Add files using upload-large-folder tool

Math_QA/group_01/adapter/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/不冻结Qwen训练/models/Qwen2.5-1.5B-Instruct
+library_name: peft
+---
+
+# 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 0.12.0

Math_QA/group_01/adapter/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/\u4e0d\u51bb\u7ed3Qwen\u8bad\u7ec3/models/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "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": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Math_QA/group_01/adapter/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
+  }
+}

Math_QA/group_01/checkpoints/checkpoint-1200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/不冻结Qwen训练/models/Qwen2.5-1.5B-Instruct
+library_name: peft
+---
+
+# 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 0.12.0

Math_QA/group_01/checkpoints/checkpoint-1200/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/\u4e0d\u51bb\u7ed3Qwen\u8bad\u7ec3/models/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "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": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Math_QA/group_01/checkpoints/checkpoint-1200/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
+}

Math_QA/group_01/checkpoints/checkpoint-1200/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 %}

Math_QA/group_01/checkpoints/checkpoint-1200/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
+  }
+}

Math_QA/group_01/checkpoints/checkpoint-1200/tokenizer_config.json

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

Math_QA/group_01/checkpoints/checkpoint-1200/trainer_state.json

@@ -0,0 +1,1721 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 300.0,
+  "eval_steps": 500,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 10.180441856384277,
+      "learning_rate": 0.0,
+      "loss": 1.8305,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 6.451148509979248,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.8074,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 3.347440481185913,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.6091,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 1.9289507865905762,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 1.1842,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.8556746244430542,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.8199,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.7173905372619629,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.6794,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.57694011926651,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.601,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.5361317992210388,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.518,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.821795701980591,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.5037,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.5809462666511536,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.3551,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 0.6679601669311523,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.3027,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 1.0066516399383545,
+      "learning_rate": 0.0001,
+      "loss": 0.2053,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 2.1689505577087402,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1499,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 1.3551698923110962,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.0919,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 0.8636834025382996,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0684,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 1.1933852434158325,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0497,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.142573118209839,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.0413,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.4700527787208557,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0385,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 0.343295693397522,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.033,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.22979414463043213,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.029,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.3299155533313751,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0299,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.13267530500888824,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0261,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.11862046271562576,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0269,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.1212410181760788,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.0271,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.4221489727497101,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0277,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.1887303739786148,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.028,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.06632087379693985,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0292,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.06920741498470306,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.0266,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.20255975425243378,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.0252,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.06548365205526352,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0262,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.3841380774974823,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0266,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.14380377531051636,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0264,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.1875791698694229,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0272,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.0587279237806797,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.026,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.1045636460185051,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0258,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.1214262992143631,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0258,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.15483546257019043,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0258,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.05430334061384201,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0249,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.059528253972530365,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0252,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.08998366445302963,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0256,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.1713639348745346,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0261,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.15917673707008362,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.026,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.06540960818529129,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.0249,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.28250637650489807,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0257,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.21159835159778595,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0252,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.17774927616119385,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0243,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.09880783408880234,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.0256,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.22325387597084045,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0348,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.18399597704410553,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0277,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.07885713130235672,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0244,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.3227796256542206,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0278,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.15556609630584717,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0298,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.21505486965179443,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0267,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.05085480958223343,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0252,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.05251656472682953,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0265,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.15204979479312897,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0245,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.12058636546134949,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0244,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.04826376959681511,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.0236,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.038287319242954254,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.0235,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.045909084379673004,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0253,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.07804425060749054,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.0237,
+      "step": 300
+    },
+    {
+      "epoch": 76.32,
+      "grad_norm": 0.04439236596226692,
+      "learning_rate": 8.56815578465063e-05,
+      "loss": 0.0241,
+      "step": 305
+    },
+    {
+      "epoch": 77.64,
+      "grad_norm": 0.0510355643928051,
+      "learning_rate": 8.539518900343643e-05,
+      "loss": 0.0247,
+      "step": 310
+    },
+    {
+      "epoch": 78.96,
+      "grad_norm": 0.04283309355378151,
+      "learning_rate": 8.510882016036655e-05,
+      "loss": 0.0244,
+      "step": 315
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.08130446821451187,
+      "learning_rate": 8.482245131729668e-05,
+      "loss": 0.0236,
+      "step": 320
+    },
+    {
+      "epoch": 81.32,
+      "grad_norm": 0.03965280205011368,
+      "learning_rate": 8.453608247422681e-05,
+      "loss": 0.0233,
+      "step": 325
+    },
+    {
+      "epoch": 82.64,
+      "grad_norm": 0.036928094923496246,
+      "learning_rate": 8.424971363115693e-05,
+      "loss": 0.0247,
+      "step": 330
+    },
+    {
+      "epoch": 83.96,
+      "grad_norm": 0.03514806181192398,
+      "learning_rate": 8.396334478808706e-05,
+      "loss": 0.0232,
+      "step": 335
+    },
+    {
+      "epoch": 85.0,
+      "grad_norm": 0.13447487354278564,
+      "learning_rate": 8.367697594501719e-05,
+      "loss": 0.0247,
+      "step": 340
+    },
+    {
+      "epoch": 86.32,
+      "grad_norm": 0.048798318952322006,
+      "learning_rate": 8.339060710194731e-05,
+      "loss": 0.0238,
+      "step": 345
+    },
+    {
+      "epoch": 87.64,
+      "grad_norm": 0.04126816615462303,
+      "learning_rate": 8.310423825887744e-05,
+      "loss": 0.0222,
+      "step": 350
+    },
+    {
+      "epoch": 88.96,
+      "grad_norm": 0.04224137216806412,
+      "learning_rate": 8.281786941580757e-05,
+      "loss": 0.0234,
+      "step": 355
+    },
+    {
+      "epoch": 90.0,
+      "grad_norm": 0.10610926151275635,
+      "learning_rate": 8.253150057273768e-05,
+      "loss": 0.0245,
+      "step": 360
+    },
+    {
+      "epoch": 91.32,
+      "grad_norm": 0.050110042095184326,
+      "learning_rate": 8.224513172966782e-05,
+      "loss": 0.0243,
+      "step": 365
+    },
+    {
+      "epoch": 92.64,
+      "grad_norm": 0.04875118285417557,
+      "learning_rate": 8.195876288659795e-05,
+      "loss": 0.0236,
+      "step": 370
+    },
+    {
+      "epoch": 93.96,
+      "grad_norm": 0.04443453252315521,
+      "learning_rate": 8.167239404352807e-05,
+      "loss": 0.0254,
+      "step": 375
+    },
+    {
+      "epoch": 95.0,
+      "grad_norm": 0.12320202589035034,
+      "learning_rate": 8.13860252004582e-05,
+      "loss": 0.0233,
+      "step": 380
+    },
+    {
+      "epoch": 96.32,
+      "grad_norm": 0.049856845289468765,
+      "learning_rate": 8.109965635738833e-05,
+      "loss": 0.0235,
+      "step": 385
+    },
+    {
+      "epoch": 97.64,
+      "grad_norm": 0.052503034472465515,
+      "learning_rate": 8.081328751431845e-05,
+      "loss": 0.0239,
+      "step": 390
+    },
+    {
+      "epoch": 98.96,
+      "grad_norm": 0.03616590052843094,
+      "learning_rate": 8.052691867124858e-05,
+      "loss": 0.024,
+      "step": 395
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.1246335357427597,
+      "learning_rate": 8.02405498281787e-05,
+      "loss": 0.0229,
+      "step": 400
+    },
+    {
+      "epoch": 101.32,
+      "grad_norm": 0.03999874368309975,
+      "learning_rate": 7.995418098510883e-05,
+      "loss": 0.0242,
+      "step": 405
+    },
+    {
+      "epoch": 102.64,
+      "grad_norm": 0.043219417333602905,
+      "learning_rate": 7.966781214203894e-05,
+      "loss": 0.0238,
+      "step": 410
+    },
+    {
+      "epoch": 103.96,
+      "grad_norm": 0.045299362391233444,
+      "learning_rate": 7.938144329896907e-05,
