Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-1750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2190/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-7B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.16.0

adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15865247ad910ae584d24b575151e137dec2d53987a11d7af1ae4f40816988ee
+size 323014168

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
+}

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 %}

checkpoint-1750/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-7B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.16.0

checkpoint-1750/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1750/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aafd5ade4ccb4275127d605f1be8e2ac78ae04c7d484f9c4369a319ba3bb47d2
+size 323014168

checkpoint-1750/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
+}

checkpoint-1750/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 %}

checkpoint-1750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6dc4c8bbbff43046310ce557cb3b33fb8a1aa78a21fdca946b3d79c0d36939
+size 646253819

checkpoint-1750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2db4b81349a009d5616e865973dadbe8e372be654278278c73cc2b2eaa52ec
+size 14645

checkpoint-1750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399572d68a51a4203be8c991e01d70e9c4a78114f3ffd47fa5f8cabc00a75a1c
+size 1465

checkpoint-1750/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
+  }
+}

checkpoint-1750/tokenizer.json

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

checkpoint-1750/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": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1750/trainer_state.json

@@ -0,0 +1,1259 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9967138162594655,
+  "eval_steps": 500,
+  "global_step": 1750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022860408629804256,
+      "grad_norm": 0.31346356868743896,
+      "learning_rate": 4.10958904109589e-06,
+      "loss": 0.4615,
+      "step": 10
+    },
+    {
+      "epoch": 0.04572081725960851,
+      "grad_norm": 0.3634890019893646,
+      "learning_rate": 8.675799086757991e-06,
+      "loss": 0.4707,
+      "step": 20
+    },
+    {
+      "epoch": 0.06858122588941278,
+      "grad_norm": 0.26333874464035034,
+      "learning_rate": 1.3242009132420092e-05,
+      "loss": 0.3731,
+      "step": 30
+    },
+    {
+      "epoch": 0.09144163451921702,
+      "grad_norm": 0.19899441301822662,
+      "learning_rate": 1.780821917808219e-05,
+      "loss": 0.2918,
+      "step": 40
+    },
+    {
+      "epoch": 0.11430204314902129,
+      "grad_norm": 0.10445400327444077,
+      "learning_rate": 2.237442922374429e-05,
+      "loss": 0.1518,
+      "step": 50
+    },
+    {
+      "epoch": 0.13716245177882555,
+      "grad_norm": 0.060141440480947495,
+      "learning_rate": 2.6940639269406392e-05,
+      "loss": 0.0826,
+      "step": 60
+    },
+    {
+      "epoch": 0.1600228604086298,
+      "grad_norm": 0.11565729230642319,
+      "learning_rate": 3.1506849315068496e-05,
+      "loss": 0.0897,
+      "step": 70
+    },
+    {
+      "epoch": 0.18288326903843405,
+      "grad_norm": 0.13073839247226715,
+      "learning_rate": 3.60730593607306e-05,
+      "loss": 0.0992,
+      "step": 80
+    },
+    {
+      "epoch": 0.2057436776682383,
+      "grad_norm": 0.08385579288005829,
+      "learning_rate": 4.063926940639269e-05,
+      "loss": 0.0867,
+      "step": 90
+    },
+    {
+      "epoch": 0.22860408629804257,
+      "grad_norm": 0.10868898034095764,
+      "learning_rate": 4.520547945205479e-05,
+      "loss": 0.1022,
+      "step": 100
+    },
+    {
+      "epoch": 0.25146449492784684,
+      "grad_norm": 0.10515399277210236,
+      "learning_rate": 4.977168949771689e-05,
+      "loss": 0.0866,
+      "step": 110
+    },
+    {
+      "epoch": 0.2743249035576511,
+      "grad_norm": 0.11809521168470383,
+      "learning_rate": 5.4337899543379e-05,
+      "loss": 0.0866,
+      "step": 120
+    },
+    {
+      "epoch": 0.29718531218745536,
+      "grad_norm": 0.09987114369869232,
+      "learning_rate": 5.89041095890411e-05,
+      "loss": 0.0942,
+      "step": 130
+    },
+    {
+      "epoch": 0.3200457208172596,
+      "grad_norm": 0.1236502081155777,
+      "learning_rate": 6.34703196347032e-05,
+      "loss": 0.0935,
+      "step": 140
+    },
+    {
+      "epoch": 0.3429061294470639,
+      "grad_norm": 0.09345820546150208,
+      "learning_rate": 6.803652968036531e-05,
+      "loss": 0.1001,
+      "step": 150
+    },
+    {
+      "epoch": 0.3657665380768681,
+      "grad_norm": 0.12369757890701294,
+      "learning_rate": 7.26027397260274e-05,
+      "loss": 0.0805,
+      "step": 160
+    },
+    {
+      "epoch": 0.38862694670667236,
+      "grad_norm": 0.12654580175876617,
+      "learning_rate": 7.716894977168951e-05,
+      "loss": 0.0704,
+      "step": 170
+    },
+    {
+      "epoch": 0.4114873553364766,
+      "grad_norm": 0.10067084431648254,
+      "learning_rate": 8.17351598173516e-05,
+      "loss": 0.0812,
+      "step": 180
+    },
+    {
+      "epoch": 0.4343477639662809,
+      "grad_norm": 0.10523034632205963,
+      "learning_rate": 8.630136986301371e-05,
+      "loss": 0.0897,
+      "step": 190
+    },
+    {
+      "epoch": 0.45720817259608515,
+      "grad_norm": 0.08805034309625626,
+      "learning_rate": 9.08675799086758e-05,
+      "loss": 0.1039,
+      "step": 200
+    },
+    {
+      "epoch": 0.4800685812258894,
+      "grad_norm": 0.10564622282981873,
+      "learning_rate": 9.543378995433791e-05,
+      "loss": 0.0931,
+      "step": 210
+    },
+    {
+      "epoch": 0.5029289898556937,
+      "grad_norm": 0.08823700249195099,
+      "learning_rate": 0.0001,
+      "loss": 0.0769,
+      "step": 220
+    },
+    {
+      "epoch": 0.5257893984854979,
+      "grad_norm": 0.07316570729017258,
+      "learning_rate": 9.999364877774174e-05,
+      "loss": 0.0893,
+      "step": 230
+    },
+    {
+      "epoch": 0.5486498071153022,
+      "grad_norm": 0.08555534482002258,
+      "learning_rate": 9.997459672448794e-05,
+      "loss": 0.0802,
+      "step": 240
+    },
+    {
+      "epoch": 0.5715102157451064,
+      "grad_norm": 0.1843150109052658,
+      "learning_rate": 9.994284868039156e-05,
+      "loss": 0.0736,
+      "step": 250
+    },
+    {
+      "epoch": 0.5943706243749107,
+      "grad_norm": 0.11401674896478653,
+      "learning_rate": 9.9898412711008e-05,
+      "loss": 0.0788,
+      "step": 260
+    },
+    {
+      "epoch": 0.6172310330047149,
+      "grad_norm": 0.07360777258872986,
+      "learning_rate": 9.984130010524597e-05,
+      "loss": 0.0807,
+      "step": 270
+    },
+    {
+      "epoch": 0.6400914416345193,
+      "grad_norm": 0.11163882166147232,
+      "learning_rate": 9.977152537249958e-05,
+      "loss": 0.072,
+      "step": 280
+    },
+    {
+      "epoch": 0.6629518502643235,
+      "grad_norm": 0.12346392124891281,
+      "learning_rate": 9.968910623896225e-05,
+      "loss": 0.0712,
+      "step": 290
+    },
+    {
+      "epoch": 0.6858122588941278,
+      "grad_norm": 0.13644632697105408,
+      "learning_rate": 9.95940636431234e-05,
+      "loss": 0.0765,
+      "step": 300
+    },
+    {
+      "epoch": 0.708672667523932,
+      "grad_norm": 0.09245093911886215,
+      "learning_rate": 9.948642173044905e-05,
+      "loss": 0.0797,
+      "step": 310
+    },
+    {
+      "epoch": 0.7315330761537362,
+      "grad_norm": 0.11467203497886658,
+      "learning_rate": 9.936620784724766e-05,
+      "loss": 0.0756,
+      "step": 320
+    },
+    {
+      "epoch": 0.7543934847835405,
+      "grad_norm": 0.12245265394449234,
+      "learning_rate": 9.923345253372287e-05,
+      "loss": 0.0671,
+      "step": 330
+    },
+    {
+      "epoch": 0.7772538934133447,
+      "grad_norm": 0.08666519820690155,
+      "learning_rate": 9.908818951621474e-05,
+      "loss": 0.0681,
+      "step": 340
+    },
+    {
+      "epoch": 0.800114302043149,
+      "grad_norm": 0.16961519420146942,
+      "learning_rate": 9.89304556986317e-05,
+      "loss": 0.072,
+      "step": 350
+    },
+    {
+      "epoch": 0.8229747106729532,
+      "grad_norm": 0.2313849776983261,
+      "learning_rate": 9.876029115307506e-05,
+      "loss": 0.0707,
+      "step": 360
+    },
+    {
+      "epoch": 0.8458351193027576,
+      "grad_norm": 0.14014111459255219,
+      "learning_rate": 9.85777391096588e-05,
+      "loss": 0.0807,
+      "step": 370
+    },
+    {
+      "epoch": 0.8686955279325618,
+      "grad_norm": 0.0991162583231926,
+      "learning_rate": 9.838284594552697e-05,
+      "loss": 0.0736,
+      "step": 380
+    },
+    {
+      "epoch": 0.8915559365623661,
+      "grad_norm": 0.14600183069705963,
+      "learning_rate": 9.817566117307167e-05,
+      "loss": 0.073,
+      "step": 390
+    },
+    {
+      "epoch": 0.9144163451921703,
+      "grad_norm": 0.12519070506095886,
+      "learning_rate": 9.79562374273544e-05,
+      "loss": 0.0573,
+      "step": 400
+    },
+    {
+      "epoch": 0.9372767538219746,
+      "grad_norm": 0.14949887990951538,
+      "learning_rate": 9.77246304527343e-05,
+      "loss": 0.0691,
+      "step": 410
+    },
+    {
+      "epoch": 0.9601371624517788,
+      "grad_norm": 0.13667669892311096,
+      "learning_rate": 9.748089908870627e-05,
+      "loss": 0.052,
+      "step": 420
+    },
+    {
+      "epoch": 0.982997571081583,
+      "grad_norm": 0.07336350530385971,
+      "learning_rate": 9.722510525495286e-05,
+      "loss": 0.0698,
+      "step": 430
+    },
+    {
+      "epoch": 1.004572081725961,
+      "grad_norm": 0.1134289801120758,
+      "learning_rate": 9.69573139356137e-05,
+      "loss": 0.0621,
+      "step": 440
+    },
+    {
+      "epoch": 1.027432490355765,
+      "grad_norm": 0.11676439642906189,
+      "learning_rate": 9.66775931627763e-05,
+      "loss": 0.0474,
+      "step": 450
+    },
+    {
+      "epoch": 1.0502928989855693,
+      "grad_norm": 0.14386767148971558,
+      "learning_rate": 9.638601399919259e-05,
+      "loss": 0.0496,
+      "step": 460
+    },
+    {
+      "epoch": 1.0731533076153736,
+      "grad_norm": 0.16757084429264069,
+      "learning_rate": 9.608265052022556e-05,
+      "loss": 0.0493,
+      "step": 470
+    },
+    {
+      "epoch": 1.096013716245178,
+      "grad_norm": 0.12976950407028198,
+      "learning_rate": 9.576757979503037e-05,
+      "loss": 0.0513,
+      "step": 480
+    },
+    {
+      "epoch": 1.118874124874982,
+      "grad_norm": 0.21009308099746704,
+      "learning_rate": 9.544088186697515e-05,
+      "loss": 0.0464,
+      "step": 490
+    },
+    {
+      "epoch": 1.1417345335047864,
+      "grad_norm": 0.1863221377134323,
+      "learning_rate": 9.5102639733306e-05,
+      "loss": 0.0388,
+      "step": 500
+    },
+    {
+      "epoch": 1.1645949421345907,
+      "grad_norm": 0.1924988180398941,
+      "learning_rate": 9.475293932406162e-05,
+      "loss": 0.0517,
+      "step": 510
+    },
+    {
+      "epoch": 1.1874553507643948,
+      "grad_norm": 0.1228746697306633,
+      "learning_rate": 9.439186948024297e-05,
+      "loss": 0.0475,
+      "step": 520
+    },
+    {
+      "epoch": 1.210315759394199,
+      "grad_norm": 0.18384294211864471,
+      "learning_rate": 9.401952193124315e-05,
+      "loss": 0.046,
+      "step": 530
+    },
+    {
+      "epoch": 1.2331761680240034,
+      "grad_norm": 0.1352134793996811,
+      "learning_rate": 9.363599127154383e-05,
+      "loss": 0.0454,
+      "step": 540
+    },
+    {
+      "epoch": 1.2560365766538077,
+      "grad_norm": 0.07320581376552582,
+      "learning_rate": 9.324137493668352e-05,
+      "loss": 0.0379,
+      "step": 550
+    },
+    {
+      "epoch": 1.278896985283612,
+      "grad_norm": 0.14689098298549652,
+      "learning_rate": 9.283577317850419e-05,
+      "loss": 0.0419,
+      "step": 560
+    },
+    {
+      "epoch": 1.3017573939134162,
+      "grad_norm": 0.14588995277881622,
+      "learning_rate": 9.24192890396824e-05,
+      "loss": 0.0451,
+      "step": 570
+    },
+    {
+      "epoch": 1.3246178025432205,
+      "grad_norm": 0.17893975973129272,
+      "learning_rate": 9.19920283275515e-05,
+      "loss": 0.0405,
+      "step": 580
+    },
+    {
+      "epoch": 1.3474782111730248,
+      "grad_norm": 0.17961391806602478,
+      "learning_rate": 9.155409958722124e-05,
+      "loss": 0.0371,
+      "step": 590
+    },
+    {
+      "epoch": 1.370338619802829,
+      "grad_norm": 0.18520987033843994,
+      "learning_rate": 9.110561407400218e-05,
+      "loss": 0.0447,
+      "step": 600
+    },
+    {
+      "epoch": 1.3931990284326332,
+      "grad_norm": 0.14877571165561676,
+      "learning_rate": 9.064668572514127e-05,
+      "loss": 0.0429,
+      "step": 610
+    },
+    {
+      "epoch": 1.4160594370624375,
+      "grad_norm": 0.1054820641875267,
+      "learning_rate": 9.01774311308763e-05,
+      "loss": 0.036,
+      "step": 620
+    },
+    {
+      "epoch": 1.4389198456922419,
+      "grad_norm": 0.1029554158449173,
+      "learning_rate": 8.96979695048162e-05,
+      "loss": 0.0473,
+      "step": 630
+    },
+    {
+      "epoch": 1.461780254322046,
+      "grad_norm": 0.26157063245773315,
+      "learning_rate": 8.920842265365503e-05,
+      "loss": 0.0343,
+      "step": 640
+    },
+    {
+      "epoch": 1.4846406629518503,
+      "grad_norm": 0.12941773235797882,
+      "learning_rate": 8.870891494622709e-05,
+      "loss": 0.0522,
+      "step": 650
+    },
+    {
+      "epoch": 1.5075010715816544,
+      "grad_norm": 0.11229275912046432,
+      "learning_rate": 8.819957328191117e-05,
+      "loss": 0.0385,
+      "step": 660
+    },
+    {
+      "epoch": 1.5303614802114587,
+      "grad_norm": 0.2675265073776245,
+      "learning_rate": 8.76805270583919e-05,
+      "loss": 0.0492,
+      "step": 670
+    },
+    {
+      "epoch": 1.553221888841263,
+      "grad_norm": 0.18951663374900818,
+      "learning_rate": 8.715190813878637e-05,
+      "loss": 0.0353,
+      "step": 680
+    },
+    {
+      "epoch": 1.5760822974710673,
+      "grad_norm": 0.14573994278907776,
+      "learning_rate": 8.661385081814453e-05,
+      "loss": 0.0334,
+      "step": 690
+    },
+    {
+      "epoch": 1.5989427061008716,
+      "grad_norm": 0.08593331277370453,
+      "learning_rate": 8.606649178933163e-05,
+      "loss": 0.0315,
+      "step": 700
+    },
+    {
+      "epoch": 1.621803114730676,
+      "grad_norm": 0.20985154807567596,
+      "learning_rate": 8.550997010830154e-05,
+      "loss": 0.0369,
+      "step": 710
+    },
+    {
+      "epoch": 1.64466352336048,
+      "grad_norm": 0.2964492738246918,
+      "learning_rate": 8.494442715876976e-05,
+      "loss": 0.0283,
+      "step": 720
+    },
+    {
+      "epoch": 1.6675239319902844,
+      "grad_norm": 0.11921142041683197,
+      "learning_rate": 8.437000661629506e-05,
+      "loss": 0.0312,
+      "step": 730
+    },
+    {
+      "epoch": 1.6903843406200885,
+      "grad_norm": 0.20576898753643036,
+      "learning_rate": 8.378685441177886e-05,
+      "loss": 0.0348,
+      "step": 740
+    },
+    {
+      "epoch": 1.7132447492498928,
+      "grad_norm": 0.27900010347366333,
+      "learning_rate": 8.31951186943916e-05,
+      "loss": 0.0294,
+      "step": 750
+    },
+    {
+      "epoch": 1.736105157879697,
+      "grad_norm": 0.18257662653923035,
+      "learning_rate": 8.259494979393563e-05,
+      "loss": 0.0264,
+      "step": 760
+    },
+    {
+      "epoch": 1.7589655665095014,
+      "grad_norm": 0.16247795522212982,
+      "learning_rate": 8.198650018265415e-05,
+      "loss": 0.0385,
+      "step": 770
+    },
+    {
+      "epoch": 1.7818259751393057,
+      "grad_norm": 0.18227055668830872,
+      "learning_rate": 8.136992443649571e-05,
+      "loss": 0.0333,
+      "step": 780
+    },
+    {
+      "epoch": 1.8046863837691098,
+      "grad_norm": 0.1283257156610489,
+      "learning_rate": 8.074537919584443e-05,
+      "loss": 0.0373,
+      "step": 790
+    },
+    {
+      "epoch": 1.8275467923989142,
+      "grad_norm": 0.21598616242408752,
+      "learning_rate": 8.011302312572566e-05,
+      "loss": 0.0427,
+      "step": 800
+    },
+    {
+      "epoch": 1.8504072010287183,
+      "grad_norm": 0.18352819979190826,
+      "learning_rate": 7.947301687549731e-05,
+      "loss": 0.04,
+      "step": 810
+    },
+    {
+      "epoch": 1.8732676096585226,
+      "grad_norm": 0.28778374195098877,
+      "learning_rate": 7.882552303803705e-05,
+      "loss": 0.035,
+      "step": 820
+    },
+    {
+      "epoch": 1.8961280182883269,
+      "grad_norm": 0.11134298145771027,
+      "learning_rate": 7.817070610843579e-05,
+      "loss": 0.0281,
+      "step": 830
+    },
+    {
+      "epoch": 1.9189884269181312,
