1596380.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.160058737151248,
+      "grad_norm": 0.5434204936027527,
+      "learning_rate": 9.882128802333775e-05,
+      "loss": 0.6314,
+      "mean_token_accuracy": 0.7599019587039948,
+      "num_tokens": 1616860.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.1747430249632893,
+      "grad_norm": 0.5666676163673401,
+      "learning_rate": 9.876829918060297e-05,
+      "loss": 0.6163,
+      "mean_token_accuracy": 0.7637371957302094,
+      "num_tokens": 1637219.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.1894273127753303,
+      "grad_norm": 0.5177666544914246,
+      "learning_rate": 9.871416016743516e-05,
+      "loss": 0.6002,
+      "mean_token_accuracy": 0.7682352900505066,
+      "num_tokens": 1657699.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2041116005873715,
+      "grad_norm": 0.5266413688659668,
+      "learning_rate": 9.865887226066977e-05,
+      "loss": 0.6196,
+      "mean_token_accuracy": 0.7619607806205749,
+      "num_tokens": 1678179.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.2187958883994126,
+      "grad_norm": 0.5798647999763489,
+      "learning_rate": 9.860243676423814e-05,
+      "loss": 0.6237,
+      "mean_token_accuracy": 0.7611274480819702,
+      "num_tokens": 1698659.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2334801762114538,
+      "grad_norm": 0.6460749506950378,
+      "learning_rate": 9.854485500913687e-05,
+      "loss": 0.6106,
+      "mean_token_accuracy": 0.7648039340972901,
+      "num_tokens": 1719139.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.2481644640234948,
+      "grad_norm": 0.5380497574806213,
+      "learning_rate": 9.848612835339634e-05,
+      "loss": 0.6308,
+      "mean_token_accuracy": 0.7592647075653076,
+      "num_tokens": 1739619.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.262848751835536,
+      "grad_norm": 0.5102669596672058,
+      "learning_rate": 9.842625818204873e-05,
+      "loss": 0.6322,
+      "mean_token_accuracy": 0.758088231086731,
+      "num_tokens": 1760099.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.277533039647577,
+      "grad_norm": 0.6140068769454956,
+      "learning_rate": 9.836524590709533e-05,
+      "loss": 0.6117,
+      "mean_token_accuracy": 0.7641176402568817,
+      "num_tokens": 1780579.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.2922173274596183,
+      "grad_norm": 0.5898679494857788,
+      "learning_rate": 9.830309296747318e-05,
+      "loss": 0.6262,
+      "mean_token_accuracy": 0.7606862783432007,
+      "num_tokens": 1801059.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.3069016152716593,
+      "grad_norm": 0.548785388469696,
+      "learning_rate": 9.823980082902131e-05,
+      "loss": 0.6173,
+      "mean_token_accuracy": 0.762156867980957,
+      "num_tokens": 1821539.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3215859030837005,
+      "grad_norm": 0.5419488549232483,
+      "learning_rate": 9.817537098444596e-05,
+      "loss": 0.6194,
+      "mean_token_accuracy": 0.7644117712974549,
+      "num_tokens": 1842019.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.3362701908957415,
+      "grad_norm": 0.4247446656227112,
+      "learning_rate": 9.810980495328555e-05,
+      "loss": 0.6113,
+      "mean_token_accuracy": 0.764950978755951,
+      "num_tokens": 1862499.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.3509544787077827,
+      "grad_norm": 0.5713850259780884,
+      "learning_rate": 9.804310428187466e-05,
+      "loss": 0.6109,
+      "mean_token_accuracy": 0.7650000035762787,
+      "num_tokens": 1882979.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.3656387665198237,
+      "grad_norm": 0.4875611960887909,
+      "learning_rate": 9.797527054330778e-05,
+      "loss": 0.6255,
+      "mean_token_accuracy": 0.7605392098426819,
+      "num_tokens": 1903459.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.380323054331865,
+      "grad_norm": 0.6159121990203857,
+      "learning_rate": 9.7906305337402e-05,
+      "loss": 0.6261,
+      "mean_token_accuracy": 0.7585294187068939,
+      "num_tokens": 1923939.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.395007342143906,
+      "grad_norm": 0.5493881106376648,
+      "learning_rate": 9.783621029065946e-05,
+      "loss": 0.636,
+      "mean_token_accuracy": 0.7579411745071412,
+      "num_tokens": 1944419.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4096916299559472,
+      "grad_norm": 0.5031521320343018,
+      "learning_rate": 9.77649870562288e-05,
+      "loss": 0.6114,
+      "mean_token_accuracy": 0.7669117748737335,
+      "num_tokens": 1964899.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4243759177679882,
+      "grad_norm": 0.5134665966033936,
+      "learning_rate": 9.76926373138664e-05,
+      "loss": 0.6332,
+      "mean_token_accuracy": 0.7555882334709167,
+      "num_tokens": 1985379.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.4390602055800295,
+      "grad_norm": 0.5811095833778381,
+      "learning_rate": 9.761916276989651e-05,
+      "loss": 0.6208,
+      "mean_token_accuracy": 0.7612745106220246,
+      "num_tokens": 2005859.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.4537444933920705,
+      "grad_norm": 0.4786250591278076,
+      "learning_rate": 9.754456515717122e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7635294139385224,
+      "num_tokens": 2026339.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.4684287812041115,
+      "grad_norm": 0.5460525751113892,
+      "learning_rate": 9.746884623502952e-05,
+      "loss": 0.6193,
+      "mean_token_accuracy": 0.7622549116611481,
+      "num_tokens": 2046819.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4831130690161527,
+      "grad_norm": 0.46199068427085876,
+      "learning_rate": 9.73920077892557e-05,
+      "loss": 0.6092,
+      "mean_token_accuracy": 0.7654411673545838,
+      "num_tokens": 2067299.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.497797356828194,
+      "grad_norm": 0.6629523634910583,
+      "learning_rate": 9.731405163203744e-05,
+      "loss": 0.6283,
+      "mean_token_accuracy": 0.7582352936267853,
+      "num_tokens": 2087779.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.512481644640235,
+      "grad_norm": 0.5012948513031006,
+      "learning_rate": 9.723497960192287e-05,
+      "loss": 0.6095,
+      "mean_token_accuracy": 0.7612385094165802,
+      "num_tokens": 2108237.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.527165932452276,
+      "grad_norm": 0.5635460019111633,
+      "learning_rate": 9.715479356377735e-05,
+      "loss": 0.6289,
+      "mean_token_accuracy": 0.7602941274642945,
+      "num_tokens": 2128717.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.5418502202643172,
+      "grad_norm": 0.7186609506607056,
+      "learning_rate": 9.707349540873942e-05,
+      "loss": 0.6089,
+      "mean_token_accuracy": 0.7640686273574829,
+      "num_tokens": 2149197.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.5565345080763584,
+      "grad_norm": 0.5319746732711792,
+      "learning_rate": 9.699108705417623e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7627941191196441,
+      "num_tokens": 2169677.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.5712187958883994,
+      "grad_norm": 0.6315519213676453,
+      "learning_rate": 9.690757044363827e-05,
+      "loss": 0.6112,
+      "mean_token_accuracy": 0.762156867980957,
+      "num_tokens": 2190157.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.5859030837004404,
+      "grad_norm": 0.5465179681777954,
+      "learning_rate": 9.68229475468136e-05,
+      "loss": 0.6355,
+      "mean_token_accuracy": 0.7547058880329132,
+      "num_tokens": 2210637.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.6005873715124816,
+      "grad_norm": 0.529995858669281,
+      "learning_rate": 9.673722035948136e-05,
+      "loss": 0.6253,
+      "mean_token_accuracy": 0.760574460029602,
+      "num_tokens": 2231013.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6152716593245229,
+      "grad_norm": 0.5319053530693054,
+      "learning_rate": 9.66503909034647e-05,
+      "loss": 0.6194,
+      "mean_token_accuracy": 0.7610784351825715,
+      "num_tokens": 2251493.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.6299559471365639,
+      "grad_norm": 0.4977491497993469,
+      "learning_rate": 9.65624612265831e-05,
+      "loss": 0.6141,
+      "mean_token_accuracy": 0.7668627440929413,
+      "num_tokens": 2271973.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.644640234948605,
+      "grad_norm": 0.566733181476593,
+      "learning_rate": 9.647343340260406e-05,
+      "loss": 0.6234,
+      "mean_token_accuracy": 0.7592156887054443,
+      "num_tokens": 2292453.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.6593245227606461,
+      "grad_norm": 0.5549957752227783,
+      "learning_rate": 9.638330953119422e-05,
+      "loss": 0.6149,
+      "mean_token_accuracy": 0.7609803915023804,
+      "num_tokens": 2312933.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.6740088105726874,
+      "grad_norm": 0.5047655701637268,
+      "learning_rate": 9.629209173786984e-05,
+      "loss": 0.6187,
+      "mean_token_accuracy": 0.7625472128391266,
+      "num_tokens": 2333324.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.6886930983847284,
+      "grad_norm": 0.6593276262283325,
+      "learning_rate": 9.619978217394663e-05,
+      "loss": 0.6225,
+      "mean_token_accuracy": 0.762598043680191,
+      "num_tokens": 2353804.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7033773861967694,
+      "grad_norm": 0.563077449798584,
+      "learning_rate": 9.610638301648905e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7612745106220246,
+      "num_tokens": 2374284.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.7180616740088106,
+      "grad_norm": 0.5723268389701843,
+      "learning_rate": 9.601189646825899e-05,
+      "loss": 0.6203,
+      "mean_token_accuracy": 0.7623447120189667,
+      "num_tokens": 2394642.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.7327459618208518,
+      "grad_norm": 0.46074366569519043,
+      "learning_rate": 9.591632475766372e-05,
+      "loss": 0.6269,
+      "mean_token_accuracy": 0.7591176450252533,
+      "num_tokens": 2415122.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.7474302496328928,
+      "grad_norm": 0.49932244420051575,
+      "learning_rate": 9.581967013870345e-05,
+      "loss": 0.6097,
+      "mean_token_accuracy": 0.7649509727954864,
+      "num_tokens": 2435602.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.7621145374449338,
+      "grad_norm": 0.4770796597003937,
+      "learning_rate": 9.57219348909181e-05,
+      "loss": 0.609,
+      "mean_token_accuracy": 0.7656404256820679,
+      "num_tokens": 2455925.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.776798825256975,
+      "grad_norm": 0.5677822232246399,
+      "learning_rate": 9.562312131933356e-05,
+      "loss": 0.6316,
+      "mean_token_accuracy": 0.7583333313465118,
+      "num_tokens": 2476405.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.7914831130690163,
+      "grad_norm": 0.5644094347953796,
+      "learning_rate": 9.552323175440732e-05,
+      "loss": 0.6237,
+      "mean_token_accuracy": 0.7615196108818054,
+      "num_tokens": 2496885.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8061674008810573,
+      "grad_norm": 0.4678439795970917,
+      "learning_rate": 9.542226855197354e-05,
+      "loss": 0.6298,
+      "mean_token_accuracy": 0.7565196096897125,
+      "num_tokens": 2517365.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.8208516886930983,
+      "grad_norm": 0.581727921962738,
+      "learning_rate": 9.532023409318741e-05,
+      "loss": 0.6152,
+      "mean_token_accuracy": 0.7653431415557861,
+      "num_tokens": 2537845.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.8355359765051396,
+      "grad_norm": 0.619175136089325,
+      "learning_rate": 9.52171307844691e-05,
+      "loss": 0.628,
+      "mean_token_accuracy": 0.7585878252983094,
+      "num_tokens": 2558165.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.8502202643171806,
+      "grad_norm": 0.4789538085460663,
+      "learning_rate": 9.511296105744693e-05,
+      "loss": 0.6182,
+      "mean_token_accuracy": 0.7605882346630096,
+      "num_tokens": 2578645.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.8649045521292216,
+      "grad_norm": 0.5343487858772278,
+      "learning_rate": 9.500772736890001e-05,
+      "loss": 0.631,
+      "mean_token_accuracy": 0.7564215660095215,
+      "num_tokens": 2599125.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.8795888399412628,
+      "grad_norm": 0.5381704568862915,
+      "learning_rate": 9.49014322007004e-05,
+      "loss": 0.6336,
+      "mean_token_accuracy": 0.7558333337306976,
+      "num_tokens": 2619605.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.894273127753304,
+      "grad_norm": 0.5045132040977478,
+      "learning_rate": 9.479407805975442e-05,
+      "loss": 0.6293,
+      "mean_token_accuracy": 0.7577450931072235,
+      "num_tokens": 2640085.0,
+      "step": 1290
+    },
+    {
+      "epoch": 1.908957415565345,
+      "grad_norm": 0.5403540134429932,
+      "learning_rate": 9.468566747794369e-05,
+      "loss": 0.6126,
+      "mean_token_accuracy": 0.7640686273574829,
+      "num_tokens": 2660565.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.923641703377386,
+      "grad_norm": 0.4776689410209656,
+      "learning_rate": 9.457620301206531e-05,
+      "loss": 0.6017,
+      "mean_token_accuracy": 0.7670351922512054,
+      "num_tokens": 2680946.0,
+      "step": 1310
+    },
+    {
+      "epoch": 1.9383259911894273,
+      "grad_norm": 0.6080910563468933,
+      "learning_rate": 9.446568724377157e-05,
+      "loss": 0.624,
+      "mean_token_accuracy": 0.759852945804596,
+      "num_tokens": 2701426.0,
+      "step": 1320
+    },
+    {
+      "epoch": 1.9530102790014685,
+      "grad_norm": 0.5421401858329773,
+      "learning_rate": 9.43541227795091e-05,
+      "loss": 0.609,
+      "mean_token_accuracy": 0.7649999976158142,
+      "num_tokens": 2721906.0,
+      "step": 1330
+    },
+    {
+      "epoch": 1.9676945668135095,
+      "grad_norm": 0.5317767262458801,
+      "learning_rate": 9.424151225045739e-05,
+      "loss": 0.6176,
+      "mean_token_accuracy": 0.7620986700057983,
+      "num_tokens": 2742354.0,
+      "step": 1340
+    },
+    {
+      "epoch": 1.9823788546255505,
+      "grad_norm": 0.5858188271522522,
+      "learning_rate": 9.412785831246673e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7616176605224609,
+      "num_tokens": 2762834.0,
+      "step": 1350
+    },
+    {
+      "epoch": 1.9970631424375918,
+      "grad_norm": 0.5256847739219666,
+      "learning_rate": 9.401316364599555e-05,
+      "loss": 0.6203,
+      "mean_token_accuracy": 0.7609804034233093,
+      "num_tokens": 2783314.0,
+      "step": 1360
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6810,
+  "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": 1.1867351473874534e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-1362/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac0efbafb523853fa46901df5567229595df957b581e4dee225a481543b5f51
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2043/README.md

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2043/adapter_config.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2043/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8bab9850d278a6af6e9e8e5d6e9b3911ca9c6bc5b4cce49bf165483b843601b
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2043/added_tokens.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2043/chat_template.jinja

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2043/special_tokens_map.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2043/tokenizer.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2043/tokenizer_config.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2043/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": 2043,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014684287812041116,
+      "grad_norm": 3.9844751358032227,
+      "learning_rate": 2.6392961876832847e-06,
+      "loss": 2.4601,
+      "mean_token_accuracy": 0.5440195977687836,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.02936857562408223,
+      "grad_norm": 3.408750295639038,
+      "learning_rate": 5.571847507331378e-06,
+      "loss": 2.4123,
+      "mean_token_accuracy": 0.5557843208312988,
+      "num_tokens": 40960.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.04405286343612335,
+      "grad_norm": 3.2006149291992188,
+      "learning_rate": 8.504398826979472e-06,
+      "loss": 2.3369,
+      "mean_token_accuracy": 0.5485294103622437,
+      "num_tokens": 61440.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.05873715124816446,
+      "grad_norm": 2.0662899017333984,
+      "learning_rate": 1.1436950146627567e-05,
+      "loss": 2.0808,
+      "mean_token_accuracy": 0.5701960742473602,
+      "num_tokens": 81920.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07342143906020558,
+      "grad_norm": 1.349193811416626,
+      "learning_rate": 1.4369501466275662e-05,
+      "loss": 1.7811,
+      "mean_token_accuracy": 0.5971078455448151,
+      "num_tokens": 102400.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.0881057268722467,
+      "grad_norm": 1.0805939435958862,
+      "learning_rate": 1.7302052785923756e-05,
+      "loss": 1.5636,
+      "mean_token_accuracy": 0.604313725233078,
+      "num_tokens": 122880.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.1027900146842878,