+      "loss": 0.0234,
+      "step": 415
+    },
+    {
+      "epoch": 105.0,
+      "grad_norm": 0.1272430568933487,
+      "learning_rate": 7.90950744558992e-05,
+      "loss": 0.025,
+      "step": 420
+    },
+    {
+      "epoch": 106.32,
+      "grad_norm": 0.03369831666350365,
+      "learning_rate": 7.880870561282932e-05,
+      "loss": 0.0232,
+      "step": 425
+    },
+    {
+      "epoch": 107.64,
+      "grad_norm": 0.03566688671708107,
+      "learning_rate": 7.852233676975945e-05,
+      "loss": 0.024,
+      "step": 430
+    },
+    {
+      "epoch": 108.96,
+      "grad_norm": 0.039571139961481094,
+      "learning_rate": 7.823596792668958e-05,
+      "loss": 0.0224,
+      "step": 435
+    },
+    {
+      "epoch": 110.0,
+      "grad_norm": 0.13205471634864807,
+      "learning_rate": 7.79495990836197e-05,
+      "loss": 0.025,
+      "step": 440
+    },
+    {
+      "epoch": 111.32,
+      "grad_norm": 0.038404062390327454,
+      "learning_rate": 7.766323024054983e-05,
+      "loss": 0.0239,
+      "step": 445
+    },
+    {
+      "epoch": 112.64,
+      "grad_norm": 0.038733795285224915,
+      "learning_rate": 7.737686139747996e-05,
+      "loss": 0.0235,
+      "step": 450
+    },
+    {
+      "epoch": 113.96,
+      "grad_norm": 0.04340984299778938,
+      "learning_rate": 7.709049255441008e-05,
+      "loss": 0.0237,
+      "step": 455
+    },
+    {
+      "epoch": 115.0,
+      "grad_norm": 0.1490347683429718,
+      "learning_rate": 7.680412371134021e-05,
+      "loss": 0.026,
+      "step": 460
+    },
+    {
+      "epoch": 116.32,
+      "grad_norm": 0.04450232908129692,
+      "learning_rate": 7.651775486827034e-05,
+      "loss": 0.0248,
+      "step": 465
+    },
+    {
+      "epoch": 117.64,
+      "grad_norm": 0.03861455246806145,
+      "learning_rate": 7.623138602520046e-05,
+      "loss": 0.0245,
+      "step": 470
+    },
+    {
+      "epoch": 118.96,
+      "grad_norm": 0.03502120077610016,
+      "learning_rate": 7.594501718213059e-05,
+      "loss": 0.0254,
+      "step": 475
+    },
+    {
+      "epoch": 120.0,
+      "grad_norm": 0.092933788895607,
+      "learning_rate": 7.565864833906071e-05,
+      "loss": 0.0242,
+      "step": 480
+    },
+    {
+      "epoch": 121.32,
+      "grad_norm": 0.03522248566150665,
+      "learning_rate": 7.537227949599084e-05,
+      "loss": 0.0232,
+      "step": 485
+    },
+    {
+      "epoch": 122.64,
+      "grad_norm": 0.030242981389164925,
+      "learning_rate": 7.508591065292097e-05,
+      "loss": 0.0229,
+      "step": 490
+    },
+    {
+      "epoch": 123.96,
+      "grad_norm": 0.03727824613451958,
+      "learning_rate": 7.47995418098511e-05,
+      "loss": 0.0239,
+      "step": 495
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 0.11968818306922913,
+      "learning_rate": 7.451317296678122e-05,
+      "loss": 0.0234,
+      "step": 500
+    },
+    {
+      "epoch": 126.32,
+      "grad_norm": 0.032707035541534424,
+      "learning_rate": 7.422680412371135e-05,
+      "loss": 0.0221,
+      "step": 505
+    },
+    {
+      "epoch": 127.64,
+      "grad_norm": 0.03655603528022766,
+      "learning_rate": 7.394043528064147e-05,
+      "loss": 0.0243,
+      "step": 510
+    },
+    {
+      "epoch": 128.96,
+      "grad_norm": 0.03384123370051384,
+      "learning_rate": 7.36540664375716e-05,
+      "loss": 0.0217,
+      "step": 515
+    },
+    {
+      "epoch": 130.0,
+      "grad_norm": 0.11020781844854355,
+      "learning_rate": 7.336769759450171e-05,
+      "loss": 0.0237,
+      "step": 520
+    },
+    {
+      "epoch": 131.32,
+      "grad_norm": 0.038297172635793686,
+      "learning_rate": 7.308132875143184e-05,
+      "loss": 0.0232,
+      "step": 525
+    },
+    {
+      "epoch": 132.64,
+      "grad_norm": 0.03700310364365578,
+      "learning_rate": 7.279495990836197e-05,
+      "loss": 0.0229,
+      "step": 530
+    },
+    {
+      "epoch": 133.96,
+      "grad_norm": 0.0338885597884655,
+      "learning_rate": 7.250859106529209e-05,
+      "loss": 0.0229,
+      "step": 535
+    },
+    {
+      "epoch": 135.0,
+      "grad_norm": 0.10868728905916214,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.0224,
+      "step": 540
+    },
+    {
+      "epoch": 136.32,
+      "grad_norm": 0.035598840564489365,
+      "learning_rate": 7.193585337915235e-05,
+      "loss": 0.0255,
+      "step": 545
+    },
+    {
+      "epoch": 137.64,
+      "grad_norm": 0.031226877123117447,
+      "learning_rate": 7.164948453608247e-05,
+      "loss": 0.0233,
+      "step": 550
+    },
+    {
+      "epoch": 138.96,
+      "grad_norm": 0.03582902252674103,
+      "learning_rate": 7.136311569301261e-05,
+      "loss": 0.0229,
+      "step": 555
+    },
+    {
+      "epoch": 140.0,
+      "grad_norm": 0.11769143491983414,
+      "learning_rate": 7.107674684994274e-05,
+      "loss": 0.0245,
+      "step": 560
+    },
+    {
+      "epoch": 141.32,
+      "grad_norm": 0.030704690143465996,
+      "learning_rate": 7.079037800687286e-05,
+      "loss": 0.0242,
+      "step": 565
+    },
+    {
+      "epoch": 142.64,
+      "grad_norm": 0.03247276693582535,
+      "learning_rate": 7.050400916380299e-05,
+      "loss": 0.0239,
+      "step": 570
+    },
+    {
+      "epoch": 143.96,
+      "grad_norm": 0.03496946021914482,
+      "learning_rate": 7.02176403207331e-05,
+      "loss": 0.0251,
+      "step": 575
+    },
+    {
+      "epoch": 145.0,
+      "grad_norm": 0.08276615291833878,
+      "learning_rate": 6.993127147766323e-05,
+      "loss": 0.0221,
+      "step": 580
+    },
+    {
+      "epoch": 146.32,
+      "grad_norm": 0.040135324001312256,
+      "learning_rate": 6.964490263459336e-05,
+      "loss": 0.0233,
+      "step": 585
+    },
+    {
+      "epoch": 147.64,
+      "grad_norm": 0.0358579121530056,
+      "learning_rate": 6.935853379152348e-05,
+      "loss": 0.0245,
+      "step": 590
+    },
+    {
+      "epoch": 148.96,
+      "grad_norm": 0.04078257456421852,
+      "learning_rate": 6.907216494845361e-05,
+      "loss": 0.0246,
+      "step": 595
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 0.07422423362731934,
+      "learning_rate": 6.878579610538374e-05,
+      "loss": 0.0217,
+      "step": 600
+    },
+    {
+      "epoch": 151.32,
+      "grad_norm": 0.036644842475652695,
+      "learning_rate": 6.849942726231386e-05,
+      "loss": 0.0234,
+      "step": 605
+    },
+    {
+      "epoch": 152.64,
+      "grad_norm": 0.03300880640745163,
+      "learning_rate": 6.821305841924399e-05,
+      "loss": 0.0228,
+      "step": 610
+    },
+    {
+      "epoch": 153.96,
+      "grad_norm": 0.03661232069134712,
+      "learning_rate": 6.792668957617412e-05,
+      "loss": 0.0237,
+      "step": 615
+    },
+    {
+      "epoch": 155.0,
+      "grad_norm": 0.12643153965473175,
+      "learning_rate": 6.764032073310424e-05,
+      "loss": 0.024,
+      "step": 620
+    },
+    {
+      "epoch": 156.32,
+      "grad_norm": 0.03363413363695145,
+      "learning_rate": 6.735395189003437e-05,
+      "loss": 0.0224,
+      "step": 625
+    },
+    {
+      "epoch": 157.64,
+      "grad_norm": 0.03167325258255005,
+      "learning_rate": 6.706758304696448e-05,
+      "loss": 0.0223,
+      "step": 630
+    },
+    {
+      "epoch": 158.96,
+      "grad_norm": 0.029550231993198395,
+      "learning_rate": 6.678121420389462e-05,
+      "loss": 0.0235,
+      "step": 635
+    },
+    {
+      "epoch": 160.0,
+      "grad_norm": 0.09065394103527069,
+      "learning_rate": 6.649484536082475e-05,
+      "loss": 0.024,
+      "step": 640
+    },
+    {
+      "epoch": 161.32,
+      "grad_norm": 0.03413796424865723,
+      "learning_rate": 6.620847651775487e-05,
+      "loss": 0.0238,
+      "step": 645
+    },
+    {
+      "epoch": 162.64,
+      "grad_norm": 0.03629285842180252,
+      "learning_rate": 6.5922107674685e-05,
+      "loss": 0.0228,
+      "step": 650
+    },
+    {
+      "epoch": 163.96,
+      "grad_norm": 0.030809171497821808,
+      "learning_rate": 6.563573883161513e-05,
+      "loss": 0.0237,
+      "step": 655
+    },
+    {
+      "epoch": 165.0,
+      "grad_norm": 0.12004661560058594,
+      "learning_rate": 6.534936998854525e-05,
+      "loss": 0.024,
+      "step": 660
+    },
+    {
+      "epoch": 166.32,
+      "grad_norm": 0.03047570399940014,
+      "learning_rate": 6.506300114547538e-05,
+      "loss": 0.0241,
+      "step": 665
+    },
+    {
+      "epoch": 167.64,
+      "grad_norm": 0.02905591018497944,
+      "learning_rate": 6.477663230240551e-05,
+      "loss": 0.0237,
+      "step": 670
+    },
+    {
+      "epoch": 168.96,
+      "grad_norm": 0.034070760011672974,
+      "learning_rate": 6.449026345933563e-05,
+      "loss": 0.0238,
+      "step": 675
+    },
+    {
+      "epoch": 170.0,
+      "grad_norm": 0.1274733990430832,
+      "learning_rate": 6.420389461626576e-05,
+      "loss": 0.0243,
+      "step": 680
+    },
+    {
+      "epoch": 171.32,
+      "grad_norm": 0.03325100615620613,
+      "learning_rate": 6.391752577319587e-05,
+      "loss": 0.0232,
+      "step": 685
+    },
+    {
+      "epoch": 172.64,
+      "grad_norm": 0.03404676914215088,
+      "learning_rate": 6.3631156930126e-05,
+      "loss": 0.0242,
+      "step": 690
+    },
+    {
+      "epoch": 173.96,
+      "grad_norm": 0.029422307386994362,
+      "learning_rate": 6.334478808705613e-05,
+      "loss": 0.0223,
+      "step": 695
+    },
+    {
+      "epoch": 175.0,
+      "grad_norm": 0.06759767234325409,
+      "learning_rate": 6.305841924398625e-05,
+      "loss": 0.0216,
+      "step": 700
+    },
+    {
+      "epoch": 176.32,
+      "grad_norm": 0.03126778081059456,
+      "learning_rate": 6.277205040091638e-05,
+      "loss": 0.0234,
+      "step": 705
+    },
+    {
+      "epoch": 177.64,
+      "grad_norm": 0.025731679052114487,
+      "learning_rate": 6.24856815578465e-05,
+      "loss": 0.0234,
+      "step": 710
+    },
+    {
+      "epoch": 178.96,
+      "grad_norm": 0.028922362253069878,
+      "learning_rate": 6.219931271477663e-05,
+      "loss": 0.0229,
+      "step": 715
+    },
+    {
+      "epoch": 180.0,
+      "grad_norm": 0.12048332393169403,
+      "learning_rate": 6.191294387170676e-05,
+      "loss": 0.023,
+      "step": 720
+    },
+    {
+      "epoch": 181.32,
+      "grad_norm": 0.033701252192258835,
+      "learning_rate": 6.162657502863689e-05,
+      "loss": 0.0253,
+      "step": 725
+    },
+    {
+      "epoch": 182.64,
+      "grad_norm": 0.034988295286893845,
+      "learning_rate": 6.134020618556701e-05,
+      "loss": 0.022,
+      "step": 730
+    },
+    {
+      "epoch": 183.96,
+      "grad_norm": 0.04288899898529053,
+      "learning_rate": 6.105383734249714e-05,
+      "loss": 0.0223,
+      "step": 735
+    },
+    {
+      "epoch": 185.0,
+      "grad_norm": 0.07889136672019958,
+      "learning_rate": 6.076746849942726e-05,
+      "loss": 0.0253,
+      "step": 740
+    },
+    {
+      "epoch": 186.32,
+      "grad_norm": 0.03613121807575226,
+      "learning_rate": 6.0481099656357384e-05,
+      "loss": 0.0231,
+      "step": 745
+    },
+    {
+      "epoch": 187.64,
+      "grad_norm": 0.029085509479045868,
+      "learning_rate": 6.019473081328752e-05,
+      "loss": 0.0243,
+      "step": 750
+    },
+    {
+      "epoch": 188.96,
+      "grad_norm": 0.029132477939128876,
+      "learning_rate": 5.9908361970217644e-05,
+      "loss": 0.0225,
+      "step": 755
+    },
+    {
+      "epoch": 190.0,
+      "grad_norm": 0.05503055825829506,
+      "learning_rate": 5.962199312714777e-05,
+      "loss": 0.0214,
+      "step": 760
+    },
+    {
+      "epoch": 191.32,
+      "grad_norm": 0.02779143489897251,
+      "learning_rate": 5.93356242840779e-05,
+      "loss": 0.023,
+      "step": 765
+    },
+    {
+      "epoch": 192.64,
+      "grad_norm": 0.03147861734032631,
+      "learning_rate": 5.904925544100802e-05,
+      "loss": 0.024,
+      "step": 770
+    },
+    {
+      "epoch": 193.96,
+      "grad_norm": 0.032027844339609146,
+      "learning_rate": 5.876288659793815e-05,
+      "loss": 0.0237,
+      "step": 775
+    },
+    {
+      "epoch": 195.0,
+      "grad_norm": 0.08647307753562927,
+      "learning_rate": 5.8476517754868276e-05,
+      "loss": 0.0229,
+      "step": 780
+    },
+    {
+      "epoch": 196.32,
+      "grad_norm": 0.03443491831421852,
+      "learning_rate": 5.81901489117984e-05,
+      "loss": 0.0225,
+      "step": 785
+    },
+    {
+      "epoch": 197.64,
+      "grad_norm": 0.03234897553920746,
+      "learning_rate": 5.790378006872853e-05,
+      "loss": 0.0226,
+      "step": 790
+    },
+    {
+      "epoch": 198.96,
+      "grad_norm": 0.033941544592380524,
+      "learning_rate": 5.761741122565865e-05,
+      "loss": 0.0236,
+      "step": 795
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 0.08900703489780426,
+      "learning_rate": 5.7331042382588775e-05,
+      "loss": 0.024,
+      "step": 800
+    },
+    {
+      "epoch": 201.32,
+      "grad_norm": 0.02964199334383011,
+      "learning_rate": 5.70446735395189e-05,
+      "loss": 0.0237,
+      "step": 805
+    },
+    {
+      "epoch": 202.64,
+      "grad_norm": 0.032776352018117905,
+      "learning_rate": 5.675830469644903e-05,
+      "loss": 0.0227,
+      "step": 810
+    },
+    {
+      "epoch": 203.96,
+      "grad_norm": 0.02906695567071438,
+      "learning_rate": 5.6471935853379155e-05,