+      "grad_norm": 0.2428896129131317,
+      "learning_rate": 7.750873244220787e-05,
+      "loss": 0.0326,
+      "step": 840
+    },
+    {
+      "epoch": 1.9418488355479355,
+      "grad_norm": 0.21082095801830292,
+      "learning_rate": 7.68397702130286e-05,
+      "loss": 0.0316,
+      "step": 850
+    },
+    {
+      "epoch": 1.9647092441777396,
+      "grad_norm": 0.14655885100364685,
+      "learning_rate": 7.616398937000999e-05,
+      "loss": 0.0292,
+      "step": 860
+    },
+    {
+      "epoch": 1.987569652807544,
+      "grad_norm": 0.16203175485134125,
+      "learning_rate": 7.548156159452531e-05,
+      "loss": 0.0272,
+      "step": 870
+    },
+    {
+      "epoch": 2.009144163451922,
+      "grad_norm": 0.1306605190038681,
+      "learning_rate": 7.479266025659365e-05,
+      "loss": 0.0209,
+      "step": 880
+    },
+    {
+      "epoch": 2.032004572081726,
+      "grad_norm": 0.13496187329292297,
+      "learning_rate": 7.409746037083548e-05,
+      "loss": 0.0138,
+      "step": 890
+    },
+    {
+      "epoch": 2.05486498071153,
+      "grad_norm": 0.18669717013835907,
+      "learning_rate": 7.339613855201032e-05,
+      "loss": 0.0149,
+      "step": 900
+    },
+    {
+      "epoch": 2.0777253893413343,
+      "grad_norm": 0.1247486025094986,
+      "learning_rate": 7.2688872970148e-05,
+      "loss": 0.0128,
+      "step": 910
+    },
+    {
+      "epoch": 2.1005857979711386,
+      "grad_norm": 0.1156638115644455,
+      "learning_rate": 7.197584330528478e-05,
+      "loss": 0.0117,
+      "step": 920
+    },
+    {
+      "epoch": 2.123446206600943,
+      "grad_norm": 0.03096736967563629,
+      "learning_rate": 7.125723070181576e-05,
+      "loss": 0.0143,
+      "step": 930
+    },
+    {
+      "epoch": 2.1463066152307473,
+      "grad_norm": 0.04739869013428688,
+      "learning_rate": 7.053321772247545e-05,
+      "loss": 0.0099,
+      "step": 940
+    },
+    {
+      "epoch": 2.1691670238605516,
+      "grad_norm": 0.1429280787706375,
+      "learning_rate": 6.980398830195785e-05,
+      "loss": 0.0109,
+      "step": 950
+    },
+    {
+      "epoch": 2.192027432490356,
+      "grad_norm": 0.2534593343734741,
+      "learning_rate": 6.906972770018802e-05,
+      "loss": 0.0163,
+      "step": 960
+    },
+    {
+      "epoch": 2.2148878411201602,
+      "grad_norm": 0.1354377567768097,
+      "learning_rate": 6.833062245525705e-05,
+      "loss": 0.0147,
+      "step": 970
+    },
+    {
+      "epoch": 2.237748249749964,
+      "grad_norm": 0.06828989833593369,
+      "learning_rate": 6.758686033603225e-05,
+      "loss": 0.0201,
+      "step": 980
+    },
+    {
+      "epoch": 2.2606086583797684,
+      "grad_norm": 0.14169731736183167,
+      "learning_rate": 6.683863029445469e-05,
+      "loss": 0.0133,
+      "step": 990
+    },
+    {
+      "epoch": 2.2834690670095728,
+      "grad_norm": 0.04132571816444397,
+      "learning_rate": 6.608612241753614e-05,
+      "loss": 0.0097,
+      "step": 1000
+    },
+    {
+      "epoch": 2.306329475639377,
+      "grad_norm": 0.3469948172569275,
+      "learning_rate": 6.532952787906771e-05,
+      "loss": 0.0139,
+      "step": 1010
+    },
+    {
+      "epoch": 2.3291898842691814,
+      "grad_norm": 0.04748811200261116,
+      "learning_rate": 6.45690388910523e-05,
+      "loss": 0.0153,
+      "step": 1020
+    },
+    {
+      "epoch": 2.3520502928989857,
+      "grad_norm": 0.1330500990152359,
+      "learning_rate": 6.380484865487347e-05,
+      "loss": 0.015,
+      "step": 1030
+    },
+    {
+      "epoch": 2.3749107015287896,
+      "grad_norm": 0.14051929116249084,
+      "learning_rate": 6.303715131221264e-05,
+      "loss": 0.0069,
+      "step": 1040
+    },
+    {
+      "epoch": 2.397771110158594,
+      "grad_norm": 0.07501324266195297,
+      "learning_rate": 6.22661418957279e-05,
+      "loss": 0.0101,
+      "step": 1050
+    },
+    {
+      "epoch": 2.420631518788398,
+      "grad_norm": 0.1099422499537468,
+      "learning_rate": 6.149201627950593e-05,
+      "loss": 0.013,
+      "step": 1060
+    },
+    {
+      "epoch": 2.4434919274182025,
+      "grad_norm": 0.09372354298830032,
+      "learning_rate": 6.071497112930047e-05,
+      "loss": 0.0126,
+      "step": 1070
+    },
+    {
+      "epoch": 2.466352336048007,
+      "grad_norm": 0.09480420500040054,
+      "learning_rate": 5.99352038525697e-05,
+      "loss": 0.0127,
+      "step": 1080
+    },
+    {
+      "epoch": 2.489212744677811,
+      "grad_norm": 0.1486363410949707,
+      "learning_rate": 5.9152912548324976e-05,
+      "loss": 0.016,
+      "step": 1090
+    },
+    {
+      "epoch": 2.5120731533076155,
+      "grad_norm": 0.10003609955310822,
+      "learning_rate": 5.836829595680406e-05,
+      "loss": 0.0128,
+      "step": 1100
+    },
+    {
+      "epoch": 2.53493356193742,
+      "grad_norm": 0.08636961132287979,
+      "learning_rate": 5.758155340898137e-05,
+      "loss": 0.0119,
+      "step": 1110
+    },
+    {
+      "epoch": 2.557793970567224,
+      "grad_norm": 0.11953787505626678,
+      "learning_rate": 5.679288477592815e-05,
+      "loss": 0.0097,
+      "step": 1120
+    },
+    {
+      "epoch": 2.580654379197028,
+      "grad_norm": 0.06493639945983887,
+      "learning_rate": 5.600249041803545e-05,
+      "loss": 0.0105,
+      "step": 1130
+    },
+    {
+      "epoch": 2.6035147878268323,
+      "grad_norm": 0.12084943801164627,
+      "learning_rate": 5.5210571134112824e-05,
+      "loss": 0.0122,
+      "step": 1140
+    },
+    {
+      "epoch": 2.6263751964566366,
+      "grad_norm": 0.13135117292404175,
+      "learning_rate": 5.44173281103756e-05,
+      "loss": 0.0142,
+      "step": 1150
+    },
+    {
+      "epoch": 2.649235605086441,
+      "grad_norm": 0.137589693069458,
+      "learning_rate": 5.362296286933371e-05,
+      "loss": 0.0126,
+      "step": 1160
+    },
+    {
+      "epoch": 2.6720960137162453,
+      "grad_norm": 0.058550190180540085,
+      "learning_rate": 5.282767721859516e-05,
+      "loss": 0.0076,
+      "step": 1170
+    },
+    {
+      "epoch": 2.6949564223460496,
+      "grad_norm": 0.07393407076597214,
+      "learning_rate": 5.203167319959702e-05,
+      "loss": 0.012,
+      "step": 1180
+    },
+    {
+      "epoch": 2.7178168309758535,
+      "grad_norm": 0.1508752703666687,
+      "learning_rate": 5.123515303627698e-05,
+      "loss": 0.009,
+      "step": 1190
+    },
+    {
+      "epoch": 2.740677239605658,
+      "grad_norm": 0.1534973382949829,
+      "learning_rate": 5.0438319083698714e-05,
+      "loss": 0.0101,
+      "step": 1200
+    },
+    {
+      "epoch": 2.763537648235462,
+      "grad_norm": 0.14507421851158142,
+      "learning_rate": 4.9641373776643616e-05,
+      "loss": 0.0081,
+      "step": 1210
+    },
+    {
+      "epoch": 2.7863980568652664,
+      "grad_norm": 0.1377381533384323,
+      "learning_rate": 4.8844519578182604e-05,
+      "loss": 0.0109,
+      "step": 1220
+    },
+    {
+      "epoch": 2.8092584654950707,
+      "grad_norm": 0.2066635936498642,
+      "learning_rate": 4.804795892824056e-05,
+      "loss": 0.0135,
+      "step": 1230
+    },
+    {
+      "epoch": 2.832118874124875,
+      "grad_norm": 0.05857717618346214,
+      "learning_rate": 4.7251894192166654e-05,
+      "loss": 0.0076,
+      "step": 1240
+    },
+    {
+      "epoch": 2.8549792827546794,
+      "grad_norm": 0.168072909116745,
+      "learning_rate": 4.645652760932376e-05,
+      "loss": 0.009,
+      "step": 1250
+    },
+    {
+      "epoch": 2.8778396913844837,
+      "grad_norm": 0.17164477705955505,
+      "learning_rate": 4.566206124170963e-05,
+      "loss": 0.0112,
+      "step": 1260
+    },
+    {
+      "epoch": 2.900700100014288,
+      "grad_norm": 0.15097732841968536,
+      "learning_rate": 4.486869692262337e-05,
+      "loss": 0.0094,
+      "step": 1270
+    },
+    {
+      "epoch": 2.923560508644092,
+      "grad_norm": 0.0871570035815239,
+      "learning_rate": 4.407663620538985e-05,
+      "loss": 0.0101,
+      "step": 1280
+    },
+    {
+      "epoch": 2.946420917273896,
+      "grad_norm": 0.13305386900901794,
+      "learning_rate": 4.328608031215539e-05,
+      "loss": 0.0092,
+      "step": 1290
+    },
+    {
+      "epoch": 2.9692813259037005,
+      "grad_norm": 0.23256619274616241,
+      "learning_rate": 4.249723008276737e-05,
+      "loss": 0.015,
+      "step": 1300
+    },
+    {
+      "epoch": 2.992141734533505,
+      "grad_norm": 0.10129191726446152,
+      "learning_rate": 4.171028592375125e-05,
+      "loss": 0.0124,
+      "step": 1310
+    },
+    {
+      "epoch": 3.0137162451778825,
+      "grad_norm": 0.15339592099189758,
+      "learning_rate": 4.092544775739735e-05,
+      "loss": 0.0067,
+      "step": 1320
+    },
+    {
+      "epoch": 3.036576653807687,
+      "grad_norm": 0.03447636589407921,
+      "learning_rate": 4.0142914970970926e-05,
+      "loss": 0.0047,
+      "step": 1330
+    },
+    {
+      "epoch": 3.059437062437491,
+      "grad_norm": 0.056881342083215714,
+      "learning_rate": 3.9362886366058025e-05,
+      "loss": 0.0074,
+      "step": 1340
+    },
+    {
+      "epoch": 3.0822974710672955,
+      "grad_norm": 0.22134284675121307,
+      "learning_rate": 3.858556010806013e-05,
+      "loss": 0.004,
+      "step": 1350
+    },
+    {
+      "epoch": 3.1051578796970998,
+      "grad_norm": 0.12356160581111908,
+      "learning_rate": 3.781113367585053e-05,
+      "loss": 0.0048,
+      "step": 1360
+    },
+    {
+      "epoch": 3.1280182883269037,
+      "grad_norm": 0.03940752521157265,
+      "learning_rate": 3.703980381160497e-05,
+      "loss": 0.003,
+      "step": 1370
+    },
+    {
+      "epoch": 3.150878696956708,
+      "grad_norm": 0.09747901558876038,
+      "learning_rate": 3.627176647081954e-05,
+      "loss": 0.0056,
+      "step": 1380
+    },
+    {
+      "epoch": 3.1737391055865123,
+      "grad_norm": 0.016509221866726875,
+      "learning_rate": 3.550721677252839e-05,
+      "loss": 0.0017,
+      "step": 1390
+    },
+    {
+      "epoch": 3.1965995142163166,
+      "grad_norm": 0.15755465626716614,
+      "learning_rate": 3.4746348949733965e-05,
+      "loss": 0.003,
+      "step": 1400
+    },
+    {
+      "epoch": 3.219459922846121,
+      "grad_norm": 0.017669400200247765,
+      "learning_rate": 3.398935630006236e-05,
+      "loss": 0.0031,
+      "step": 1410
+    },
+    {
+      "epoch": 3.2423203314759252,
+      "grad_norm": 0.07502660900354385,
+      "learning_rate": 3.32364311366562e-05,
+      "loss": 0.005,
+      "step": 1420
+    },
+    {
+      "epoch": 3.2651807401057296,
+      "grad_norm": 0.4353109300136566,
+      "learning_rate": 3.248776473931774e-05,
+      "loss": 0.0058,
+      "step": 1430
+    },
+    {
+      "epoch": 3.288041148735534,
+      "grad_norm": 0.06076102331280708,
+      "learning_rate": 3.174354730591447e-05,
+      "loss": 0.0055,
+      "step": 1440
+    },
+    {
+      "epoch": 3.3109015573653378,
+      "grad_norm": 0.04932214692234993,
+      "learning_rate": 3.100396790405948e-05,
+      "loss": 0.0041,
+      "step": 1450
+    },
+    {
+      "epoch": 3.333761965995142,
+      "grad_norm": 0.12315461784601212,
+      "learning_rate": 3.026921442307916e-05,
+      "loss": 0.0034,
+      "step": 1460
+    },
+    {
+      "epoch": 3.3566223746249464,
+      "grad_norm": 0.08378969877958298,
+      "learning_rate": 2.9539473526280005e-05,
+      "loss": 0.0021,
+      "step": 1470
+    },
+    {
+      "epoch": 3.3794827832547507,
+      "grad_norm": 0.1416824609041214,
+      "learning_rate": 2.8814930603527068e-05,
+      "loss": 0.0024,
+      "step": 1480
+    },
+    {
+      "epoch": 3.402343191884555,
+      "grad_norm": 0.09372381865978241,
+      "learning_rate": 2.809576972414587e-05,
+      "loss": 0.0023,
+      "step": 1490
+    },
+    {
+      "epoch": 3.4252036005143593,
+      "grad_norm": 0.16745346784591675,
+      "learning_rate": 2.738217359015981e-05,
+      "loss": 0.0041,
+      "step": 1500
+    },
+    {
+      "epoch": 3.4480640091441632,
+      "grad_norm": 0.1455969363451004,
+      "learning_rate": 2.6674323489874843e-05,
+      "loss": 0.0056,
+      "step": 1510
+    },
+    {
+      "epoch": 3.4709244177739675,
+      "grad_norm": 0.07298196107149124,
+      "learning_rate": 2.5972399251823488e-05,
+      "loss": 0.0034,
+      "step": 1520
+    },
+    {
+      "epoch": 3.493784826403772,
+      "grad_norm": 0.024875745177268982,
+      "learning_rate": 2.5276579199079486e-05,
+      "loss": 0.0043,
+      "step": 1530
+    },
+    {
+      "epoch": 3.516645235033576,
+      "grad_norm": 0.17137651145458221,
+      "learning_rate": 2.4587040103955134e-05,
+      "loss": 0.0041,
+      "step": 1540
+    },
+    {
+      "epoch": 3.5395056436633805,
+      "grad_norm": 0.10219382494688034,
+      "learning_rate": 2.39039571430924e-05,
+      "loss": 0.0037,
+      "step": 1550
+    },
+    {
+      "epoch": 3.562366052293185,
+      "grad_norm": 0.05997829884290695,
+      "learning_rate": 2.3227503852959453e-05,
+      "loss": 0.0025,
+      "step": 1560
+    },
+    {
+      "epoch": 3.585226460922989,
+      "grad_norm": 0.022572757676243782,
+      "learning_rate": 2.2557852085764053e-05,
+      "loss": 0.0087,
+      "step": 1570
+    },
+    {
+      "epoch": 3.6080868695527935,
+      "grad_norm": 0.025689126923680305,
+      "learning_rate": 2.189517196579453e-05,
+      "loss": 0.0046,
+      "step": 1580
+    },
+    {
+      "epoch": 3.6309472781825978,
+      "grad_norm": 0.19351957738399506,
+      "learning_rate": 2.1239631846200026e-05,
+      "loss": 0.0041,
+      "step": 1590
+    },
+    {
+      "epoch": 3.6538076868124016,
+      "grad_norm": 0.05244070664048195,
+      "learning_rate": 2.0591398266220502e-05,
+      "loss": 0.0025,
+      "step": 1600
+    },
+    {
+      "epoch": 3.676668095442206,
+      "grad_norm": 0.05331341549754143,
+      "learning_rate": 1.995063590887759e-05,
+      "loss": 0.0045,
+      "step": 1610
+    },
+    {
+      "epoch": 3.6995285040720103,
+      "grad_norm": 0.038474228233098984,
+      "learning_rate": 1.9317507559137184e-05,
+      "loss": 0.0039,
+      "step": 1620
+    },
+    {
+      "epoch": 3.7223889127018146,
+      "grad_norm": 0.046009331941604614,
+      "learning_rate": 1.8692174062553924e-05,
+      "loss": 0.004,
+      "step": 1630
+    },
+    {
+      "epoch": 3.745249321331619,
+      "grad_norm": 0.024187810719013214,
+      "learning_rate": 1.807479428440873e-05,
+      "loss": 0.0024,
+      "step": 1640
+    },
+    {
+      "epoch": 3.768109729961423,
+      "grad_norm": 0.07836172729730606,
+      "learning_rate": 1.746552506934917e-05,
+      "loss": 0.0027,
+      "step": 1650
+    },
+    {
+      "epoch": 3.790970138591227,
+      "grad_norm": 0.0379299558699131,
+      "learning_rate": 1.6864521201543197e-05,
+      "loss": 0.0032,
+      "step": 1660
+    },
+    {
+      "epoch": 3.8138305472210314,
+      "grad_norm": 0.04367607831954956,
+      "learning_rate": 1.627193536535656e-05,
+      "loss": 0.002,
+      "step": 1670
+    },
+    {
+      "epoch": 3.8366909558508357,
+      "grad_norm": 0.18003098666667938,
+      "learning_rate": 1.5687918106563326e-05,
+      "loss": 0.0025,
+      "step": 1680
+    },
+    {
+      "epoch": 3.85955136448064,
+      "grad_norm": 0.04013814404606819,
+      "learning_rate": 1.5112617794100047e-05,
+      "loss": 0.0026,
+      "step": 1690
+    },
+    {
+      "epoch": 3.8824117731104444,
+      "grad_norm": 0.030205566436052322,
+      "learning_rate": 1.454618058237272e-05,
+      "loss": 0.0029,
+      "step": 1700
+    },
+    {
+      "epoch": 3.9052721817402487,
+      "grad_norm": 0.10214164853096008,
+      "learning_rate": 1.3988750374126396e-05,
+      "loss": 0.0026,
+      "step": 1710
+    },
+    {
+      "epoch": 3.928132590370053,
+      "grad_norm": 0.027208510786294937,
+      "learning_rate": 1.344046878388695e-05,
+      "loss": 0.0026,
+      "step": 1720
+    },
+    {
+      "epoch": 3.9509929989998573,
+      "grad_norm": 0.020535435527563095,
+      "learning_rate": 1.2901475101983939e-05,
+      "loss": 0.0018,
+      "step": 1730
+    },
+    {
+      "epoch": 3.973853407629661,
+      "grad_norm": 0.03657793253660202,
+      "learning_rate": 1.2371906259164168e-05,
+      "loss": 0.0023,
+      "step": 1740
+    },
+    {
+      "epoch": 3.9967138162594655,
+      "grad_norm": 0.037314701825380325,
+      "learning_rate": 1.1851896791804507e-05,
+      "loss": 0.004,
+      "step": 1750
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2190,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.082116411512586e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d307b97811482d7107b2c2d37efb72e66e5e343ee5862d771d5d8278d370a73a
+size 5777