+      "grad_norm": 0.9003157615661621,
+      "learning_rate": 2.0234604105571847e-05,
+      "loss": 1.3844,
+      "mean_token_accuracy": 0.6224509835243225,
+      "num_tokens": 143360.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.11747430249632893,
+      "grad_norm": 0.8923518657684326,
+      "learning_rate": 2.3167155425219943e-05,
+      "loss": 1.2358,
+      "mean_token_accuracy": 0.6361274480819702,
+      "num_tokens": 163840.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.13215859030837004,
+      "grad_norm": 1.0202796459197998,
+      "learning_rate": 2.6099706744868034e-05,
+      "loss": 1.0774,
+      "mean_token_accuracy": 0.6648529529571533,
+      "num_tokens": 184320.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.14684287812041116,
+      "grad_norm": 1.149533748626709,
+      "learning_rate": 2.9032258064516133e-05,
+      "loss": 0.9291,
+      "mean_token_accuracy": 0.6854411721229553,
+      "num_tokens": 204800.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.16152716593245228,
+      "grad_norm": 1.153542160987854,
+      "learning_rate": 3.1964809384164225e-05,
+      "loss": 0.8269,
+      "mean_token_accuracy": 0.709852933883667,
+      "num_tokens": 225280.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.1762114537444934,
+      "grad_norm": 1.2031893730163574,
+      "learning_rate": 3.489736070381232e-05,
+      "loss": 0.7872,
+      "mean_token_accuracy": 0.7195098102092743,
+      "num_tokens": 245760.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.19089574155653452,
+      "grad_norm": 1.1650404930114746,
+      "learning_rate": 3.7829912023460415e-05,
+      "loss": 0.7448,
+      "mean_token_accuracy": 0.7316666603088379,
+      "num_tokens": 266240.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.2055800293685756,
+      "grad_norm": 1.1167842149734497,
+      "learning_rate": 4.076246334310851e-05,
+      "loss": 0.7018,
+      "mean_token_accuracy": 0.7435784280300141,
+      "num_tokens": 286720.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.22026431718061673,
+      "grad_norm": 1.1387581825256348,
+      "learning_rate": 4.36950146627566e-05,
+      "loss": 0.6919,
+      "mean_token_accuracy": 0.7467156887054444,
+      "num_tokens": 307200.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.23494860499265785,
+      "grad_norm": 1.0053479671478271,
+      "learning_rate": 4.6627565982404694e-05,
+      "loss": 0.7028,
+      "mean_token_accuracy": 0.7395588219165802,
+      "num_tokens": 327680.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.24963289280469897,
+      "grad_norm": 0.9742514491081238,
+      "learning_rate": 4.956011730205279e-05,
+      "loss": 0.6858,
+      "mean_token_accuracy": 0.745686274766922,
+      "num_tokens": 348160.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.2643171806167401,
+      "grad_norm": 0.8818563222885132,
+      "learning_rate": 5.249266862170088e-05,
+      "loss": 0.6913,
+      "mean_token_accuracy": 0.7424509763717652,
+      "num_tokens": 368640.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2790014684287812,
+      "grad_norm": 0.8835548162460327,
+      "learning_rate": 5.542521994134897e-05,
+      "loss": 0.6767,
+      "mean_token_accuracy": 0.7474999964237213,
+      "num_tokens": 389120.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.2936857562408223,
+      "grad_norm": 0.8910827040672302,
+      "learning_rate": 5.8357771260997075e-05,
+      "loss": 0.6789,
+      "mean_token_accuracy": 0.7434803903102875,
+      "num_tokens": 409600.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.30837004405286345,
+      "grad_norm": 0.9448742866516113,
+      "learning_rate": 6.129032258064517e-05,
+      "loss": 0.6637,
+      "mean_token_accuracy": 0.7499999940395355,
+      "num_tokens": 430080.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.32305433186490456,
+      "grad_norm": 0.7906215190887451,
+      "learning_rate": 6.422287390029326e-05,
+      "loss": 0.6593,
+      "mean_token_accuracy": 0.7529411673545837,
+      "num_tokens": 450560.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.3377386196769457,
+      "grad_norm": 0.854017436504364,
+      "learning_rate": 6.715542521994135e-05,
+      "loss": 0.6682,
+      "mean_token_accuracy": 0.7474509835243225,
+      "num_tokens": 471040.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.3524229074889868,
+      "grad_norm": 0.7827669978141785,
+      "learning_rate": 7.008797653958945e-05,
+      "loss": 0.6857,
+      "mean_token_accuracy": 0.741813725233078,
+      "num_tokens": 491520.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.3671071953010279,
+      "grad_norm": 0.7865115404129028,
+      "learning_rate": 7.302052785923754e-05,
+      "loss": 0.657,
+      "mean_token_accuracy": 0.7524509787559509,
+      "num_tokens": 512000.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.38179148311306904,
+      "grad_norm": 0.7960774302482605,
+      "learning_rate": 7.595307917888564e-05,
+      "loss": 0.6569,
+      "mean_token_accuracy": 0.752205890417099,
+      "num_tokens": 532480.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.3964757709251101,
+      "grad_norm": 0.7246135473251343,
+      "learning_rate": 7.888563049853373e-05,
+      "loss": 0.6506,
+      "mean_token_accuracy": 0.7553921639919281,
+      "num_tokens": 552960.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.4111600587371512,
+      "grad_norm": 0.6880009770393372,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 0.6617,
+      "mean_token_accuracy": 0.7480882346630097,
+      "num_tokens": 573440.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.42584434654919234,
+      "grad_norm": 0.7460880279541016,
+      "learning_rate": 8.475073313782992e-05,
+      "loss": 0.641,
+      "mean_token_accuracy": 0.7563235282897949,
+      "num_tokens": 593920.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.44052863436123346,
+      "grad_norm": 0.6125314831733704,
+      "learning_rate": 8.7683284457478e-05,
+      "loss": 0.662,
+      "mean_token_accuracy": 0.7470588207244873,
+      "num_tokens": 614400.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.4552129221732746,
+      "grad_norm": 0.8595872521400452,
+      "learning_rate": 9.06158357771261e-05,
+      "loss": 0.6428,
+      "mean_token_accuracy": 0.753333330154419,
+      "num_tokens": 634880.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.4698972099853157,
+      "grad_norm": 0.7512183785438538,
+      "learning_rate": 9.35483870967742e-05,
+      "loss": 0.6474,
+      "mean_token_accuracy": 0.7549509763717651,
+      "num_tokens": 655360.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.4845814977973568,
+      "grad_norm": 0.5831340551376343,
+      "learning_rate": 9.64809384164223e-05,
+      "loss": 0.6484,
+      "mean_token_accuracy": 0.7540196001529693,
+      "num_tokens": 675840.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.49926578560939794,
+      "grad_norm": 0.7933578491210938,
+      "learning_rate": 9.941348973607039e-05,
+      "loss": 0.6486,
+      "mean_token_accuracy": 0.7517647087574005,
+      "num_tokens": 696320.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5139500734214391,
+      "grad_norm": 0.5593725442886353,
+      "learning_rate": 9.99996226495437e-05,
+      "loss": 0.6685,
+      "mean_token_accuracy": 0.7433085501194,
+      "num_tokens": 716778.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5286343612334802,
+      "grad_norm": 0.8261681795120239,
+      "learning_rate": 9.999808967307669e-05,
+      "loss": 0.6481,
+      "mean_token_accuracy": 0.7506862759590149,
+      "num_tokens": 737258.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5433186490455213,
+      "grad_norm": 0.5749596953392029,
+      "learning_rate": 9.999537752232195e-05,
+      "loss": 0.6569,
+      "mean_token_accuracy": 0.749117648601532,
+      "num_tokens": 757738.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5580029368575624,
+      "grad_norm": 0.7790083885192871,
+      "learning_rate": 9.999148626124389e-05,
+      "loss": 0.6498,
+      "mean_token_accuracy": 0.7523039162158967,
+      "num_tokens": 778218.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.5726872246696035,
+      "grad_norm": 0.5859090685844421,
+      "learning_rate": 9.998641598161553e-05,
+      "loss": 0.6519,
+      "mean_token_accuracy": 0.7507352948188781,
+      "num_tokens": 798698.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.5873715124816447,
+      "grad_norm": 0.5902988910675049,
+      "learning_rate": 9.998016680301629e-05,
+      "loss": 0.6371,
+      "mean_token_accuracy": 0.7570588231086731,
+      "num_tokens": 819178.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6020558002936858,
+      "grad_norm": 0.5497356653213501,
+      "learning_rate": 9.997273887282922e-05,
+      "loss": 0.645,
+      "mean_token_accuracy": 0.7509313642978668,
+      "num_tokens": 839658.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6167400881057269,
+      "grad_norm": 0.6334931254386902,
+      "learning_rate": 9.996413236623751e-05,
+      "loss": 0.6551,
+      "mean_token_accuracy": 0.7505392134189606,
+      "num_tokens": 860138.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.631424375917768,
+      "grad_norm": 0.6489232778549194,
+      "learning_rate": 9.995434748622034e-05,
+      "loss": 0.6561,
+      "mean_token_accuracy": 0.751323527097702,
+      "num_tokens": 880618.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6461086637298091,
+      "grad_norm": 0.5434768795967102,
+      "learning_rate": 9.994338446354809e-05,
+      "loss": 0.6433,
+      "mean_token_accuracy": 0.7540266394615174,
+      "num_tokens": 901066.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6607929515418502,
+      "grad_norm": 0.5775740146636963,
+      "learning_rate": 9.993124355677692e-05,
+      "loss": 0.6448,
+      "mean_token_accuracy": 0.7538183212280274,
+      "num_tokens": 921389.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.6754772393538914,
+      "grad_norm": 0.4898783564567566,
+      "learning_rate": 9.99179250522427e-05,
+      "loss": 0.6371,
+      "mean_token_accuracy": 0.7541666686534881,
+      "num_tokens": 941869.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.6901615271659325,
+      "grad_norm": 0.53432297706604,
+      "learning_rate": 9.990342926405419e-05,
+      "loss": 0.6399,
+      "mean_token_accuracy": 0.7554790556430817,
+      "num_tokens": 962250.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7048458149779736,
+      "grad_norm": 0.5491565465927124,
+      "learning_rate": 9.988775653408564e-05,
+      "loss": 0.6432,
+      "mean_token_accuracy": 0.7505809485912323,
+      "num_tokens": 982609.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.7195301027900147,
+      "grad_norm": 0.6353980302810669,
+      "learning_rate": 9.987090723196881e-05,
+      "loss": 0.6411,
+      "mean_token_accuracy": 0.7574509799480438,
+      "num_tokens": 1003089.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7342143906020558,
+      "grad_norm": 0.4572882056236267,
+      "learning_rate": 9.985288175508413e-05,
+      "loss": 0.6317,
+      "mean_token_accuracy": 0.7595588326454162,
+      "num_tokens": 1023569.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.748898678414097,
+      "grad_norm": 0.579796552658081,
+      "learning_rate": 9.983368052855143e-05,
+      "loss": 0.6463,
+      "mean_token_accuracy": 0.7553976953029633,
+      "num_tokens": 1043972.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.7635829662261381,
+      "grad_norm": 0.6805964112281799,
+      "learning_rate": 9.981330400521987e-05,
+      "loss": 0.6219,
+      "mean_token_accuracy": 0.7632352948188782,
+      "num_tokens": 1064452.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.7782672540381792,
+      "grad_norm": 0.4945206642150879,
+      "learning_rate": 9.979175266565725e-05,
+      "loss": 0.6408,
+      "mean_token_accuracy": 0.7531372547149658,
+      "num_tokens": 1084932.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.7929515418502202,
+      "grad_norm": 0.7035859227180481,
+      "learning_rate": 9.97690270181387e-05,
+      "loss": 0.6156,
+      "mean_token_accuracy": 0.7650490283966065,
+      "num_tokens": 1105412.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8076358296622613,
+      "grad_norm": 0.4683134853839874,
+      "learning_rate": 9.97451275986347e-05,
+      "loss": 0.6467,
+      "mean_token_accuracy": 0.7550490260124206,
+      "num_tokens": 1125892.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8223201174743024,
+      "grad_norm": 0.6907538771629333,
+      "learning_rate": 9.972005497079838e-05,
+      "loss": 0.6378,
+      "mean_token_accuracy": 0.7559075593948364,
+      "num_tokens": 1146250.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8370044052863436,
+      "grad_norm": 0.45830196142196655,
+      "learning_rate": 9.96938097259523e-05,
+      "loss": 0.6442,
+      "mean_token_accuracy": 0.7528921604156494,
+      "num_tokens": 1166730.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8516886930983847,
+      "grad_norm": 0.5164074301719666,
+      "learning_rate": 9.966639248307447e-05,
+      "loss": 0.6338,
+      "mean_token_accuracy": 0.7568260788917541,
+      "num_tokens": 1187017.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.8663729809104258,
+      "grad_norm": 0.5325213670730591,
+      "learning_rate": 9.963780388878377e-05,
+      "loss": 0.6408,
+      "mean_token_accuracy": 0.7529411792755127,
+      "num_tokens": 1207497.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.8810572687224669,
+      "grad_norm": 0.5315613746643066,
+      "learning_rate": 9.960804461732463e-05,
+      "loss": 0.6428,
+      "mean_token_accuracy": 0.7546401798725129,
+      "num_tokens": 1227817.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.895741556534508,
+      "grad_norm": 0.5416283011436462,
+      "learning_rate": 9.957711537055126e-05,
+      "loss": 0.629,
+      "mean_token_accuracy": 0.7575490176677704,
+      "num_tokens": 1248297.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9104258443465492,
+      "grad_norm": 0.5316348671913147,
+      "learning_rate": 9.954501687791093e-05,
+      "loss": 0.6296,
+      "mean_token_accuracy": 0.7591666758060456,
+      "num_tokens": 1268777.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9251101321585903,
+      "grad_norm": 0.4492694139480591,
+      "learning_rate": 9.951174989642695e-05,
+      "loss": 0.6361,
+      "mean_token_accuracy": 0.7559313774108887,
+      "num_tokens": 1289257.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9397944199706314,
+      "grad_norm": 0.48100170493125916,
+      "learning_rate": 9.947731521068067e-05,
+      "loss": 0.6507,
+      "mean_token_accuracy": 0.7501960873603821,
+      "num_tokens": 1309737.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.9544787077826725,
+      "grad_norm": 0.4680826663970947,
+      "learning_rate": 9.944171363279305e-05,
+      "loss": 0.611,
+      "mean_token_accuracy": 0.7656862795352936,
+      "num_tokens": 1330217.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.9691629955947136,
+      "grad_norm": 0.5119115114212036,
+      "learning_rate": 9.940494600240544e-05,
+      "loss": 0.6283,
+      "mean_token_accuracy": 0.7572058737277985,
+      "num_tokens": 1350697.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.9838472834067548,
+      "grad_norm": 0.5171290040016174,
+      "learning_rate": 9.936701318665988e-05,
+      "loss": 0.6331,
+      "mean_token_accuracy": 0.7570098042488098,
+      "num_tokens": 1371177.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.9985315712187959,
+      "grad_norm": 0.48826828598976135,
+      "learning_rate": 9.932791608017857e-05,
+      "loss": 0.6237,
+      "mean_token_accuracy": 0.7597549021244049,
+      "num_tokens": 1391657.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.013215859030837,
+      "grad_norm": 0.6590768098831177,
+      "learning_rate": 9.92876556050428e-05,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.7640686333179474,
+      "num_tokens": 1412137.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0279001468428781,
+      "grad_norm": 0.5727214217185974,
+      "learning_rate": 9.924623271077116e-05,
+      "loss": 0.6321,
+      "mean_token_accuracy": 0.758725494146347,
+      "num_tokens": 1432617.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.0425844346549193,
+      "grad_norm": 0.6612036824226379,
+      "learning_rate": 9.920364837429726e-05,
+      "loss": 0.624,
+      "mean_token_accuracy": 0.7604901969432831,
+      "num_tokens": 1453097.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.0572687224669604,
+      "grad_norm": 0.5342158675193787,
+      "learning_rate": 9.915990359994654e-05,
+      "loss": 0.6083,
+      "mean_token_accuracy": 0.7637745201587677,
+      "num_tokens": 1473577.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.0719530102790014,
+      "grad_norm": 0.5662015676498413,
+      "learning_rate": 9.911499941941265e-05,
+      "loss": 0.6117,
+      "mean_token_accuracy": 0.7661274611949921,
+      "num_tokens": 1494057.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.0866372980910426,
+      "grad_norm": 0.5665001273155212,
+      "learning_rate": 9.90689368917332e-05,
+      "loss": 0.6106,
+      "mean_token_accuracy": 0.7660784244537353,
+      "num_tokens": 1514537.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.1013215859030836,
+      "grad_norm": 0.5586121678352356,
+      "learning_rate": 9.902171710326464e-05,
+      "loss": 0.6174,
+      "mean_token_accuracy": 0.7632494688034057,