+      "loss": 0.0247,
+      "step": 815
+    },
+    {
+      "epoch": 205.0,
+      "grad_norm": 0.10413157194852829,
+      "learning_rate": 5.618556701030928e-05,
+      "loss": 0.0231,
+      "step": 820
+    },
+    {
+      "epoch": 206.32,
+      "grad_norm": 0.027301495894789696,
+      "learning_rate": 5.589919816723941e-05,
+      "loss": 0.0235,
+      "step": 825
+    },
+    {
+      "epoch": 207.64,
+      "grad_norm": 0.02905373089015484,
+      "learning_rate": 5.5612829324169534e-05,
+      "loss": 0.0235,
+      "step": 830
+    },
+    {
+      "epoch": 208.96,
+      "grad_norm": 0.02877797745168209,
+      "learning_rate": 5.532646048109966e-05,
+      "loss": 0.0224,
+      "step": 835
+    },
+    {
+      "epoch": 210.0,
+      "grad_norm": 0.0836072713136673,
+      "learning_rate": 5.504009163802979e-05,
+      "loss": 0.0233,
+      "step": 840
+    },
+    {
+      "epoch": 211.32,
+      "grad_norm": 0.030773388221859932,
+      "learning_rate": 5.4753722794959914e-05,
+      "loss": 0.0243,
+      "step": 845
+    },
+    {
+      "epoch": 212.64,
+      "grad_norm": 0.028844933956861496,
+      "learning_rate": 5.4467353951890033e-05,
+      "loss": 0.0224,
+      "step": 850
+    },
+    {
+      "epoch": 213.96,
+      "grad_norm": 0.032330844551324844,
+      "learning_rate": 5.418098510882016e-05,
+      "loss": 0.023,
+      "step": 855
+    },
+    {
+      "epoch": 215.0,
+      "grad_norm": 0.13418708741664886,
+      "learning_rate": 5.3894616265750286e-05,
+      "loss": 0.0229,
+      "step": 860
+    },
+    {
+      "epoch": 216.32,
+      "grad_norm": 0.0328691340982914,
+      "learning_rate": 5.360824742268041e-05,
+      "loss": 0.0237,
+      "step": 865
+    },
+    {
+      "epoch": 217.64,
+      "grad_norm": 0.030551306903362274,
+      "learning_rate": 5.332187857961054e-05,
+      "loss": 0.0226,
+      "step": 870
+    },
+    {
+      "epoch": 218.96,
+      "grad_norm": 0.03350970149040222,
+      "learning_rate": 5.3035509736540666e-05,
+      "loss": 0.0234,
+      "step": 875
+    },
+    {
+      "epoch": 220.0,
+      "grad_norm": 0.08607557415962219,
+      "learning_rate": 5.274914089347079e-05,
+      "loss": 0.0235,
+      "step": 880
+    },
+    {
+      "epoch": 221.32,
+      "grad_norm": 0.028927354142069817,
+      "learning_rate": 5.246277205040092e-05,
+      "loss": 0.0244,
+      "step": 885
+    },
+    {
+      "epoch": 222.64,
+      "grad_norm": 0.02603020891547203,
+      "learning_rate": 5.2176403207331045e-05,
+      "loss": 0.0223,
+      "step": 890
+    },
+    {
+      "epoch": 223.96,
+      "grad_norm": 0.025388307869434357,
+      "learning_rate": 5.189003436426118e-05,
+      "loss": 0.0238,
+      "step": 895
+    },
+    {
+      "epoch": 225.0,
+      "grad_norm": 0.08444017916917801,
+      "learning_rate": 5.1603665521191305e-05,
+      "loss": 0.0239,
+      "step": 900
+    },
+    {
+      "epoch": 226.32,
+      "grad_norm": 0.02715456858277321,
+      "learning_rate": 5.131729667812142e-05,
+      "loss": 0.0242,
+      "step": 905
+    },
+    {
+      "epoch": 227.64,
+      "grad_norm": 0.0326889231801033,
+      "learning_rate": 5.1030927835051544e-05,
+      "loss": 0.0216,
+      "step": 910
+    },
+    {
+      "epoch": 228.96,
+      "grad_norm": 0.03151186928153038,
+      "learning_rate": 5.074455899198167e-05,
+      "loss": 0.0232,
+      "step": 915
+    },
+    {
+      "epoch": 230.0,
+      "grad_norm": 0.1081857904791832,
+      "learning_rate": 5.04581901489118e-05,
+      "loss": 0.0243,
+      "step": 920
+    },
+    {
+      "epoch": 231.32,
+      "grad_norm": 0.02827647142112255,
+      "learning_rate": 5.0171821305841924e-05,
+      "loss": 0.0234,
+      "step": 925
+    },
+    {
+      "epoch": 232.64,
+      "grad_norm": 0.027565542608499527,
+      "learning_rate": 4.988545246277205e-05,
+      "loss": 0.023,
+      "step": 930
+    },
+    {
+      "epoch": 233.96,
+      "grad_norm": 0.03328179195523262,
+      "learning_rate": 4.9599083619702184e-05,
+      "loss": 0.0234,
+      "step": 935
+    },
+    {
+      "epoch": 235.0,
+      "grad_norm": 0.14499929547309875,
+      "learning_rate": 4.931271477663231e-05,
+      "loss": 0.0241,
+      "step": 940
+    },
+    {
+      "epoch": 236.32,
+      "grad_norm": 0.025718634948134422,
+      "learning_rate": 4.902634593356243e-05,
+      "loss": 0.0229,
+      "step": 945
+    },
+    {
+      "epoch": 237.64,
+      "grad_norm": 0.03075622022151947,
+      "learning_rate": 4.8739977090492556e-05,
+      "loss": 0.0233,
+      "step": 950
+    },
+    {
+      "epoch": 238.96,
+      "grad_norm": 0.03137879818677902,
+      "learning_rate": 4.845360824742268e-05,
+      "loss": 0.0243,
+      "step": 955
+    },
+    {
+      "epoch": 240.0,
+      "grad_norm": 0.08810659497976303,
+      "learning_rate": 4.816723940435281e-05,
+      "loss": 0.0227,
+      "step": 960
+    },
+    {
+      "epoch": 241.32,
+      "grad_norm": 0.030054708942770958,
+      "learning_rate": 4.7880870561282936e-05,
+      "loss": 0.0234,
+      "step": 965
+    },
+    {
+      "epoch": 242.64,
+      "grad_norm": 0.028709901496767998,
+      "learning_rate": 4.7594501718213055e-05,
+      "loss": 0.0228,
+      "step": 970
+    },
+    {
+      "epoch": 243.96,
+      "grad_norm": 0.027529578655958176,
+      "learning_rate": 4.730813287514318e-05,
+      "loss": 0.0224,
+      "step": 975
+    },
+    {
+      "epoch": 245.0,
+      "grad_norm": 0.10843145102262497,
+      "learning_rate": 4.7021764032073315e-05,
+      "loss": 0.0244,
+      "step": 980
+    },
+    {
+      "epoch": 246.32,
+      "grad_norm": 0.028441136702895164,
+      "learning_rate": 4.673539518900344e-05,
+      "loss": 0.0244,
+      "step": 985
+    },
+    {
+      "epoch": 247.64,
+      "grad_norm": 0.027241505682468414,
+      "learning_rate": 4.644902634593357e-05,
+      "loss": 0.0223,
+      "step": 990
+    },
+    {
+      "epoch": 248.96,
+      "grad_norm": 0.029671119526028633,
+      "learning_rate": 4.6162657502863694e-05,
+      "loss": 0.0236,
+      "step": 995
+    },
+    {
+      "epoch": 250.0,
+      "grad_norm": 0.10153710842132568,
+      "learning_rate": 4.5876288659793814e-05,
+      "loss": 0.0243,
+      "step": 1000
+    },
+    {
+      "epoch": 251.32,
+      "grad_norm": 0.03248867765069008,
+      "learning_rate": 4.558991981672394e-05,
+      "loss": 0.0239,
+      "step": 1005
+    },
+    {
+      "epoch": 252.64,
+      "grad_norm": 0.03408573195338249,
+      "learning_rate": 4.530355097365407e-05,
+      "loss": 0.023,
+      "step": 1010
+    },
+    {
+      "epoch": 253.96,
+      "grad_norm": 0.027460109442472458,
+      "learning_rate": 4.5017182130584194e-05,
+      "loss": 0.0228,
+      "step": 1015
+    },
+    {
+      "epoch": 255.0,
+      "grad_norm": 0.0669630840420723,
+      "learning_rate": 4.473081328751432e-05,
+      "loss": 0.0231,
+      "step": 1020
+    },
+    {
+      "epoch": 256.32,
+      "grad_norm": 0.026929493993520737,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.022,
+      "step": 1025
+    },
+    {
+      "epoch": 257.64,
+      "grad_norm": 0.026157841086387634,
+      "learning_rate": 4.415807560137457e-05,
+      "loss": 0.0232,
+      "step": 1030
+    },
+    {
+      "epoch": 258.96,
+      "grad_norm": 0.03178902342915535,
+      "learning_rate": 4.38717067583047e-05,
+      "loss": 0.0235,
+      "step": 1035
+    },
+    {
+      "epoch": 260.0,
+      "grad_norm": 0.09565325826406479,
+      "learning_rate": 4.3585337915234826e-05,
+      "loss": 0.0244,
+      "step": 1040
+    },
+    {
+      "epoch": 261.32,
+      "grad_norm": 0.028645526617765427,
+      "learning_rate": 4.329896907216495e-05,
+      "loss": 0.0229,
+      "step": 1045
+    },
+    {
+      "epoch": 262.64,
+      "grad_norm": 0.02763913758099079,
+      "learning_rate": 4.301260022909508e-05,
+      "loss": 0.0235,
+      "step": 1050
+    },
+    {
+      "epoch": 263.96,
+      "grad_norm": 0.02442869544029236,
+      "learning_rate": 4.27262313860252e-05,
+      "loss": 0.023,
+      "step": 1055
+    },
+    {
+      "epoch": 265.0,
+      "grad_norm": 0.07956762611865997,
+      "learning_rate": 4.2439862542955325e-05,
+      "loss": 0.0228,
+      "step": 1060
+    },
+    {
+      "epoch": 266.32,
+      "grad_norm": 0.027121301740407944,
+      "learning_rate": 4.215349369988545e-05,
+      "loss": 0.0231,
+      "step": 1065
+    },
+    {
+      "epoch": 267.64,
+      "grad_norm": 0.028464002534747124,
+      "learning_rate": 4.1867124856815585e-05,
+      "loss": 0.0216,
+      "step": 1070
+    },
+    {
+      "epoch": 268.96,
+      "grad_norm": 0.028463657945394516,
+      "learning_rate": 4.158075601374571e-05,
+      "loss": 0.0235,
+      "step": 1075
+    },
+    {
+      "epoch": 270.0,
+      "grad_norm": 0.11043697595596313,
+      "learning_rate": 4.129438717067583e-05,
+      "loss": 0.0238,
+      "step": 1080
+    },
+    {
+      "epoch": 271.32,
+      "grad_norm": 0.028240198269486427,
+      "learning_rate": 4.100801832760596e-05,
+      "loss": 0.0228,
+      "step": 1085
+    },
+    {
+      "epoch": 272.64,
+      "grad_norm": 0.03129616379737854,
+      "learning_rate": 4.0721649484536084e-05,
+      "loss": 0.0236,
+      "step": 1090
+    },
+    {
+      "epoch": 273.96,
+      "grad_norm": 0.02936883457005024,
+      "learning_rate": 4.043528064146621e-05,
+      "loss": 0.0219,
+      "step": 1095
+    },
+    {
+      "epoch": 275.0,
+      "grad_norm": 0.08938605338335037,
+      "learning_rate": 4.014891179839634e-05,
+      "loss": 0.0234,
+      "step": 1100
+    },
+    {
+      "epoch": 276.32,
+      "grad_norm": 0.031886886805295944,
+      "learning_rate": 3.9862542955326463e-05,
+      "loss": 0.022,
+      "step": 1105
+    },
+    {
+      "epoch": 277.64,
+      "grad_norm": 0.027169784530997276,
+      "learning_rate": 3.957617411225659e-05,
+      "loss": 0.0231,
+      "step": 1110
+    },
+    {
+      "epoch": 278.96,
+      "grad_norm": 0.030490893870592117,
+      "learning_rate": 3.9289805269186716e-05,
+      "loss": 0.0225,
+      "step": 1115
+    },
+    {
+      "epoch": 280.0,
+      "grad_norm": 0.10452266782522202,
+      "learning_rate": 3.900343642611684e-05,
+      "loss": 0.0229,
+      "step": 1120
+    },
+    {
+      "epoch": 281.32,
+      "grad_norm": 0.031348999589681625,
+      "learning_rate": 3.871706758304697e-05,
+      "loss": 0.0225,
+      "step": 1125
+    },
+    {
+      "epoch": 282.64,
+      "grad_norm": 0.025815803557634354,
+      "learning_rate": 3.8430698739977096e-05,
+      "loss": 0.0224,
+      "step": 1130
+    },
+    {
+      "epoch": 283.96,
+      "grad_norm": 0.026555614545941353,
+      "learning_rate": 3.8144329896907216e-05,
+      "loss": 0.0218,
+      "step": 1135
+    },
+    {
+      "epoch": 285.0,
+      "grad_norm": 0.11624571681022644,
+      "learning_rate": 3.785796105383734e-05,
+      "loss": 0.0251,
+      "step": 1140
+    },
+    {
+      "epoch": 286.32,
+      "grad_norm": 0.03565097600221634,
+      "learning_rate": 3.757159221076747e-05,
+      "loss": 0.0225,
+      "step": 1145
+    },
+    {
+      "epoch": 287.64,
+      "grad_norm": 0.02672787383198738,
+      "learning_rate": 3.7285223367697595e-05,
+      "loss": 0.0217,
+      "step": 1150
+    },
+    {
+      "epoch": 288.96,
+      "grad_norm": 0.02724423073232174,
+      "learning_rate": 3.699885452462772e-05,
+      "loss": 0.0231,
+      "step": 1155
+    },
+    {
+      "epoch": 290.0,
+      "grad_norm": 0.10171245783567429,
+      "learning_rate": 3.671248568155785e-05,
+      "loss": 0.0236,
+      "step": 1160
+    },
+    {
+      "epoch": 291.32,
+      "grad_norm": 0.02749449387192726,
+      "learning_rate": 3.6426116838487974e-05,
+      "loss": 0.0227,
+      "step": 1165
+    },
+    {
+      "epoch": 292.64,
+      "grad_norm": 0.02680155821144581,
+      "learning_rate": 3.61397479954181e-05,
+      "loss": 0.0234,
+      "step": 1170
+    },
+    {
+      "epoch": 293.96,
+      "grad_norm": 0.025701116770505905,
+      "learning_rate": 3.585337915234823e-05,
+      "loss": 0.0228,
+      "step": 1175
+    },
+    {
+      "epoch": 295.0,
+      "grad_norm": 0.0642700269818306,
+      "learning_rate": 3.5567010309278354e-05,
+      "loss": 0.0211,
+      "step": 1180
+    },
+    {
+      "epoch": 296.32,
+      "grad_norm": 0.025475211441516876,
+      "learning_rate": 3.528064146620848e-05,
+      "loss": 0.0224,
+      "step": 1185
+    },
+    {
+      "epoch": 297.64,
+      "grad_norm": 0.028312934562563896,
+      "learning_rate": 3.49942726231386e-05,
+      "loss": 0.0234,
+      "step": 1190
+    },
+    {
+      "epoch": 298.96,
+      "grad_norm": 0.026962120085954666,
+      "learning_rate": 3.4707903780068726e-05,
+      "loss": 0.0223,
+      "step": 1195
+    },
+    {
+      "epoch": 300.0,
+      "grad_norm": 0.08954183757305145,
+      "learning_rate": 3.442153493699885e-05,
+      "loss": 0.0226,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 450,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0205427400704e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Math_QA/group_01/checkpoints/checkpoint-1500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/不冻结Qwen训练/models/Qwen2.5-1.5B-Instruct
+library_name: peft
+---
+
+# 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 0.12.0