checkpoint-2000/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-7B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.16.0

checkpoint-2000/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e0cf1b2a445af6ff8e294d159f92436ae67933688d9f18f711b0167de7278e
+size 323014168

checkpoint-2000/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
+}

checkpoint-2000/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 %}

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1b20813a2ad9e5ec61e1d6fc3319303ac563bc84edf598b8a65e6abf1085beb
+size 646253819

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e281539681e1461680a8f03dae385b1b5b8c0448bff23c6aa7923a713d08dd
+size 14645

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c625f8b81111bc5fb1c4b6e5254635917ed663fe6e407ad47a74d7d641a26076
+size 1465

checkpoint-2000/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
+  }
+}

checkpoint-2000/tokenizer.json

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

checkpoint-2000/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": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.5669381340191455,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022860408629804256,
+      "grad_norm": 0.31346356868743896,
+      "learning_rate": 4.10958904109589e-06,
+      "loss": 0.4615,
+      "step": 10
+    },
+    {
+      "epoch": 0.04572081725960851,
+      "grad_norm": 0.3634890019893646,
+      "learning_rate": 8.675799086757991e-06,
+      "loss": 0.4707,
+      "step": 20
+    },
+    {
+      "epoch": 0.06858122588941278,
+      "grad_norm": 0.26333874464035034,
+      "learning_rate": 1.3242009132420092e-05,
+      "loss": 0.3731,
+      "step": 30
+    },
+    {
+      "epoch": 0.09144163451921702,
+      "grad_norm": 0.19899441301822662,
+      "learning_rate": 1.780821917808219e-05,
+      "loss": 0.2918,
+      "step": 40
+    },
+    {
+      "epoch": 0.11430204314902129,
+      "grad_norm": 0.10445400327444077,
+      "learning_rate": 2.237442922374429e-05,
+      "loss": 0.1518,
+      "step": 50
+    },
+    {
+      "epoch": 0.13716245177882555,
+      "grad_norm": 0.060141440480947495,
+      "learning_rate": 2.6940639269406392e-05,
+      "loss": 0.0826,
+      "step": 60
+    },
+    {
+      "epoch": 0.1600228604086298,
+      "grad_norm": 0.11565729230642319,
+      "learning_rate": 3.1506849315068496e-05,
+      "loss": 0.0897,
+      "step": 70
+    },
+    {
+      "epoch": 0.18288326903843405,
+      "grad_norm": 0.13073839247226715,
+      "learning_rate": 3.60730593607306e-05,
+      "loss": 0.0992,
+      "step": 80
+    },
+    {
+      "epoch": 0.2057436776682383,
+      "grad_norm": 0.08385579288005829,
+      "learning_rate": 4.063926940639269e-05,
+      "loss": 0.0867,
+      "step": 90
+    },
+    {
+      "epoch": 0.22860408629804257,
+      "grad_norm": 0.10868898034095764,
+      "learning_rate": 4.520547945205479e-05,
+      "loss": 0.1022,
+      "step": 100
+    },
+    {
+      "epoch": 0.25146449492784684,
+      "grad_norm": 0.10515399277210236,
+      "learning_rate": 4.977168949771689e-05,
+      "loss": 0.0866,
+      "step": 110
+    },
+    {
+      "epoch": 0.2743249035576511,
+      "grad_norm": 0.11809521168470383,
+      "learning_rate": 5.4337899543379e-05,
+      "loss": 0.0866,
+      "step": 120
+    },
+    {
+      "epoch": 0.29718531218745536,
+      "grad_norm": 0.09987114369869232,
+      "learning_rate": 5.89041095890411e-05,
+      "loss": 0.0942,
+      "step": 130
+    },
+    {
+      "epoch": 0.3200457208172596,
+      "grad_norm": 0.1236502081155777,
+      "learning_rate": 6.34703196347032e-05,
+      "loss": 0.0935,
+      "step": 140
+    },
+    {
+      "epoch": 0.3429061294470639,
+      "grad_norm": 0.09345820546150208,
+      "learning_rate": 6.803652968036531e-05,
+      "loss": 0.1001,
+      "step": 150
+    },
+    {
+      "epoch": 0.3657665380768681,
+      "grad_norm": 0.12369757890701294,
+      "learning_rate": 7.26027397260274e-05,
+      "loss": 0.0805,
+      "step": 160
+    },
+    {
+      "epoch": 0.38862694670667236,
+      "grad_norm": 0.12654580175876617,
+      "learning_rate": 7.716894977168951e-05,
+      "loss": 0.0704,
+      "step": 170
+    },
+    {
+      "epoch": 0.4114873553364766,
+      "grad_norm": 0.10067084431648254,
+      "learning_rate": 8.17351598173516e-05,
+      "loss": 0.0812,
+      "step": 180
+    },
+    {
+      "epoch": 0.4343477639662809,
+      "grad_norm": 0.10523034632205963,
+      "learning_rate": 8.630136986301371e-05,
+      "loss": 0.0897,
+      "step": 190
+    },
+    {
+      "epoch": 0.45720817259608515,
+      "grad_norm": 0.08805034309625626,
+      "learning_rate": 9.08675799086758e-05,
+      "loss": 0.1039,
+      "step": 200
+    },
+    {
+      "epoch": 0.4800685812258894,
+      "grad_norm": 0.10564622282981873,
+      "learning_rate": 9.543378995433791e-05,
+      "loss": 0.0931,
+      "step": 210
+    },
+    {
+      "epoch": 0.5029289898556937,
+      "grad_norm": 0.08823700249195099,
+      "learning_rate": 0.0001,
+      "loss": 0.0769,
+      "step": 220
+    },
+    {
+      "epoch": 0.5257893984854979,
+      "grad_norm": 0.07316570729017258,
+      "learning_rate": 9.999364877774174e-05,
+      "loss": 0.0893,
+      "step": 230
+    },
+    {
+      "epoch": 0.5486498071153022,
+      "grad_norm": 0.08555534482002258,
+      "learning_rate": 9.997459672448794e-05,
+      "loss": 0.0802,
+      "step": 240
+    },
+    {
+      "epoch": 0.5715102157451064,
+      "grad_norm": 0.1843150109052658,
+      "learning_rate": 9.994284868039156e-05,
+      "loss": 0.0736,
+      "step": 250
+    },
+    {
+      "epoch": 0.5943706243749107,
+      "grad_norm": 0.11401674896478653,
+      "learning_rate": 9.9898412711008e-05,
+      "loss": 0.0788,
+      "step": 260
+    },
+    {
+      "epoch": 0.6172310330047149,
+      "grad_norm": 0.07360777258872986,
+      "learning_rate": 9.984130010524597e-05,
+      "loss": 0.0807,
+      "step": 270
+    },
+    {
+      "epoch": 0.6400914416345193,
+      "grad_norm": 0.11163882166147232,
+      "learning_rate": 9.977152537249958e-05,
+      "loss": 0.072,
+      "step": 280
+    },
+    {
+      "epoch": 0.6629518502643235,
+      "grad_norm": 0.12346392124891281,
+      "learning_rate": 9.968910623896225e-05,
+      "loss": 0.0712,
+      "step": 290
+    },
+    {
+      "epoch": 0.6858122588941278,
+      "grad_norm": 0.13644632697105408,
+      "learning_rate": 9.95940636431234e-05,
+      "loss": 0.0765,
+      "step": 300
+    },
+    {
+      "epoch": 0.708672667523932,
+      "grad_norm": 0.09245093911886215,
+      "learning_rate": 9.948642173044905e-05,
+      "loss": 0.0797,
+      "step": 310
+    },
+    {
+      "epoch": 0.7315330761537362,
+      "grad_norm": 0.11467203497886658,
+      "learning_rate": 9.936620784724766e-05,
+      "loss": 0.0756,
+      "step": 320
+    },
+    {
+      "epoch": 0.7543934847835405,
+      "grad_norm": 0.12245265394449234,
+      "learning_rate": 9.923345253372287e-05,
+      "loss": 0.0671,
+      "step": 330
+    },
+    {
+      "epoch": 0.7772538934133447,
+      "grad_norm": 0.08666519820690155,
+      "learning_rate": 9.908818951621474e-05,
+      "loss": 0.0681,
+      "step": 340
+    },
+    {
+      "epoch": 0.800114302043149,
+      "grad_norm": 0.16961519420146942,
+      "learning_rate": 9.89304556986317e-05,
+      "loss": 0.072,
+      "step": 350
+    },
+    {
+      "epoch": 0.8229747106729532,
+      "grad_norm": 0.2313849776983261,
+      "learning_rate": 9.876029115307506e-05,
+      "loss": 0.0707,
+      "step": 360
+    },
+    {
+      "epoch": 0.8458351193027576,
+      "grad_norm": 0.14014111459255219,
+      "learning_rate": 9.85777391096588e-05,
+      "loss": 0.0807,
+      "step": 370
+    },
+    {
+      "epoch": 0.8686955279325618,
+      "grad_norm": 0.0991162583231926,
+      "learning_rate": 9.838284594552697e-05,
+      "loss": 0.0736,
+      "step": 380
+    },
+    {
+      "epoch": 0.8915559365623661,
+      "grad_norm": 0.14600183069705963,
+      "learning_rate": 9.817566117307167e-05,
+      "loss": 0.073,
+      "step": 390
+    },
+    {
+      "epoch": 0.9144163451921703,
+      "grad_norm": 0.12519070506095886,
+      "learning_rate": 9.79562374273544e-05,
+      "loss": 0.0573,
+      "step": 400
+    },
+    {
+      "epoch": 0.9372767538219746,
+      "grad_norm": 0.14949887990951538,
+      "learning_rate": 9.77246304527343e-05,
+      "loss": 0.0691,
+      "step": 410
+    },
+    {
+      "epoch": 0.9601371624517788,
+      "grad_norm": 0.13667669892311096,
+      "learning_rate": 9.748089908870627e-05,
+      "loss": 0.052,
+      "step": 420
+    },
+    {
+      "epoch": 0.982997571081583,
+      "grad_norm": 0.07336350530385971,
+      "learning_rate": 9.722510525495286e-05,
+      "loss": 0.0698,
+      "step": 430
+    },
+    {
+      "epoch": 1.004572081725961,
+      "grad_norm": 0.1134289801120758,
+      "learning_rate": 9.69573139356137e-05,
+      "loss": 0.0621,
+      "step": 440
+    },
+    {
+      "epoch": 1.027432490355765,
+      "grad_norm": 0.11676439642906189,
+      "learning_rate": 9.66775931627763e-05,
+      "loss": 0.0474,
+      "step": 450
+    },
+    {
+      "epoch": 1.0502928989855693,
+      "grad_norm": 0.14386767148971558,
+      "learning_rate": 9.638601399919259e-05,
+      "loss": 0.0496,
+      "step": 460
+    },
+    {
+      "epoch": 1.0731533076153736,
+      "grad_norm": 0.16757084429264069,
+      "learning_rate": 9.608265052022556e-05,
+      "loss": 0.0493,
+      "step": 470
+    },
+    {
+      "epoch": 1.096013716245178,
+      "grad_norm": 0.12976950407028198,
+      "learning_rate": 9.576757979503037e-05,
+      "loss": 0.0513,
+      "step": 480
+    },
+    {
+      "epoch": 1.118874124874982,
+      "grad_norm": 0.21009308099746704,
+      "learning_rate": 9.544088186697515e-05,
+      "loss": 0.0464,
+      "step": 490
+    },
+    {
+      "epoch": 1.1417345335047864,
+      "grad_norm": 0.1863221377134323,
+      "learning_rate": 9.5102639733306e-05,
+      "loss": 0.0388,
+      "step": 500
+    },
+    {
+      "epoch": 1.1645949421345907,
+      "grad_norm": 0.1924988180398941,
+      "learning_rate": 9.475293932406162e-05,
+      "loss": 0.0517,
+      "step": 510
+    },
+    {
+      "epoch": 1.1874553507643948,
+      "grad_norm": 0.1228746697306633,
+      "learning_rate": 9.439186948024297e-05,
+      "loss": 0.0475,
+      "step": 520
+    },
+    {
+      "epoch": 1.210315759394199,
+      "grad_norm": 0.18384294211864471,
+      "learning_rate": 9.401952193124315e-05,
+      "loss": 0.046,
+      "step": 530
+    },
+    {
+      "epoch": 1.2331761680240034,
+      "grad_norm": 0.1352134793996811,
+      "learning_rate": 9.363599127154383e-05,
+      "loss": 0.0454,
+      "step": 540
+    },
+    {
+      "epoch": 1.2560365766538077,
+      "grad_norm": 0.07320581376552582,
+      "learning_rate": 9.324137493668352e-05,
+      "loss": 0.0379,
+      "step": 550
+    },
+    {
+      "epoch": 1.278896985283612,
+      "grad_norm": 0.14689098298549652,
+      "learning_rate": 9.283577317850419e-05,
+      "loss": 0.0419,
+      "step": 560
+    },
+    {
+      "epoch": 1.3017573939134162,
+      "grad_norm": 0.14588995277881622,
+      "learning_rate": 9.24192890396824e-05,
+      "loss": 0.0451,
+      "step": 570
+    },
+    {
+      "epoch": 1.3246178025432205,
+      "grad_norm": 0.17893975973129272,
+      "learning_rate": 9.19920283275515e-05,
+      "loss": 0.0405,
+      "step": 580
+    },
+    {
+      "epoch": 1.3474782111730248,
+      "grad_norm": 0.17961391806602478,
+      "learning_rate": 9.155409958722124e-05,
+      "loss": 0.0371,
+      "step": 590
+    },
+    {
+      "epoch": 1.370338619802829,
+      "grad_norm": 0.18520987033843994,
+      "learning_rate": 9.110561407400218e-05,
+      "loss": 0.0447,
+      "step": 600
+    },
+    {
+      "epoch": 1.3931990284326332,
+      "grad_norm": 0.14877571165561676,
+      "learning_rate": 9.064668572514127e-05,
+      "loss": 0.0429,
+      "step": 610
+    },
+    {
+      "epoch": 1.4160594370624375,
+      "grad_norm": 0.1054820641875267,
+      "learning_rate": 9.01774311308763e-05,
+      "loss": 0.036,
+      "step": 620
+    },
+    {
+      "epoch": 1.4389198456922419,
+      "grad_norm": 0.1029554158449173,
+      "learning_rate": 8.96979695048162e-05,
+      "loss": 0.0473,
+      "step": 630
+    },
+    {