+      "num_tokens": 1534940.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1160058737151248,
+      "grad_norm": 0.6175503134727478,
+      "learning_rate": 9.897334116765674e-05,
+      "loss": 0.6362,
+      "mean_token_accuracy": 0.755294120311737,
+      "num_tokens": 1555420.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.1306901615271658,
+      "grad_norm": 0.5187695026397705,
+      "learning_rate": 9.892381022582627e-05,
+      "loss": 0.6112,
+      "mean_token_accuracy": 0.7644117712974549,
+      "num_tokens": 1575900.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.145374449339207,
+      "grad_norm": 0.64495849609375,
+      "learning_rate": 9.88731254459301e-05,
+      "loss": 0.6286,
+      "mean_token_accuracy": 0.759852945804596,
+      "num_tokens": 1596380.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.160058737151248,
+      "grad_norm": 0.5434204936027527,
+      "learning_rate": 9.882128802333775e-05,
+      "loss": 0.6314,
+      "mean_token_accuracy": 0.7599019587039948,
+      "num_tokens": 1616860.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.1747430249632893,
+      "grad_norm": 0.5666676163673401,
+      "learning_rate": 9.876829918060297e-05,
+      "loss": 0.6163,
+      "mean_token_accuracy": 0.7637371957302094,
+      "num_tokens": 1637219.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.1894273127753303,
+      "grad_norm": 0.5177666544914246,
+      "learning_rate": 9.871416016743516e-05,
+      "loss": 0.6002,
+      "mean_token_accuracy": 0.7682352900505066,
+      "num_tokens": 1657699.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2041116005873715,
+      "grad_norm": 0.5266413688659668,
+      "learning_rate": 9.865887226066977e-05,
+      "loss": 0.6196,
+      "mean_token_accuracy": 0.7619607806205749,
+      "num_tokens": 1678179.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.2187958883994126,
+      "grad_norm": 0.5798647999763489,
+      "learning_rate": 9.860243676423814e-05,
+      "loss": 0.6237,
+      "mean_token_accuracy": 0.7611274480819702,
+      "num_tokens": 1698659.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2334801762114538,
+      "grad_norm": 0.6460749506950378,
+      "learning_rate": 9.854485500913687e-05,
+      "loss": 0.6106,
+      "mean_token_accuracy": 0.7648039340972901,
+      "num_tokens": 1719139.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.2481644640234948,
+      "grad_norm": 0.5380497574806213,
+      "learning_rate": 9.848612835339634e-05,
+      "loss": 0.6308,
+      "mean_token_accuracy": 0.7592647075653076,
+      "num_tokens": 1739619.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.262848751835536,
+      "grad_norm": 0.5102669596672058,
+      "learning_rate": 9.842625818204873e-05,
+      "loss": 0.6322,
+      "mean_token_accuracy": 0.758088231086731,
+      "num_tokens": 1760099.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.277533039647577,
+      "grad_norm": 0.6140068769454956,
+      "learning_rate": 9.836524590709533e-05,
+      "loss": 0.6117,
+      "mean_token_accuracy": 0.7641176402568817,
+      "num_tokens": 1780579.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.2922173274596183,
+      "grad_norm": 0.5898679494857788,
+      "learning_rate": 9.830309296747318e-05,
+      "loss": 0.6262,
+      "mean_token_accuracy": 0.7606862783432007,
+      "num_tokens": 1801059.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.3069016152716593,
+      "grad_norm": 0.548785388469696,
+      "learning_rate": 9.823980082902131e-05,
+      "loss": 0.6173,
+      "mean_token_accuracy": 0.762156867980957,
+      "num_tokens": 1821539.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3215859030837005,
+      "grad_norm": 0.5419488549232483,
+      "learning_rate": 9.817537098444596e-05,
+      "loss": 0.6194,
+      "mean_token_accuracy": 0.7644117712974549,
+      "num_tokens": 1842019.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.3362701908957415,
+      "grad_norm": 0.4247446656227112,
+      "learning_rate": 9.810980495328555e-05,
+      "loss": 0.6113,
+      "mean_token_accuracy": 0.764950978755951,
+      "num_tokens": 1862499.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.3509544787077827,
+      "grad_norm": 0.5713850259780884,
+      "learning_rate": 9.804310428187466e-05,
+      "loss": 0.6109,
+      "mean_token_accuracy": 0.7650000035762787,
+      "num_tokens": 1882979.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.3656387665198237,
+      "grad_norm": 0.4875611960887909,
+      "learning_rate": 9.797527054330778e-05,
+      "loss": 0.6255,
+      "mean_token_accuracy": 0.7605392098426819,
+      "num_tokens": 1903459.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.380323054331865,
+      "grad_norm": 0.6159121990203857,
+      "learning_rate": 9.7906305337402e-05,
+      "loss": 0.6261,
+      "mean_token_accuracy": 0.7585294187068939,
+      "num_tokens": 1923939.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.395007342143906,
+      "grad_norm": 0.5493881106376648,
+      "learning_rate": 9.783621029065946e-05,
+      "loss": 0.636,
+      "mean_token_accuracy": 0.7579411745071412,
+      "num_tokens": 1944419.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4096916299559472,
+      "grad_norm": 0.5031521320343018,
+      "learning_rate": 9.77649870562288e-05,
+      "loss": 0.6114,
+      "mean_token_accuracy": 0.7669117748737335,
+      "num_tokens": 1964899.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4243759177679882,
+      "grad_norm": 0.5134665966033936,
+      "learning_rate": 9.76926373138664e-05,
+      "loss": 0.6332,
+      "mean_token_accuracy": 0.7555882334709167,
+      "num_tokens": 1985379.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.4390602055800295,
+      "grad_norm": 0.5811095833778381,
+      "learning_rate": 9.761916276989651e-05,
+      "loss": 0.6208,
+      "mean_token_accuracy": 0.7612745106220246,
+      "num_tokens": 2005859.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.4537444933920705,
+      "grad_norm": 0.4786250591278076,
+      "learning_rate": 9.754456515717122e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7635294139385224,
+      "num_tokens": 2026339.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.4684287812041115,
+      "grad_norm": 0.5460525751113892,
+      "learning_rate": 9.746884623502952e-05,
+      "loss": 0.6193,
+      "mean_token_accuracy": 0.7622549116611481,
+      "num_tokens": 2046819.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4831130690161527,
+      "grad_norm": 0.46199068427085876,
+      "learning_rate": 9.73920077892557e-05,
+      "loss": 0.6092,
+      "mean_token_accuracy": 0.7654411673545838,
+      "num_tokens": 2067299.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.497797356828194,
+      "grad_norm": 0.6629523634910583,
+      "learning_rate": 9.731405163203744e-05,
+      "loss": 0.6283,
+      "mean_token_accuracy": 0.7582352936267853,
+      "num_tokens": 2087779.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.512481644640235,
+      "grad_norm": 0.5012948513031006,
+      "learning_rate": 9.723497960192287e-05,
+      "loss": 0.6095,
+      "mean_token_accuracy": 0.7612385094165802,
+      "num_tokens": 2108237.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.527165932452276,
+      "grad_norm": 0.5635460019111633,
+      "learning_rate": 9.715479356377735e-05,
+      "loss": 0.6289,
+      "mean_token_accuracy": 0.7602941274642945,
+      "num_tokens": 2128717.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.5418502202643172,
+      "grad_norm": 0.7186609506607056,
+      "learning_rate": 9.707349540873942e-05,
+      "loss": 0.6089,
+      "mean_token_accuracy": 0.7640686273574829,
+      "num_tokens": 2149197.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.5565345080763584,
+      "grad_norm": 0.5319746732711792,
+      "learning_rate": 9.699108705417623e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7627941191196441,
+      "num_tokens": 2169677.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.5712187958883994,
+      "grad_norm": 0.6315519213676453,
+      "learning_rate": 9.690757044363827e-05,
+      "loss": 0.6112,
+      "mean_token_accuracy": 0.762156867980957,
+      "num_tokens": 2190157.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.5859030837004404,
+      "grad_norm": 0.5465179681777954,
+      "learning_rate": 9.68229475468136e-05,
+      "loss": 0.6355,
+      "mean_token_accuracy": 0.7547058880329132,
+      "num_tokens": 2210637.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.6005873715124816,
+      "grad_norm": 0.529995858669281,
+      "learning_rate": 9.673722035948136e-05,
+      "loss": 0.6253,
+      "mean_token_accuracy": 0.760574460029602,
+      "num_tokens": 2231013.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6152716593245229,
+      "grad_norm": 0.5319053530693054,
+      "learning_rate": 9.66503909034647e-05,
+      "loss": 0.6194,
+      "mean_token_accuracy": 0.7610784351825715,
+      "num_tokens": 2251493.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.6299559471365639,
+      "grad_norm": 0.4977491497993469,
+      "learning_rate": 9.65624612265831e-05,
+      "loss": 0.6141,
+      "mean_token_accuracy": 0.7668627440929413,
+      "num_tokens": 2271973.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.644640234948605,
+      "grad_norm": 0.566733181476593,
+      "learning_rate": 9.647343340260406e-05,
+      "loss": 0.6234,
+      "mean_token_accuracy": 0.7592156887054443,
+      "num_tokens": 2292453.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.6593245227606461,
+      "grad_norm": 0.5549957752227783,
+      "learning_rate": 9.638330953119422e-05,
+      "loss": 0.6149,
+      "mean_token_accuracy": 0.7609803915023804,
+      "num_tokens": 2312933.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.6740088105726874,
+      "grad_norm": 0.5047655701637268,
+      "learning_rate": 9.629209173786984e-05,
+      "loss": 0.6187,
+      "mean_token_accuracy": 0.7625472128391266,
+      "num_tokens": 2333324.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.6886930983847284,
+      "grad_norm": 0.6593276262283325,
+      "learning_rate": 9.619978217394663e-05,
+      "loss": 0.6225,
+      "mean_token_accuracy": 0.762598043680191,
+      "num_tokens": 2353804.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7033773861967694,
+      "grad_norm": 0.563077449798584,
+      "learning_rate": 9.610638301648905e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7612745106220246,
+      "num_tokens": 2374284.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.7180616740088106,
+      "grad_norm": 0.5723268389701843,
+      "learning_rate": 9.601189646825899e-05,
+      "loss": 0.6203,
+      "mean_token_accuracy": 0.7623447120189667,
+      "num_tokens": 2394642.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.7327459618208518,
+      "grad_norm": 0.46074366569519043,
+      "learning_rate": 9.591632475766372e-05,
+      "loss": 0.6269,
+      "mean_token_accuracy": 0.7591176450252533,
+      "num_tokens": 2415122.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.7474302496328928,
+      "grad_norm": 0.49932244420051575,
+      "learning_rate": 9.581967013870345e-05,
+      "loss": 0.6097,
+      "mean_token_accuracy": 0.7649509727954864,
+      "num_tokens": 2435602.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.7621145374449338,
+      "grad_norm": 0.4770796597003937,
+      "learning_rate": 9.57219348909181e-05,
+      "loss": 0.609,
+      "mean_token_accuracy": 0.7656404256820679,
+      "num_tokens": 2455925.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.776798825256975,
+      "grad_norm": 0.5677822232246399,
+      "learning_rate": 9.562312131933356e-05,
+      "loss": 0.6316,
+      "mean_token_accuracy": 0.7583333313465118,
+      "num_tokens": 2476405.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.7914831130690163,
+      "grad_norm": 0.5644094347953796,
+      "learning_rate": 9.552323175440732e-05,
+      "loss": 0.6237,
+      "mean_token_accuracy": 0.7615196108818054,
+      "num_tokens": 2496885.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8061674008810573,
+      "grad_norm": 0.4678439795970917,
+      "learning_rate": 9.542226855197354e-05,
+      "loss": 0.6298,
+      "mean_token_accuracy": 0.7565196096897125,
+      "num_tokens": 2517365.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.8208516886930983,
+      "grad_norm": 0.581727921962738,
+      "learning_rate": 9.532023409318741e-05,
+      "loss": 0.6152,
+      "mean_token_accuracy": 0.7653431415557861,
+      "num_tokens": 2537845.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.8355359765051396,
+      "grad_norm": 0.619175136089325,
+      "learning_rate": 9.52171307844691e-05,
+      "loss": 0.628,
+      "mean_token_accuracy": 0.7585878252983094,
+      "num_tokens": 2558165.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.8502202643171806,
+      "grad_norm": 0.4789538085460663,
+      "learning_rate": 9.511296105744693e-05,
+      "loss": 0.6182,
+      "mean_token_accuracy": 0.7605882346630096,
+      "num_tokens": 2578645.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.8649045521292216,
+      "grad_norm": 0.5343487858772278,
+      "learning_rate": 9.500772736890001e-05,
+      "loss": 0.631,
+      "mean_token_accuracy": 0.7564215660095215,
+      "num_tokens": 2599125.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.8795888399412628,
+      "grad_norm": 0.5381704568862915,
+      "learning_rate": 9.49014322007004e-05,
+      "loss": 0.6336,
+      "mean_token_accuracy": 0.7558333337306976,
+      "num_tokens": 2619605.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.894273127753304,
+      "grad_norm": 0.5045132040977478,
+      "learning_rate": 9.479407805975442e-05,
+      "loss": 0.6293,
+      "mean_token_accuracy": 0.7577450931072235,
+      "num_tokens": 2640085.0,
+      "step": 1290
+    },
+    {
+      "epoch": 1.908957415565345,
+      "grad_norm": 0.5403540134429932,
+      "learning_rate": 9.468566747794369e-05,
+      "loss": 0.6126,
+      "mean_token_accuracy": 0.7640686273574829,
+      "num_tokens": 2660565.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.923641703377386,
+      "grad_norm": 0.4776689410209656,
+      "learning_rate": 9.457620301206531e-05,
+      "loss": 0.6017,
+      "mean_token_accuracy": 0.7670351922512054,
+      "num_tokens": 2680946.0,
+      "step": 1310
+    },
+    {
+      "epoch": 1.9383259911894273,
+      "grad_norm": 0.6080910563468933,
+      "learning_rate": 9.446568724377157e-05,
+      "loss": 0.624,
+      "mean_token_accuracy": 0.759852945804596,
+      "num_tokens": 2701426.0,
+      "step": 1320
+    },
+    {
+      "epoch": 1.9530102790014685,
+      "grad_norm": 0.5421401858329773,
+      "learning_rate": 9.43541227795091e-05,
+      "loss": 0.609,
+      "mean_token_accuracy": 0.7649999976158142,
+      "num_tokens": 2721906.0,
+      "step": 1330
+    },
+    {
+      "epoch": 1.9676945668135095,
+      "grad_norm": 0.5317767262458801,
+      "learning_rate": 9.424151225045739e-05,
+      "loss": 0.6176,
+      "mean_token_accuracy": 0.7620986700057983,
+      "num_tokens": 2742354.0,
+      "step": 1340
+    },
+    {
+      "epoch": 1.9823788546255505,
+      "grad_norm": 0.5858188271522522,
+      "learning_rate": 9.412785831246673e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7616176605224609,
+      "num_tokens": 2762834.0,
+      "step": 1350
+    },
+    {
+      "epoch": 1.9970631424375918,
+      "grad_norm": 0.5256847739219666,
+      "learning_rate": 9.401316364599555e-05,
+      "loss": 0.6203,
+      "mean_token_accuracy": 0.7609804034233093,
+      "num_tokens": 2783314.0,
+      "step": 1360
+    },
+    {
+      "epoch": 2.011747430249633,
+      "grad_norm": 0.550944447517395,
+      "learning_rate": 9.38974309560472e-05,
+      "loss": 0.5797,
+      "mean_token_accuracy": 0.7753431320190429,
+      "num_tokens": 2803794.0,
+      "step": 1370
+    },
+    {
+      "epoch": 2.026431718061674,
+      "grad_norm": 0.5684255361557007,
+      "learning_rate": 9.378066297210626e-05,
+      "loss": 0.5937,
+      "mean_token_accuracy": 0.7721078515052795,
+      "num_tokens": 2824274.0,
+      "step": 1380
+    },
+    {
+      "epoch": 2.041116005873715,
+      "grad_norm": 0.5539990663528442,
+      "learning_rate": 9.3662862448074e-05,
+      "loss": 0.5736,
+      "mean_token_accuracy": 0.7790686249732971,
+      "num_tokens": 2844754.0,
+      "step": 1390
+    },
+    {
+      "epoch": 2.0558002936857562,
+      "grad_norm": 0.5530731081962585,
+      "learning_rate": 9.354403216220356e-05,
+      "loss": 0.5779,
+      "mean_token_accuracy": 0.7777450978755951,
+      "num_tokens": 2865234.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.0704845814977975,
+      "grad_norm": 0.7104700207710266,
+      "learning_rate": 9.342417491703437e-05,
+      "loss": 0.5739,
+      "mean_token_accuracy": 0.7786274552345276,
+      "num_tokens": 2885714.0,
+      "step": 1410
+    },
+    {
+      "epoch": 2.0851688693098387,
+      "grad_norm": 0.6746625304222107,
+      "learning_rate": 9.330329353932605e-05,
+      "loss": 0.5858,
+      "mean_token_accuracy": 0.7741674959659577,
+      "num_tokens": 2906095.0,
+      "step": 1420
+    },
+    {
+      "epoch": 2.0998531571218795,
+      "grad_norm": 0.5403460264205933,
+      "learning_rate": 9.31813908799918e-05,
+      "loss": 0.6028,
+      "mean_token_accuracy": 0.7677451014518738,
+      "num_tokens": 2926575.0,
+      "step": 1430
+    },
+    {
+      "epoch": 2.1145374449339207,
+      "grad_norm": 0.6738181114196777,