Math_QA/group_01/checkpoints/checkpoint-1500/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/\u4e0d\u51bb\u7ed3Qwen\u8bad\u7ec3/models/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "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": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Math_QA/group_01/checkpoints/checkpoint-1500/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
+}

Math_QA/group_01/checkpoints/checkpoint-1500/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 %}

Math_QA/group_01/checkpoints/checkpoint-1500/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
+  }
+}

Math_QA/group_01/checkpoints/checkpoint-1500/tokenizer_config.json

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

Math_QA/group_01/checkpoints/checkpoint-1500/trainer_state.json

@@ -0,0 +1,2141 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 375.0,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 10.180441856384277,
+      "learning_rate": 0.0,
+      "loss": 1.8305,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 6.451148509979248,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.8074,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 3.347440481185913,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.6091,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 1.9289507865905762,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 1.1842,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.8556746244430542,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.8199,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.7173905372619629,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.6794,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.57694011926651,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.601,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.5361317992210388,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.518,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.821795701980591,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.5037,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.5809462666511536,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.3551,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 0.6679601669311523,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.3027,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 1.0066516399383545,
+      "learning_rate": 0.0001,
+      "loss": 0.2053,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 2.1689505577087402,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1499,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 1.3551698923110962,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.0919,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 0.8636834025382996,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0684,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 1.1933852434158325,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0497,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.142573118209839,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.0413,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.4700527787208557,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0385,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 0.343295693397522,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.033,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.22979414463043213,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.029,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.3299155533313751,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0299,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.13267530500888824,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0261,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.11862046271562576,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0269,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.1212410181760788,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.0271,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.4221489727497101,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0277,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.1887303739786148,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.028,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.06632087379693985,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0292,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.06920741498470306,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.0266,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.20255975425243378,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.0252,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.06548365205526352,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0262,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.3841380774974823,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0266,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.14380377531051636,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0264,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.1875791698694229,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0272,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.0587279237806797,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.026,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.1045636460185051,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0258,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.1214262992143631,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0258,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.15483546257019043,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0258,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.05430334061384201,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0249,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.059528253972530365,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0252,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.08998366445302963,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0256,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.1713639348745346,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0261,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.15917673707008362,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.026,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.06540960818529129,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.0249,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.28250637650489807,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0257,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.21159835159778595,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0252,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.17774927616119385,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0243,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.09880783408880234,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.0256,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.22325387597084045,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0348,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.18399597704410553,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0277,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.07885713130235672,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0244,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.3227796256542206,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0278,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.15556609630584717,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0298,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.21505486965179443,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0267,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.05085480958223343,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0252,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.05251656472682953,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0265,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.15204979479312897,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0245,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.12058636546134949,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0244,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.04826376959681511,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.0236,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.038287319242954254,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.0235,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.045909084379673004,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0253,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.07804425060749054,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.0237,
+      "step": 300
+    },
+    {
+      "epoch": 76.32,
+      "grad_norm": 0.04439236596226692,
+      "learning_rate": 8.56815578465063e-05,
+      "loss": 0.0241,
+      "step": 305
+    },
+    {
+      "epoch": 77.64,
+      "grad_norm": 0.0510355643928051,
+      "learning_rate": 8.539518900343643e-05,
+      "loss": 0.0247,
+      "step": 310
+    },
+    {
+      "epoch": 78.96,
+      "grad_norm": 0.04283309355378151,
+      "learning_rate": 8.510882016036655e-05,
+      "loss": 0.0244,
+      "step": 315
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.08130446821451187,
+      "learning_rate": 8.482245131729668e-05,
+      "loss": 0.0236,
+      "step": 320
+    },
+    {
+      "epoch": 81.32,
+      "grad_norm": 0.03965280205011368,
+      "learning_rate": 8.453608247422681e-05,
+      "loss": 0.0233,
+      "step": 325
+    },
+    {
+      "epoch": 82.64,
+      "grad_norm": 0.036928094923496246,
+      "learning_rate": 8.424971363115693e-05,
+      "loss": 0.0247,
+      "step": 330
+    },
+    {
+      "epoch": 83.96,
+      "grad_norm": 0.03514806181192398,
+      "learning_rate": 8.396334478808706e-05,
+      "loss": 0.0232,
+      "step": 335
+    },
+    {
+      "epoch": 85.0,
+      "grad_norm": 0.13447487354278564,