+      "epoch": 1.461780254322046,
+      "grad_norm": 0.26157063245773315,
+      "learning_rate": 8.920842265365503e-05,
+      "loss": 0.0343,
+      "step": 640
+    },
+    {
+      "epoch": 1.4846406629518503,
+      "grad_norm": 0.12941773235797882,
+      "learning_rate": 8.870891494622709e-05,
+      "loss": 0.0522,
+      "step": 650
+    },
+    {
+      "epoch": 1.5075010715816544,
+      "grad_norm": 0.11229275912046432,
+      "learning_rate": 8.819957328191117e-05,
+      "loss": 0.0385,
+      "step": 660
+    },
+    {
+      "epoch": 1.5303614802114587,
+      "grad_norm": 0.2675265073776245,
+      "learning_rate": 8.76805270583919e-05,
+      "loss": 0.0492,
+      "step": 670
+    },
+    {
+      "epoch": 1.553221888841263,
+      "grad_norm": 0.18951663374900818,
+      "learning_rate": 8.715190813878637e-05,
+      "loss": 0.0353,
+      "step": 680
+    },
+    {
+      "epoch": 1.5760822974710673,
+      "grad_norm": 0.14573994278907776,
+      "learning_rate": 8.661385081814453e-05,
+      "loss": 0.0334,
+      "step": 690
+    },
+    {
+      "epoch": 1.5989427061008716,
+      "grad_norm": 0.08593331277370453,
+      "learning_rate": 8.606649178933163e-05,
+      "loss": 0.0315,
+      "step": 700
+    },
+    {
+      "epoch": 1.621803114730676,
+      "grad_norm": 0.20985154807567596,
+      "learning_rate": 8.550997010830154e-05,
+      "loss": 0.0369,
+      "step": 710
+    },
+    {
+      "epoch": 1.64466352336048,
+      "grad_norm": 0.2964492738246918,
+      "learning_rate": 8.494442715876976e-05,
+      "loss": 0.0283,
+      "step": 720
+    },
+    {
+      "epoch": 1.6675239319902844,
+      "grad_norm": 0.11921142041683197,
+      "learning_rate": 8.437000661629506e-05,
+      "loss": 0.0312,
+      "step": 730
+    },
+    {
+      "epoch": 1.6903843406200885,
+      "grad_norm": 0.20576898753643036,
+      "learning_rate": 8.378685441177886e-05,
+      "loss": 0.0348,
+      "step": 740
+    },
+    {
+      "epoch": 1.7132447492498928,
+      "grad_norm": 0.27900010347366333,
+      "learning_rate": 8.31951186943916e-05,
+      "loss": 0.0294,
+      "step": 750
+    },
+    {
+      "epoch": 1.736105157879697,
+      "grad_norm": 0.18257662653923035,
+      "learning_rate": 8.259494979393563e-05,
+      "loss": 0.0264,
+      "step": 760
+    },
+    {
+      "epoch": 1.7589655665095014,
+      "grad_norm": 0.16247795522212982,
+      "learning_rate": 8.198650018265415e-05,
+      "loss": 0.0385,
+      "step": 770
+    },
+    {
+      "epoch": 1.7818259751393057,
+      "grad_norm": 0.18227055668830872,
+      "learning_rate": 8.136992443649571e-05,
+      "loss": 0.0333,
+      "step": 780
+    },
+    {
+      "epoch": 1.8046863837691098,
+      "grad_norm": 0.1283257156610489,
+      "learning_rate": 8.074537919584443e-05,
+      "loss": 0.0373,
+      "step": 790
+    },
+    {
+      "epoch": 1.8275467923989142,
+      "grad_norm": 0.21598616242408752,
+      "learning_rate": 8.011302312572566e-05,
+      "loss": 0.0427,
+      "step": 800
+    },
+    {
+      "epoch": 1.8504072010287183,
+      "grad_norm": 0.18352819979190826,
+      "learning_rate": 7.947301687549731e-05,
+      "loss": 0.04,
+      "step": 810
+    },
+    {
+      "epoch": 1.8732676096585226,
+      "grad_norm": 0.28778374195098877,
+      "learning_rate": 7.882552303803705e-05,
+      "loss": 0.035,
+      "step": 820
+    },
+    {
+      "epoch": 1.8961280182883269,
+      "grad_norm": 0.11134298145771027,
+      "learning_rate": 7.817070610843579e-05,
+      "loss": 0.0281,
+      "step": 830
+    },
+    {
+      "epoch": 1.9189884269181312,
+      "grad_norm": 0.2428896129131317,
+      "learning_rate": 7.750873244220787e-05,
+      "loss": 0.0326,
+      "step": 840
+    },
+    {
+      "epoch": 1.9418488355479355,
+      "grad_norm": 0.21082095801830292,
+      "learning_rate": 7.68397702130286e-05,
+      "loss": 0.0316,
+      "step": 850
+    },
+    {
+      "epoch": 1.9647092441777396,
+      "grad_norm": 0.14655885100364685,
+      "learning_rate": 7.616398937000999e-05,
+      "loss": 0.0292,
+      "step": 860
+    },
+    {
+      "epoch": 1.987569652807544,
+      "grad_norm": 0.16203175485134125,
+      "learning_rate": 7.548156159452531e-05,
+      "loss": 0.0272,
+      "step": 870
+    },
+    {
+      "epoch": 2.009144163451922,
+      "grad_norm": 0.1306605190038681,
+      "learning_rate": 7.479266025659365e-05,
+      "loss": 0.0209,
+      "step": 880
+    },
+    {
+      "epoch": 2.032004572081726,
+      "grad_norm": 0.13496187329292297,
+      "learning_rate": 7.409746037083548e-05,
+      "loss": 0.0138,
+      "step": 890
+    },
+    {
+      "epoch": 2.05486498071153,
+      "grad_norm": 0.18669717013835907,
+      "learning_rate": 7.339613855201032e-05,
+      "loss": 0.0149,
+      "step": 900
+    },
+    {
+      "epoch": 2.0777253893413343,
+      "grad_norm": 0.1247486025094986,
+      "learning_rate": 7.2688872970148e-05,
+      "loss": 0.0128,
+      "step": 910
+    },
+    {
+      "epoch": 2.1005857979711386,
+      "grad_norm": 0.1156638115644455,
+      "learning_rate": 7.197584330528478e-05,
+      "loss": 0.0117,
+      "step": 920
+    },
+    {
+      "epoch": 2.123446206600943,
+      "grad_norm": 0.03096736967563629,
+      "learning_rate": 7.125723070181576e-05,
+      "loss": 0.0143,
+      "step": 930
+    },
+    {
+      "epoch": 2.1463066152307473,
+      "grad_norm": 0.04739869013428688,
+      "learning_rate": 7.053321772247545e-05,
+      "loss": 0.0099,
+      "step": 940
+    },
+    {
+      "epoch": 2.1691670238605516,
+      "grad_norm": 0.1429280787706375,
+      "learning_rate": 6.980398830195785e-05,
+      "loss": 0.0109,
+      "step": 950
+    },
+    {
+      "epoch": 2.192027432490356,
+      "grad_norm": 0.2534593343734741,
+      "learning_rate": 6.906972770018802e-05,
+      "loss": 0.0163,
+      "step": 960
+    },
+    {
+      "epoch": 2.2148878411201602,
+      "grad_norm": 0.1354377567768097,
+      "learning_rate": 6.833062245525705e-05,
+      "loss": 0.0147,
+      "step": 970
+    },
+    {
+      "epoch": 2.237748249749964,
+      "grad_norm": 0.06828989833593369,
+      "learning_rate": 6.758686033603225e-05,
+      "loss": 0.0201,
+      "step": 980
+    },
+    {
+      "epoch": 2.2606086583797684,
+      "grad_norm": 0.14169731736183167,
+      "learning_rate": 6.683863029445469e-05,
+      "loss": 0.0133,
+      "step": 990
+    },
+    {
+      "epoch": 2.2834690670095728,
+      "grad_norm": 0.04132571816444397,
+      "learning_rate": 6.608612241753614e-05,
+      "loss": 0.0097,
+      "step": 1000
+    },
+    {
+      "epoch": 2.306329475639377,
+      "grad_norm": 0.3469948172569275,
+      "learning_rate": 6.532952787906771e-05,
+      "loss": 0.0139,
+      "step": 1010
+    },
+    {
+      "epoch": 2.3291898842691814,
+      "grad_norm": 0.04748811200261116,
+      "learning_rate": 6.45690388910523e-05,
+      "loss": 0.0153,
+      "step": 1020
+    },
+    {
+      "epoch": 2.3520502928989857,
+      "grad_norm": 0.1330500990152359,
+      "learning_rate": 6.380484865487347e-05,
+      "loss": 0.015,
+      "step": 1030
+    },
+    {
+      "epoch": 2.3749107015287896,
+      "grad_norm": 0.14051929116249084,
+      "learning_rate": 6.303715131221264e-05,
+      "loss": 0.0069,
+      "step": 1040
+    },
+    {
+      "epoch": 2.397771110158594,
+      "grad_norm": 0.07501324266195297,
+      "learning_rate": 6.22661418957279e-05,
+      "loss": 0.0101,
+      "step": 1050
+    },
+    {
+      "epoch": 2.420631518788398,
+      "grad_norm": 0.1099422499537468,
+      "learning_rate": 6.149201627950593e-05,
+      "loss": 0.013,
+      "step": 1060
+    },
+    {
+      "epoch": 2.4434919274182025,
+      "grad_norm": 0.09372354298830032,
+      "learning_rate": 6.071497112930047e-05,
+      "loss": 0.0126,
+      "step": 1070
+    },
+    {
+      "epoch": 2.466352336048007,
+      "grad_norm": 0.09480420500040054,
+      "learning_rate": 5.99352038525697e-05,
+      "loss": 0.0127,
+      "step": 1080
+    },
+    {
+      "epoch": 2.489212744677811,
+      "grad_norm": 0.1486363410949707,
+      "learning_rate": 5.9152912548324976e-05,
+      "loss": 0.016,
+      "step": 1090
+    },
+    {
+      "epoch": 2.5120731533076155,
+      "grad_norm": 0.10003609955310822,
+      "learning_rate": 5.836829595680406e-05,
+      "loss": 0.0128,
+      "step": 1100
+    },
+    {
+      "epoch": 2.53493356193742,
+      "grad_norm": 0.08636961132287979,
+      "learning_rate": 5.758155340898137e-05,
+      "loss": 0.0119,
+      "step": 1110
+    },
+    {
+      "epoch": 2.557793970567224,
+      "grad_norm": 0.11953787505626678,
+      "learning_rate": 5.679288477592815e-05,
+      "loss": 0.0097,
+      "step": 1120
+    },
+    {
+      "epoch": 2.580654379197028,
+      "grad_norm": 0.06493639945983887,
+      "learning_rate": 5.600249041803545e-05,
+      "loss": 0.0105,
+      "step": 1130
+    },
+    {
+      "epoch": 2.6035147878268323,
+      "grad_norm": 0.12084943801164627,
+      "learning_rate": 5.5210571134112824e-05,
+      "loss": 0.0122,
+      "step": 1140
+    },
+    {
+      "epoch": 2.6263751964566366,
+      "grad_norm": 0.13135117292404175,
+      "learning_rate": 5.44173281103756e-05,
+      "loss": 0.0142,
+      "step": 1150
+    },
+    {
+      "epoch": 2.649235605086441,
+      "grad_norm": 0.137589693069458,
+      "learning_rate": 5.362296286933371e-05,
+      "loss": 0.0126,
+      "step": 1160
+    },
+    {
+      "epoch": 2.6720960137162453,
+      "grad_norm": 0.058550190180540085,
+      "learning_rate": 5.282767721859516e-05,
+      "loss": 0.0076,
+      "step": 1170
+    },
+    {
+      "epoch": 2.6949564223460496,
+      "grad_norm": 0.07393407076597214,
+      "learning_rate": 5.203167319959702e-05,
+      "loss": 0.012,
+      "step": 1180
+    },
+    {
+      "epoch": 2.7178168309758535,
+      "grad_norm": 0.1508752703666687,
+      "learning_rate": 5.123515303627698e-05,
+      "loss": 0.009,
+      "step": 1190
+    },
+    {
+      "epoch": 2.740677239605658,
+      "grad_norm": 0.1534973382949829,
+      "learning_rate": 5.0438319083698714e-05,
+      "loss": 0.0101,
+      "step": 1200
+    },
+    {
+      "epoch": 2.763537648235462,
+      "grad_norm": 0.14507421851158142,
+      "learning_rate": 4.9641373776643616e-05,
+      "loss": 0.0081,
+      "step": 1210
+    },
+    {
+      "epoch": 2.7863980568652664,
+      "grad_norm": 0.1377381533384323,
+      "learning_rate": 4.8844519578182604e-05,
+      "loss": 0.0109,
+      "step": 1220
+    },
+    {
+      "epoch": 2.8092584654950707,
+      "grad_norm": 0.2066635936498642,
+      "learning_rate": 4.804795892824056e-05,
+      "loss": 0.0135,
+      "step": 1230
+    },
+    {
+      "epoch": 2.832118874124875,
+      "grad_norm": 0.05857717618346214,
+      "learning_rate": 4.7251894192166654e-05,
+      "loss": 0.0076,
+      "step": 1240
+    },
+    {
+      "epoch": 2.8549792827546794,
+      "grad_norm": 0.168072909116745,
+      "learning_rate": 4.645652760932376e-05,
+      "loss": 0.009,
+      "step": 1250
+    },
+    {
+      "epoch": 2.8778396913844837,
+      "grad_norm": 0.17164477705955505,
+      "learning_rate": 4.566206124170963e-05,
+      "loss": 0.0112,
+      "step": 1260
+    },
+    {
+      "epoch": 2.900700100014288,
+      "grad_norm": 0.15097732841968536,
+      "learning_rate": 4.486869692262337e-05,
+      "loss": 0.0094,
+      "step": 1270
+    },
+    {
+      "epoch": 2.923560508644092,
+      "grad_norm": 0.0871570035815239,
+      "learning_rate": 4.407663620538985e-05,
+      "loss": 0.0101,
+      "step": 1280
+    },
+    {
+      "epoch": 2.946420917273896,
+      "grad_norm": 0.13305386900901794,
+      "learning_rate": 4.328608031215539e-05,
+      "loss": 0.0092,
+      "step": 1290
+    },
+    {
+      "epoch": 2.9692813259037005,
+      "grad_norm": 0.23256619274616241,
+      "learning_rate": 4.249723008276737e-05,
+      "loss": 0.015,
+      "step": 1300
+    },
+    {
+      "epoch": 2.992141734533505,
+      "grad_norm": 0.10129191726446152,
+      "learning_rate": 4.171028592375125e-05,
+      "loss": 0.0124,
+      "step": 1310
+    },
+    {
+      "epoch": 3.0137162451778825,
+      "grad_norm": 0.15339592099189758,
+      "learning_rate": 4.092544775739735e-05,
+      "loss": 0.0067,
+      "step": 1320
+    },
+    {
+      "epoch": 3.036576653807687,
+      "grad_norm": 0.03447636589407921,