+      "learning_rate": 9.305846981403108e-05,
+      "loss": 0.5969,
+      "mean_token_accuracy": 0.769019615650177,
+      "num_tokens": 2947055.0,
+      "step": 1440
+    },
+    {
+      "epoch": 2.129221732745962,
+      "grad_norm": 0.6410481929779053,
+      "learning_rate": 9.293453324046184e-05,
+      "loss": 0.5912,
+      "mean_token_accuracy": 0.7737745106220245,
+      "num_tokens": 2967535.0,
+      "step": 1450
+    },
+    {
+      "epoch": 2.1439060205580027,
+      "grad_norm": 0.603144645690918,
+      "learning_rate": 9.28095840822522e-05,
+      "loss": 0.5981,
+      "mean_token_accuracy": 0.7708823561668396,
+      "num_tokens": 2988015.0,
+      "step": 1460
+    },
+    {
+      "epoch": 2.158590308370044,
+      "grad_norm": 0.6693764328956604,
+      "learning_rate": 9.268362528625143e-05,
+      "loss": 0.5893,
+      "mean_token_accuracy": 0.7714215636253356,
+      "num_tokens": 3008495.0,
+      "step": 1470
+    },
+    {
+      "epoch": 2.173274596182085,
+      "grad_norm": 0.7435688376426697,
+      "learning_rate": 9.255665982312051e-05,
+      "loss": 0.5876,
+      "mean_token_accuracy": 0.7747548997402192,
+      "num_tokens": 3028975.0,
+      "step": 1480
+    },
+    {
+      "epoch": 2.1879588839941264,
+      "grad_norm": 0.6606314182281494,
+      "learning_rate": 9.242869068726203e-05,
+      "loss": 0.5874,
+      "mean_token_accuracy": 0.7729901850223542,
+      "num_tokens": 3049455.0,
+      "step": 1490
+    },
+    {
+      "epoch": 2.202643171806167,
+      "grad_norm": 0.6513794660568237,
+      "learning_rate": 9.229972089674958e-05,
+      "loss": 0.5966,
+      "mean_token_accuracy": 0.7689705848693847,
+      "num_tokens": 3069935.0,
+      "step": 1500
+    },
+    {
+      "epoch": 2.2173274596182084,
+      "grad_norm": 0.6829274892807007,
+      "learning_rate": 9.21697534932566e-05,
+      "loss": 0.5921,
+      "mean_token_accuracy": 0.774656867980957,
+      "num_tokens": 3090415.0,
+      "step": 1510
+    },
+    {
+      "epoch": 2.2320117474302497,
+      "grad_norm": 0.7045487761497498,
+      "learning_rate": 9.203879154198463e-05,
+      "loss": 0.5974,
+      "mean_token_accuracy": 0.7675490260124207,
+      "num_tokens": 3110895.0,
+      "step": 1520
+    },
+    {
+      "epoch": 2.246696035242291,
+      "grad_norm": 0.7174296379089355,
+      "learning_rate": 9.190683813159096e-05,
+      "loss": 0.592,
+      "mean_token_accuracy": 0.7730392098426819,
+      "num_tokens": 3131375.0,
+      "step": 1530
+    },
+    {
+      "epoch": 2.2613803230543317,
+      "grad_norm": 0.5941780209541321,
+      "learning_rate": 9.177389637411586e-05,
+      "loss": 0.5906,
+      "mean_token_accuracy": 0.7713007450103759,
+      "num_tokens": 3151734.0,
+      "step": 1540
+    },
+    {
+      "epoch": 2.276064610866373,
+      "grad_norm": 0.7417426705360413,
+      "learning_rate": 9.163996940490919e-05,
+      "loss": 0.5997,
+      "mean_token_accuracy": 0.7695588171482086,
+      "num_tokens": 3172214.0,
+      "step": 1550
+    },
+    {
+      "epoch": 2.290748898678414,
+      "grad_norm": 0.645305871963501,
+      "learning_rate": 9.150506038255639e-05,
+      "loss": 0.6148,
+      "mean_token_accuracy": 0.7645098030567169,
+      "num_tokens": 3192694.0,
+      "step": 1560
+    },
+    {
+      "epoch": 2.3054331864904554,
+      "grad_norm": 0.675000011920929,
+      "learning_rate": 9.136917248880403e-05,
+      "loss": 0.6115,
+      "mean_token_accuracy": 0.7670098125934601,
+      "num_tokens": 3213174.0,
+      "step": 1570
+    },
+    {
+      "epoch": 2.320117474302496,
+      "grad_norm": 0.8232929110527039,
+      "learning_rate": 9.123230892848476e-05,
+      "loss": 0.6013,
+      "mean_token_accuracy": 0.7694117724895477,
+      "num_tokens": 3233654.0,
+      "step": 1580
+    },
+    {
+      "epoch": 2.3348017621145374,
+      "grad_norm": 0.8386849761009216,
+      "learning_rate": 9.109447292944172e-05,
+      "loss": 0.5906,
+      "mean_token_accuracy": 0.7733310997486115,
+      "num_tokens": 3254030.0,
+      "step": 1590
+    },
+    {
+      "epoch": 2.3494860499265786,
+      "grad_norm": 0.5846053957939148,
+      "learning_rate": 9.095566774245245e-05,
+      "loss": 0.5799,
+      "mean_token_accuracy": 0.7751470506191254,
+      "num_tokens": 3274510.0,
+      "step": 1600
+    },
+    {
+      "epoch": 2.36417033773862,
+      "grad_norm": 0.6155494451522827,
+      "learning_rate": 9.081589664115216e-05,
+      "loss": 0.5874,
+      "mean_token_accuracy": 0.7761764764785767,
+      "num_tokens": 3294990.0,
+      "step": 1610
+    },
+    {
+      "epoch": 2.3788546255506606,
+      "grad_norm": 0.6446321606636047,
+      "learning_rate": 9.067516292195659e-05,
+      "loss": 0.589,
+      "mean_token_accuracy": 0.7732843041419983,
+      "num_tokens": 3315470.0,
+      "step": 1620
+    },
+    {
+      "epoch": 2.393538913362702,
+      "grad_norm": 0.5833125114440918,
+      "learning_rate": 9.053346990398418e-05,
+      "loss": 0.5905,
+      "mean_token_accuracy": 0.7725448489189148,
+      "num_tokens": 3335790.0,
+      "step": 1630
+    },
+    {
+      "epoch": 2.408223201174743,
+      "grad_norm": 0.5974801778793335,
+      "learning_rate": 9.03908209289779e-05,
+      "loss": 0.5928,
+      "mean_token_accuracy": 0.7697549045085907,
+      "num_tokens": 3356270.0,
+      "step": 1640
+    },
+    {
+      "epoch": 2.4229074889867843,
+      "grad_norm": 0.674152672290802,
+      "learning_rate": 9.024721936122637e-05,
+      "loss": 0.579,
+      "mean_token_accuracy": 0.7773039281368256,
+      "num_tokens": 3376750.0,
+      "step": 1650
+    },
+    {
+      "epoch": 2.437591776798825,
+      "grad_norm": 0.6326053142547607,
+      "learning_rate": 9.01026685874845e-05,
+      "loss": 0.5947,
+      "mean_token_accuracy": 0.7713235318660736,
+      "num_tokens": 3397230.0,
+      "step": 1660
+    },
+    {
+      "epoch": 2.4522760646108663,
+      "grad_norm": 0.9275988936424255,
+      "learning_rate": 8.995717201689364e-05,
+      "loss": 0.6013,
+      "mean_token_accuracy": 0.7695053398609162,
+      "num_tokens": 3417688.0,
+      "step": 1670
+    },
+    {
+      "epoch": 2.4669603524229076,
+      "grad_norm": 0.9451805353164673,
+      "learning_rate": 8.981073308090121e-05,
+      "loss": 0.5935,
+      "mean_token_accuracy": 0.7727451086044311,
+      "num_tokens": 3438168.0,
+      "step": 1680
+    },
+    {
+      "epoch": 2.481644640234949,
+      "grad_norm": 0.7964608669281006,
+      "learning_rate": 8.966335523317973e-05,
+      "loss": 0.6065,
+      "mean_token_accuracy": 0.7658823549747467,
+      "num_tokens": 3458648.0,
+      "step": 1690
+    },
+    {
+      "epoch": 2.4963289280469896,
+      "grad_norm": 0.7540594935417175,
+      "learning_rate": 8.951504194954536e-05,
+      "loss": 0.593,
+      "mean_token_accuracy": 0.7717647135257721,
+      "num_tokens": 3479128.0,
+      "step": 1700
+    },
+    {
+      "epoch": 2.511013215859031,
+      "grad_norm": 0.6480241417884827,
+      "learning_rate": 8.936579672787594e-05,
+      "loss": 0.6103,
+      "mean_token_accuracy": 0.7662254810333252,
+      "num_tokens": 3499608.0,
+      "step": 1710
+    },
+    {
+      "epoch": 2.525697503671072,
+      "grad_norm": 0.58002769947052,
+      "learning_rate": 8.921562308802854e-05,
+      "loss": 0.5903,
+      "mean_token_accuracy": 0.7746568620204926,
+      "num_tokens": 3520088.0,
+      "step": 1720
+    },
+    {
+      "epoch": 2.540381791483113,
+      "grad_norm": 0.6285786628723145,
+      "learning_rate": 8.906452457175635e-05,
+      "loss": 0.5971,
+      "mean_token_accuracy": 0.7731372594833374,
+      "num_tokens": 3540568.0,
+      "step": 1730
+    },
+    {
+      "epoch": 2.555066079295154,
+      "grad_norm": 0.7330060601234436,
+      "learning_rate": 8.891250474262526e-05,
+      "loss": 0.597,
+      "mean_token_accuracy": 0.7697058916091919,
+      "num_tokens": 3561048.0,
+      "step": 1740
+    },
+    {
+      "epoch": 2.5697503671071953,
+      "grad_norm": 0.8705717921257019,
+      "learning_rate": 8.875956718592969e-05,
+      "loss": 0.5991,
+      "mean_token_accuracy": 0.771127450466156,
+      "num_tokens": 3581528.0,
+      "step": 1750
+    },
+    {
+      "epoch": 2.5844346549192365,
+      "grad_norm": 0.6374325752258301,
+      "learning_rate": 8.860571550860817e-05,
+      "loss": 0.6011,
+      "mean_token_accuracy": 0.7709877014160156,
+      "num_tokens": 3601919.0,
+      "step": 1760
+    },
+    {
+      "epoch": 2.5991189427312777,
+      "grad_norm": 0.5832578539848328,
+      "learning_rate": 8.845095333915814e-05,
+      "loss": 0.598,
+      "mean_token_accuracy": 0.7690686225891114,
+      "num_tokens": 3622399.0,
+      "step": 1770
+    },
+    {
+      "epoch": 2.6138032305433185,
+      "grad_norm": 0.7307887673377991,
+      "learning_rate": 8.829528432755047e-05,
+      "loss": 0.5943,
+      "mean_token_accuracy": 0.7725000083446503,
+      "num_tokens": 3642879.0,
+      "step": 1780
+    },
+    {
+      "epoch": 2.6284875183553598,
+      "grad_norm": 0.5733655691146851,
+      "learning_rate": 8.81387121451434e-05,
+      "loss": 0.5906,
+      "mean_token_accuracy": 0.7725490212440491,
+      "num_tokens": 3663359.0,
+      "step": 1790
+    },
+    {
+      "epoch": 2.643171806167401,
+      "grad_norm": 0.7298516631126404,
+      "learning_rate": 8.798124048459579e-05,
+      "loss": 0.5962,
+      "mean_token_accuracy": 0.7727451086044311,
+      "num_tokens": 3683839.0,
+      "step": 1800
+    },
+    {
+      "epoch": 2.657856093979442,
+      "grad_norm": 0.6217687726020813,
+      "learning_rate": 8.782287305978023e-05,
+      "loss": 0.5953,
+      "mean_token_accuracy": 0.7705882310867309,
+      "num_tokens": 3704319.0,
+      "step": 1810
+    },
+    {
+      "epoch": 2.672540381791483,
+      "grad_norm": 0.7209094166755676,
+      "learning_rate": 8.766361360569531e-05,
+      "loss": 0.5824,
+      "mean_token_accuracy": 0.7764705955982208,
+      "num_tokens": 3724799.0,
+      "step": 1820
+    },
+    {
+      "epoch": 2.6872246696035242,
+      "grad_norm": 0.7357442378997803,
+      "learning_rate": 8.750346587837762e-05,
+      "loss": 0.6124,
+      "mean_token_accuracy": 0.7663725554943085,
+      "num_tokens": 3745279.0,
+      "step": 1830
+    },
+    {
+      "epoch": 2.7019089574155655,
+      "grad_norm": 0.5689270496368408,
+      "learning_rate": 8.734243365481307e-05,
+      "loss": 0.5754,
+      "mean_token_accuracy": 0.7779902040958404,
+      "num_tokens": 3765759.0,
+      "step": 1840
+    },
+    {
+      "epoch": 2.7165932452276067,
+      "grad_norm": 0.543701171875,
+      "learning_rate": 8.718052073284797e-05,
+      "loss": 0.6025,
+      "mean_token_accuracy": 0.7700490236282349,
+      "num_tokens": 3786239.0,
+      "step": 1850
+    },
+    {
+      "epoch": 2.7312775330396475,
+      "grad_norm": 0.7923574447631836,
+      "learning_rate": 8.701773093109928e-05,
+      "loss": 0.5983,
+      "mean_token_accuracy": 0.7687254965305328,
+      "num_tokens": 3806719.0,
+      "step": 1860
+    },
+    {
+      "epoch": 2.7459618208516887,
+      "grad_norm": 0.8049069046974182,
+      "learning_rate": 8.685406808886464e-05,
+      "loss": 0.5885,
+      "mean_token_accuracy": 0.7746568620204926,
+      "num_tokens": 3827199.0,
+      "step": 1870
+    },
+    {
+      "epoch": 2.76064610866373,
+      "grad_norm": 0.7629956603050232,
+      "learning_rate": 8.668953606603188e-05,
+      "loss": 0.6193,
+      "mean_token_accuracy": 0.761813735961914,
+      "num_tokens": 3847679.0,
+      "step": 1880
+    },
+    {
+      "epoch": 2.7753303964757707,
+      "grad_norm": 0.6295118927955627,
+      "learning_rate": 8.652413874298782e-05,
+      "loss": 0.5955,
+      "mean_token_accuracy": 0.7699999988079071,
+      "num_tokens": 3868159.0,
+      "step": 1890
+    },
+    {
+      "epoch": 2.790014684287812,
+      "grad_norm": 0.5915569067001343,
+      "learning_rate": 8.635788002052691e-05,
+      "loss": 0.6096,
+      "mean_token_accuracy": 0.7661764740943908,
+      "num_tokens": 3888639.0,
+      "step": 1900
+    },
+    {
+      "epoch": 2.804698972099853,
+      "grad_norm": 0.559986412525177,
+      "learning_rate": 8.619076381975922e-05,
+      "loss": 0.5988,
+      "mean_token_accuracy": 0.7696575880050659,
+      "num_tokens": 3908965.0,
+      "step": 1910
+    },
+    {
+      "epoch": 2.8193832599118944,
+      "grad_norm": 0.6710847616195679,
+      "learning_rate": 8.602279408201783e-05,
+      "loss": 0.5804,
+      "mean_token_accuracy": 0.7760784268379212,
+      "num_tokens": 3929445.0,
+      "step": 1920
+    },
+    {
+      "epoch": 2.8340675477239357,
+      "grad_norm": 0.6383255124092102,
+      "learning_rate": 8.585397476876602e-05,
+      "loss": 0.5799,
+      "mean_token_accuracy": 0.7754902064800262,
+      "num_tokens": 3949925.0,
+      "step": 1930
+    },
+    {
+      "epoch": 2.8487518355359764,
+      "grad_norm": 0.7135127186775208,
+      "learning_rate": 8.56843098615038e-05,
+      "loss": 0.5865,
+      "mean_token_accuracy": 0.7747548937797546,
+      "num_tokens": 3970405.0,
+      "step": 1940
+    },
+    {
+      "epoch": 2.8634361233480177,
+      "grad_norm": 0.6053532361984253,
+      "learning_rate": 8.551380336167396e-05,
+      "loss": 0.5981,
+      "mean_token_accuracy": 0.769705879688263,
+      "num_tokens": 3990885.0,
+      "step": 1950
+    },
+    {
+      "epoch": 2.878120411160059,
+      "grad_norm": 0.6343899369239807,
+      "learning_rate": 8.534245929056776e-05,
+      "loss": 0.5857,
+      "mean_token_accuracy": 0.7750490307807922,
+      "num_tokens": 4011365.0,
+      "step": 1960
+    },
+    {
+      "epoch": 2.8928046989720997,
+      "grad_norm": 0.5568163394927979,
+      "learning_rate": 8.517028168923002e-05,
+      "loss": 0.5797,
+      "mean_token_accuracy": 0.7752941131591797,
+      "num_tokens": 4031845.0,
+      "step": 1970
+    },
+    {
+      "epoch": 2.907488986784141,
+      "grad_norm": 0.549111008644104,
+      "learning_rate": 8.499727461836395e-05,
+      "loss": 0.5979,
+      "mean_token_accuracy": 0.7684820890426636,
+      "num_tokens": 4052248.0,
+      "step": 1980
+    },
+    {
+      "epoch": 2.922173274596182,
+      "grad_norm": 0.7707120776176453,
+      "learning_rate": 8.48234421582352e-05,
+      "loss": 0.5789,
+      "mean_token_accuracy": 0.7774509847164154,
+      "num_tokens": 4072728.0,
+      "step": 1990
+    },
+    {
+      "epoch": 2.936857562408223,
+      "grad_norm": 0.6881651878356934,
+      "learning_rate": 8.464878840857574e-05,
+      "loss": 0.6027,
+      "mean_token_accuracy": 0.766813725233078,
+      "num_tokens": 4093208.0,
+      "step": 2000
+    },
+    {
+      "epoch": 2.951541850220264,
+      "grad_norm": 0.7717125415802002,
+      "learning_rate": 8.447331748848718e-05,
+      "loss": 0.5836,
+      "mean_token_accuracy": 0.7729411721229553,
+      "num_tokens": 4113688.0,
+      "step": 2010
+    },
+    {
+      "epoch": 2.9662261380323054,
+      "grad_norm": 0.6662061810493469,
+      "learning_rate": 8.429703353634357e-05,
+      "loss": 0.5997,
+      "mean_token_accuracy": 0.7697549045085907,
+      "num_tokens": 4134168.0,
+      "step": 2020
+    },
+    {
+      "epoch": 2.9809104258443466,
+      "grad_norm": 0.8073809146881104,
+      "learning_rate": 8.411994070969386e-05,
+      "loss": 0.59,
+      "mean_token_accuracy": 0.7718137264251709,
+      "num_tokens": 4154648.0,
+      "step": 2030
+    },
+    {
+      "epoch": 2.995594713656388,
+      "grad_norm": 0.6692283153533936,
+      "learning_rate": 8.394204318516374e-05,
+      "loss": 0.5857,
+      "mean_token_accuracy": 0.7729605972766876,
+      "num_tokens": 4174971.0,
+      "step": 2040
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6810,
+  "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": 1.78010272108118e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2043/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac0efbafb523853fa46901df5567229595df957b581e4dee225a481543b5f51
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2724/README.md

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2724/adapter_config.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2724/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f722f26c696b2190dd52d58d9d0d26d57ef033e3221a7fd407b845b928c6ae16
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2724/added_tokens.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2724/chat_template.jinja

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2724/special_tokens_map.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2724/tokenizer.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2724/tokenizer_config.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2724/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": 2724,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014684287812041116,
+      "grad_norm": 3.9844751358032227,
+      "learning_rate": 2.6392961876832847e-06,
+      "loss": 2.4601,
+      "mean_token_accuracy": 0.5440195977687836,
+      "num_tokens": 20480.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.02936857562408223,
+      "grad_norm": 3.408750295639038,
+      "learning_rate": 5.571847507331378e-06,
+      "loss": 2.4123,
+      "mean_token_accuracy": 0.5557843208312988,
+      "num_tokens": 40960.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.04405286343612335,
+      "grad_norm": 3.2006149291992188,
+      "learning_rate": 8.504398826979472e-06,
+      "loss": 2.3369,
+      "mean_token_accuracy": 0.5485294103622437,
+      "num_tokens": 61440.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.05873715124816446,