+      "learning_rate": 8.367697594501719e-05,
+      "loss": 0.0247,
+      "step": 340
+    },
+    {
+      "epoch": 86.32,
+      "grad_norm": 0.048798318952322006,
+      "learning_rate": 8.339060710194731e-05,
+      "loss": 0.0238,
+      "step": 345
+    },
+    {
+      "epoch": 87.64,
+      "grad_norm": 0.04126816615462303,
+      "learning_rate": 8.310423825887744e-05,
+      "loss": 0.0222,
+      "step": 350
+    },
+    {
+      "epoch": 88.96,
+      "grad_norm": 0.04224137216806412,
+      "learning_rate": 8.281786941580757e-05,
+      "loss": 0.0234,
+      "step": 355
+    },
+    {
+      "epoch": 90.0,
+      "grad_norm": 0.10610926151275635,
+      "learning_rate": 8.253150057273768e-05,
+      "loss": 0.0245,
+      "step": 360
+    },
+    {
+      "epoch": 91.32,
+      "grad_norm": 0.050110042095184326,
+      "learning_rate": 8.224513172966782e-05,
+      "loss": 0.0243,
+      "step": 365
+    },
+    {
+      "epoch": 92.64,
+      "grad_norm": 0.04875118285417557,
+      "learning_rate": 8.195876288659795e-05,
+      "loss": 0.0236,
+      "step": 370
+    },
+    {
+      "epoch": 93.96,
+      "grad_norm": 0.04443453252315521,
+      "learning_rate": 8.167239404352807e-05,
+      "loss": 0.0254,
+      "step": 375
+    },
+    {
+      "epoch": 95.0,
+      "grad_norm": 0.12320202589035034,
+      "learning_rate": 8.13860252004582e-05,
+      "loss": 0.0233,
+      "step": 380
+    },
+    {
+      "epoch": 96.32,
+      "grad_norm": 0.049856845289468765,
+      "learning_rate": 8.109965635738833e-05,
+      "loss": 0.0235,
+      "step": 385
+    },
+    {
+      "epoch": 97.64,
+      "grad_norm": 0.052503034472465515,
+      "learning_rate": 8.081328751431845e-05,
+      "loss": 0.0239,
+      "step": 390
+    },
+    {
+      "epoch": 98.96,
+      "grad_norm": 0.03616590052843094,
+      "learning_rate": 8.052691867124858e-05,
+      "loss": 0.024,
+      "step": 395
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.1246335357427597,
+      "learning_rate": 8.02405498281787e-05,
+      "loss": 0.0229,
+      "step": 400
+    },
+    {
+      "epoch": 101.32,
+      "grad_norm": 0.03999874368309975,
+      "learning_rate": 7.995418098510883e-05,
+      "loss": 0.0242,
+      "step": 405
+    },
+    {
+      "epoch": 102.64,
+      "grad_norm": 0.043219417333602905,
+      "learning_rate": 7.966781214203894e-05,
+      "loss": 0.0238,
+      "step": 410
+    },
+    {
+      "epoch": 103.96,
+      "grad_norm": 0.045299362391233444,
+      "learning_rate": 7.938144329896907e-05,
+      "loss": 0.0234,
+      "step": 415
+    },
+    {
+      "epoch": 105.0,
+      "grad_norm": 0.1272430568933487,
+      "learning_rate": 7.90950744558992e-05,
+      "loss": 0.025,
+      "step": 420
+    },
+    {
+      "epoch": 106.32,
+      "grad_norm": 0.03369831666350365,
+      "learning_rate": 7.880870561282932e-05,
+      "loss": 0.0232,
+      "step": 425
+    },
+    {
+      "epoch": 107.64,
+      "grad_norm": 0.03566688671708107,
+      "learning_rate": 7.852233676975945e-05,
+      "loss": 0.024,
+      "step": 430
+    },
+    {
+      "epoch": 108.96,
+      "grad_norm": 0.039571139961481094,
+      "learning_rate": 7.823596792668958e-05,
+      "loss": 0.0224,
+      "step": 435
+    },
+    {
+      "epoch": 110.0,
+      "grad_norm": 0.13205471634864807,
+      "learning_rate": 7.79495990836197e-05,
+      "loss": 0.025,
+      "step": 440
+    },
+    {
+      "epoch": 111.32,
+      "grad_norm": 0.038404062390327454,
+      "learning_rate": 7.766323024054983e-05,
+      "loss": 0.0239,
+      "step": 445
+    },
+    {
+      "epoch": 112.64,
+      "grad_norm": 0.038733795285224915,
+      "learning_rate": 7.737686139747996e-05,
+      "loss": 0.0235,
+      "step": 450
+    },
+    {
+      "epoch": 113.96,
+      "grad_norm": 0.04340984299778938,
+      "learning_rate": 7.709049255441008e-05,
+      "loss": 0.0237,
+      "step": 455
+    },
+    {
+      "epoch": 115.0,
+      "grad_norm": 0.1490347683429718,
+      "learning_rate": 7.680412371134021e-05,
+      "loss": 0.026,
+      "step": 460
+    },
+    {
+      "epoch": 116.32,
+      "grad_norm": 0.04450232908129692,
+      "learning_rate": 7.651775486827034e-05,
+      "loss": 0.0248,
+      "step": 465
+    },
+    {
+      "epoch": 117.64,
+      "grad_norm": 0.03861455246806145,
+      "learning_rate": 7.623138602520046e-05,
+      "loss": 0.0245,
+      "step": 470
+    },
+    {
+      "epoch": 118.96,
+      "grad_norm": 0.03502120077610016,
+      "learning_rate": 7.594501718213059e-05,
+      "loss": 0.0254,
+      "step": 475
+    },
+    {
+      "epoch": 120.0,
+      "grad_norm": 0.092933788895607,
+      "learning_rate": 7.565864833906071e-05,
+      "loss": 0.0242,
+      "step": 480
+    },
+    {
+      "epoch": 121.32,
+      "grad_norm": 0.03522248566150665,
+      "learning_rate": 7.537227949599084e-05,
+      "loss": 0.0232,
+      "step": 485
+    },
+    {
+      "epoch": 122.64,
+      "grad_norm": 0.030242981389164925,
+      "learning_rate": 7.508591065292097e-05,
+      "loss": 0.0229,
+      "step": 490
+    },
+    {
+      "epoch": 123.96,
+      "grad_norm": 0.03727824613451958,
+      "learning_rate": 7.47995418098511e-05,
+      "loss": 0.0239,
+      "step": 495
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 0.11968818306922913,
+      "learning_rate": 7.451317296678122e-05,
+      "loss": 0.0234,
+      "step": 500
+    },
+    {
+      "epoch": 126.32,
+      "grad_norm": 0.032707035541534424,
+      "learning_rate": 7.422680412371135e-05,
+      "loss": 0.0221,
+      "step": 505
+    },
+    {
+      "epoch": 127.64,
+      "grad_norm": 0.03655603528022766,
+      "learning_rate": 7.394043528064147e-05,
+      "loss": 0.0243,
+      "step": 510
+    },
+    {
+      "epoch": 128.96,
+      "grad_norm": 0.03384123370051384,
+      "learning_rate": 7.36540664375716e-05,
+      "loss": 0.0217,
+      "step": 515
+    },
+    {
+      "epoch": 130.0,
+      "grad_norm": 0.11020781844854355,
+      "learning_rate": 7.336769759450171e-05,
+      "loss": 0.0237,
+      "step": 520
+    },
+    {
+      "epoch": 131.32,
+      "grad_norm": 0.038297172635793686,
+      "learning_rate": 7.308132875143184e-05,
+      "loss": 0.0232,
+      "step": 525
+    },
+    {
+      "epoch": 132.64,
+      "grad_norm": 0.03700310364365578,
+      "learning_rate": 7.279495990836197e-05,
+      "loss": 0.0229,
+      "step": 530
+    },
+    {
+      "epoch": 133.96,
+      "grad_norm": 0.0338885597884655,
+      "learning_rate": 7.250859106529209e-05,
+      "loss": 0.0229,
+      "step": 535
+    },
+    {
+      "epoch": 135.0,
+      "grad_norm": 0.10868728905916214,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.0224,
+      "step": 540
+    },
+    {
+      "epoch": 136.32,
+      "grad_norm": 0.035598840564489365,
+      "learning_rate": 7.193585337915235e-05,
+      "loss": 0.0255,
+      "step": 545
+    },
+    {
+      "epoch": 137.64,
+      "grad_norm": 0.031226877123117447,
+      "learning_rate": 7.164948453608247e-05,
+      "loss": 0.0233,
+      "step": 550
+    },
+    {
+      "epoch": 138.96,
+      "grad_norm": 0.03582902252674103,
+      "learning_rate": 7.136311569301261e-05,
+      "loss": 0.0229,
+      "step": 555
+    },
+    {
+      "epoch": 140.0,
+      "grad_norm": 0.11769143491983414,
+      "learning_rate": 7.107674684994274e-05,
+      "loss": 0.0245,
+      "step": 560
+    },
+    {
+      "epoch": 141.32,
+      "grad_norm": 0.030704690143465996,
+      "learning_rate": 7.079037800687286e-05,
+      "loss": 0.0242,
+      "step": 565
+    },
+    {
+      "epoch": 142.64,
+      "grad_norm": 0.03247276693582535,
+      "learning_rate": 7.050400916380299e-05,
+      "loss": 0.0239,
+      "step": 570
+    },
+    {
+      "epoch": 143.96,
+      "grad_norm": 0.03496946021914482,
+      "learning_rate": 7.02176403207331e-05,
+      "loss": 0.0251,
+      "step": 575
+    },
+    {
+      "epoch": 145.0,
+      "grad_norm": 0.08276615291833878,
+      "learning_rate": 6.993127147766323e-05,
+      "loss": 0.0221,
+      "step": 580
+    },
+    {
+      "epoch": 146.32,
+      "grad_norm": 0.040135324001312256,
+      "learning_rate": 6.964490263459336e-05,
+      "loss": 0.0233,
+      "step": 585
+    },
+    {
+      "epoch": 147.64,
+      "grad_norm": 0.0358579121530056,
+      "learning_rate": 6.935853379152348e-05,
+      "loss": 0.0245,
+      "step": 590
+    },
+    {
+      "epoch": 148.96,
+      "grad_norm": 0.04078257456421852,
+      "learning_rate": 6.907216494845361e-05,
+      "loss": 0.0246,
+      "step": 595
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 0.07422423362731934,
+      "learning_rate": 6.878579610538374e-05,
+      "loss": 0.0217,
+      "step": 600
+    },
+    {
+      "epoch": 151.32,
+      "grad_norm": 0.036644842475652695,
+      "learning_rate": 6.849942726231386e-05,
+      "loss": 0.0234,
+      "step": 605
+    },
+    {
+      "epoch": 152.64,
+      "grad_norm": 0.03300880640745163,
+      "learning_rate": 6.821305841924399e-05,
+      "loss": 0.0228,
+      "step": 610
+    },
+    {
+      "epoch": 153.96,
+      "grad_norm": 0.03661232069134712,
+      "learning_rate": 6.792668957617412e-05,
+      "loss": 0.0237,
+      "step": 615
+    },
+    {
+      "epoch": 155.0,
+      "grad_norm": 0.12643153965473175,
+      "learning_rate": 6.764032073310424e-05,
+      "loss": 0.024,
+      "step": 620
+    },
+    {
+      "epoch": 156.32,
+      "grad_norm": 0.03363413363695145,
+      "learning_rate": 6.735395189003437e-05,
+      "loss": 0.0224,
+      "step": 625
+    },
+    {
+      "epoch": 157.64,
+      "grad_norm": 0.03167325258255005,
+      "learning_rate": 6.706758304696448e-05,
+      "loss": 0.0223,
+      "step": 630
+    },
+    {
+      "epoch": 158.96,
+      "grad_norm": 0.029550231993198395,
+      "learning_rate": 6.678121420389462e-05,
+      "loss": 0.0235,
+      "step": 635
+    },
+    {
+      "epoch": 160.0,
+      "grad_norm": 0.09065394103527069,