+      "learning_rate": 4.0142914970970926e-05,
+      "loss": 0.0047,
+      "step": 1330
+    },
+    {
+      "epoch": 3.059437062437491,
+      "grad_norm": 0.056881342083215714,
+      "learning_rate": 3.9362886366058025e-05,
+      "loss": 0.0074,
+      "step": 1340
+    },
+    {
+      "epoch": 3.0822974710672955,
+      "grad_norm": 0.22134284675121307,
+      "learning_rate": 3.858556010806013e-05,
+      "loss": 0.004,
+      "step": 1350
+    },
+    {
+      "epoch": 3.1051578796970998,
+      "grad_norm": 0.12356160581111908,
+      "learning_rate": 3.781113367585053e-05,
+      "loss": 0.0048,
+      "step": 1360
+    },
+    {
+      "epoch": 3.1280182883269037,
+      "grad_norm": 0.03940752521157265,
+      "learning_rate": 3.703980381160497e-05,
+      "loss": 0.003,
+      "step": 1370
+    },
+    {
+      "epoch": 3.150878696956708,
+      "grad_norm": 0.09747901558876038,
+      "learning_rate": 3.627176647081954e-05,
+      "loss": 0.0056,
+      "step": 1380
+    },
+    {
+      "epoch": 3.1737391055865123,
+      "grad_norm": 0.016509221866726875,
+      "learning_rate": 3.550721677252839e-05,
+      "loss": 0.0017,
+      "step": 1390
+    },
+    {
+      "epoch": 3.1965995142163166,
+      "grad_norm": 0.15755465626716614,
+      "learning_rate": 3.4746348949733965e-05,
+      "loss": 0.003,
+      "step": 1400
+    },
+    {
+      "epoch": 3.219459922846121,
+      "grad_norm": 0.017669400200247765,
+      "learning_rate": 3.398935630006236e-05,
+      "loss": 0.0031,
+      "step": 1410
+    },
+    {
+      "epoch": 3.2423203314759252,
+      "grad_norm": 0.07502660900354385,
+      "learning_rate": 3.32364311366562e-05,
+      "loss": 0.005,
+      "step": 1420
+    },
+    {
+      "epoch": 3.2651807401057296,
+      "grad_norm": 0.4353109300136566,
+      "learning_rate": 3.248776473931774e-05,
+      "loss": 0.0058,
+      "step": 1430
+    },
+    {
+      "epoch": 3.288041148735534,
+      "grad_norm": 0.06076102331280708,
+      "learning_rate": 3.174354730591447e-05,
+      "loss": 0.0055,
+      "step": 1440
+    },
+    {
+      "epoch": 3.3109015573653378,
+      "grad_norm": 0.04932214692234993,
+      "learning_rate": 3.100396790405948e-05,
+      "loss": 0.0041,
+      "step": 1450
+    },
+    {
+      "epoch": 3.333761965995142,
+      "grad_norm": 0.12315461784601212,
+      "learning_rate": 3.026921442307916e-05,
+      "loss": 0.0034,
+      "step": 1460
+    },
+    {
+      "epoch": 3.3566223746249464,
+      "grad_norm": 0.08378969877958298,
+      "learning_rate": 2.9539473526280005e-05,
+      "loss": 0.0021,
+      "step": 1470
+    },
+    {
+      "epoch": 3.3794827832547507,
+      "grad_norm": 0.1416824609041214,
+      "learning_rate": 2.8814930603527068e-05,
+      "loss": 0.0024,
+      "step": 1480
+    },
+    {
+      "epoch": 3.402343191884555,
+      "grad_norm": 0.09372381865978241,
+      "learning_rate": 2.809576972414587e-05,
+      "loss": 0.0023,
+      "step": 1490
+    },
+    {
+      "epoch": 3.4252036005143593,
+      "grad_norm": 0.16745346784591675,
+      "learning_rate": 2.738217359015981e-05,
+      "loss": 0.0041,
+      "step": 1500
+    },
+    {
+      "epoch": 3.4480640091441632,
+      "grad_norm": 0.1455969363451004,
+      "learning_rate": 2.6674323489874843e-05,
+      "loss": 0.0056,
+      "step": 1510
+    },
+    {
+      "epoch": 3.4709244177739675,
+      "grad_norm": 0.07298196107149124,
+      "learning_rate": 2.5972399251823488e-05,
+      "loss": 0.0034,
+      "step": 1520
+    },
+    {
+      "epoch": 3.493784826403772,
+      "grad_norm": 0.024875745177268982,
+      "learning_rate": 2.5276579199079486e-05,
+      "loss": 0.0043,
+      "step": 1530
+    },
+    {
+      "epoch": 3.516645235033576,
+      "grad_norm": 0.17137651145458221,
+      "learning_rate": 2.4587040103955134e-05,
+      "loss": 0.0041,
+      "step": 1540
+    },
+    {
+      "epoch": 3.5395056436633805,
+      "grad_norm": 0.10219382494688034,
+      "learning_rate": 2.39039571430924e-05,
+      "loss": 0.0037,
+      "step": 1550
+    },
+    {
+      "epoch": 3.562366052293185,
+      "grad_norm": 0.05997829884290695,
+      "learning_rate": 2.3227503852959453e-05,
+      "loss": 0.0025,
+      "step": 1560
+    },
+    {
+      "epoch": 3.585226460922989,
+      "grad_norm": 0.022572757676243782,
+      "learning_rate": 2.2557852085764053e-05,
+      "loss": 0.0087,
+      "step": 1570
+    },
+    {
+      "epoch": 3.6080868695527935,
+      "grad_norm": 0.025689126923680305,
+      "learning_rate": 2.189517196579453e-05,
+      "loss": 0.0046,
+      "step": 1580
+    },
+    {
+      "epoch": 3.6309472781825978,
+      "grad_norm": 0.19351957738399506,
+      "learning_rate": 2.1239631846200026e-05,
+      "loss": 0.0041,
+      "step": 1590
+    },
+    {
+      "epoch": 3.6538076868124016,
+      "grad_norm": 0.05244070664048195,
+      "learning_rate": 2.0591398266220502e-05,
+      "loss": 0.0025,
+      "step": 1600
+    },
+    {
+      "epoch": 3.676668095442206,
+      "grad_norm": 0.05331341549754143,
+      "learning_rate": 1.995063590887759e-05,
+      "loss": 0.0045,
+      "step": 1610
+    },
+    {
+      "epoch": 3.6995285040720103,
+      "grad_norm": 0.038474228233098984,
+      "learning_rate": 1.9317507559137184e-05,
+      "loss": 0.0039,
+      "step": 1620
+    },
+    {
+      "epoch": 3.7223889127018146,
+      "grad_norm": 0.046009331941604614,
+      "learning_rate": 1.8692174062553924e-05,
+      "loss": 0.004,
+      "step": 1630
+    },
+    {
+      "epoch": 3.745249321331619,
+      "grad_norm": 0.024187810719013214,
+      "learning_rate": 1.807479428440873e-05,
+      "loss": 0.0024,
+      "step": 1640
+    },
+    {
+      "epoch": 3.768109729961423,
+      "grad_norm": 0.07836172729730606,
+      "learning_rate": 1.746552506934917e-05,
+      "loss": 0.0027,
+      "step": 1650
+    },
+    {
+      "epoch": 3.790970138591227,
+      "grad_norm": 0.0379299558699131,
+      "learning_rate": 1.6864521201543197e-05,
+      "loss": 0.0032,
+      "step": 1660
+    },
+    {
+      "epoch": 3.8138305472210314,
+      "grad_norm": 0.04367607831954956,
+      "learning_rate": 1.627193536535656e-05,
+      "loss": 0.002,
+      "step": 1670
+    },
+    {
+      "epoch": 3.8366909558508357,
+      "grad_norm": 0.18003098666667938,
+      "learning_rate": 1.5687918106563326e-05,
+      "loss": 0.0025,
+      "step": 1680
+    },
+    {
+      "epoch": 3.85955136448064,
+      "grad_norm": 0.04013814404606819,
+      "learning_rate": 1.5112617794100047e-05,
+      "loss": 0.0026,
+      "step": 1690
+    },
+    {
+      "epoch": 3.8824117731104444,
+      "grad_norm": 0.030205566436052322,
+      "learning_rate": 1.454618058237272e-05,
+      "loss": 0.0029,
+      "step": 1700
+    },
+    {
+      "epoch": 3.9052721817402487,
+      "grad_norm": 0.10214164853096008,
+      "learning_rate": 1.3988750374126396e-05,
+      "loss": 0.0026,
+      "step": 1710
+    },
+    {
+      "epoch": 3.928132590370053,
+      "grad_norm": 0.027208510786294937,
+      "learning_rate": 1.344046878388695e-05,
+      "loss": 0.0026,
+      "step": 1720
+    },
+    {
+      "epoch": 3.9509929989998573,
+      "grad_norm": 0.020535435527563095,
+      "learning_rate": 1.2901475101983939e-05,
+      "loss": 0.0018,
+      "step": 1730
+    },
+    {
+      "epoch": 3.973853407629661,
+      "grad_norm": 0.03657793253660202,
+      "learning_rate": 1.2371906259164168e-05,
+      "loss": 0.0023,
+      "step": 1740
+    },
+    {
+      "epoch": 3.9967138162594655,
+      "grad_norm": 0.037314701825380325,
+      "learning_rate": 1.1851896791804507e-05,
+      "loss": 0.004,
+      "step": 1750
+    },
+    {
+      "epoch": 4.018288326903844,
+      "grad_norm": 0.01339447870850563,
+      "learning_rate": 1.1341578807733088e-05,
+      "loss": 0.0017,
+      "step": 1760
+    },
+    {
+      "epoch": 4.041148735533648,
+      "grad_norm": 0.0763229951262474,
+      "learning_rate": 1.0841081952667498e-05,
+      "loss": 0.0018,
+      "step": 1770
+    },
+    {
+      "epoch": 4.064009144163452,
+      "grad_norm": 0.029324688017368317,
+      "learning_rate": 1.0350533377278353e-05,
+      "loss": 0.0015,
+      "step": 1780
+    },
+    {
+      "epoch": 4.086869552793257,
+      "grad_norm": 0.021862059831619263,
+      "learning_rate": 9.870057704886908e-06,
+      "loss": 0.0011,
+      "step": 1790
+    },
+    {
+      "epoch": 4.10972996142306,
+      "grad_norm": 0.011852990835905075,
+      "learning_rate": 9.399776999804566e-06,
+      "loss": 0.0012,
+      "step": 1800
+    },
+    {
+      "epoch": 4.132590370052864,
+      "grad_norm": 0.022478003054857254,
+      "learning_rate": 8.939810736322574e-06,
+      "loss": 0.0013,
+      "step": 1810
+    },
+    {
+      "epoch": 4.155450778682669,
+      "grad_norm": 0.08652134984731674,
+      "learning_rate": 8.490275768359784e-06,
+      "loss": 0.0017,
+      "step": 1820
+    },
+    {
+      "epoch": 4.178311187312473,
+      "grad_norm": 0.03378741443157196,
+      "learning_rate": 8.051286299775951e-06,
+      "loss": 0.0015,
+      "step": 1830
+    },
+    {
+      "epoch": 4.201171595942277,
+      "grad_norm": 0.0582275353372097,
+      "learning_rate": 7.6229538553584556e-06,
+      "loss": 0.0011,
+      "step": 1840
+    },
+    {
+      "epoch": 4.224032004572082,
+      "grad_norm": 0.016311751678586006,
+      "learning_rate": 7.20538725248947e-06,
+      "loss": 0.0024,
+      "step": 1850
+    },
+    {
+      "epoch": 4.246892413201886,
+      "grad_norm": 0.017814885824918747,
+      "learning_rate": 6.798692573501114e-06,
+      "loss": 0.0011,
+      "step": 1860
+    },
+    {
+      "epoch": 4.26975282183169,
+      "grad_norm": 0.029111934825778008,
+      "learning_rate": 6.402973138725282e-06,
+      "loss": 0.0013,
+      "step": 1870
+    },
+    {
+      "epoch": 4.292613230461495,
+      "grad_norm": 0.08662671595811844,
+      "learning_rate": 6.018329480245255e-06,
+      "loss": 0.0017,
+      "step": 1880
+    },
+    {
+      "epoch": 4.315473639091299,
+      "grad_norm": 0.026320841163396835,
+      "learning_rate": 5.64485931635565e-06,
+      "loss": 0.0014,
+      "step": 1890
+    },
+    {
+      "epoch": 4.338334047721103,
+      "grad_norm": 0.01906999573111534,
+      "learning_rate": 5.2826575267371615e-06,
+      "loss": 0.0039,
+      "step": 1900
+    },
+    {
+      "epoch": 4.3611944563509075,
+      "grad_norm": 0.019031250849366188,
+      "learning_rate": 4.931816128352534e-06,
+      "loss": 0.0011,
+      "step": 1910
+    },
+    {
+      "epoch": 4.384054864980712,
+      "grad_norm": 0.14129675924777985,
+      "learning_rate": 4.592424252069705e-06,
+      "loss": 0.0017,
+      "step": 1920
+    },
+    {
+      "epoch": 4.406915273610516,
+      "grad_norm": 0.012528040446341038,
+      "learning_rate": 4.26456812001822e-06,
+      "loss": 0.0014,
+      "step": 1930
+    },
+    {
+      "epoch": 4.4297756822403205,
+      "grad_norm": 0.02767062373459339,
+      "learning_rate": 3.948331023684637e-06,
+      "loss": 0.0014,
+      "step": 1940
+    },
+    {
+      "epoch": 4.452636090870124,
+      "grad_norm": 0.03427803888916969,
+      "learning_rate": 3.64379330275233e-06,
+      "loss": 0.0014,
+      "step": 1950
+    },
+    {
+      "epoch": 4.475496499499928,
+      "grad_norm": 0.01602611131966114,
+      "learning_rate": 3.3510323246913887e-06,
+      "loss": 0.001,
+      "step": 1960
+    },
+    {
+      "epoch": 4.4983569081297325,
+      "grad_norm": 0.031283311545848846,
+      "learning_rate": 3.07012246510342e-06,
+      "loss": 0.001,
+      "step": 1970
+    },
+    {
+      "epoch": 4.521217316759537,
+      "grad_norm": 0.010646236129105091,
+      "learning_rate": 2.801135088826529e-06,
+      "loss": 0.0011,
+      "step": 1980
+    },
+    {
+      "epoch": 4.544077725389341,
+      "grad_norm": 0.040134090930223465,
+      "learning_rate": 2.5441385318051735e-06,
+      "loss": 0.0012,
+      "step": 1990
+    },
+    {
+      "epoch": 4.5669381340191455,
+      "grad_norm": 0.020084287971258163,
+      "learning_rate": 2.2991980837294757e-06,
+      "loss": 0.001,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2190,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.6707991595135795e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d307b97811482d7107b2c2d37efb72e66e5e343ee5862d771d5d8278d370a73a
+size 5777