+      "grad_norm": 2.0662899017333984,
+      "learning_rate": 1.1436950146627567e-05,
+      "loss": 2.0808,
+      "mean_token_accuracy": 0.5701960742473602,
+      "num_tokens": 81920.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.07342143906020558,
+      "grad_norm": 1.349193811416626,
+      "learning_rate": 1.4369501466275662e-05,
+      "loss": 1.7811,
+      "mean_token_accuracy": 0.5971078455448151,
+      "num_tokens": 102400.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.0881057268722467,
+      "grad_norm": 1.0805939435958862,
+      "learning_rate": 1.7302052785923756e-05,
+      "loss": 1.5636,
+      "mean_token_accuracy": 0.604313725233078,
+      "num_tokens": 122880.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.1027900146842878,
+      "grad_norm": 0.9003157615661621,
+      "learning_rate": 2.0234604105571847e-05,
+      "loss": 1.3844,
+      "mean_token_accuracy": 0.6224509835243225,
+      "num_tokens": 143360.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.11747430249632893,
+      "grad_norm": 0.8923518657684326,
+      "learning_rate": 2.3167155425219943e-05,
+      "loss": 1.2358,
+      "mean_token_accuracy": 0.6361274480819702,
+      "num_tokens": 163840.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.13215859030837004,
+      "grad_norm": 1.0202796459197998,
+      "learning_rate": 2.6099706744868034e-05,
+      "loss": 1.0774,
+      "mean_token_accuracy": 0.6648529529571533,
+      "num_tokens": 184320.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.14684287812041116,
+      "grad_norm": 1.149533748626709,
+      "learning_rate": 2.9032258064516133e-05,
+      "loss": 0.9291,
+      "mean_token_accuracy": 0.6854411721229553,
+      "num_tokens": 204800.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.16152716593245228,
+      "grad_norm": 1.153542160987854,
+      "learning_rate": 3.1964809384164225e-05,
+      "loss": 0.8269,
+      "mean_token_accuracy": 0.709852933883667,
+      "num_tokens": 225280.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.1762114537444934,
+      "grad_norm": 1.2031893730163574,
+      "learning_rate": 3.489736070381232e-05,
+      "loss": 0.7872,
+      "mean_token_accuracy": 0.7195098102092743,
+      "num_tokens": 245760.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.19089574155653452,
+      "grad_norm": 1.1650404930114746,
+      "learning_rate": 3.7829912023460415e-05,
+      "loss": 0.7448,
+      "mean_token_accuracy": 0.7316666603088379,
+      "num_tokens": 266240.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.2055800293685756,
+      "grad_norm": 1.1167842149734497,
+      "learning_rate": 4.076246334310851e-05,
+      "loss": 0.7018,
+      "mean_token_accuracy": 0.7435784280300141,
+      "num_tokens": 286720.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.22026431718061673,
+      "grad_norm": 1.1387581825256348,
+      "learning_rate": 4.36950146627566e-05,
+      "loss": 0.6919,
+      "mean_token_accuracy": 0.7467156887054444,
+      "num_tokens": 307200.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.23494860499265785,
+      "grad_norm": 1.0053479671478271,
+      "learning_rate": 4.6627565982404694e-05,
+      "loss": 0.7028,
+      "mean_token_accuracy": 0.7395588219165802,
+      "num_tokens": 327680.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.24963289280469897,
+      "grad_norm": 0.9742514491081238,
+      "learning_rate": 4.956011730205279e-05,
+      "loss": 0.6858,
+      "mean_token_accuracy": 0.745686274766922,
+      "num_tokens": 348160.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.2643171806167401,
+      "grad_norm": 0.8818563222885132,
+      "learning_rate": 5.249266862170088e-05,
+      "loss": 0.6913,
+      "mean_token_accuracy": 0.7424509763717652,
+      "num_tokens": 368640.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.2790014684287812,
+      "grad_norm": 0.8835548162460327,
+      "learning_rate": 5.542521994134897e-05,
+      "loss": 0.6767,
+      "mean_token_accuracy": 0.7474999964237213,
+      "num_tokens": 389120.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.2936857562408223,
+      "grad_norm": 0.8910827040672302,
+      "learning_rate": 5.8357771260997075e-05,
+      "loss": 0.6789,
+      "mean_token_accuracy": 0.7434803903102875,
+      "num_tokens": 409600.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.30837004405286345,
+      "grad_norm": 0.9448742866516113,
+      "learning_rate": 6.129032258064517e-05,
+      "loss": 0.6637,
+      "mean_token_accuracy": 0.7499999940395355,
+      "num_tokens": 430080.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.32305433186490456,
+      "grad_norm": 0.7906215190887451,
+      "learning_rate": 6.422287390029326e-05,
+      "loss": 0.6593,
+      "mean_token_accuracy": 0.7529411673545837,
+      "num_tokens": 450560.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.3377386196769457,
+      "grad_norm": 0.854017436504364,
+      "learning_rate": 6.715542521994135e-05,
+      "loss": 0.6682,
+      "mean_token_accuracy": 0.7474509835243225,
+      "num_tokens": 471040.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.3524229074889868,
+      "grad_norm": 0.7827669978141785,
+      "learning_rate": 7.008797653958945e-05,
+      "loss": 0.6857,
+      "mean_token_accuracy": 0.741813725233078,
+      "num_tokens": 491520.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.3671071953010279,
+      "grad_norm": 0.7865115404129028,
+      "learning_rate": 7.302052785923754e-05,
+      "loss": 0.657,
+      "mean_token_accuracy": 0.7524509787559509,
+      "num_tokens": 512000.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.38179148311306904,
+      "grad_norm": 0.7960774302482605,
+      "learning_rate": 7.595307917888564e-05,
+      "loss": 0.6569,
+      "mean_token_accuracy": 0.752205890417099,
+      "num_tokens": 532480.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.3964757709251101,
+      "grad_norm": 0.7246135473251343,
+      "learning_rate": 7.888563049853373e-05,
+      "loss": 0.6506,
+      "mean_token_accuracy": 0.7553921639919281,
+      "num_tokens": 552960.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.4111600587371512,
+      "grad_norm": 0.6880009770393372,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 0.6617,
+      "mean_token_accuracy": 0.7480882346630097,
+      "num_tokens": 573440.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.42584434654919234,
+      "grad_norm": 0.7460880279541016,
+      "learning_rate": 8.475073313782992e-05,
+      "loss": 0.641,
+      "mean_token_accuracy": 0.7563235282897949,
+      "num_tokens": 593920.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.44052863436123346,
+      "grad_norm": 0.6125314831733704,
+      "learning_rate": 8.7683284457478e-05,
+      "loss": 0.662,
+      "mean_token_accuracy": 0.7470588207244873,
+      "num_tokens": 614400.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.4552129221732746,
+      "grad_norm": 0.8595872521400452,
+      "learning_rate": 9.06158357771261e-05,
+      "loss": 0.6428,
+      "mean_token_accuracy": 0.753333330154419,
+      "num_tokens": 634880.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.4698972099853157,
+      "grad_norm": 0.7512183785438538,
+      "learning_rate": 9.35483870967742e-05,
+      "loss": 0.6474,
+      "mean_token_accuracy": 0.7549509763717651,
+      "num_tokens": 655360.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.4845814977973568,
+      "grad_norm": 0.5831340551376343,
+      "learning_rate": 9.64809384164223e-05,
+      "loss": 0.6484,
+      "mean_token_accuracy": 0.7540196001529693,
+      "num_tokens": 675840.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.49926578560939794,
+      "grad_norm": 0.7933578491210938,
+      "learning_rate": 9.941348973607039e-05,
+      "loss": 0.6486,
+      "mean_token_accuracy": 0.7517647087574005,
+      "num_tokens": 696320.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.5139500734214391,
+      "grad_norm": 0.5593725442886353,
+      "learning_rate": 9.99996226495437e-05,
+      "loss": 0.6685,
+      "mean_token_accuracy": 0.7433085501194,
+      "num_tokens": 716778.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.5286343612334802,
+      "grad_norm": 0.8261681795120239,
+      "learning_rate": 9.999808967307669e-05,
+      "loss": 0.6481,
+      "mean_token_accuracy": 0.7506862759590149,
+      "num_tokens": 737258.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.5433186490455213,
+      "grad_norm": 0.5749596953392029,
+      "learning_rate": 9.999537752232195e-05,
+      "loss": 0.6569,
+      "mean_token_accuracy": 0.749117648601532,
+      "num_tokens": 757738.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.5580029368575624,
+      "grad_norm": 0.7790083885192871,
+      "learning_rate": 9.999148626124389e-05,
+      "loss": 0.6498,
+      "mean_token_accuracy": 0.7523039162158967,
+      "num_tokens": 778218.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.5726872246696035,
+      "grad_norm": 0.5859090685844421,
+      "learning_rate": 9.998641598161553e-05,
+      "loss": 0.6519,
+      "mean_token_accuracy": 0.7507352948188781,
+      "num_tokens": 798698.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.5873715124816447,
+      "grad_norm": 0.5902988910675049,
+      "learning_rate": 9.998016680301629e-05,
+      "loss": 0.6371,
+      "mean_token_accuracy": 0.7570588231086731,
+      "num_tokens": 819178.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.6020558002936858,
+      "grad_norm": 0.5497356653213501,
+      "learning_rate": 9.997273887282922e-05,
+      "loss": 0.645,
+      "mean_token_accuracy": 0.7509313642978668,
+      "num_tokens": 839658.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.6167400881057269,
+      "grad_norm": 0.6334931254386902,
+      "learning_rate": 9.996413236623751e-05,
+      "loss": 0.6551,
+      "mean_token_accuracy": 0.7505392134189606,
+      "num_tokens": 860138.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.631424375917768,
+      "grad_norm": 0.6489232778549194,
+      "learning_rate": 9.995434748622034e-05,
+      "loss": 0.6561,
+      "mean_token_accuracy": 0.751323527097702,
+      "num_tokens": 880618.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.6461086637298091,
+      "grad_norm": 0.5434768795967102,
+      "learning_rate": 9.994338446354809e-05,
+      "loss": 0.6433,
+      "mean_token_accuracy": 0.7540266394615174,
+      "num_tokens": 901066.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.6607929515418502,
+      "grad_norm": 0.5775740146636963,
+      "learning_rate": 9.993124355677692e-05,
+      "loss": 0.6448,
+      "mean_token_accuracy": 0.7538183212280274,
+      "num_tokens": 921389.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.6754772393538914,
+      "grad_norm": 0.4898783564567566,
+      "learning_rate": 9.99179250522427e-05,
+      "loss": 0.6371,
+      "mean_token_accuracy": 0.7541666686534881,
+      "num_tokens": 941869.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.6901615271659325,
+      "grad_norm": 0.53432297706604,
+      "learning_rate": 9.990342926405419e-05,
+      "loss": 0.6399,
+      "mean_token_accuracy": 0.7554790556430817,
+      "num_tokens": 962250.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.7048458149779736,
+      "grad_norm": 0.5491565465927124,
+      "learning_rate": 9.988775653408564e-05,
+      "loss": 0.6432,
+      "mean_token_accuracy": 0.7505809485912323,
+      "num_tokens": 982609.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.7195301027900147,
+      "grad_norm": 0.6353980302810669,
+      "learning_rate": 9.987090723196881e-05,
+      "loss": 0.6411,
+      "mean_token_accuracy": 0.7574509799480438,
+      "num_tokens": 1003089.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.7342143906020558,
+      "grad_norm": 0.4572882056236267,
+      "learning_rate": 9.985288175508413e-05,
+      "loss": 0.6317,
+      "mean_token_accuracy": 0.7595588326454162,
+      "num_tokens": 1023569.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.748898678414097,
+      "grad_norm": 0.579796552658081,
+      "learning_rate": 9.983368052855143e-05,
+      "loss": 0.6463,
+      "mean_token_accuracy": 0.7553976953029633,
+      "num_tokens": 1043972.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.7635829662261381,
+      "grad_norm": 0.6805964112281799,
+      "learning_rate": 9.981330400521987e-05,
+      "loss": 0.6219,
+      "mean_token_accuracy": 0.7632352948188782,
+      "num_tokens": 1064452.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.7782672540381792,
+      "grad_norm": 0.4945206642150879,
+      "learning_rate": 9.979175266565725e-05,
+      "loss": 0.6408,
+      "mean_token_accuracy": 0.7531372547149658,
+      "num_tokens": 1084932.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.7929515418502202,
+      "grad_norm": 0.7035859227180481,
+      "learning_rate": 9.97690270181387e-05,
+      "loss": 0.6156,
+      "mean_token_accuracy": 0.7650490283966065,
+      "num_tokens": 1105412.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.8076358296622613,
+      "grad_norm": 0.4683134853839874,
+      "learning_rate": 9.97451275986347e-05,
+      "loss": 0.6467,
+      "mean_token_accuracy": 0.7550490260124206,
+      "num_tokens": 1125892.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.8223201174743024,
+      "grad_norm": 0.6907538771629333,
+      "learning_rate": 9.972005497079838e-05,
+      "loss": 0.6378,
+      "mean_token_accuracy": 0.7559075593948364,
+      "num_tokens": 1146250.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.8370044052863436,
+      "grad_norm": 0.45830196142196655,
+      "learning_rate": 9.96938097259523e-05,
+      "loss": 0.6442,
+      "mean_token_accuracy": 0.7528921604156494,
+      "num_tokens": 1166730.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.8516886930983847,
+      "grad_norm": 0.5164074301719666,
+      "learning_rate": 9.966639248307447e-05,
+      "loss": 0.6338,
+      "mean_token_accuracy": 0.7568260788917541,
+      "num_tokens": 1187017.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.8663729809104258,
+      "grad_norm": 0.5325213670730591,
+      "learning_rate": 9.963780388878377e-05,
+      "loss": 0.6408,
+      "mean_token_accuracy": 0.7529411792755127,
+      "num_tokens": 1207497.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.8810572687224669,
+      "grad_norm": 0.5315613746643066,
+      "learning_rate": 9.960804461732463e-05,
+      "loss": 0.6428,
+      "mean_token_accuracy": 0.7546401798725129,
+      "num_tokens": 1227817.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.895741556534508,
+      "grad_norm": 0.5416283011436462,
+      "learning_rate": 9.957711537055126e-05,
+      "loss": 0.629,
+      "mean_token_accuracy": 0.7575490176677704,
+      "num_tokens": 1248297.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.9104258443465492,
+      "grad_norm": 0.5316348671913147,
+      "learning_rate": 9.954501687791093e-05,
+      "loss": 0.6296,
+      "mean_token_accuracy": 0.7591666758060456,
+      "num_tokens": 1268777.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.9251101321585903,
+      "grad_norm": 0.4492694139480591,
+      "learning_rate": 9.951174989642695e-05,
+      "loss": 0.6361,
+      "mean_token_accuracy": 0.7559313774108887,
+      "num_tokens": 1289257.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.9397944199706314,
+      "grad_norm": 0.48100170493125916,
+      "learning_rate": 9.947731521068067e-05,
+      "loss": 0.6507,
+      "mean_token_accuracy": 0.7501960873603821,
+      "num_tokens": 1309737.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.9544787077826725,
+      "grad_norm": 0.4680826663970947,
+      "learning_rate": 9.944171363279305e-05,
+      "loss": 0.611,
+      "mean_token_accuracy": 0.7656862795352936,
+      "num_tokens": 1330217.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.9691629955947136,
+      "grad_norm": 0.5119115114212036,
+      "learning_rate": 9.940494600240544e-05,
+      "loss": 0.6283,
+      "mean_token_accuracy": 0.7572058737277985,
+      "num_tokens": 1350697.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.9838472834067548,
+      "grad_norm": 0.5171290040016174,
+      "learning_rate": 9.936701318665988e-05,
+      "loss": 0.6331,
+      "mean_token_accuracy": 0.7570098042488098,
+      "num_tokens": 1371177.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.9985315712187959,
+      "grad_norm": 0.48826828598976135,
+      "learning_rate": 9.932791608017857e-05,
+      "loss": 0.6237,
+      "mean_token_accuracy": 0.7597549021244049,
+      "num_tokens": 1391657.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.013215859030837,
+      "grad_norm": 0.6590768098831177,
+      "learning_rate": 9.92876556050428e-05,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.7640686333179474,
+      "num_tokens": 1412137.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.0279001468428781,
+      "grad_norm": 0.5727214217185974,
+      "learning_rate": 9.924623271077116e-05,
+      "loss": 0.6321,
+      "mean_token_accuracy": 0.758725494146347,
+      "num_tokens": 1432617.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.0425844346549193,
+      "grad_norm": 0.6612036824226379,
+      "learning_rate": 9.920364837429726e-05,
+      "loss": 0.624,
+      "mean_token_accuracy": 0.7604901969432831,
+      "num_tokens": 1453097.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.0572687224669604,
+      "grad_norm": 0.5342158675193787,
+      "learning_rate": 9.915990359994654e-05,
+      "loss": 0.6083,