+      "learning_rate": 6.649484536082475e-05,
+      "loss": 0.024,
+      "step": 640
+    },
+    {
+      "epoch": 161.32,
+      "grad_norm": 0.03413796424865723,
+      "learning_rate": 6.620847651775487e-05,
+      "loss": 0.0238,
+      "step": 645
+    },
+    {
+      "epoch": 162.64,
+      "grad_norm": 0.03629285842180252,
+      "learning_rate": 6.5922107674685e-05,
+      "loss": 0.0228,
+      "step": 650
+    },
+    {
+      "epoch": 163.96,
+      "grad_norm": 0.030809171497821808,
+      "learning_rate": 6.563573883161513e-05,
+      "loss": 0.0237,
+      "step": 655
+    },
+    {
+      "epoch": 165.0,
+      "grad_norm": 0.12004661560058594,
+      "learning_rate": 6.534936998854525e-05,
+      "loss": 0.024,
+      "step": 660
+    },
+    {
+      "epoch": 166.32,
+      "grad_norm": 0.03047570399940014,
+      "learning_rate": 6.506300114547538e-05,
+      "loss": 0.0241,
+      "step": 665
+    },
+    {
+      "epoch": 167.64,
+      "grad_norm": 0.02905591018497944,
+      "learning_rate": 6.477663230240551e-05,
+      "loss": 0.0237,
+      "step": 670
+    },
+    {
+      "epoch": 168.96,
+      "grad_norm": 0.034070760011672974,
+      "learning_rate": 6.449026345933563e-05,
+      "loss": 0.0238,
+      "step": 675
+    },
+    {
+      "epoch": 170.0,
+      "grad_norm": 0.1274733990430832,
+      "learning_rate": 6.420389461626576e-05,
+      "loss": 0.0243,
+      "step": 680
+    },
+    {
+      "epoch": 171.32,
+      "grad_norm": 0.03325100615620613,
+      "learning_rate": 6.391752577319587e-05,
+      "loss": 0.0232,
+      "step": 685
+    },
+    {
+      "epoch": 172.64,
+      "grad_norm": 0.03404676914215088,
+      "learning_rate": 6.3631156930126e-05,
+      "loss": 0.0242,
+      "step": 690
+    },
+    {
+      "epoch": 173.96,
+      "grad_norm": 0.029422307386994362,
+      "learning_rate": 6.334478808705613e-05,
+      "loss": 0.0223,
+      "step": 695
+    },
+    {
+      "epoch": 175.0,
+      "grad_norm": 0.06759767234325409,
+      "learning_rate": 6.305841924398625e-05,
+      "loss": 0.0216,
+      "step": 700
+    },
+    {
+      "epoch": 176.32,
+      "grad_norm": 0.03126778081059456,
+      "learning_rate": 6.277205040091638e-05,
+      "loss": 0.0234,
+      "step": 705
+    },
+    {
+      "epoch": 177.64,
+      "grad_norm": 0.025731679052114487,
+      "learning_rate": 6.24856815578465e-05,
+      "loss": 0.0234,
+      "step": 710
+    },
+    {
+      "epoch": 178.96,
+      "grad_norm": 0.028922362253069878,
+      "learning_rate": 6.219931271477663e-05,
+      "loss": 0.0229,
+      "step": 715
+    },
+    {
+      "epoch": 180.0,
+      "grad_norm": 0.12048332393169403,
+      "learning_rate": 6.191294387170676e-05,
+      "loss": 0.023,
+      "step": 720
+    },
+    {
+      "epoch": 181.32,
+      "grad_norm": 0.033701252192258835,
+      "learning_rate": 6.162657502863689e-05,
+      "loss": 0.0253,
+      "step": 725
+    },
+    {
+      "epoch": 182.64,
+      "grad_norm": 0.034988295286893845,
+      "learning_rate": 6.134020618556701e-05,
+      "loss": 0.022,
+      "step": 730
+    },
+    {
+      "epoch": 183.96,
+      "grad_norm": 0.04288899898529053,
+      "learning_rate": 6.105383734249714e-05,
+      "loss": 0.0223,
+      "step": 735
+    },
+    {
+      "epoch": 185.0,
+      "grad_norm": 0.07889136672019958,
+      "learning_rate": 6.076746849942726e-05,
+      "loss": 0.0253,
+      "step": 740
+    },
+    {
+      "epoch": 186.32,
+      "grad_norm": 0.03613121807575226,
+      "learning_rate": 6.0481099656357384e-05,
+      "loss": 0.0231,
+      "step": 745
+    },
+    {
+      "epoch": 187.64,
+      "grad_norm": 0.029085509479045868,
+      "learning_rate": 6.019473081328752e-05,
+      "loss": 0.0243,
+      "step": 750
+    },
+    {
+      "epoch": 188.96,
+      "grad_norm": 0.029132477939128876,
+      "learning_rate": 5.9908361970217644e-05,
+      "loss": 0.0225,
+      "step": 755
+    },
+    {
+      "epoch": 190.0,
+      "grad_norm": 0.05503055825829506,
+      "learning_rate": 5.962199312714777e-05,
+      "loss": 0.0214,
+      "step": 760
+    },
+    {
+      "epoch": 191.32,
+      "grad_norm": 0.02779143489897251,
+      "learning_rate": 5.93356242840779e-05,
+      "loss": 0.023,
+      "step": 765
+    },
+    {
+      "epoch": 192.64,
+      "grad_norm": 0.03147861734032631,
+      "learning_rate": 5.904925544100802e-05,
+      "loss": 0.024,
+      "step": 770
+    },
+    {
+      "epoch": 193.96,
+      "grad_norm": 0.032027844339609146,
+      "learning_rate": 5.876288659793815e-05,
+      "loss": 0.0237,
+      "step": 775
+    },
+    {
+      "epoch": 195.0,
+      "grad_norm": 0.08647307753562927,
+      "learning_rate": 5.8476517754868276e-05,
+      "loss": 0.0229,
+      "step": 780
+    },
+    {
+      "epoch": 196.32,
+      "grad_norm": 0.03443491831421852,
+      "learning_rate": 5.81901489117984e-05,
+      "loss": 0.0225,
+      "step": 785
+    },
+    {
+      "epoch": 197.64,
+      "grad_norm": 0.03234897553920746,
+      "learning_rate": 5.790378006872853e-05,
+      "loss": 0.0226,
+      "step": 790
+    },
+    {
+      "epoch": 198.96,
+      "grad_norm": 0.033941544592380524,
+      "learning_rate": 5.761741122565865e-05,
+      "loss": 0.0236,
+      "step": 795
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 0.08900703489780426,
+      "learning_rate": 5.7331042382588775e-05,
+      "loss": 0.024,
+      "step": 800
+    },
+    {
+      "epoch": 201.32,
+      "grad_norm": 0.02964199334383011,
+      "learning_rate": 5.70446735395189e-05,
+      "loss": 0.0237,
+      "step": 805
+    },
+    {
+      "epoch": 202.64,
+      "grad_norm": 0.032776352018117905,
+      "learning_rate": 5.675830469644903e-05,
+      "loss": 0.0227,
+      "step": 810
+    },
+    {
+      "epoch": 203.96,
+      "grad_norm": 0.02906695567071438,
+      "learning_rate": 5.6471935853379155e-05,
+      "loss": 0.0247,
+      "step": 815
+    },
+    {
+      "epoch": 205.0,
+      "grad_norm": 0.10413157194852829,
+      "learning_rate": 5.618556701030928e-05,
+      "loss": 0.0231,
+      "step": 820
+    },
+    {
+      "epoch": 206.32,
+      "grad_norm": 0.027301495894789696,
+      "learning_rate": 5.589919816723941e-05,
+      "loss": 0.0235,
+      "step": 825
+    },
+    {
+      "epoch": 207.64,
+      "grad_norm": 0.02905373089015484,
+      "learning_rate": 5.5612829324169534e-05,
+      "loss": 0.0235,
+      "step": 830
+    },
+    {
+      "epoch": 208.96,
+      "grad_norm": 0.02877797745168209,
+      "learning_rate": 5.532646048109966e-05,
+      "loss": 0.0224,
+      "step": 835
+    },
+    {
+      "epoch": 210.0,
+      "grad_norm": 0.0836072713136673,
+      "learning_rate": 5.504009163802979e-05,
+      "loss": 0.0233,
+      "step": 840
+    },
+    {
+      "epoch": 211.32,
+      "grad_norm": 0.030773388221859932,
+      "learning_rate": 5.4753722794959914e-05,
+      "loss": 0.0243,
+      "step": 845
+    },
+    {
+      "epoch": 212.64,
+      "grad_norm": 0.028844933956861496,
+      "learning_rate": 5.4467353951890033e-05,
+      "loss": 0.0224,
+      "step": 850
+    },
+    {
+      "epoch": 213.96,
+      "grad_norm": 0.032330844551324844,
+      "learning_rate": 5.418098510882016e-05,
+      "loss": 0.023,
+      "step": 855
+    },
+    {
+      "epoch": 215.0,
+      "grad_norm": 0.13418708741664886,
+      "learning_rate": 5.3894616265750286e-05,
+      "loss": 0.0229,
+      "step": 860
+    },
+    {
+      "epoch": 216.32,
+      "grad_norm": 0.0328691340982914,
+      "learning_rate": 5.360824742268041e-05,
+      "loss": 0.0237,
+      "step": 865
+    },
+    {
+      "epoch": 217.64,
+      "grad_norm": 0.030551306903362274,
+      "learning_rate": 5.332187857961054e-05,
+      "loss": 0.0226,
+      "step": 870
+    },
+    {
+      "epoch": 218.96,
+      "grad_norm": 0.03350970149040222,
+      "learning_rate": 5.3035509736540666e-05,
+      "loss": 0.0234,
+      "step": 875
+    },
+    {
+      "epoch": 220.0,
+      "grad_norm": 0.08607557415962219,
+      "learning_rate": 5.274914089347079e-05,
+      "loss": 0.0235,
+      "step": 880
+    },
+    {
+      "epoch": 221.32,
+      "grad_norm": 0.028927354142069817,
+      "learning_rate": 5.246277205040092e-05,
+      "loss": 0.0244,
+      "step": 885
+    },
+    {
+      "epoch": 222.64,
+      "grad_norm": 0.02603020891547203,
+      "learning_rate": 5.2176403207331045e-05,
+      "loss": 0.0223,
+      "step": 890
+    },
+    {
+      "epoch": 223.96,
+      "grad_norm": 0.025388307869434357,
+      "learning_rate": 5.189003436426118e-05,
+      "loss": 0.0238,
+      "step": 895
+    },
+    {
+      "epoch": 225.0,
+      "grad_norm": 0.08444017916917801,
+      "learning_rate": 5.1603665521191305e-05,
+      "loss": 0.0239,
+      "step": 900
+    },
+    {
+      "epoch": 226.32,
+      "grad_norm": 0.02715456858277321,
+      "learning_rate": 5.131729667812142e-05,
+      "loss": 0.0242,
+      "step": 905
+    },
+    {
+      "epoch": 227.64,
+      "grad_norm": 0.0326889231801033,
+      "learning_rate": 5.1030927835051544e-05,
+      "loss": 0.0216,
+      "step": 910
+    },
+    {
+      "epoch": 228.96,
+      "grad_norm": 0.03151186928153038,
+      "learning_rate": 5.074455899198167e-05,
+      "loss": 0.0232,
+      "step": 915
+    },
+    {
+      "epoch": 230.0,
+      "grad_norm": 0.1081857904791832,
+      "learning_rate": 5.04581901489118e-05,
+      "loss": 0.0243,
+      "step": 920
+    },
+    {
+      "epoch": 231.32,
+      "grad_norm": 0.02827647142112255,
+      "learning_rate": 5.0171821305841924e-05,
+      "loss": 0.0234,
+      "step": 925
+    },
+    {
+      "epoch": 232.64,
+      "grad_norm": 0.027565542608499527,
+      "learning_rate": 4.988545246277205e-05,
+      "loss": 0.023,
+      "step": 930
+    },
+    {
+      "epoch": 233.96,
+      "grad_norm": 0.03328179195523262,
+      "learning_rate": 4.9599083619702184e-05,
+      "loss": 0.0234,
+      "step": 935
+    },
+    {