checkpoint-2190/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-7B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.16.0

checkpoint-2190/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-2190/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15865247ad910ae584d24b575151e137dec2d53987a11d7af1ae4f40816988ee
+size 323014168

checkpoint-2190/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
+}

checkpoint-2190/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 %}

checkpoint-2190/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0c58ba268f2ef0c3fac7a4648c5ff3fb328efd6133b7049d8c46af5905d831
+size 646253819

checkpoint-2190/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5dafcd4d6bddeaf502e237c74f9c6117d902237d99b836f38755b92105ca39
+size 14645

checkpoint-2190/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a1695593ca728cae642c033ca23528a245dda65a37a0102e22bd339c20799fe
+size 1465

checkpoint-2190/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
+  }
+}

checkpoint-2190/tokenizer.json

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

checkpoint-2190/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": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-2190/trainer_state.json

@@ -0,0 +1,1567 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2190,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022860408629804256,
+      "grad_norm": 0.31346356868743896,
+      "learning_rate": 4.10958904109589e-06,
+      "loss": 0.4615,
+      "step": 10
+    },
+    {
+      "epoch": 0.04572081725960851,
+      "grad_norm": 0.3634890019893646,
+      "learning_rate": 8.675799086757991e-06,
+      "loss": 0.4707,
+      "step": 20
+    },
+    {
+      "epoch": 0.06858122588941278,
+      "grad_norm": 0.26333874464035034,
+      "learning_rate": 1.3242009132420092e-05,
+      "loss": 0.3731,
+      "step": 30
+    },
+    {
+      "epoch": 0.09144163451921702,
+      "grad_norm": 0.19899441301822662,
+      "learning_rate": 1.780821917808219e-05,
+      "loss": 0.2918,
+      "step": 40
+    },
+    {
+      "epoch": 0.11430204314902129,
+      "grad_norm": 0.10445400327444077,
+      "learning_rate": 2.237442922374429e-05,
+      "loss": 0.1518,
+      "step": 50
+    },
+    {
+      "epoch": 0.13716245177882555,
+      "grad_norm": 0.060141440480947495,
+      "learning_rate": 2.6940639269406392e-05,
+      "loss": 0.0826,
+      "step": 60
+    },
+    {
+      "epoch": 0.1600228604086298,
+      "grad_norm": 0.11565729230642319,
+      "learning_rate": 3.1506849315068496e-05,
+      "loss": 0.0897,
+      "step": 70
+    },
+    {
+      "epoch": 0.18288326903843405,
+      "grad_norm": 0.13073839247226715,
+      "learning_rate": 3.60730593607306e-05,
+      "loss": 0.0992,
+      "step": 80
+    },
+    {
+      "epoch": 0.2057436776682383,
+      "grad_norm": 0.08385579288005829,
+      "learning_rate": 4.063926940639269e-05,
+      "loss": 0.0867,
+      "step": 90
+    },
+    {
+      "epoch": 0.22860408629804257,
+      "grad_norm": 0.10868898034095764,
+      "learning_rate": 4.520547945205479e-05,
+      "loss": 0.1022,
+      "step": 100
+    },
+    {
+      "epoch": 0.25146449492784684,
+      "grad_norm": 0.10515399277210236,
+      "learning_rate": 4.977168949771689e-05,
+      "loss": 0.0866,
+      "step": 110
+    },
+    {
+      "epoch": 0.2743249035576511,
+      "grad_norm": 0.11809521168470383,
+      "learning_rate": 5.4337899543379e-05,
+      "loss": 0.0866,
+      "step": 120
+    },
+    {
+      "epoch": 0.29718531218745536,
+      "grad_norm": 0.09987114369869232,
+      "learning_rate": 5.89041095890411e-05,
+      "loss": 0.0942,
+      "step": 130
+    },
+    {
+      "epoch": 0.3200457208172596,
+      "grad_norm": 0.1236502081155777,
+      "learning_rate": 6.34703196347032e-05,
+      "loss": 0.0935,
+      "step": 140
+    },
+    {
+      "epoch": 0.3429061294470639,
+      "grad_norm": 0.09345820546150208,
+      "learning_rate": 6.803652968036531e-05,
+      "loss": 0.1001,
+      "step": 150
+    },
+    {
+      "epoch": 0.3657665380768681,
+      "grad_norm": 0.12369757890701294,
+      "learning_rate": 7.26027397260274e-05,
+      "loss": 0.0805,
+      "step": 160
+    },
+    {
+      "epoch": 0.38862694670667236,
+      "grad_norm": 0.12654580175876617,
+      "learning_rate": 7.716894977168951e-05,
+      "loss": 0.0704,
+      "step": 170
+    },
+    {
+      "epoch": 0.4114873553364766,
+      "grad_norm": 0.10067084431648254,
+      "learning_rate": 8.17351598173516e-05,
+      "loss": 0.0812,
+      "step": 180
+    },
+    {
+      "epoch": 0.4343477639662809,
+      "grad_norm": 0.10523034632205963,
+      "learning_rate": 8.630136986301371e-05,
+      "loss": 0.0897,
+      "step": 190
+    },
+    {
+      "epoch": 0.45720817259608515,
+      "grad_norm": 0.08805034309625626,
+      "learning_rate": 9.08675799086758e-05,
+      "loss": 0.1039,
+      "step": 200
+    },
+    {
+      "epoch": 0.4800685812258894,
+      "grad_norm": 0.10564622282981873,
+      "learning_rate": 9.543378995433791e-05,
+      "loss": 0.0931,
+      "step": 210
+    },
+    {
+      "epoch": 0.5029289898556937,
+      "grad_norm": 0.08823700249195099,
+      "learning_rate": 0.0001,
+      "loss": 0.0769,
+      "step": 220
+    },
+    {
+      "epoch": 0.5257893984854979,
+      "grad_norm": 0.07316570729017258,
+      "learning_rate": 9.999364877774174e-05,
+      "loss": 0.0893,
+      "step": 230
+    },
+    {
+      "epoch": 0.5486498071153022,
+      "grad_norm": 0.08555534482002258,
+      "learning_rate": 9.997459672448794e-05,
+      "loss": 0.0802,
+      "step": 240
+    },
+    {
+      "epoch": 0.5715102157451064,
+      "grad_norm": 0.1843150109052658,
+      "learning_rate": 9.994284868039156e-05,
+      "loss": 0.0736,
+      "step": 250
+    },
+    {
+      "epoch": 0.5943706243749107,
+      "grad_norm": 0.11401674896478653,
+      "learning_rate": 9.9898412711008e-05,
+      "loss": 0.0788,
+      "step": 260
+    },
+    {
+      "epoch": 0.6172310330047149,
+      "grad_norm": 0.07360777258872986,
+      "learning_rate": 9.984130010524597e-05,
+      "loss": 0.0807,
+      "step": 270
+    },
+    {
+      "epoch": 0.6400914416345193,
+      "grad_norm": 0.11163882166147232,
+      "learning_rate": 9.977152537249958e-05,
+      "loss": 0.072,
+      "step": 280
+    },
+    {
+      "epoch": 0.6629518502643235,
+      "grad_norm": 0.12346392124891281,
+      "learning_rate": 9.968910623896225e-05,
+      "loss": 0.0712,
+      "step": 290
+    },
+    {
+      "epoch": 0.6858122588941278,
+      "grad_norm": 0.13644632697105408,
+      "learning_rate": 9.95940636431234e-05,
+      "loss": 0.0765,
+      "step": 300
+    },
+    {
+      "epoch": 0.708672667523932,
+      "grad_norm": 0.09245093911886215,
+      "learning_rate": 9.948642173044905e-05,
+      "loss": 0.0797,
+      "step": 310
+    },
+    {
+      "epoch": 0.7315330761537362,
+      "grad_norm": 0.11467203497886658,
+      "learning_rate": 9.936620784724766e-05,
+      "loss": 0.0756,
+      "step": 320
+    },
+    {
+      "epoch": 0.7543934847835405,
+      "grad_norm": 0.12245265394449234,
+      "learning_rate": 9.923345253372287e-05,
+      "loss": 0.0671,
+      "step": 330
+    },
+    {
+      "epoch": 0.7772538934133447,
+      "grad_norm": 0.08666519820690155,
+      "learning_rate": 9.908818951621474e-05,
+      "loss": 0.0681,
+      "step": 340
+    },
+    {
+      "epoch": 0.800114302043149,
+      "grad_norm": 0.16961519420146942,
+      "learning_rate": 9.89304556986317e-05,
+      "loss": 0.072,
+      "step": 350
+    },
+    {
+      "epoch": 0.8229747106729532,
+      "grad_norm": 0.2313849776983261,
+      "learning_rate": 9.876029115307506e-05,
+      "loss": 0.0707,
+      "step": 360
+    },
+    {
+      "epoch": 0.8458351193027576,
+      "grad_norm": 0.14014111459255219,
+      "learning_rate": 9.85777391096588e-05,
+      "loss": 0.0807,
+      "step": 370
+    },
+    {
+      "epoch": 0.8686955279325618,
+      "grad_norm": 0.0991162583231926,
+      "learning_rate": 9.838284594552697e-05,
+      "loss": 0.0736,
+      "step": 380
+    },
+    {
+      "epoch": 0.8915559365623661,
+      "grad_norm": 0.14600183069705963,
+      "learning_rate": 9.817566117307167e-05,
+      "loss": 0.073,
+      "step": 390
+    },
+    {
+      "epoch": 0.9144163451921703,
+      "grad_norm": 0.12519070506095886,
+      "learning_rate": 9.79562374273544e-05,
+      "loss": 0.0573,
+      "step": 400
+    },
+    {
+      "epoch": 0.9372767538219746,
+      "grad_norm": 0.14949887990951538,
+      "learning_rate": 9.77246304527343e-05,
+      "loss": 0.0691,
+      "step": 410
+    },
+    {
+      "epoch": 0.9601371624517788,
+      "grad_norm": 0.13667669892311096,
+      "learning_rate": 9.748089908870627e-05,
+      "loss": 0.052,
+      "step": 420
+    },
+    {
+      "epoch": 0.982997571081583,
+      "grad_norm": 0.07336350530385971,
+      "learning_rate": 9.722510525495286e-05,
+      "loss": 0.0698,
+      "step": 430
+    },
+    {
+      "epoch": 1.004572081725961,
+      "grad_norm": 0.1134289801120758,
+      "learning_rate": 9.69573139356137e-05,
+      "loss": 0.0621,
+      "step": 440
+    },
+    {
+      "epoch": 1.027432490355765,
+      "grad_norm": 0.11676439642906189,
+      "learning_rate": 9.66775931627763e-05,
+      "loss": 0.0474,
+      "step": 450
+    },
+    {
+      "epoch": 1.0502928989855693,
+      "grad_norm": 0.14386767148971558,
+      "learning_rate": 9.638601399919259e-05,
+      "loss": 0.0496,
+      "step": 460
+    },
+    {
+      "epoch": 1.0731533076153736,
+      "grad_norm": 0.16757084429264069,
+      "learning_rate": 9.608265052022556e-05,
+      "loss": 0.0493,
+      "step": 470
+    },
+    {
+      "epoch": 1.096013716245178,
+      "grad_norm": 0.12976950407028198,
+      "learning_rate": 9.576757979503037e-05,
+      "loss": 0.0513,
+      "step": 480
+    },
+    {
+      "epoch": 1.118874124874982,
+      "grad_norm": 0.21009308099746704,
+      "learning_rate": 9.544088186697515e-05,
+      "loss": 0.0464,
+      "step": 490
+    },
+    {
+      "epoch": 1.1417345335047864,
+      "grad_norm": 0.1863221377134323,
+      "learning_rate": 9.5102639733306e-05,
+      "loss": 0.0388,
+      "step": 500
+    },
+    {
+      "epoch": 1.1645949421345907,
+      "grad_norm": 0.1924988180398941,
+      "learning_rate": 9.475293932406162e-05,
+      "loss": 0.0517,
+      "step": 510
+    },
+    {
+      "epoch": 1.1874553507643948,
+      "grad_norm": 0.1228746697306633,
+      "learning_rate": 9.439186948024297e-05,
+      "loss": 0.0475,
+      "step": 520
+    },
+    {
+      "epoch": 1.210315759394199,
+      "grad_norm": 0.18384294211864471,
+      "learning_rate": 9.401952193124315e-05,
+      "loss": 0.046,
+      "step": 530
+    },
+    {
+      "epoch": 1.2331761680240034,
+      "grad_norm": 0.1352134793996811,
+      "learning_rate": 9.363599127154383e-05,
+      "loss": 0.0454,
+      "step": 540
+    },
+    {
+      "epoch": 1.2560365766538077,
+      "grad_norm": 0.07320581376552582,
+      "learning_rate": 9.324137493668352e-05,
+      "loss": 0.0379,
+      "step": 550
+    },
+    {
+      "epoch": 1.278896985283612,
+      "grad_norm": 0.14689098298549652,
+      "learning_rate": 9.283577317850419e-05,
+      "loss": 0.0419,
+      "step": 560
+    },
+    {
+      "epoch": 1.3017573939134162,
+      "grad_norm": 0.14588995277881622,
+      "learning_rate": 9.24192890396824e-05,
+      "loss": 0.0451,
+      "step": 570
+    },
+    {
+      "epoch": 1.3246178025432205,
+      "grad_norm": 0.17893975973129272,
+      "learning_rate": 9.19920283275515e-05,
+      "loss": 0.0405,
+      "step": 580
+    },
+    {
+      "epoch": 1.3474782111730248,
+      "grad_norm": 0.17961391806602478,
+      "learning_rate": 9.155409958722124e-05,
+      "loss": 0.0371,
+      "step": 590
+    },
+    {
+      "epoch": 1.370338619802829,
+      "grad_norm": 0.18520987033843994,
+      "learning_rate": 9.110561407400218e-05,
+      "loss": 0.0447,
+      "step": 600
+    },
+    {
+      "epoch": 1.3931990284326332,
+      "grad_norm": 0.14877571165561676,
+      "learning_rate": 9.064668572514127e-05,
+      "loss": 0.0429,
+      "step": 610
+    },
+    {
+      "epoch": 1.4160594370624375,
+      "grad_norm": 0.1054820641875267,
+      "learning_rate": 9.01774311308763e-05,
+      "loss": 0.036,
+      "step": 620
+    },
+    {
+      "epoch": 1.4389198456922419,
+      "grad_norm": 0.1029554158449173,
+      "learning_rate": 8.96979695048162e-05,
+      "loss": 0.0473,
+      "step": 630
+    },
+    {
+      "epoch": 1.461780254322046,
+      "grad_norm": 0.26157063245773315,
+      "learning_rate": 8.920842265365503e-05,
+      "loss": 0.0343,
+      "step": 640
+    },
+    {
+      "epoch": 1.4846406629518503,
+      "grad_norm": 0.12941773235797882,
+      "learning_rate": 8.870891494622709e-05,
+      "loss": 0.0522,
+      "step": 650
+    },
+    {
+      "epoch": 1.5075010715816544,
+      "grad_norm": 0.11229275912046432,
+      "learning_rate": 8.819957328191117e-05,
+      "loss": 0.0385,
+      "step": 660
+    },
+    {
+      "epoch": 1.5303614802114587,
+      "grad_norm": 0.2675265073776245,
+      "learning_rate": 8.76805270583919e-05,
+      "loss": 0.0492,
+      "step": 670
+    },
+    {
+      "epoch": 1.553221888841263,
+      "grad_norm": 0.18951663374900818,
+      "learning_rate": 8.715190813878637e-05,
+      "loss": 0.0353,
+      "step": 680
+    },
+    {
+      "epoch": 1.5760822974710673,
+      "grad_norm": 0.14573994278907776,
+      "learning_rate": 8.661385081814453e-05,
+      "loss": 0.0334,