+      "mean_token_accuracy": 0.7637745201587677,
+      "num_tokens": 1473577.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.0719530102790014,
+      "grad_norm": 0.5662015676498413,
+      "learning_rate": 9.911499941941265e-05,
+      "loss": 0.6117,
+      "mean_token_accuracy": 0.7661274611949921,
+      "num_tokens": 1494057.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.0866372980910426,
+      "grad_norm": 0.5665001273155212,
+      "learning_rate": 9.90689368917332e-05,
+      "loss": 0.6106,
+      "mean_token_accuracy": 0.7660784244537353,
+      "num_tokens": 1514537.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.1013215859030836,
+      "grad_norm": 0.5586121678352356,
+      "learning_rate": 9.902171710326464e-05,
+      "loss": 0.6174,
+      "mean_token_accuracy": 0.7632494688034057,
+      "num_tokens": 1534940.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.1160058737151248,
+      "grad_norm": 0.6175503134727478,
+      "learning_rate": 9.897334116765674e-05,
+      "loss": 0.6362,
+      "mean_token_accuracy": 0.755294120311737,
+      "num_tokens": 1555420.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.1306901615271658,
+      "grad_norm": 0.5187695026397705,
+      "learning_rate": 9.892381022582627e-05,
+      "loss": 0.6112,
+      "mean_token_accuracy": 0.7644117712974549,
+      "num_tokens": 1575900.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.145374449339207,
+      "grad_norm": 0.64495849609375,
+      "learning_rate": 9.88731254459301e-05,
+      "loss": 0.6286,
+      "mean_token_accuracy": 0.759852945804596,
+      "num_tokens": 1596380.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.160058737151248,
+      "grad_norm": 0.5434204936027527,
+      "learning_rate": 9.882128802333775e-05,
+      "loss": 0.6314,
+      "mean_token_accuracy": 0.7599019587039948,
+      "num_tokens": 1616860.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.1747430249632893,
+      "grad_norm": 0.5666676163673401,
+      "learning_rate": 9.876829918060297e-05,
+      "loss": 0.6163,
+      "mean_token_accuracy": 0.7637371957302094,
+      "num_tokens": 1637219.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.1894273127753303,
+      "grad_norm": 0.5177666544914246,
+      "learning_rate": 9.871416016743516e-05,
+      "loss": 0.6002,
+      "mean_token_accuracy": 0.7682352900505066,
+      "num_tokens": 1657699.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.2041116005873715,
+      "grad_norm": 0.5266413688659668,
+      "learning_rate": 9.865887226066977e-05,
+      "loss": 0.6196,
+      "mean_token_accuracy": 0.7619607806205749,
+      "num_tokens": 1678179.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.2187958883994126,
+      "grad_norm": 0.5798647999763489,
+      "learning_rate": 9.860243676423814e-05,
+      "loss": 0.6237,
+      "mean_token_accuracy": 0.7611274480819702,
+      "num_tokens": 1698659.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.2334801762114538,
+      "grad_norm": 0.6460749506950378,
+      "learning_rate": 9.854485500913687e-05,
+      "loss": 0.6106,
+      "mean_token_accuracy": 0.7648039340972901,
+      "num_tokens": 1719139.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.2481644640234948,
+      "grad_norm": 0.5380497574806213,
+      "learning_rate": 9.848612835339634e-05,
+      "loss": 0.6308,
+      "mean_token_accuracy": 0.7592647075653076,
+      "num_tokens": 1739619.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.262848751835536,
+      "grad_norm": 0.5102669596672058,
+      "learning_rate": 9.842625818204873e-05,
+      "loss": 0.6322,
+      "mean_token_accuracy": 0.758088231086731,
+      "num_tokens": 1760099.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.277533039647577,
+      "grad_norm": 0.6140068769454956,
+      "learning_rate": 9.836524590709533e-05,
+      "loss": 0.6117,
+      "mean_token_accuracy": 0.7641176402568817,
+      "num_tokens": 1780579.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.2922173274596183,
+      "grad_norm": 0.5898679494857788,
+      "learning_rate": 9.830309296747318e-05,
+      "loss": 0.6262,
+      "mean_token_accuracy": 0.7606862783432007,
+      "num_tokens": 1801059.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.3069016152716593,
+      "grad_norm": 0.548785388469696,
+      "learning_rate": 9.823980082902131e-05,
+      "loss": 0.6173,
+      "mean_token_accuracy": 0.762156867980957,
+      "num_tokens": 1821539.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.3215859030837005,
+      "grad_norm": 0.5419488549232483,
+      "learning_rate": 9.817537098444596e-05,
+      "loss": 0.6194,
+      "mean_token_accuracy": 0.7644117712974549,
+      "num_tokens": 1842019.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.3362701908957415,
+      "grad_norm": 0.4247446656227112,
+      "learning_rate": 9.810980495328555e-05,
+      "loss": 0.6113,
+      "mean_token_accuracy": 0.764950978755951,
+      "num_tokens": 1862499.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.3509544787077827,
+      "grad_norm": 0.5713850259780884,
+      "learning_rate": 9.804310428187466e-05,
+      "loss": 0.6109,
+      "mean_token_accuracy": 0.7650000035762787,
+      "num_tokens": 1882979.0,
+      "step": 920
+    },
+    {
+      "epoch": 1.3656387665198237,
+      "grad_norm": 0.4875611960887909,
+      "learning_rate": 9.797527054330778e-05,
+      "loss": 0.6255,
+      "mean_token_accuracy": 0.7605392098426819,
+      "num_tokens": 1903459.0,
+      "step": 930
+    },
+    {
+      "epoch": 1.380323054331865,
+      "grad_norm": 0.6159121990203857,
+      "learning_rate": 9.7906305337402e-05,
+      "loss": 0.6261,
+      "mean_token_accuracy": 0.7585294187068939,
+      "num_tokens": 1923939.0,
+      "step": 940
+    },
+    {
+      "epoch": 1.395007342143906,
+      "grad_norm": 0.5493881106376648,
+      "learning_rate": 9.783621029065946e-05,
+      "loss": 0.636,
+      "mean_token_accuracy": 0.7579411745071412,
+      "num_tokens": 1944419.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.4096916299559472,
+      "grad_norm": 0.5031521320343018,
+      "learning_rate": 9.77649870562288e-05,
+      "loss": 0.6114,
+      "mean_token_accuracy": 0.7669117748737335,
+      "num_tokens": 1964899.0,
+      "step": 960
+    },
+    {
+      "epoch": 1.4243759177679882,
+      "grad_norm": 0.5134665966033936,
+      "learning_rate": 9.76926373138664e-05,
+      "loss": 0.6332,
+      "mean_token_accuracy": 0.7555882334709167,
+      "num_tokens": 1985379.0,
+      "step": 970
+    },
+    {
+      "epoch": 1.4390602055800295,
+      "grad_norm": 0.5811095833778381,
+      "learning_rate": 9.761916276989651e-05,
+      "loss": 0.6208,
+      "mean_token_accuracy": 0.7612745106220246,
+      "num_tokens": 2005859.0,
+      "step": 980
+    },
+    {
+      "epoch": 1.4537444933920705,
+      "grad_norm": 0.4786250591278076,
+      "learning_rate": 9.754456515717122e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7635294139385224,
+      "num_tokens": 2026339.0,
+      "step": 990
+    },
+    {
+      "epoch": 1.4684287812041115,
+      "grad_norm": 0.5460525751113892,
+      "learning_rate": 9.746884623502952e-05,
+      "loss": 0.6193,
+      "mean_token_accuracy": 0.7622549116611481,
+      "num_tokens": 2046819.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4831130690161527,
+      "grad_norm": 0.46199068427085876,
+      "learning_rate": 9.73920077892557e-05,
+      "loss": 0.6092,
+      "mean_token_accuracy": 0.7654411673545838,
+      "num_tokens": 2067299.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.497797356828194,
+      "grad_norm": 0.6629523634910583,
+      "learning_rate": 9.731405163203744e-05,
+      "loss": 0.6283,
+      "mean_token_accuracy": 0.7582352936267853,
+      "num_tokens": 2087779.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.512481644640235,
+      "grad_norm": 0.5012948513031006,
+      "learning_rate": 9.723497960192287e-05,
+      "loss": 0.6095,
+      "mean_token_accuracy": 0.7612385094165802,
+      "num_tokens": 2108237.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.527165932452276,
+      "grad_norm": 0.5635460019111633,
+      "learning_rate": 9.715479356377735e-05,
+      "loss": 0.6289,
+      "mean_token_accuracy": 0.7602941274642945,
+      "num_tokens": 2128717.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.5418502202643172,
+      "grad_norm": 0.7186609506607056,
+      "learning_rate": 9.707349540873942e-05,
+      "loss": 0.6089,
+      "mean_token_accuracy": 0.7640686273574829,
+      "num_tokens": 2149197.0,
+      "step": 1050
+    },
+    {
+      "epoch": 1.5565345080763584,
+      "grad_norm": 0.5319746732711792,
+      "learning_rate": 9.699108705417623e-05,
+      "loss": 0.615,
+      "mean_token_accuracy": 0.7627941191196441,
+      "num_tokens": 2169677.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.5712187958883994,
+      "grad_norm": 0.6315519213676453,
+      "learning_rate": 9.690757044363827e-05,
+      "loss": 0.6112,
+      "mean_token_accuracy": 0.762156867980957,
+      "num_tokens": 2190157.0,
+      "step": 1070
+    },
+    {
+      "epoch": 1.5859030837004404,
+      "grad_norm": 0.5465179681777954,
+      "learning_rate": 9.68229475468136e-05,
+      "loss": 0.6355,
+      "mean_token_accuracy": 0.7547058880329132,
+      "num_tokens": 2210637.0,
+      "step": 1080
+    },
+    {
+      "epoch": 1.6005873715124816,
+      "grad_norm": 0.529995858669281,
+      "learning_rate": 9.673722035948136e-05,
+      "loss": 0.6253,
+      "mean_token_accuracy": 0.760574460029602,
+      "num_tokens": 2231013.0,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6152716593245229,
+      "grad_norm": 0.5319053530693054,
+      "learning_rate": 9.66503909034647e-05,
+      "loss": 0.6194,
+      "mean_token_accuracy": 0.7610784351825715,
+      "num_tokens": 2251493.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.6299559471365639,
+      "grad_norm": 0.4977491497993469,
+      "learning_rate": 9.65624612265831e-05,
+      "loss": 0.6141,
+      "mean_token_accuracy": 0.7668627440929413,
+      "num_tokens": 2271973.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.644640234948605,
+      "grad_norm": 0.566733181476593,
+      "learning_rate": 9.647343340260406e-05,
+      "loss": 0.6234,
+      "mean_token_accuracy": 0.7592156887054443,
+      "num_tokens": 2292453.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.6593245227606461,
+      "grad_norm": 0.5549957752227783,
+      "learning_rate": 9.638330953119422e-05,
+      "loss": 0.6149,
+      "mean_token_accuracy": 0.7609803915023804,
+      "num_tokens": 2312933.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.6740088105726874,
+      "grad_norm": 0.5047655701637268,
+      "learning_rate": 9.629209173786984e-05,
+      "loss": 0.6187,
+      "mean_token_accuracy": 0.7625472128391266,
+      "num_tokens": 2333324.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.6886930983847284,
+      "grad_norm": 0.6593276262283325,
+      "learning_rate": 9.619978217394663e-05,
+      "loss": 0.6225,
+      "mean_token_accuracy": 0.762598043680191,
+      "num_tokens": 2353804.0,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7033773861967694,
+      "grad_norm": 0.563077449798584,
+      "learning_rate": 9.610638301648905e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7612745106220246,
+      "num_tokens": 2374284.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.7180616740088106,
+      "grad_norm": 0.5723268389701843,
+      "learning_rate": 9.601189646825899e-05,
+      "loss": 0.6203,
+      "mean_token_accuracy": 0.7623447120189667,
+      "num_tokens": 2394642.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.7327459618208518,
+      "grad_norm": 0.46074366569519043,
+      "learning_rate": 9.591632475766372e-05,
+      "loss": 0.6269,
+      "mean_token_accuracy": 0.7591176450252533,
+      "num_tokens": 2415122.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.7474302496328928,
+      "grad_norm": 0.49932244420051575,
+      "learning_rate": 9.581967013870345e-05,
+      "loss": 0.6097,
+      "mean_token_accuracy": 0.7649509727954864,
+      "num_tokens": 2435602.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.7621145374449338,
+      "grad_norm": 0.4770796597003937,
+      "learning_rate": 9.57219348909181e-05,
+      "loss": 0.609,
+      "mean_token_accuracy": 0.7656404256820679,
+      "num_tokens": 2455925.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.776798825256975,
+      "grad_norm": 0.5677822232246399,
+      "learning_rate": 9.562312131933356e-05,
+      "loss": 0.6316,
+      "mean_token_accuracy": 0.7583333313465118,
+      "num_tokens": 2476405.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.7914831130690163,
+      "grad_norm": 0.5644094347953796,
+      "learning_rate": 9.552323175440732e-05,
+      "loss": 0.6237,
+      "mean_token_accuracy": 0.7615196108818054,
+      "num_tokens": 2496885.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8061674008810573,
+      "grad_norm": 0.4678439795970917,
+      "learning_rate": 9.542226855197354e-05,
+      "loss": 0.6298,
+      "mean_token_accuracy": 0.7565196096897125,
+      "num_tokens": 2517365.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.8208516886930983,
+      "grad_norm": 0.581727921962738,
+      "learning_rate": 9.532023409318741e-05,
+      "loss": 0.6152,
+      "mean_token_accuracy": 0.7653431415557861,
+      "num_tokens": 2537845.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.8355359765051396,
+      "grad_norm": 0.619175136089325,
+      "learning_rate": 9.52171307844691e-05,
+      "loss": 0.628,
+      "mean_token_accuracy": 0.7585878252983094,
+      "num_tokens": 2558165.0,
+      "step": 1250
+    },
+    {
+      "epoch": 1.8502202643171806,
+      "grad_norm": 0.4789538085460663,
+      "learning_rate": 9.511296105744693e-05,
+      "loss": 0.6182,
+      "mean_token_accuracy": 0.7605882346630096,
+      "num_tokens": 2578645.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.8649045521292216,
+      "grad_norm": 0.5343487858772278,
+      "learning_rate": 9.500772736890001e-05,
+      "loss": 0.631,
+      "mean_token_accuracy": 0.7564215660095215,
+      "num_tokens": 2599125.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.8795888399412628,
+      "grad_norm": 0.5381704568862915,
+      "learning_rate": 9.49014322007004e-05,
+      "loss": 0.6336,
+      "mean_token_accuracy": 0.7558333337306976,
+      "num_tokens": 2619605.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.894273127753304,
+      "grad_norm": 0.5045132040977478,
+      "learning_rate": 9.479407805975442e-05,
+      "loss": 0.6293,
+      "mean_token_accuracy": 0.7577450931072235,
+      "num_tokens": 2640085.0,
+      "step": 1290
+    },
+    {
+      "epoch": 1.908957415565345,
+      "grad_norm": 0.5403540134429932,
+      "learning_rate": 9.468566747794369e-05,
+      "loss": 0.6126,
+      "mean_token_accuracy": 0.7640686273574829,
+      "num_tokens": 2660565.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.923641703377386,
+      "grad_norm": 0.4776689410209656,
+      "learning_rate": 9.457620301206531e-05,
+      "loss": 0.6017,
+      "mean_token_accuracy": 0.7670351922512054,
+      "num_tokens": 2680946.0,
+      "step": 1310
+    },
+    {
+      "epoch": 1.9383259911894273,
+      "grad_norm": 0.6080910563468933,
+      "learning_rate": 9.446568724377157e-05,
+      "loss": 0.624,
+      "mean_token_accuracy": 0.759852945804596,
+      "num_tokens": 2701426.0,
+      "step": 1320
+    },
+    {
+      "epoch": 1.9530102790014685,
+      "grad_norm": 0.5421401858329773,
+      "learning_rate": 9.43541227795091e-05,
+      "loss": 0.609,
+      "mean_token_accuracy": 0.7649999976158142,
+      "num_tokens": 2721906.0,
+      "step": 1330
+    },
+    {
+      "epoch": 1.9676945668135095,
+      "grad_norm": 0.5317767262458801,
+      "learning_rate": 9.424151225045739e-05,
+      "loss": 0.6176,
+      "mean_token_accuracy": 0.7620986700057983,
+      "num_tokens": 2742354.0,
+      "step": 1340
+    },
+    {
+      "epoch": 1.9823788546255505,
+      "grad_norm": 0.5858188271522522,
+      "learning_rate": 9.412785831246673e-05,
+      "loss": 0.6202,
+      "mean_token_accuracy": 0.7616176605224609,
+      "num_tokens": 2762834.0,
+      "step": 1350
+    },
+    {
+      "epoch": 1.9970631424375918,
+      "grad_norm": 0.5256847739219666,
+      "learning_rate": 9.401316364599555e-05,
+      "loss": 0.6203,
+      "mean_token_accuracy": 0.7609804034233093,
+      "num_tokens": 2783314.0,
+      "step": 1360
+    },
+    {
+      "epoch": 2.011747430249633,
+      "grad_norm": 0.550944447517395,
+      "learning_rate": 9.38974309560472e-05,
+      "loss": 0.5797,
+      "mean_token_accuracy": 0.7753431320190429,
+      "num_tokens": 2803794.0,
+      "step": 1370
+    },
+    {
+      "epoch": 2.026431718061674,
+      "grad_norm": 0.5684255361557007,
+      "learning_rate": 9.378066297210626e-05,
+      "loss": 0.5937,
+      "mean_token_accuracy": 0.7721078515052795,
+      "num_tokens": 2824274.0,
+      "step": 1380
+    },
+    {
+      "epoch": 2.041116005873715,
+      "grad_norm": 0.5539990663528442,
+      "learning_rate": 9.3662862448074e-05,
+      "loss": 0.5736,
+      "mean_token_accuracy": 0.7790686249732971,
+      "num_tokens": 2844754.0,
+      "step": 1390
+    },
+    {
+      "epoch": 2.0558002936857562,
+      "grad_norm": 0.5530731081962585,
+      "learning_rate": 9.354403216220356e-05,
+      "loss": 0.5779,
+      "mean_token_accuracy": 0.7777450978755951,
+      "num_tokens": 2865234.0,
+      "step": 1400