+      "epoch": 235.0,
+      "grad_norm": 0.14499929547309875,
+      "learning_rate": 4.931271477663231e-05,
+      "loss": 0.0241,
+      "step": 940
+    },
+    {
+      "epoch": 236.32,
+      "grad_norm": 0.025718634948134422,
+      "learning_rate": 4.902634593356243e-05,
+      "loss": 0.0229,
+      "step": 945
+    },
+    {
+      "epoch": 237.64,
+      "grad_norm": 0.03075622022151947,
+      "learning_rate": 4.8739977090492556e-05,
+      "loss": 0.0233,
+      "step": 950
+    },
+    {
+      "epoch": 238.96,
+      "grad_norm": 0.03137879818677902,
+      "learning_rate": 4.845360824742268e-05,
+      "loss": 0.0243,
+      "step": 955
+    },
+    {
+      "epoch": 240.0,
+      "grad_norm": 0.08810659497976303,
+      "learning_rate": 4.816723940435281e-05,
+      "loss": 0.0227,
+      "step": 960
+    },
+    {
+      "epoch": 241.32,
+      "grad_norm": 0.030054708942770958,
+      "learning_rate": 4.7880870561282936e-05,
+      "loss": 0.0234,
+      "step": 965
+    },
+    {
+      "epoch": 242.64,
+      "grad_norm": 0.028709901496767998,
+      "learning_rate": 4.7594501718213055e-05,
+      "loss": 0.0228,
+      "step": 970
+    },
+    {
+      "epoch": 243.96,
+      "grad_norm": 0.027529578655958176,
+      "learning_rate": 4.730813287514318e-05,
+      "loss": 0.0224,
+      "step": 975
+    },
+    {
+      "epoch": 245.0,
+      "grad_norm": 0.10843145102262497,
+      "learning_rate": 4.7021764032073315e-05,
+      "loss": 0.0244,
+      "step": 980
+    },
+    {
+      "epoch": 246.32,
+      "grad_norm": 0.028441136702895164,
+      "learning_rate": 4.673539518900344e-05,
+      "loss": 0.0244,
+      "step": 985
+    },
+    {
+      "epoch": 247.64,
+      "grad_norm": 0.027241505682468414,
+      "learning_rate": 4.644902634593357e-05,
+      "loss": 0.0223,
+      "step": 990
+    },
+    {
+      "epoch": 248.96,
+      "grad_norm": 0.029671119526028633,
+      "learning_rate": 4.6162657502863694e-05,
+      "loss": 0.0236,
+      "step": 995
+    },
+    {
+      "epoch": 250.0,
+      "grad_norm": 0.10153710842132568,
+      "learning_rate": 4.5876288659793814e-05,
+      "loss": 0.0243,
+      "step": 1000
+    },
+    {
+      "epoch": 251.32,
+      "grad_norm": 0.03248867765069008,
+      "learning_rate": 4.558991981672394e-05,
+      "loss": 0.0239,
+      "step": 1005
+    },
+    {
+      "epoch": 252.64,
+      "grad_norm": 0.03408573195338249,
+      "learning_rate": 4.530355097365407e-05,
+      "loss": 0.023,
+      "step": 1010
+    },
+    {
+      "epoch": 253.96,
+      "grad_norm": 0.027460109442472458,
+      "learning_rate": 4.5017182130584194e-05,
+      "loss": 0.0228,
+      "step": 1015
+    },
+    {
+      "epoch": 255.0,
+      "grad_norm": 0.0669630840420723,
+      "learning_rate": 4.473081328751432e-05,
+      "loss": 0.0231,
+      "step": 1020
+    },
+    {
+      "epoch": 256.32,
+      "grad_norm": 0.026929493993520737,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.022,
+      "step": 1025
+    },
+    {
+      "epoch": 257.64,
+      "grad_norm": 0.026157841086387634,
+      "learning_rate": 4.415807560137457e-05,
+      "loss": 0.0232,
+      "step": 1030
+    },
+    {
+      "epoch": 258.96,
+      "grad_norm": 0.03178902342915535,
+      "learning_rate": 4.38717067583047e-05,
+      "loss": 0.0235,
+      "step": 1035
+    },
+    {
+      "epoch": 260.0,
+      "grad_norm": 0.09565325826406479,
+      "learning_rate": 4.3585337915234826e-05,
+      "loss": 0.0244,
+      "step": 1040
+    },
+    {
+      "epoch": 261.32,
+      "grad_norm": 0.028645526617765427,
+      "learning_rate": 4.329896907216495e-05,
+      "loss": 0.0229,
+      "step": 1045
+    },
+    {
+      "epoch": 262.64,
+      "grad_norm": 0.02763913758099079,
+      "learning_rate": 4.301260022909508e-05,
+      "loss": 0.0235,
+      "step": 1050
+    },
+    {
+      "epoch": 263.96,
+      "grad_norm": 0.02442869544029236,
+      "learning_rate": 4.27262313860252e-05,
+      "loss": 0.023,
+      "step": 1055
+    },
+    {
+      "epoch": 265.0,
+      "grad_norm": 0.07956762611865997,
+      "learning_rate": 4.2439862542955325e-05,
+      "loss": 0.0228,
+      "step": 1060
+    },
+    {
+      "epoch": 266.32,
+      "grad_norm": 0.027121301740407944,
+      "learning_rate": 4.215349369988545e-05,
+      "loss": 0.0231,
+      "step": 1065
+    },
+    {
+      "epoch": 267.64,
+      "grad_norm": 0.028464002534747124,
+      "learning_rate": 4.1867124856815585e-05,
+      "loss": 0.0216,
+      "step": 1070
+    },
+    {
+      "epoch": 268.96,
+      "grad_norm": 0.028463657945394516,
+      "learning_rate": 4.158075601374571e-05,
+      "loss": 0.0235,
+      "step": 1075
+    },
+    {
+      "epoch": 270.0,
+      "grad_norm": 0.11043697595596313,
+      "learning_rate": 4.129438717067583e-05,
+      "loss": 0.0238,
+      "step": 1080
+    },
+    {
+      "epoch": 271.32,
+      "grad_norm": 0.028240198269486427,
+      "learning_rate": 4.100801832760596e-05,
+      "loss": 0.0228,
+      "step": 1085
+    },
+    {
+      "epoch": 272.64,
+      "grad_norm": 0.03129616379737854,
+      "learning_rate": 4.0721649484536084e-05,
+      "loss": 0.0236,
+      "step": 1090
+    },
+    {
+      "epoch": 273.96,
+      "grad_norm": 0.02936883457005024,
+      "learning_rate": 4.043528064146621e-05,
+      "loss": 0.0219,
+      "step": 1095
+    },
+    {
+      "epoch": 275.0,
+      "grad_norm": 0.08938605338335037,
+      "learning_rate": 4.014891179839634e-05,
+      "loss": 0.0234,
+      "step": 1100
+    },
+    {
+      "epoch": 276.32,
+      "grad_norm": 0.031886886805295944,
+      "learning_rate": 3.9862542955326463e-05,
+      "loss": 0.022,
+      "step": 1105
+    },
+    {
+      "epoch": 277.64,
+      "grad_norm": 0.027169784530997276,
+      "learning_rate": 3.957617411225659e-05,
+      "loss": 0.0231,
+      "step": 1110
+    },
+    {
+      "epoch": 278.96,
+      "grad_norm": 0.030490893870592117,
+      "learning_rate": 3.9289805269186716e-05,
+      "loss": 0.0225,
+      "step": 1115
+    },
+    {
+      "epoch": 280.0,
+      "grad_norm": 0.10452266782522202,
+      "learning_rate": 3.900343642611684e-05,
+      "loss": 0.0229,
+      "step": 1120
+    },
+    {
+      "epoch": 281.32,
+      "grad_norm": 0.031348999589681625,
+      "learning_rate": 3.871706758304697e-05,
+      "loss": 0.0225,
+      "step": 1125
+    },
+    {
+      "epoch": 282.64,
+      "grad_norm": 0.025815803557634354,
+      "learning_rate": 3.8430698739977096e-05,
+      "loss": 0.0224,
+      "step": 1130
+    },
+    {
+      "epoch": 283.96,
+      "grad_norm": 0.026555614545941353,
+      "learning_rate": 3.8144329896907216e-05,
+      "loss": 0.0218,
+      "step": 1135
+    },
+    {
+      "epoch": 285.0,
+      "grad_norm": 0.11624571681022644,
+      "learning_rate": 3.785796105383734e-05,
+      "loss": 0.0251,
+      "step": 1140
+    },
+    {
+      "epoch": 286.32,
+      "grad_norm": 0.03565097600221634,
+      "learning_rate": 3.757159221076747e-05,
+      "loss": 0.0225,
+      "step": 1145
+    },
+    {
+      "epoch": 287.64,
+      "grad_norm": 0.02672787383198738,
+      "learning_rate": 3.7285223367697595e-05,
+      "loss": 0.0217,
+      "step": 1150
+    },
+    {
+      "epoch": 288.96,
+      "grad_norm": 0.02724423073232174,
+      "learning_rate": 3.699885452462772e-05,
+      "loss": 0.0231,
+      "step": 1155
+    },
+    {
+      "epoch": 290.0,
+      "grad_norm": 0.10171245783567429,
+      "learning_rate": 3.671248568155785e-05,
+      "loss": 0.0236,
+      "step": 1160
+    },
+    {
+      "epoch": 291.32,
+      "grad_norm": 0.02749449387192726,
+      "learning_rate": 3.6426116838487974e-05,
+      "loss": 0.0227,
+      "step": 1165
+    },
+    {
+      "epoch": 292.64,
+      "grad_norm": 0.02680155821144581,
+      "learning_rate": 3.61397479954181e-05,
+      "loss": 0.0234,
+      "step": 1170
+    },
+    {
+      "epoch": 293.96,
+      "grad_norm": 0.025701116770505905,
+      "learning_rate": 3.585337915234823e-05,
+      "loss": 0.0228,
+      "step": 1175
+    },
+    {
+      "epoch": 295.0,
+      "grad_norm": 0.0642700269818306,
+      "learning_rate": 3.5567010309278354e-05,
+      "loss": 0.0211,
+      "step": 1180
+    },
+    {
+      "epoch": 296.32,
+      "grad_norm": 0.025475211441516876,
+      "learning_rate": 3.528064146620848e-05,
+      "loss": 0.0224,
+      "step": 1185
+    },
+    {
+      "epoch": 297.64,
+      "grad_norm": 0.028312934562563896,
+      "learning_rate": 3.49942726231386e-05,
+      "loss": 0.0234,
+      "step": 1190
+    },
+    {
+      "epoch": 298.96,
+      "grad_norm": 0.026962120085954666,
+      "learning_rate": 3.4707903780068726e-05,
+      "loss": 0.0223,
+      "step": 1195
+    },
+    {
+      "epoch": 300.0,
+      "grad_norm": 0.08954183757305145,
+      "learning_rate": 3.442153493699885e-05,
+      "loss": 0.0226,
+      "step": 1200
+    },
+    {
+      "epoch": 301.32,
+      "grad_norm": 0.027179185301065445,
+      "learning_rate": 3.4135166093928986e-05,
+      "loss": 0.0224,
+      "step": 1205
+    },
+    {
+      "epoch": 302.64,
+      "grad_norm": 0.026793546974658966,
+      "learning_rate": 3.384879725085911e-05,
+      "loss": 0.0222,
+      "step": 1210
+    },
+    {
+      "epoch": 303.96,
+      "grad_norm": 0.029869597405195236,
+      "learning_rate": 3.356242840778923e-05,
+      "loss": 0.0232,
+      "step": 1215
+    },
+    {
+      "epoch": 305.0,
+      "grad_norm": 0.12393646687269211,
+      "learning_rate": 3.327605956471936e-05,
+      "loss": 0.0229,
+      "step": 1220
+    },
+    {
+      "epoch": 306.32,
+      "grad_norm": 0.029647044837474823,
+      "learning_rate": 3.2989690721649485e-05,
+      "loss": 0.0229,
+      "step": 1225
+    },
+    {
+      "epoch": 307.64,
+      "grad_norm": 0.02922012098133564,
+      "learning_rate": 3.270332187857961e-05,
+      "loss": 0.0228,
+      "step": 1230
+    },
+    {
+      "epoch": 308.96,
+      "grad_norm": 0.028046652674674988,