+      "step": 690
+    },
+    {
+      "epoch": 1.5989427061008716,
+      "grad_norm": 0.08593331277370453,
+      "learning_rate": 8.606649178933163e-05,
+      "loss": 0.0315,
+      "step": 700
+    },
+    {
+      "epoch": 1.621803114730676,
+      "grad_norm": 0.20985154807567596,
+      "learning_rate": 8.550997010830154e-05,
+      "loss": 0.0369,
+      "step": 710
+    },
+    {
+      "epoch": 1.64466352336048,
+      "grad_norm": 0.2964492738246918,
+      "learning_rate": 8.494442715876976e-05,
+      "loss": 0.0283,
+      "step": 720
+    },
+    {
+      "epoch": 1.6675239319902844,
+      "grad_norm": 0.11921142041683197,
+      "learning_rate": 8.437000661629506e-05,
+      "loss": 0.0312,
+      "step": 730
+    },
+    {
+      "epoch": 1.6903843406200885,
+      "grad_norm": 0.20576898753643036,
+      "learning_rate": 8.378685441177886e-05,
+      "loss": 0.0348,
+      "step": 740
+    },
+    {
+      "epoch": 1.7132447492498928,
+      "grad_norm": 0.27900010347366333,
+      "learning_rate": 8.31951186943916e-05,
+      "loss": 0.0294,
+      "step": 750
+    },
+    {
+      "epoch": 1.736105157879697,
+      "grad_norm": 0.18257662653923035,
+      "learning_rate": 8.259494979393563e-05,
+      "loss": 0.0264,
+      "step": 760
+    },
+    {
+      "epoch": 1.7589655665095014,
+      "grad_norm": 0.16247795522212982,
+      "learning_rate": 8.198650018265415e-05,
+      "loss": 0.0385,
+      "step": 770
+    },
+    {
+      "epoch": 1.7818259751393057,
+      "grad_norm": 0.18227055668830872,
+      "learning_rate": 8.136992443649571e-05,
+      "loss": 0.0333,
+      "step": 780
+    },
+    {
+      "epoch": 1.8046863837691098,
+      "grad_norm": 0.1283257156610489,
+      "learning_rate": 8.074537919584443e-05,
+      "loss": 0.0373,
+      "step": 790
+    },
+    {
+      "epoch": 1.8275467923989142,
+      "grad_norm": 0.21598616242408752,
+      "learning_rate": 8.011302312572566e-05,
+      "loss": 0.0427,
+      "step": 800
+    },
+    {
+      "epoch": 1.8504072010287183,
+      "grad_norm": 0.18352819979190826,
+      "learning_rate": 7.947301687549731e-05,
+      "loss": 0.04,
+      "step": 810
+    },
+    {
+      "epoch": 1.8732676096585226,
+      "grad_norm": 0.28778374195098877,
+      "learning_rate": 7.882552303803705e-05,
+      "loss": 0.035,
+      "step": 820
+    },
+    {
+      "epoch": 1.8961280182883269,
+      "grad_norm": 0.11134298145771027,
+      "learning_rate": 7.817070610843579e-05,
+      "loss": 0.0281,
+      "step": 830
+    },
+    {
+      "epoch": 1.9189884269181312,
+      "grad_norm": 0.2428896129131317,
+      "learning_rate": 7.750873244220787e-05,
+      "loss": 0.0326,
+      "step": 840
+    },
+    {
+      "epoch": 1.9418488355479355,
+      "grad_norm": 0.21082095801830292,
+      "learning_rate": 7.68397702130286e-05,
+      "loss": 0.0316,
+      "step": 850
+    },
+    {
+      "epoch": 1.9647092441777396,
+      "grad_norm": 0.14655885100364685,
+      "learning_rate": 7.616398937000999e-05,
+      "loss": 0.0292,
+      "step": 860
+    },
+    {
+      "epoch": 1.987569652807544,
+      "grad_norm": 0.16203175485134125,
+      "learning_rate": 7.548156159452531e-05,
+      "loss": 0.0272,
+      "step": 870
+    },
+    {
+      "epoch": 2.009144163451922,
+      "grad_norm": 0.1306605190038681,
+      "learning_rate": 7.479266025659365e-05,
+      "loss": 0.0209,
+      "step": 880
+    },
+    {
+      "epoch": 2.032004572081726,
+      "grad_norm": 0.13496187329292297,
+      "learning_rate": 7.409746037083548e-05,
+      "loss": 0.0138,
+      "step": 890
+    },
+    {
+      "epoch": 2.05486498071153,
+      "grad_norm": 0.18669717013835907,
+      "learning_rate": 7.339613855201032e-05,
+      "loss": 0.0149,
+      "step": 900
+    },
+    {
+      "epoch": 2.0777253893413343,
+      "grad_norm": 0.1247486025094986,
+      "learning_rate": 7.2688872970148e-05,
+      "loss": 0.0128,
+      "step": 910
+    },
+    {
+      "epoch": 2.1005857979711386,
+      "grad_norm": 0.1156638115644455,
+      "learning_rate": 7.197584330528478e-05,
+      "loss": 0.0117,
+      "step": 920
+    },
+    {
+      "epoch": 2.123446206600943,
+      "grad_norm": 0.03096736967563629,
+      "learning_rate": 7.125723070181576e-05,
+      "loss": 0.0143,
+      "step": 930
+    },
+    {
+      "epoch": 2.1463066152307473,
+      "grad_norm": 0.04739869013428688,
+      "learning_rate": 7.053321772247545e-05,
+      "loss": 0.0099,
+      "step": 940
+    },
+    {
+      "epoch": 2.1691670238605516,
+      "grad_norm": 0.1429280787706375,
+      "learning_rate": 6.980398830195785e-05,
+      "loss": 0.0109,
+      "step": 950
+    },
+    {
+      "epoch": 2.192027432490356,
+      "grad_norm": 0.2534593343734741,
+      "learning_rate": 6.906972770018802e-05,
+      "loss": 0.0163,
+      "step": 960
+    },
+    {
+      "epoch": 2.2148878411201602,
+      "grad_norm": 0.1354377567768097,
+      "learning_rate": 6.833062245525705e-05,
+      "loss": 0.0147,
+      "step": 970
+    },
+    {
+      "epoch": 2.237748249749964,
+      "grad_norm": 0.06828989833593369,
+      "learning_rate": 6.758686033603225e-05,
+      "loss": 0.0201,
+      "step": 980
+    },
+    {
+      "epoch": 2.2606086583797684,
+      "grad_norm": 0.14169731736183167,
+      "learning_rate": 6.683863029445469e-05,
+      "loss": 0.0133,
+      "step": 990
+    },
+    {
+      "epoch": 2.2834690670095728,
+      "grad_norm": 0.04132571816444397,
+      "learning_rate": 6.608612241753614e-05,
+      "loss": 0.0097,
+      "step": 1000
+    },
+    {
+      "epoch": 2.306329475639377,
+      "grad_norm": 0.3469948172569275,
+      "learning_rate": 6.532952787906771e-05,
+      "loss": 0.0139,
+      "step": 1010
+    },
+    {
+      "epoch": 2.3291898842691814,
+      "grad_norm": 0.04748811200261116,
+      "learning_rate": 6.45690388910523e-05,
+      "loss": 0.0153,
+      "step": 1020
+    },
+    {
+      "epoch": 2.3520502928989857,
+      "grad_norm": 0.1330500990152359,
+      "learning_rate": 6.380484865487347e-05,
+      "loss": 0.015,
+      "step": 1030
+    },
+    {
+      "epoch": 2.3749107015287896,
+      "grad_norm": 0.14051929116249084,
+      "learning_rate": 6.303715131221264e-05,
+      "loss": 0.0069,
+      "step": 1040
+    },
+    {
+      "epoch": 2.397771110158594,
+      "grad_norm": 0.07501324266195297,
+      "learning_rate": 6.22661418957279e-05,
+      "loss": 0.0101,
+      "step": 1050
+    },
+    {
+      "epoch": 2.420631518788398,
+      "grad_norm": 0.1099422499537468,
+      "learning_rate": 6.149201627950593e-05,
+      "loss": 0.013,
+      "step": 1060
+    },
+    {
+      "epoch": 2.4434919274182025,
+      "grad_norm": 0.09372354298830032,
+      "learning_rate": 6.071497112930047e-05,
+      "loss": 0.0126,
+      "step": 1070
+    },
+    {
+      "epoch": 2.466352336048007,
+      "grad_norm": 0.09480420500040054,
+      "learning_rate": 5.99352038525697e-05,
+      "loss": 0.0127,
+      "step": 1080
+    },
+    {
+      "epoch": 2.489212744677811,
+      "grad_norm": 0.1486363410949707,
+      "learning_rate": 5.9152912548324976e-05,
+      "loss": 0.016,
+      "step": 1090
+    },
+    {
+      "epoch": 2.5120731533076155,
+      "grad_norm": 0.10003609955310822,
+      "learning_rate": 5.836829595680406e-05,
+      "loss": 0.0128,
+      "step": 1100
+    },
+    {
+      "epoch": 2.53493356193742,
+      "grad_norm": 0.08636961132287979,
+      "learning_rate": 5.758155340898137e-05,
+      "loss": 0.0119,
+      "step": 1110
+    },
+    {
+      "epoch": 2.557793970567224,
+      "grad_norm": 0.11953787505626678,
+      "learning_rate": 5.679288477592815e-05,
+      "loss": 0.0097,
+      "step": 1120
+    },
+    {
+      "epoch": 2.580654379197028,
+      "grad_norm": 0.06493639945983887,
+      "learning_rate": 5.600249041803545e-05,
+      "loss": 0.0105,
+      "step": 1130
+    },
+    {
+      "epoch": 2.6035147878268323,
+      "grad_norm": 0.12084943801164627,
+      "learning_rate": 5.5210571134112824e-05,
+      "loss": 0.0122,
+      "step": 1140
+    },
+    {
+      "epoch": 2.6263751964566366,
+      "grad_norm": 0.13135117292404175,
+      "learning_rate": 5.44173281103756e-05,
+      "loss": 0.0142,
+      "step": 1150
+    },
+    {
+      "epoch": 2.649235605086441,
+      "grad_norm": 0.137589693069458,
+      "learning_rate": 5.362296286933371e-05,
+      "loss": 0.0126,
+      "step": 1160
+    },
+    {
+      "epoch": 2.6720960137162453,
+      "grad_norm": 0.058550190180540085,
+      "learning_rate": 5.282767721859516e-05,
+      "loss": 0.0076,
+      "step": 1170
+    },
+    {
+      "epoch": 2.6949564223460496,
+      "grad_norm": 0.07393407076597214,
+      "learning_rate": 5.203167319959702e-05,
+      "loss": 0.012,
+      "step": 1180
+    },
+    {
+      "epoch": 2.7178168309758535,
+      "grad_norm": 0.1508752703666687,
+      "learning_rate": 5.123515303627698e-05,
+      "loss": 0.009,
+      "step": 1190
+    },
+    {
+      "epoch": 2.740677239605658,
+      "grad_norm": 0.1534973382949829,
+      "learning_rate": 5.0438319083698714e-05,
+      "loss": 0.0101,
+      "step": 1200
+    },
+    {
+      "epoch": 2.763537648235462,
+      "grad_norm": 0.14507421851158142,
+      "learning_rate": 4.9641373776643616e-05,
+      "loss": 0.0081,
+      "step": 1210
+    },
+    {
+      "epoch": 2.7863980568652664,
+      "grad_norm": 0.1377381533384323,
+      "learning_rate": 4.8844519578182604e-05,
+      "loss": 0.0109,
+      "step": 1220
+    },
+    {
+      "epoch": 2.8092584654950707,
+      "grad_norm": 0.2066635936498642,
+      "learning_rate": 4.804795892824056e-05,
+      "loss": 0.0135,
+      "step": 1230
+    },
+    {
+      "epoch": 2.832118874124875,
+      "grad_norm": 0.05857717618346214,
+      "learning_rate": 4.7251894192166654e-05,
+      "loss": 0.0076,
+      "step": 1240
+    },
+    {
+      "epoch": 2.8549792827546794,
+      "grad_norm": 0.168072909116745,
+      "learning_rate": 4.645652760932376e-05,
+      "loss": 0.009,
+      "step": 1250
+    },
+    {
+      "epoch": 2.8778396913844837,
+      "grad_norm": 0.17164477705955505,
+      "learning_rate": 4.566206124170963e-05,
+      "loss": 0.0112,
+      "step": 1260
+    },
+    {
+      "epoch": 2.900700100014288,
+      "grad_norm": 0.15097732841968536,
+      "learning_rate": 4.486869692262337e-05,
+      "loss": 0.0094,
+      "step": 1270
+    },
+    {
+      "epoch": 2.923560508644092,
+      "grad_norm": 0.0871570035815239,
+      "learning_rate": 4.407663620538985e-05,
+      "loss": 0.0101,
+      "step": 1280
+    },
+    {
+      "epoch": 2.946420917273896,
+      "grad_norm": 0.13305386900901794,
+      "learning_rate": 4.328608031215539e-05,
+      "loss": 0.0092,
+      "step": 1290
+    },
+    {
+      "epoch": 2.9692813259037005,
+      "grad_norm": 0.23256619274616241,
+      "learning_rate": 4.249723008276737e-05,
+      "loss": 0.015,
+      "step": 1300
+    },
+    {
+      "epoch": 2.992141734533505,
+      "grad_norm": 0.10129191726446152,
+      "learning_rate": 4.171028592375125e-05,
+      "loss": 0.0124,
+      "step": 1310
+    },
+    {
+      "epoch": 3.0137162451778825,
+      "grad_norm": 0.15339592099189758,
+      "learning_rate": 4.092544775739735e-05,
+      "loss": 0.0067,
+      "step": 1320
+    },
+    {
+      "epoch": 3.036576653807687,
+      "grad_norm": 0.03447636589407921,
+      "learning_rate": 4.0142914970970926e-05,
+      "loss": 0.0047,
+      "step": 1330
+    },
+    {
+      "epoch": 3.059437062437491,
+      "grad_norm": 0.056881342083215714,
+      "learning_rate": 3.9362886366058025e-05,
+      "loss": 0.0074,
+      "step": 1340
+    },
+    {
+      "epoch": 3.0822974710672955,
+      "grad_norm": 0.22134284675121307,
+      "learning_rate": 3.858556010806013e-05,
+      "loss": 0.004,
+      "step": 1350
+    },
+    {
+      "epoch": 3.1051578796970998,
+      "grad_norm": 0.12356160581111908,
+      "learning_rate": 3.781113367585053e-05,
+      "loss": 0.0048,
+      "step": 1360
+    },
+    {
+      "epoch": 3.1280182883269037,
+      "grad_norm": 0.03940752521157265,
+      "learning_rate": 3.703980381160497e-05,
+      "loss": 0.003,
+      "step": 1370
+    },
+    {
+      "epoch": 3.150878696956708,
+      "grad_norm": 0.09747901558876038,
+      "learning_rate": 3.627176647081954e-05,
+      "loss": 0.0056,
+      "step": 1380
+    },
+    {
+      "epoch": 3.1737391055865123,
+      "grad_norm": 0.016509221866726875,
+      "learning_rate": 3.550721677252839e-05,
+      "loss": 0.0017,
+      "step": 1390
+    },
+    {
+      "epoch": 3.1965995142163166,
+      "grad_norm": 0.15755465626716614,
+      "learning_rate": 3.4746348949733965e-05,
+      "loss": 0.003,
+      "step": 1400
+    },
+    {
+      "epoch": 3.219459922846121,
+      "grad_norm": 0.017669400200247765,
+      "learning_rate": 3.398935630006236e-05,
+      "loss": 0.0031,
+      "step": 1410
+    },
+    {
+      "epoch": 3.2423203314759252,
+      "grad_norm": 0.07502660900354385,
+      "learning_rate": 3.32364311366562e-05,
+      "loss": 0.005,
+      "step": 1420
+    },
+    {
+      "epoch": 3.2651807401057296,
+      "grad_norm": 0.4353109300136566,
+      "learning_rate": 3.248776473931774e-05,
+      "loss": 0.0058,
+      "step": 1430
+    },
+    {
+      "epoch": 3.288041148735534,
+      "grad_norm": 0.06076102331280708,
+      "learning_rate": 3.174354730591447e-05,
+      "loss": 0.0055,
+      "step": 1440
+    },
+    {
+      "epoch": 3.3109015573653378,
+      "grad_norm": 0.04932214692234993,
+      "learning_rate": 3.100396790405948e-05,
+      "loss": 0.0041,
+      "step": 1450
+    },