+    },
+    {
+      "epoch": 2.0704845814977975,
+      "grad_norm": 0.7104700207710266,
+      "learning_rate": 9.342417491703437e-05,
+      "loss": 0.5739,
+      "mean_token_accuracy": 0.7786274552345276,
+      "num_tokens": 2885714.0,
+      "step": 1410
+    },
+    {
+      "epoch": 2.0851688693098387,
+      "grad_norm": 0.6746625304222107,
+      "learning_rate": 9.330329353932605e-05,
+      "loss": 0.5858,
+      "mean_token_accuracy": 0.7741674959659577,
+      "num_tokens": 2906095.0,
+      "step": 1420
+    },
+    {
+      "epoch": 2.0998531571218795,
+      "grad_norm": 0.5403460264205933,
+      "learning_rate": 9.31813908799918e-05,
+      "loss": 0.6028,
+      "mean_token_accuracy": 0.7677451014518738,
+      "num_tokens": 2926575.0,
+      "step": 1430
+    },
+    {
+      "epoch": 2.1145374449339207,
+      "grad_norm": 0.6738181114196777,
+      "learning_rate": 9.305846981403108e-05,
+      "loss": 0.5969,
+      "mean_token_accuracy": 0.769019615650177,
+      "num_tokens": 2947055.0,
+      "step": 1440
+    },
+    {
+      "epoch": 2.129221732745962,
+      "grad_norm": 0.6410481929779053,
+      "learning_rate": 9.293453324046184e-05,
+      "loss": 0.5912,
+      "mean_token_accuracy": 0.7737745106220245,
+      "num_tokens": 2967535.0,
+      "step": 1450
+    },
+    {
+      "epoch": 2.1439060205580027,
+      "grad_norm": 0.603144645690918,
+      "learning_rate": 9.28095840822522e-05,
+      "loss": 0.5981,
+      "mean_token_accuracy": 0.7708823561668396,
+      "num_tokens": 2988015.0,
+      "step": 1460
+    },
+    {
+      "epoch": 2.158590308370044,
+      "grad_norm": 0.6693764328956604,
+      "learning_rate": 9.268362528625143e-05,
+      "loss": 0.5893,
+      "mean_token_accuracy": 0.7714215636253356,
+      "num_tokens": 3008495.0,
+      "step": 1470
+    },
+    {
+      "epoch": 2.173274596182085,
+      "grad_norm": 0.7435688376426697,
+      "learning_rate": 9.255665982312051e-05,
+      "loss": 0.5876,
+      "mean_token_accuracy": 0.7747548997402192,
+      "num_tokens": 3028975.0,
+      "step": 1480
+    },
+    {
+      "epoch": 2.1879588839941264,
+      "grad_norm": 0.6606314182281494,
+      "learning_rate": 9.242869068726203e-05,
+      "loss": 0.5874,
+      "mean_token_accuracy": 0.7729901850223542,
+      "num_tokens": 3049455.0,
+      "step": 1490
+    },
+    {
+      "epoch": 2.202643171806167,
+      "grad_norm": 0.6513794660568237,
+      "learning_rate": 9.229972089674958e-05,
+      "loss": 0.5966,
+      "mean_token_accuracy": 0.7689705848693847,
+      "num_tokens": 3069935.0,
+      "step": 1500
+    },
+    {
+      "epoch": 2.2173274596182084,
+      "grad_norm": 0.6829274892807007,
+      "learning_rate": 9.21697534932566e-05,
+      "loss": 0.5921,
+      "mean_token_accuracy": 0.774656867980957,
+      "num_tokens": 3090415.0,
+      "step": 1510
+    },
+    {
+      "epoch": 2.2320117474302497,
+      "grad_norm": 0.7045487761497498,
+      "learning_rate": 9.203879154198463e-05,
+      "loss": 0.5974,
+      "mean_token_accuracy": 0.7675490260124207,
+      "num_tokens": 3110895.0,
+      "step": 1520
+    },
+    {
+      "epoch": 2.246696035242291,
+      "grad_norm": 0.7174296379089355,
+      "learning_rate": 9.190683813159096e-05,
+      "loss": 0.592,
+      "mean_token_accuracy": 0.7730392098426819,
+      "num_tokens": 3131375.0,
+      "step": 1530
+    },
+    {
+      "epoch": 2.2613803230543317,
+      "grad_norm": 0.5941780209541321,
+      "learning_rate": 9.177389637411586e-05,
+      "loss": 0.5906,
+      "mean_token_accuracy": 0.7713007450103759,
+      "num_tokens": 3151734.0,
+      "step": 1540
+    },
+    {
+      "epoch": 2.276064610866373,
+      "grad_norm": 0.7417426705360413,
+      "learning_rate": 9.163996940490919e-05,
+      "loss": 0.5997,
+      "mean_token_accuracy": 0.7695588171482086,
+      "num_tokens": 3172214.0,
+      "step": 1550
+    },
+    {
+      "epoch": 2.290748898678414,
+      "grad_norm": 0.645305871963501,
+      "learning_rate": 9.150506038255639e-05,
+      "loss": 0.6148,
+      "mean_token_accuracy": 0.7645098030567169,
+      "num_tokens": 3192694.0,
+      "step": 1560
+    },
+    {
+      "epoch": 2.3054331864904554,
+      "grad_norm": 0.675000011920929,
+      "learning_rate": 9.136917248880403e-05,
+      "loss": 0.6115,
+      "mean_token_accuracy": 0.7670098125934601,
+      "num_tokens": 3213174.0,
+      "step": 1570
+    },
+    {
+      "epoch": 2.320117474302496,
+      "grad_norm": 0.8232929110527039,
+      "learning_rate": 9.123230892848476e-05,
+      "loss": 0.6013,
+      "mean_token_accuracy": 0.7694117724895477,
+      "num_tokens": 3233654.0,
+      "step": 1580
+    },
+    {
+      "epoch": 2.3348017621145374,
+      "grad_norm": 0.8386849761009216,
+      "learning_rate": 9.109447292944172e-05,
+      "loss": 0.5906,
+      "mean_token_accuracy": 0.7733310997486115,
+      "num_tokens": 3254030.0,
+      "step": 1590
+    },
+    {
+      "epoch": 2.3494860499265786,
+      "grad_norm": 0.5846053957939148,
+      "learning_rate": 9.095566774245245e-05,
+      "loss": 0.5799,
+      "mean_token_accuracy": 0.7751470506191254,
+      "num_tokens": 3274510.0,
+      "step": 1600
+    },
+    {
+      "epoch": 2.36417033773862,
+      "grad_norm": 0.6155494451522827,
+      "learning_rate": 9.081589664115216e-05,
+      "loss": 0.5874,
+      "mean_token_accuracy": 0.7761764764785767,
+      "num_tokens": 3294990.0,
+      "step": 1610
+    },
+    {
+      "epoch": 2.3788546255506606,
+      "grad_norm": 0.6446321606636047,
+      "learning_rate": 9.067516292195659e-05,
+      "loss": 0.589,
+      "mean_token_accuracy": 0.7732843041419983,
+      "num_tokens": 3315470.0,
+      "step": 1620
+    },
+    {
+      "epoch": 2.393538913362702,
+      "grad_norm": 0.5833125114440918,
+      "learning_rate": 9.053346990398418e-05,
+      "loss": 0.5905,
+      "mean_token_accuracy": 0.7725448489189148,
+      "num_tokens": 3335790.0,
+      "step": 1630
+    },
+    {
+      "epoch": 2.408223201174743,
+      "grad_norm": 0.5974801778793335,
+      "learning_rate": 9.03908209289779e-05,
+      "loss": 0.5928,
+      "mean_token_accuracy": 0.7697549045085907,
+      "num_tokens": 3356270.0,
+      "step": 1640
+    },
+    {
+      "epoch": 2.4229074889867843,
+      "grad_norm": 0.674152672290802,
+      "learning_rate": 9.024721936122637e-05,
+      "loss": 0.579,
+      "mean_token_accuracy": 0.7773039281368256,
+      "num_tokens": 3376750.0,
+      "step": 1650
+    },
+    {
+      "epoch": 2.437591776798825,
+      "grad_norm": 0.6326053142547607,
+      "learning_rate": 9.01026685874845e-05,
+      "loss": 0.5947,
+      "mean_token_accuracy": 0.7713235318660736,
+      "num_tokens": 3397230.0,
+      "step": 1660
+    },
+    {
+      "epoch": 2.4522760646108663,
+      "grad_norm": 0.9275988936424255,
+      "learning_rate": 8.995717201689364e-05,
+      "loss": 0.6013,
+      "mean_token_accuracy": 0.7695053398609162,
+      "num_tokens": 3417688.0,
+      "step": 1670
+    },
+    {
+      "epoch": 2.4669603524229076,
+      "grad_norm": 0.9451805353164673,
+      "learning_rate": 8.981073308090121e-05,
+      "loss": 0.5935,
+      "mean_token_accuracy": 0.7727451086044311,
+      "num_tokens": 3438168.0,
+      "step": 1680
+    },
+    {
+      "epoch": 2.481644640234949,
+      "grad_norm": 0.7964608669281006,
+      "learning_rate": 8.966335523317973e-05,
+      "loss": 0.6065,
+      "mean_token_accuracy": 0.7658823549747467,
+      "num_tokens": 3458648.0,
+      "step": 1690
+    },
+    {
+      "epoch": 2.4963289280469896,
+      "grad_norm": 0.7540594935417175,
+      "learning_rate": 8.951504194954536e-05,
+      "loss": 0.593,
+      "mean_token_accuracy": 0.7717647135257721,
+      "num_tokens": 3479128.0,
+      "step": 1700
+    },
+    {
+      "epoch": 2.511013215859031,
+      "grad_norm": 0.6480241417884827,
+      "learning_rate": 8.936579672787594e-05,
+      "loss": 0.6103,
+      "mean_token_accuracy": 0.7662254810333252,
+      "num_tokens": 3499608.0,
+      "step": 1710
+    },
+    {
+      "epoch": 2.525697503671072,
+      "grad_norm": 0.58002769947052,
+      "learning_rate": 8.921562308802854e-05,
+      "loss": 0.5903,
+      "mean_token_accuracy": 0.7746568620204926,
+      "num_tokens": 3520088.0,
+      "step": 1720
+    },
+    {
+      "epoch": 2.540381791483113,
+      "grad_norm": 0.6285786628723145,
+      "learning_rate": 8.906452457175635e-05,
+      "loss": 0.5971,
+      "mean_token_accuracy": 0.7731372594833374,
+      "num_tokens": 3540568.0,
+      "step": 1730
+    },
+    {
+      "epoch": 2.555066079295154,
+      "grad_norm": 0.7330060601234436,
+      "learning_rate": 8.891250474262526e-05,
+      "loss": 0.597,
+      "mean_token_accuracy": 0.7697058916091919,
+      "num_tokens": 3561048.0,
+      "step": 1740
+    },
+    {
+      "epoch": 2.5697503671071953,
+      "grad_norm": 0.8705717921257019,
+      "learning_rate": 8.875956718592969e-05,
+      "loss": 0.5991,
+      "mean_token_accuracy": 0.771127450466156,
+      "num_tokens": 3581528.0,
+      "step": 1750
+    },
+    {
+      "epoch": 2.5844346549192365,
+      "grad_norm": 0.6374325752258301,
+      "learning_rate": 8.860571550860817e-05,
+      "loss": 0.6011,
+      "mean_token_accuracy": 0.7709877014160156,
+      "num_tokens": 3601919.0,
+      "step": 1760
+    },
+    {
+      "epoch": 2.5991189427312777,
+      "grad_norm": 0.5832578539848328,
+      "learning_rate": 8.845095333915814e-05,
+      "loss": 0.598,
+      "mean_token_accuracy": 0.7690686225891114,
+      "num_tokens": 3622399.0,
+      "step": 1770
+    },
+    {
+      "epoch": 2.6138032305433185,
+      "grad_norm": 0.7307887673377991,
+      "learning_rate": 8.829528432755047e-05,
+      "loss": 0.5943,
+      "mean_token_accuracy": 0.7725000083446503,
+      "num_tokens": 3642879.0,
+      "step": 1780
+    },
+    {
+      "epoch": 2.6284875183553598,
+      "grad_norm": 0.5733655691146851,
+      "learning_rate": 8.81387121451434e-05,
+      "loss": 0.5906,
+      "mean_token_accuracy": 0.7725490212440491,
+      "num_tokens": 3663359.0,
+      "step": 1790
+    },
+    {
+      "epoch": 2.643171806167401,
+      "grad_norm": 0.7298516631126404,
+      "learning_rate": 8.798124048459579e-05,
+      "loss": 0.5962,
+      "mean_token_accuracy": 0.7727451086044311,
+      "num_tokens": 3683839.0,
+      "step": 1800
+    },
+    {
+      "epoch": 2.657856093979442,
+      "grad_norm": 0.6217687726020813,
+      "learning_rate": 8.782287305978023e-05,
+      "loss": 0.5953,
+      "mean_token_accuracy": 0.7705882310867309,
+      "num_tokens": 3704319.0,
+      "step": 1810
+    },
+    {
+      "epoch": 2.672540381791483,
+      "grad_norm": 0.7209094166755676,
+      "learning_rate": 8.766361360569531e-05,
+      "loss": 0.5824,
+      "mean_token_accuracy": 0.7764705955982208,
+      "num_tokens": 3724799.0,
+      "step": 1820
+    },
+    {
+      "epoch": 2.6872246696035242,
+      "grad_norm": 0.7357442378997803,
+      "learning_rate": 8.750346587837762e-05,
+      "loss": 0.6124,
+      "mean_token_accuracy": 0.7663725554943085,
+      "num_tokens": 3745279.0,
+      "step": 1830
+    },
+    {
+      "epoch": 2.7019089574155655,
+      "grad_norm": 0.5689270496368408,
+      "learning_rate": 8.734243365481307e-05,
+      "loss": 0.5754,
+      "mean_token_accuracy": 0.7779902040958404,
+      "num_tokens": 3765759.0,
+      "step": 1840
+    },
+    {
+      "epoch": 2.7165932452276067,
+      "grad_norm": 0.543701171875,
+      "learning_rate": 8.718052073284797e-05,
+      "loss": 0.6025,
+      "mean_token_accuracy": 0.7700490236282349,
+      "num_tokens": 3786239.0,
+      "step": 1850
+    },
+    {
+      "epoch": 2.7312775330396475,
+      "grad_norm": 0.7923574447631836,
+      "learning_rate": 8.701773093109928e-05,
+      "loss": 0.5983,
+      "mean_token_accuracy": 0.7687254965305328,
+      "num_tokens": 3806719.0,
+      "step": 1860
+    },
+    {
+      "epoch": 2.7459618208516887,
+      "grad_norm": 0.8049069046974182,
+      "learning_rate": 8.685406808886464e-05,
+      "loss": 0.5885,
+      "mean_token_accuracy": 0.7746568620204926,
+      "num_tokens": 3827199.0,
+      "step": 1870
+    },
+    {
+      "epoch": 2.76064610866373,
+      "grad_norm": 0.7629956603050232,
+      "learning_rate": 8.668953606603188e-05,
+      "loss": 0.6193,
+      "mean_token_accuracy": 0.761813735961914,
+      "num_tokens": 3847679.0,
+      "step": 1880
+    },
+    {
+      "epoch": 2.7753303964757707,
+      "grad_norm": 0.6295118927955627,
+      "learning_rate": 8.652413874298782e-05,
+      "loss": 0.5955,
+      "mean_token_accuracy": 0.7699999988079071,
+      "num_tokens": 3868159.0,
+      "step": 1890
+    },
+    {
+      "epoch": 2.790014684287812,
+      "grad_norm": 0.5915569067001343,
+      "learning_rate": 8.635788002052691e-05,
+      "loss": 0.6096,
+      "mean_token_accuracy": 0.7661764740943908,
+      "num_tokens": 3888639.0,
+      "step": 1900
+    },
+    {
+      "epoch": 2.804698972099853,
+      "grad_norm": 0.559986412525177,
+      "learning_rate": 8.619076381975922e-05,
+      "loss": 0.5988,
+      "mean_token_accuracy": 0.7696575880050659,
+      "num_tokens": 3908965.0,
+      "step": 1910
+    },
+    {
+      "epoch": 2.8193832599118944,
+      "grad_norm": 0.6710847616195679,
+      "learning_rate": 8.602279408201783e-05,
+      "loss": 0.5804,
+      "mean_token_accuracy": 0.7760784268379212,
+      "num_tokens": 3929445.0,
+      "step": 1920
+    },
+    {
+      "epoch": 2.8340675477239357,
+      "grad_norm": 0.6383255124092102,
+      "learning_rate": 8.585397476876602e-05,
+      "loss": 0.5799,
+      "mean_token_accuracy": 0.7754902064800262,
+      "num_tokens": 3949925.0,
+      "step": 1930
+    },
+    {
+      "epoch": 2.8487518355359764,
+      "grad_norm": 0.7135127186775208,
+      "learning_rate": 8.56843098615038e-05,
+      "loss": 0.5865,
+      "mean_token_accuracy": 0.7747548937797546,
+      "num_tokens": 3970405.0,
+      "step": 1940
+    },
+    {
+      "epoch": 2.8634361233480177,
+      "grad_norm": 0.6053532361984253,
+      "learning_rate": 8.551380336167396e-05,
+      "loss": 0.5981,
+      "mean_token_accuracy": 0.769705879688263,
+      "num_tokens": 3990885.0,
+      "step": 1950
+    },
+    {
+      "epoch": 2.878120411160059,
+      "grad_norm": 0.6343899369239807,
+      "learning_rate": 8.534245929056776e-05,
+      "loss": 0.5857,
+      "mean_token_accuracy": 0.7750490307807922,
+      "num_tokens": 4011365.0,
+      "step": 1960
+    },
+    {
+      "epoch": 2.8928046989720997,
+      "grad_norm": 0.5568163394927979,
+      "learning_rate": 8.517028168923002e-05,
+      "loss": 0.5797,
+      "mean_token_accuracy": 0.7752941131591797,
+      "num_tokens": 4031845.0,
+      "step": 1970
+    },
+    {
+      "epoch": 2.907488986784141,
+      "grad_norm": 0.549111008644104,
+      "learning_rate": 8.499727461836395e-05,
+      "loss": 0.5979,
+      "mean_token_accuracy": 0.7684820890426636,
+      "num_tokens": 4052248.0,
+      "step": 1980
+    },
+    {
+      "epoch": 2.922173274596182,
+      "grad_norm": 0.7707120776176453,
+      "learning_rate": 8.48234421582352e-05,
+      "loss": 0.5789,
+      "mean_token_accuracy": 0.7774509847164154,
+      "num_tokens": 4072728.0,
+      "step": 1990
+    },
+    {
+      "epoch": 2.936857562408223,
+      "grad_norm": 0.6881651878356934,
+      "learning_rate": 8.464878840857574e-05,
+      "loss": 0.6027,
+      "mean_token_accuracy": 0.766813725233078,
+      "num_tokens": 4093208.0,
+      "step": 2000
+    },
+    {
+      "epoch": 2.951541850220264,
+      "grad_norm": 0.7717125415802002,
+      "learning_rate": 8.447331748848718e-05,
+      "loss": 0.5836,
+      "mean_token_accuracy": 0.7729411721229553,
+      "num_tokens": 4113688.0,
+      "step": 2010
+    },
+    {
+      "epoch": 2.9662261380323054,
+      "grad_norm": 0.6662061810493469,
+      "learning_rate": 8.429703353634357e-05,
+      "loss": 0.5997,
+      "mean_token_accuracy": 0.7697549045085907,
+      "num_tokens": 4134168.0,
+      "step": 2020
+    },
+    {
+      "epoch": 2.9809104258443466,
+      "grad_norm": 0.8073809146881104,
+      "learning_rate": 8.411994070969386e-05,
+      "loss": 0.59,
+      "mean_token_accuracy": 0.7718137264251709,
+      "num_tokens": 4154648.0,
+      "step": 2030
+    },
+    {
+      "epoch": 2.995594713656388,
+      "grad_norm": 0.6692283153533936,
+      "learning_rate": 8.394204318516374e-05,
+      "loss": 0.5857,
+      "mean_token_accuracy": 0.7729605972766876,
+      "num_tokens": 4174971.0,
+      "step": 2040
+    },
+    {
+      "epoch": 3.0102790014684286,
+      "grad_norm": 0.7445379495620728,
+      "learning_rate": 8.376334515835726e-05,
+      "loss": 0.5919,
+      "mean_token_accuracy": 0.7757352948188782,
+      "num_tokens": 4195451.0,
+      "step": 2050
+    },
+    {
+      "epoch": 3.02496328928047,
+      "grad_norm": 0.8607472777366638,
+      "learning_rate": 8.358385084375781e-05,
+      "loss": 0.5769,
+      "mean_token_accuracy": 0.778333330154419,
+      "num_tokens": 4215931.0,
+      "step": 2060
+    },
+    {
+      "epoch": 3.039647577092511,
+      "grad_norm": 0.806833803653717,
+      "learning_rate": 8.340356447462876e-05,
+      "loss": 0.5565,
+      "mean_token_accuracy": 0.7870588302612305,
+      "num_tokens": 4236411.0,
+      "step": 2070
+    },
+    {
+      "epoch": 3.0543318649045523,
+      "grad_norm": 0.7553666830062866,
+      "learning_rate": 8.322249030291356e-05,
+      "loss": 0.5553,
+      "mean_token_accuracy": 0.7866666615009308,
+      "num_tokens": 4256891.0,
+      "step": 2080
+    },