+    {
+      "epoch": 3.333761965995142,
+      "grad_norm": 0.12315461784601212,
+      "learning_rate": 3.026921442307916e-05,
+      "loss": 0.0034,
+      "step": 1460
+    },
+    {
+      "epoch": 3.3566223746249464,
+      "grad_norm": 0.08378969877958298,
+      "learning_rate": 2.9539473526280005e-05,
+      "loss": 0.0021,
+      "step": 1470
+    },
+    {
+      "epoch": 3.3794827832547507,
+      "grad_norm": 0.1416824609041214,
+      "learning_rate": 2.8814930603527068e-05,
+      "loss": 0.0024,
+      "step": 1480
+    },
+    {
+      "epoch": 3.402343191884555,
+      "grad_norm": 0.09372381865978241,
+      "learning_rate": 2.809576972414587e-05,
+      "loss": 0.0023,
+      "step": 1490
+    },
+    {
+      "epoch": 3.4252036005143593,
+      "grad_norm": 0.16745346784591675,
+      "learning_rate": 2.738217359015981e-05,
+      "loss": 0.0041,
+      "step": 1500
+    },
+    {
+      "epoch": 3.4480640091441632,
+      "grad_norm": 0.1455969363451004,
+      "learning_rate": 2.6674323489874843e-05,
+      "loss": 0.0056,
+      "step": 1510
+    },
+    {
+      "epoch": 3.4709244177739675,
+      "grad_norm": 0.07298196107149124,
+      "learning_rate": 2.5972399251823488e-05,
+      "loss": 0.0034,
+      "step": 1520
+    },
+    {
+      "epoch": 3.493784826403772,
+      "grad_norm": 0.024875745177268982,
+      "learning_rate": 2.5276579199079486e-05,
+      "loss": 0.0043,
+      "step": 1530
+    },
+    {
+      "epoch": 3.516645235033576,
+      "grad_norm": 0.17137651145458221,
+      "learning_rate": 2.4587040103955134e-05,
+      "loss": 0.0041,
+      "step": 1540
+    },
+    {
+      "epoch": 3.5395056436633805,
+      "grad_norm": 0.10219382494688034,
+      "learning_rate": 2.39039571430924e-05,
+      "loss": 0.0037,
+      "step": 1550
+    },
+    {
+      "epoch": 3.562366052293185,
+      "grad_norm": 0.05997829884290695,
+      "learning_rate": 2.3227503852959453e-05,
+      "loss": 0.0025,
+      "step": 1560
+    },
+    {
+      "epoch": 3.585226460922989,
+      "grad_norm": 0.022572757676243782,
+      "learning_rate": 2.2557852085764053e-05,
+      "loss": 0.0087,
+      "step": 1570
+    },
+    {
+      "epoch": 3.6080868695527935,
+      "grad_norm": 0.025689126923680305,
+      "learning_rate": 2.189517196579453e-05,
+      "loss": 0.0046,
+      "step": 1580
+    },
+    {
+      "epoch": 3.6309472781825978,
+      "grad_norm": 0.19351957738399506,
+      "learning_rate": 2.1239631846200026e-05,
+      "loss": 0.0041,
+      "step": 1590
+    },
+    {
+      "epoch": 3.6538076868124016,
+      "grad_norm": 0.05244070664048195,
+      "learning_rate": 2.0591398266220502e-05,
+      "loss": 0.0025,
+      "step": 1600
+    },
+    {
+      "epoch": 3.676668095442206,
+      "grad_norm": 0.05331341549754143,
+      "learning_rate": 1.995063590887759e-05,
+      "loss": 0.0045,
+      "step": 1610
+    },
+    {
+      "epoch": 3.6995285040720103,
+      "grad_norm": 0.038474228233098984,
+      "learning_rate": 1.9317507559137184e-05,
+      "loss": 0.0039,
+      "step": 1620
+    },
+    {
+      "epoch": 3.7223889127018146,
+      "grad_norm": 0.046009331941604614,
+      "learning_rate": 1.8692174062553924e-05,
+      "loss": 0.004,
+      "step": 1630
+    },
+    {
+      "epoch": 3.745249321331619,
+      "grad_norm": 0.024187810719013214,
+      "learning_rate": 1.807479428440873e-05,
+      "loss": 0.0024,
+      "step": 1640
+    },
+    {
+      "epoch": 3.768109729961423,
+      "grad_norm": 0.07836172729730606,
+      "learning_rate": 1.746552506934917e-05,
+      "loss": 0.0027,
+      "step": 1650
+    },
+    {
+      "epoch": 3.790970138591227,
+      "grad_norm": 0.0379299558699131,
+      "learning_rate": 1.6864521201543197e-05,
+      "loss": 0.0032,
+      "step": 1660
+    },
+    {
+      "epoch": 3.8138305472210314,
+      "grad_norm": 0.04367607831954956,
+      "learning_rate": 1.627193536535656e-05,
+      "loss": 0.002,
+      "step": 1670
+    },
+    {
+      "epoch": 3.8366909558508357,
+      "grad_norm": 0.18003098666667938,
+      "learning_rate": 1.5687918106563326e-05,
+      "loss": 0.0025,
+      "step": 1680
+    },
+    {
+      "epoch": 3.85955136448064,
+      "grad_norm": 0.04013814404606819,
+      "learning_rate": 1.5112617794100047e-05,
+      "loss": 0.0026,
+      "step": 1690
+    },
+    {
+      "epoch": 3.8824117731104444,
+      "grad_norm": 0.030205566436052322,
+      "learning_rate": 1.454618058237272e-05,
+      "loss": 0.0029,
+      "step": 1700
+    },
+    {
+      "epoch": 3.9052721817402487,
+      "grad_norm": 0.10214164853096008,
+      "learning_rate": 1.3988750374126396e-05,
+      "loss": 0.0026,
+      "step": 1710
+    },
+    {
+      "epoch": 3.928132590370053,
+      "grad_norm": 0.027208510786294937,
+      "learning_rate": 1.344046878388695e-05,
+      "loss": 0.0026,
+      "step": 1720
+    },
+    {
+      "epoch": 3.9509929989998573,
+      "grad_norm": 0.020535435527563095,
+      "learning_rate": 1.2901475101983939e-05,
+      "loss": 0.0018,
+      "step": 1730
+    },
+    {
+      "epoch": 3.973853407629661,
+      "grad_norm": 0.03657793253660202,
+      "learning_rate": 1.2371906259164168e-05,
+      "loss": 0.0023,
+      "step": 1740
+    },
+    {
+      "epoch": 3.9967138162594655,
+      "grad_norm": 0.037314701825380325,
+      "learning_rate": 1.1851896791804507e-05,
+      "loss": 0.004,
+      "step": 1750
+    },
+    {
+      "epoch": 4.018288326903844,
+      "grad_norm": 0.01339447870850563,
+      "learning_rate": 1.1341578807733088e-05,
+      "loss": 0.0017,
+      "step": 1760
+    },
+    {
+      "epoch": 4.041148735533648,
+      "grad_norm": 0.0763229951262474,
+      "learning_rate": 1.0841081952667498e-05,
+      "loss": 0.0018,
+      "step": 1770
+    },
+    {
+      "epoch": 4.064009144163452,
+      "grad_norm": 0.029324688017368317,
+      "learning_rate": 1.0350533377278353e-05,
+      "loss": 0.0015,
+      "step": 1780
+    },
+    {
+      "epoch": 4.086869552793257,
+      "grad_norm": 0.021862059831619263,
+      "learning_rate": 9.870057704886908e-06,
+      "loss": 0.0011,
+      "step": 1790
+    },
+    {
+      "epoch": 4.10972996142306,
+      "grad_norm": 0.011852990835905075,
+      "learning_rate": 9.399776999804566e-06,
+      "loss": 0.0012,
+      "step": 1800
+    },
+    {
+      "epoch": 4.132590370052864,
+      "grad_norm": 0.022478003054857254,
+      "learning_rate": 8.939810736322574e-06,
+      "loss": 0.0013,
+      "step": 1810
+    },
+    {
+      "epoch": 4.155450778682669,
+      "grad_norm": 0.08652134984731674,
+      "learning_rate": 8.490275768359784e-06,
+      "loss": 0.0017,
+      "step": 1820
+    },
+    {
+      "epoch": 4.178311187312473,
+      "grad_norm": 0.03378741443157196,
+      "learning_rate": 8.051286299775951e-06,
+      "loss": 0.0015,
+      "step": 1830
+    },
+    {
+      "epoch": 4.201171595942277,
+      "grad_norm": 0.0582275353372097,
+      "learning_rate": 7.6229538553584556e-06,
+      "loss": 0.0011,
+      "step": 1840
+    },
+    {
+      "epoch": 4.224032004572082,
+      "grad_norm": 0.016311751678586006,
+      "learning_rate": 7.20538725248947e-06,
+      "loss": 0.0024,
+      "step": 1850
+    },
+    {
+      "epoch": 4.246892413201886,
+      "grad_norm": 0.017814885824918747,
+      "learning_rate": 6.798692573501114e-06,
+      "loss": 0.0011,
+      "step": 1860
+    },
+    {
+      "epoch": 4.26975282183169,
+      "grad_norm": 0.029111934825778008,
+      "learning_rate": 6.402973138725282e-06,
+      "loss": 0.0013,
+      "step": 1870
+    },
+    {
+      "epoch": 4.292613230461495,
+      "grad_norm": 0.08662671595811844,
+      "learning_rate": 6.018329480245255e-06,
+      "loss": 0.0017,
+      "step": 1880
+    },
+    {
+      "epoch": 4.315473639091299,
+      "grad_norm": 0.026320841163396835,
+      "learning_rate": 5.64485931635565e-06,
+      "loss": 0.0014,
+      "step": 1890
+    },
+    {
+      "epoch": 4.338334047721103,
+      "grad_norm": 0.01906999573111534,
+      "learning_rate": 5.2826575267371615e-06,
+      "loss": 0.0039,
+      "step": 1900
+    },
+    {
+      "epoch": 4.3611944563509075,
+      "grad_norm": 0.019031250849366188,
+      "learning_rate": 4.931816128352534e-06,
+      "loss": 0.0011,
+      "step": 1910
+    },
+    {
+      "epoch": 4.384054864980712,
+      "grad_norm": 0.14129675924777985,
+      "learning_rate": 4.592424252069705e-06,
+      "loss": 0.0017,
+      "step": 1920
+    },
+    {
+      "epoch": 4.406915273610516,
+      "grad_norm": 0.012528040446341038,
+      "learning_rate": 4.26456812001822e-06,
+      "loss": 0.0014,
+      "step": 1930
+    },
+    {
+      "epoch": 4.4297756822403205,
+      "grad_norm": 0.02767062373459339,
+      "learning_rate": 3.948331023684637e-06,
+      "loss": 0.0014,
+      "step": 1940
+    },
+    {
+      "epoch": 4.452636090870124,
+      "grad_norm": 0.03427803888916969,
+      "learning_rate": 3.64379330275233e-06,
+      "loss": 0.0014,
+      "step": 1950
+    },
+    {
+      "epoch": 4.475496499499928,
+      "grad_norm": 0.01602611131966114,
+      "learning_rate": 3.3510323246913887e-06,
+      "loss": 0.001,
+      "step": 1960
+    },
+    {
+      "epoch": 4.4983569081297325,
+      "grad_norm": 0.031283311545848846,
+      "learning_rate": 3.07012246510342e-06,
+      "loss": 0.001,
+      "step": 1970
+    },
+    {
+      "epoch": 4.521217316759537,
+      "grad_norm": 0.010646236129105091,
+      "learning_rate": 2.801135088826529e-06,
+      "loss": 0.0011,
+      "step": 1980
+    },
+    {
+      "epoch": 4.544077725389341,
+      "grad_norm": 0.040134090930223465,
+      "learning_rate": 2.5441385318051735e-06,
+      "loss": 0.0012,
+      "step": 1990
+    },
+    {
+      "epoch": 4.5669381340191455,
+      "grad_norm": 0.020084287971258163,
+      "learning_rate": 2.2991980837294757e-06,
+      "loss": 0.001,
+      "step": 2000
+    },
+    {
+      "epoch": 4.58979854264895,
+      "grad_norm": 0.023815790191292763,
+      "learning_rate": 2.066375971448481e-06,
+      "loss": 0.0013,
+      "step": 2010
+    },
+    {
+      "epoch": 4.612658951278754,
+      "grad_norm": 0.054296255111694336,
+      "learning_rate": 1.8457313431614498e-06,
+      "loss": 0.0015,
+      "step": 2020
+    },
+    {
+      "epoch": 4.6355193599085585,
+      "grad_norm": 0.030289700254797935,
+      "learning_rate": 1.6373202533913556e-06,
+      "loss": 0.0009,
+      "step": 2030
+    },
+    {
+      "epoch": 4.658379768538363,
+      "grad_norm": 0.01671276055276394,
+      "learning_rate": 1.4411956487442925e-06,
+      "loss": 0.0012,
+      "step": 2040
+    },
+    {
+      "epoch": 4.681240177168167,
+      "grad_norm": 0.034442536532878876,
+      "learning_rate": 1.2574073544584286e-06,
+      "loss": 0.001,
+      "step": 2050
+    },
+    {
+      "epoch": 4.704100585797971,
+      "grad_norm": 0.06515878438949585,
+      "learning_rate": 1.0860020617459887e-06,
+      "loss": 0.0018,
+      "step": 2060
+    },
+    {
+      "epoch": 4.726960994427776,
+      "grad_norm": 0.008722376078367233,
+      "learning_rate": 9.270233159313912e-07,
+      "loss": 0.0013,
+      "step": 2070
+    },
+    {
+      "epoch": 4.749821403057579,
+      "grad_norm": 0.006462674122303724,
+      "learning_rate": 7.805115053885758e-07,
+      "loss": 0.0016,
+      "step": 2080
+    },
+    {
+      "epoch": 4.772681811687384,
+      "grad_norm": 0.018205828964710236,
+      "learning_rate": 6.465038512804555e-07,
+      "loss": 0.0009,
+      "step": 2090
+    },
+    {
+      "epoch": 4.795542220317188,
+      "grad_norm": 0.011852984316647053,
+      "learning_rate": 5.250343981028305e-07,
+      "loss": 0.0009,
+      "step": 2100
+    },
+    {
+      "epoch": 4.818402628946992,
+      "grad_norm": 0.04381529241800308,
+      "learning_rate": 4.1613400503550114e-07,
+      "loss": 0.001,
+      "step": 2110
+    },
+    {
+      "epoch": 4.841263037576796,
+      "grad_norm": 0.06918981671333313,
+      "learning_rate": 3.1983033810248366e-07,
+      "loss": 0.0017,
+      "step": 2120
+    },
+    {
+      "epoch": 4.864123446206601,
+      "grad_norm": 0.009174630045890808,
+      "learning_rate": 2.3614786314348768e-07,
+      "loss": 0.0011,
+      "step": 2130
+    },
+    {
+      "epoch": 4.886983854836405,
+      "grad_norm": 0.0225895494222641,
+      "learning_rate": 1.651078395984329e-07,
+      "loss": 0.0018,
+      "step": 2140
+    },
+    {
+      "epoch": 4.909844263466209,
+      "grad_norm": 0.02551046386361122,
+      "learning_rate": 1.0672831510645242e-07,
+      "loss": 0.0017,
+      "step": 2150
+    },
+    {
+      "epoch": 4.932704672096014,
+      "grad_norm": 0.03379609063267708,
+      "learning_rate": 6.102412092097165e-08,
+      "loss": 0.0015,
+      "step": 2160
+    },
+    {
+      "epoch": 4.955565080725818,
+      "grad_norm": 0.03675275668501854,
+      "learning_rate": 2.8006868141805533e-08,
+      "loss": 0.0011,
+      "step": 2170
+    },
+    {
+      "epoch": 4.978425489355622,
+      "grad_norm": 0.12221638858318329,
+      "learning_rate": 7.684944765379286e-09,
+      "loss": 0.0016,
+      "step": 2180
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.0298867579549551,
+      "learning_rate": 6.351355378297896e-11,
+      "loss": 0.0018,
+      "step": 2190
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2190,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.1069953280835584e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2190/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d307b97811482d7107b2c2d37efb72e66e5e343ee5862d771d5d8278d370a73a
+size 5777