+    {
+      "epoch": 3.069016152716593,
+      "grad_norm": 0.6877645254135132,
+      "learning_rate": 8.30406325991355e-05,
+      "loss": 0.5624,
+      "mean_token_accuracy": 0.7857353031635285,
+      "num_tokens": 4277371.0,
+      "step": 2090
+    },
+    {
+      "epoch": 3.0837004405286343,
+      "grad_norm": 0.7888927459716797,
+      "learning_rate": 8.285799565229706e-05,
+      "loss": 0.5458,
+      "mean_token_accuracy": 0.7912745118141175,
+      "num_tokens": 4297851.0,
+      "step": 2100
+    },
+    {
+      "epoch": 3.0983847283406756,
+      "grad_norm": 0.9763121604919434,
+      "learning_rate": 8.267458376977861e-05,
+      "loss": 0.5519,
+      "mean_token_accuracy": 0.7874019622802735,
+      "num_tokens": 4318331.0,
+      "step": 2110
+    },
+    {
+      "epoch": 3.113069016152717,
+      "grad_norm": 0.6729934215545654,
+      "learning_rate": 8.249040127723695e-05,
+      "loss": 0.5441,
+      "mean_token_accuracy": 0.7899011552333832,
+      "num_tokens": 4338654.0,
+      "step": 2120
+    },
+    {
+      "epoch": 3.1277533039647576,
+      "grad_norm": 0.7944905161857605,
+      "learning_rate": 8.230545251850324e-05,
+      "loss": 0.5748,
+      "mean_token_accuracy": 0.7788600981235504,
+      "num_tokens": 4359045.0,
+      "step": 2130
+    },
+    {
+      "epoch": 3.142437591776799,
+      "grad_norm": 0.7210076451301575,
+      "learning_rate": 8.211974185548052e-05,
+      "loss": 0.5653,
+      "mean_token_accuracy": 0.7825490176677704,
+      "num_tokens": 4379525.0,
+      "step": 2140
+    },
+    {
+      "epoch": 3.15712187958884,
+      "grad_norm": 0.8901041746139526,
+      "learning_rate": 8.193327366804094e-05,
+      "loss": 0.5551,
+      "mean_token_accuracy": 0.7878921627998352,
+      "num_tokens": 4400005.0,
+      "step": 2150
+    },
+    {
+      "epoch": 3.171806167400881,
+      "grad_norm": 0.7609846591949463,
+      "learning_rate": 8.174605235392234e-05,
+      "loss": 0.5582,
+      "mean_token_accuracy": 0.7842067062854767,
+      "num_tokens": 4420264.0,
+      "step": 2160
+    },
+    {
+      "epoch": 3.186490455212922,
+      "grad_norm": 0.9557706713676453,
+      "learning_rate": 8.155808232862462e-05,
+      "loss": 0.5605,
+      "mean_token_accuracy": 0.7852451026439666,
+      "num_tokens": 4440744.0,
+      "step": 2170
+    },
+    {
+      "epoch": 3.2011747430249633,
+      "grad_norm": 0.8045010566711426,
+      "learning_rate": 8.13693680253056e-05,
+      "loss": 0.5624,
+      "mean_token_accuracy": 0.784852945804596,
+      "num_tokens": 4461224.0,
+      "step": 2180
+    },
+    {
+      "epoch": 3.2158590308370045,
+      "grad_norm": 0.8936928510665894,
+      "learning_rate": 8.117991389467637e-05,
+      "loss": 0.5761,
+      "mean_token_accuracy": 0.7834313690662384,
+      "num_tokens": 4481704.0,
+      "step": 2190
+    },
+    {
+      "epoch": 3.2305433186490453,
+      "grad_norm": 0.8331916332244873,
+      "learning_rate": 8.098972440489644e-05,
+      "loss": 0.5488,
+      "mean_token_accuracy": 0.7888725459575653,
+      "num_tokens": 4502184.0,
+      "step": 2200
+    },
+    {
+      "epoch": 3.2452276064610865,
+      "grad_norm": 0.9143285155296326,
+      "learning_rate": 8.079880404146833e-05,
+      "loss": 0.5576,
+      "mean_token_accuracy": 0.7834803938865662,
+      "num_tokens": 4522664.0,
+      "step": 2210
+    },
+    {
+      "epoch": 3.2599118942731278,
+      "grad_norm": 0.6985664963722229,
+      "learning_rate": 8.060715730713173e-05,
+      "loss": 0.5574,
+      "mean_token_accuracy": 0.7850980341434479,
+      "num_tokens": 4543144.0,
+      "step": 2220
+    },
+    {
+      "epoch": 3.274596182085169,
+      "grad_norm": 0.8404681086540222,
+      "learning_rate": 8.041478872175736e-05,
+      "loss": 0.5641,
+      "mean_token_accuracy": 0.7834803879261016,
+      "num_tokens": 4563624.0,
+      "step": 2230
+    },
+    {
+      "epoch": 3.28928046989721,
+      "grad_norm": 0.8397653698921204,
+      "learning_rate": 8.022170282224035e-05,
+      "loss": 0.5471,
+      "mean_token_accuracy": 0.7898368597030639,
+      "num_tokens": 4584082.0,
+      "step": 2240
+    },
+    {
+      "epoch": 3.303964757709251,
+      "grad_norm": 0.8517851829528809,
+      "learning_rate": 8.002790416239326e-05,
+      "loss": 0.5712,
+      "mean_token_accuracy": 0.7824019610881805,
+      "num_tokens": 4604562.0,
+      "step": 2250
+    },
+    {
+      "epoch": 3.3186490455212923,
+      "grad_norm": 0.8386510014533997,
+      "learning_rate": 7.983339731283861e-05,
+      "loss": 0.5565,
+      "mean_token_accuracy": 0.7859313786029816,
+      "num_tokens": 4625042.0,
+      "step": 2260
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.6675034761428833,
+      "learning_rate": 7.963818686090125e-05,
+      "loss": 0.547,
+      "mean_token_accuracy": 0.7906862795352936,
+      "num_tokens": 4645522.0,
+      "step": 2270
+    },
+    {
+      "epoch": 3.3480176211453743,
+      "grad_norm": 0.8069822788238525,
+      "learning_rate": 7.944227741049992e-05,
+      "loss": 0.565,
+      "mean_token_accuracy": 0.7823039293289185,
+      "num_tokens": 4666002.0,
+      "step": 2280
+    },
+    {
+      "epoch": 3.3627019089574155,
+      "grad_norm": 0.7937156558036804,
+      "learning_rate": 7.924567358203893e-05,
+      "loss": 0.5471,
+      "mean_token_accuracy": 0.7883833944797516,
+      "num_tokens": 4686322.0,
+      "step": 2290
+    },
+    {
+      "epoch": 3.3773861967694567,
+      "grad_norm": 0.9723342657089233,
+      "learning_rate": 7.904838001229902e-05,
+      "loss": 0.5613,
+      "mean_token_accuracy": 0.7817156851291657,
+      "num_tokens": 4706802.0,
+      "step": 2300
+    },
+    {
+      "epoch": 3.392070484581498,
+      "grad_norm": 0.9010858535766602,
+      "learning_rate": 7.885040135432803e-05,
+      "loss": 0.5599,
+      "mean_token_accuracy": 0.7837745130062104,
+      "num_tokens": 4727282.0,
+      "step": 2310
+    },
+    {
+      "epoch": 3.4067547723935387,
+      "grad_norm": 1.0012130737304688,
+      "learning_rate": 7.865174227733124e-05,
+      "loss": 0.5633,
+      "mean_token_accuracy": 0.7831372618675232,
+      "num_tokens": 4747762.0,
+      "step": 2320
+    },
+    {
+      "epoch": 3.42143906020558,
+      "grad_norm": 0.9231986999511719,
+      "learning_rate": 7.845240746656116e-05,
+      "loss": 0.5599,
+      "mean_token_accuracy": 0.7850000083446502,
+      "num_tokens": 4768242.0,
+      "step": 2330
+    },
+    {
+      "epoch": 3.436123348017621,
+      "grad_norm": 0.6982397437095642,
+      "learning_rate": 7.825240162320707e-05,
+      "loss": 0.5457,
+      "mean_token_accuracy": 0.789705890417099,
+      "num_tokens": 4788722.0,
+      "step": 2340
+    },
+    {
+      "epoch": 3.4508076358296624,
+      "grad_norm": 0.9564845561981201,
+      "learning_rate": 7.805172946428416e-05,
+      "loss": 0.5669,
+      "mean_token_accuracy": 0.7831235706806183,
+      "num_tokens": 4809125.0,
+      "step": 2350
+    },
+    {
+      "epoch": 3.465491923641703,
+      "grad_norm": 1.016622543334961,
+      "learning_rate": 7.785039572252226e-05,
+      "loss": 0.5484,
+      "mean_token_accuracy": 0.7899509787559509,
+      "num_tokens": 4829605.0,
+      "step": 2360
+    },
+    {
+      "epoch": 3.4801762114537445,
+      "grad_norm": 0.8882852792739868,
+      "learning_rate": 7.76484051462542e-05,
+      "loss": 0.5574,
+      "mean_token_accuracy": 0.7854411780834198,
+      "num_tokens": 4850085.0,
+      "step": 2370
+    },
+    {
+      "epoch": 3.4948604992657857,
+      "grad_norm": 0.718890368938446,
+      "learning_rate": 7.744576249930386e-05,
+      "loss": 0.5588,
+      "mean_token_accuracy": 0.7816176533699035,
+      "num_tokens": 4870565.0,
+      "step": 2380
+    },
+    {
+      "epoch": 3.509544787077827,
+      "grad_norm": 0.8828749060630798,
+      "learning_rate": 7.724247256087384e-05,
+      "loss": 0.5542,
+      "mean_token_accuracy": 0.7838235199451447,
+      "num_tokens": 4891045.0,
+      "step": 2390
+    },
+    {
+      "epoch": 3.5242290748898677,
+      "grad_norm": 0.8082349300384521,
+      "learning_rate": 7.703854012543266e-05,
+      "loss": 0.5468,
+      "mean_token_accuracy": 0.7892647027969361,
+      "num_tokens": 4911525.0,
+      "step": 2400
+    },
+    {
+      "epoch": 3.538913362701909,
+      "grad_norm": 0.9021029472351074,
+      "learning_rate": 7.68339700026018e-05,
+      "loss": 0.5555,
+      "mean_token_accuracy": 0.7868627548217774,
+      "num_tokens": 4932005.0,
+      "step": 2410
+    },
+    {
+      "epoch": 3.55359765051395,
+      "grad_norm": 0.8278372883796692,
+      "learning_rate": 7.662876701704214e-05,
+      "loss": 0.5493,
+      "mean_token_accuracy": 0.7884313702583313,
+      "num_tokens": 4952485.0,
+      "step": 2420
+    },
+    {
+      "epoch": 3.568281938325991,
+      "grad_norm": 0.7349909543991089,
+      "learning_rate": 7.64229360083403e-05,
+      "loss": 0.5568,
+      "mean_token_accuracy": 0.7873529434204102,
+      "num_tokens": 4972965.0,
+      "step": 2430
+    },
+    {
+      "epoch": 3.582966226138032,
+      "grad_norm": 0.807925820350647,
+      "learning_rate": 7.621648183089439e-05,
+      "loss": 0.565,
+      "mean_token_accuracy": 0.7818137228488922,
+      "num_tokens": 4993445.0,
+      "step": 2440
+    },
+    {
+      "epoch": 3.5976505139500734,
+      "grad_norm": 0.7990140914916992,
+      "learning_rate": 7.600940935379957e-05,
+      "loss": 0.5568,
+      "mean_token_accuracy": 0.7867647051811218,
+      "num_tokens": 5013925.0,
+      "step": 2450
+    },
+    {
+      "epoch": 3.6123348017621146,
+      "grad_norm": 0.8395295143127441,
+      "learning_rate": 7.580172346073328e-05,
+      "loss": 0.5521,
+      "mean_token_accuracy": 0.7903431355953217,
+      "num_tokens": 5034405.0,
+      "step": 2460
+    },
+    {
+      "epoch": 3.627019089574156,
+      "grad_norm": 0.9869875311851501,
+      "learning_rate": 7.559342904983996e-05,
+      "loss": 0.5674,
+      "mean_token_accuracy": 0.7835294127464294,
+      "num_tokens": 5054885.0,
+      "step": 2470
+    },
+    {
+      "epoch": 3.6417033773861966,
+      "grad_norm": 0.9769387245178223,
+      "learning_rate": 7.538453103361557e-05,
+      "loss": 0.551,
+      "mean_token_accuracy": 0.7895098090171814,
+      "num_tokens": 5075365.0,
+      "step": 2480
+    },
+    {
+      "epoch": 3.656387665198238,
+      "grad_norm": 0.9901081919670105,
+      "learning_rate": 7.51750343387917e-05,
+      "loss": 0.5657,
+      "mean_token_accuracy": 0.7828683078289032,
+      "num_tokens": 5095692.0,
+      "step": 2490
+    },
+    {
+      "epoch": 3.671071953010279,
+      "grad_norm": 0.8940699696540833,
+      "learning_rate": 7.496494390621949e-05,
+      "loss": 0.5706,
+      "mean_token_accuracy": 0.7809803903102874,
+      "num_tokens": 5116172.0,
+      "step": 2500
+    },
+    {
+      "epoch": 3.68575624082232,
+      "grad_norm": 0.7755618691444397,
+      "learning_rate": 7.475426469075294e-05,
+      "loss": 0.5652,
+      "mean_token_accuracy": 0.7830392241477966,
+      "num_tokens": 5136652.0,
+      "step": 2510
+    },
+    {
+      "epoch": 3.700440528634361,
+      "grad_norm": 0.7705824375152588,
+      "learning_rate": 7.454300166113218e-05,
+      "loss": 0.5777,
+      "mean_token_accuracy": 0.7779411792755127,
+      "num_tokens": 5157132.0,
+      "step": 2520
+    },
+    {
+      "epoch": 3.7151248164464024,
+      "grad_norm": 0.8891183137893677,
+      "learning_rate": 7.43311597998662e-05,
+      "loss": 0.5329,
+      "mean_token_accuracy": 0.7936274468898773,
+      "num_tokens": 5177612.0,
+      "step": 2530
+    },
+    {
+      "epoch": 3.7298091042584436,
+      "grad_norm": 0.750442385673523,
+      "learning_rate": 7.411874410311544e-05,
+      "loss": 0.5872,
+      "mean_token_accuracy": 0.7738725483417511,
+      "num_tokens": 5198092.0,
+      "step": 2540
+    },
+    {
+      "epoch": 3.744493392070485,
+      "grad_norm": 0.79774010181427,
+      "learning_rate": 7.390575958057383e-05,
+      "loss": 0.5435,
+      "mean_token_accuracy": 0.791813713312149,
+      "num_tokens": 5218572.0,
+      "step": 2550
+    },
+    {
+      "epoch": 3.7591776798825256,
+      "grad_norm": 0.8193868398666382,
+      "learning_rate": 7.369221125535075e-05,
+      "loss": 0.5446,
+      "mean_token_accuracy": 0.7921078443527222,
+      "num_tokens": 5239052.0,
+      "step": 2560
+    },
+    {
+      "epoch": 3.773861967694567,
+      "grad_norm": 0.7679403424263,
+      "learning_rate": 7.347810416385251e-05,
+      "loss": 0.5535,
+      "mean_token_accuracy": 0.7857843101024627,
+      "num_tokens": 5259532.0,
+      "step": 2570
+    },
+    {
+      "epoch": 3.788546255506608,
+      "grad_norm": 0.8320531845092773,
+      "learning_rate": 7.326344335566359e-05,
+      "loss": 0.5757,
+      "mean_token_accuracy": 0.7823039293289185,
+      "num_tokens": 5280012.0,
+      "step": 2580
+    },
+    {
+      "epoch": 3.803230543318649,
+      "grad_norm": 0.9579612612724304,
+      "learning_rate": 7.30482338934275e-05,
+      "loss": 0.5607,
+      "mean_token_accuracy": 0.7852450907230377,
+      "num_tokens": 5300492.0,
+      "step": 2590
+    },
+    {
+      "epoch": 3.81791483113069,
+      "grad_norm": 0.8408456444740295,
+      "learning_rate": 7.283248085272749e-05,
+      "loss": 0.5614,
+      "mean_token_accuracy": 0.7849019587039947,
+      "num_tokens": 5320972.0,
+      "step": 2600
+    },
+    {
+      "epoch": 3.8325991189427313,
+      "grad_norm": 0.8341405391693115,
+      "learning_rate": 7.26161893219667e-05,
+      "loss": 0.5524,
+      "mean_token_accuracy": 0.7872548937797547,
+      "num_tokens": 5341452.0,
+      "step": 2610
+    },
+    {
+      "epoch": 3.8472834067547725,
+      "grad_norm": 0.8393822312355042,
+      "learning_rate": 7.239936440224825e-05,
+      "loss": 0.5522,
+      "mean_token_accuracy": 0.7898529350757599,
+      "num_tokens": 5361932.0,
+      "step": 2620
+    },
+    {
+      "epoch": 3.8619676945668138,
+      "grad_norm": 0.9326363205909729,
+      "learning_rate": 7.218201120725495e-05,
+      "loss": 0.5631,
+      "mean_token_accuracy": 0.7835784196853638,
+      "num_tokens": 5382412.0,
+      "step": 2630
+    },
+    {
+      "epoch": 3.8766519823788546,
+      "grad_norm": 0.7576234936714172,
+      "learning_rate": 7.196413486312862e-05,
+      "loss": 0.5821,
+      "mean_token_accuracy": 0.7781862854957581,
+      "num_tokens": 5402892.0,
+      "step": 2640
+    },
+    {
+      "epoch": 3.891336270190896,
+      "grad_norm": 0.6815731525421143,
+      "learning_rate": 7.174574050834923e-05,
+      "loss": 0.5548,
+      "mean_token_accuracy": 0.7875490248203277,
+      "num_tokens": 5423372.0,
+      "step": 2650
+    },
+    {
+      "epoch": 3.906020558002937,
+      "grad_norm": 0.7920679450035095,
+      "learning_rate": 7.152683329361376e-05,
+      "loss": 0.569,
+      "mean_token_accuracy": 0.77955761551857,
+      "num_tokens": 5443748.0,
+      "step": 2660
+    },
+    {
+      "epoch": 3.920704845814978,
+      "grad_norm": 0.7348102927207947,
+      "learning_rate": 7.13074183817146e-05,
+      "loss": 0.5569,
+      "mean_token_accuracy": 0.7847058832645416,
+      "num_tokens": 5464228.0,
+      "step": 2670
+    },
+    {
+      "epoch": 3.935389133627019,
+      "grad_norm": 0.9041562080383301,
+      "learning_rate": 7.108750094741793e-05,
+      "loss": 0.5529,
+      "mean_token_accuracy": 0.788921570777893,
+      "num_tokens": 5484708.0,
+      "step": 2680
+    },
+    {
+      "epoch": 3.9500734214390603,
+      "grad_norm": 0.8101287484169006,
+      "learning_rate": 7.086708617734159e-05,
+      "loss": 0.5599,
+      "mean_token_accuracy": 0.7865196228027344,
+      "num_tokens": 5505188.0,
+      "step": 2690
+    },
+    {
+      "epoch": 3.964757709251101,
+      "grad_norm": 0.8553786277770996,
+      "learning_rate": 7.064617926983277e-05,
+      "loss": 0.5687,
+      "mean_token_accuracy": 0.7813725590705871,
+      "num_tokens": 5525668.0,
+      "step": 2700
+    },
+    {
+      "epoch": 3.9794419970631423,
+      "grad_norm": 0.7138819098472595,
+      "learning_rate": 7.042478543484546e-05,
+      "loss": 0.5629,
+      "mean_token_accuracy": 0.7855882406234741,
+      "num_tokens": 5546148.0,
+      "step": 2710
+    },
+    {
+      "epoch": 3.9941262848751835,
+      "grad_norm": 0.8690739870071411,
+      "learning_rate": 7.020290989381747e-05,
+      "loss": 0.5528,
+      "mean_token_accuracy": 0.7844117641448974,
+      "num_tokens": 5566628.0,
+      "step": 2720
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6810,
+  "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": 2.373470294774907e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2724/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac0efbafb523853fa46901df5567229595df957b581e4dee225a481543b5f51
+size 6289

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-3405/README.md

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-3405/adapter_config.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-3405/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc9903585c459cca3fc9e1477bd951cecd0bdcab151879c49336da66a61bd92d
+size 80792096

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-3405/added_tokens.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-3405/chat_template.jinja

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-3405/special_tokens_map.json

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

checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-3405/tokenizer.json

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