+      "learning_rate": 3.241695303550974e-05,
+      "loss": 0.0218,
+      "step": 1235
+    },
+    {
+      "epoch": 310.0,
+      "grad_norm": 0.09626638144254684,
+      "learning_rate": 3.2130584192439865e-05,
+      "loss": 0.0241,
+      "step": 1240
+    },
+    {
+      "epoch": 311.32,
+      "grad_norm": 0.025637533515691757,
+      "learning_rate": 3.184421534936999e-05,
+      "loss": 0.0247,
+      "step": 1245
+    },
+    {
+      "epoch": 312.64,
+      "grad_norm": 0.0269307903945446,
+      "learning_rate": 3.155784650630012e-05,
+      "loss": 0.024,
+      "step": 1250
+    },
+    {
+      "epoch": 313.96,
+      "grad_norm": 0.025975301861763,
+      "learning_rate": 3.1271477663230244e-05,
+      "loss": 0.0232,
+      "step": 1255
+    },
+    {
+      "epoch": 315.0,
+      "grad_norm": 0.10530711710453033,
+      "learning_rate": 3.098510882016037e-05,
+      "loss": 0.0242,
+      "step": 1260
+    },
+    {
+      "epoch": 316.32,
+      "grad_norm": 0.026885682716965675,
+      "learning_rate": 3.06987399770905e-05,
+      "loss": 0.0225,
+      "step": 1265
+    },
+    {
+      "epoch": 317.64,
+      "grad_norm": 0.027477962896227837,
+      "learning_rate": 3.0412371134020617e-05,
+      "loss": 0.0233,
+      "step": 1270
+    },
+    {
+      "epoch": 318.96,
+      "grad_norm": 0.031309112906455994,
+      "learning_rate": 3.0126002290950743e-05,
+      "loss": 0.0226,
+      "step": 1275
+    },
+    {
+      "epoch": 320.0,
+      "grad_norm": 0.0752459242939949,
+      "learning_rate": 2.983963344788087e-05,
+      "loss": 0.0209,
+      "step": 1280
+    },
+    {
+      "epoch": 321.32,
+      "grad_norm": 0.029426634311676025,
+      "learning_rate": 2.9553264604811e-05,
+      "loss": 0.0219,
+      "step": 1285
+    },
+    {
+      "epoch": 322.64,
+      "grad_norm": 0.02936774678528309,
+      "learning_rate": 2.9266895761741126e-05,
+      "loss": 0.0228,
+      "step": 1290
+    },
+    {
+      "epoch": 323.96,
+      "grad_norm": 0.028937801718711853,
+      "learning_rate": 2.8980526918671253e-05,
+      "loss": 0.022,
+      "step": 1295
+    },
+    {
+      "epoch": 325.0,
+      "grad_norm": 0.09840500354766846,
+      "learning_rate": 2.8694158075601372e-05,
+      "loss": 0.023,
+      "step": 1300
+    },
+    {
+      "epoch": 326.32,
+      "grad_norm": 0.03570740297436714,
+      "learning_rate": 2.8407789232531502e-05,
+      "loss": 0.0248,
+      "step": 1305
+    },
+    {
+      "epoch": 327.64,
+      "grad_norm": 0.02928864397108555,
+      "learning_rate": 2.812142038946163e-05,
+      "loss": 0.0223,
+      "step": 1310
+    },
+    {
+      "epoch": 328.96,
+      "grad_norm": 0.026148077100515366,
+      "learning_rate": 2.7835051546391755e-05,
+      "loss": 0.0216,
+      "step": 1315
+    },
+    {
+      "epoch": 330.0,
+      "grad_norm": 0.08714782446622849,
+      "learning_rate": 2.754868270332188e-05,
+      "loss": 0.0224,
+      "step": 1320
+    },
+    {
+      "epoch": 331.32,
+      "grad_norm": 0.027646895498037338,
+      "learning_rate": 2.7262313860252005e-05,
+      "loss": 0.022,
+      "step": 1325
+    },
+    {
+      "epoch": 332.64,
+      "grad_norm": 0.02741863578557968,
+      "learning_rate": 2.697594501718213e-05,
+      "loss": 0.0238,
+      "step": 1330
+    },
+    {
+      "epoch": 333.96,
+      "grad_norm": 0.031554851680994034,
+      "learning_rate": 2.6689576174112258e-05,
+      "loss": 0.0238,
+      "step": 1335
+    },
+    {
+      "epoch": 335.0,
+      "grad_norm": 0.10320069640874863,
+      "learning_rate": 2.6403207331042384e-05,
+      "loss": 0.0247,
+      "step": 1340
+    },
+    {
+      "epoch": 336.32,
+      "grad_norm": 0.027910800650715828,
+      "learning_rate": 2.611683848797251e-05,
+      "loss": 0.0218,
+      "step": 1345
+    },
+    {
+      "epoch": 337.64,
+      "grad_norm": 0.0307508185505867,
+      "learning_rate": 2.5830469644902637e-05,
+      "loss": 0.0227,
+      "step": 1350
+    },
+    {
+      "epoch": 338.96,
+      "grad_norm": 0.028163570910692215,
+      "learning_rate": 2.554410080183276e-05,
+      "loss": 0.0228,
+      "step": 1355
+    },
+    {
+      "epoch": 340.0,
+      "grad_norm": 0.07637765258550644,
+      "learning_rate": 2.5257731958762887e-05,
+      "loss": 0.0214,
+      "step": 1360
+    },
+    {
+      "epoch": 341.32,
+      "grad_norm": 0.028695199638605118,
+      "learning_rate": 2.4971363115693013e-05,
+      "loss": 0.0227,
+      "step": 1365
+    },
+    {
+      "epoch": 342.64,
+      "grad_norm": 0.026736624538898468,
+      "learning_rate": 2.468499427262314e-05,
+      "loss": 0.0218,
+      "step": 1370
+    },
+    {
+      "epoch": 343.96,
+      "grad_norm": 0.02612302638590336,
+      "learning_rate": 2.4398625429553266e-05,
+      "loss": 0.0233,
+      "step": 1375
+    },
+    {
+      "epoch": 345.0,
+      "grad_norm": 0.11723119765520096,
+      "learning_rate": 2.4112256586483393e-05,
+      "loss": 0.0242,
+      "step": 1380
+    },
+    {
+      "epoch": 346.32,
+      "grad_norm": 0.028947005048394203,
+      "learning_rate": 2.3825887743413516e-05,
+      "loss": 0.0224,
+      "step": 1385
+    },
+    {
+      "epoch": 347.64,
+      "grad_norm": 0.027752472087740898,
+      "learning_rate": 2.3539518900343642e-05,
+      "loss": 0.0232,
+      "step": 1390
+    },
+    {
+      "epoch": 348.96,
+      "grad_norm": 0.02834869734942913,
+      "learning_rate": 2.3253150057273772e-05,
+      "loss": 0.0219,
+      "step": 1395
+    },
+    {
+      "epoch": 350.0,
+      "grad_norm": 0.11914043128490448,
+      "learning_rate": 2.2966781214203895e-05,
+      "loss": 0.0219,
+      "step": 1400
+    },
+    {
+      "epoch": 351.32,
+      "grad_norm": 0.026326792314648628,
+      "learning_rate": 2.268041237113402e-05,
+      "loss": 0.0231,
+      "step": 1405
+    },
+    {
+      "epoch": 352.64,
+      "grad_norm": 0.027006076648831367,
+      "learning_rate": 2.2394043528064148e-05,
+      "loss": 0.0242,
+      "step": 1410
+    },
+    {
+      "epoch": 353.96,
+      "grad_norm": 0.026360318064689636,
+      "learning_rate": 2.210767468499427e-05,
+      "loss": 0.0236,
+      "step": 1415
+    },
+    {
+      "epoch": 355.0,
+      "grad_norm": 0.0959874838590622,
+      "learning_rate": 2.18213058419244e-05,
+      "loss": 0.0221,
+      "step": 1420
+    },
+    {
+      "epoch": 356.32,
+      "grad_norm": 0.026437407359480858,
+      "learning_rate": 2.1534936998854528e-05,
+      "loss": 0.0231,
+      "step": 1425
+    },
+    {
+      "epoch": 357.64,
+      "grad_norm": 0.028155773878097534,
+      "learning_rate": 2.124856815578465e-05,
+      "loss": 0.0234,
+      "step": 1430
+    },
+    {
+      "epoch": 358.96,
+      "grad_norm": 0.03281427174806595,
+      "learning_rate": 2.0962199312714777e-05,
+      "loss": 0.023,
+      "step": 1435
+    },
+    {
+      "epoch": 360.0,
+      "grad_norm": 0.07536535710096359,
+      "learning_rate": 2.0675830469644904e-05,
+      "loss": 0.0228,
+      "step": 1440
+    },
+    {
+      "epoch": 361.32,
+      "grad_norm": 0.028682468459010124,
+      "learning_rate": 2.038946162657503e-05,
+      "loss": 0.024,
+      "step": 1445
+    },
+    {
+      "epoch": 362.64,
+      "grad_norm": 0.026450011879205704,
+      "learning_rate": 2.0103092783505157e-05,
+      "loss": 0.0236,
+      "step": 1450
+    },
+    {
+      "epoch": 363.96,
+      "grad_norm": 0.02757578156888485,
+      "learning_rate": 1.981672394043528e-05,
+      "loss": 0.0227,
+      "step": 1455
+    },
+    {
+      "epoch": 365.0,
+      "grad_norm": 0.09330349415540695,
+      "learning_rate": 1.9530355097365406e-05,
+      "loss": 0.0228,
+      "step": 1460
+    },
+    {
+      "epoch": 366.32,
+      "grad_norm": 0.02596072480082512,
+      "learning_rate": 1.9243986254295536e-05,
+      "loss": 0.0225,
+      "step": 1465
+    },
+    {
+      "epoch": 367.64,
+      "grad_norm": 0.025059539824724197,
+      "learning_rate": 1.895761741122566e-05,
+      "loss": 0.0226,
+      "step": 1470
+    },
+    {
+      "epoch": 368.96,
+      "grad_norm": 0.029328053817152977,
+      "learning_rate": 1.8671248568155786e-05,
+      "loss": 0.0242,
+      "step": 1475
+    },
+    {
+      "epoch": 370.0,
+      "grad_norm": 0.09089489281177521,
+      "learning_rate": 1.8384879725085912e-05,
+      "loss": 0.0226,
+      "step": 1480
+    },
+    {
+      "epoch": 371.32,
+      "grad_norm": 0.026843125000596046,
+      "learning_rate": 1.809851088201604e-05,
+      "loss": 0.0228,
+      "step": 1485
+    },
+    {
+      "epoch": 372.64,
+      "grad_norm": 0.025317925959825516,
+      "learning_rate": 1.7812142038946165e-05,
+      "loss": 0.0223,
+      "step": 1490
+    },
+    {
+      "epoch": 373.96,
+      "grad_norm": 0.02977876551449299,
+      "learning_rate": 1.7525773195876288e-05,
+      "loss": 0.025,
+      "step": 1495
+    },
+    {
+      "epoch": 375.0,
+      "grad_norm": 0.09727901220321655,
+      "learning_rate": 1.7239404352806415e-05,
+      "loss": 0.0231,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 450,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.275678425088e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Math_QA/group_01/checkpoints/checkpoint-1800/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/不冻结Qwen训练/models/Qwen2.5-1.5B-Instruct
+library_name: peft
+---
+
+# 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 0.12.0

Math_QA/group_01/checkpoints/checkpoint-1800/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/\u4e0d\u51bb\u7ed3Qwen\u8bad\u7ec3/models/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "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": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Math_QA/group_01/checkpoints/checkpoint-1800/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
+}

Math_QA/group_01/checkpoints/checkpoint-1800/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 %}

Math_QA/group_01/checkpoints/checkpoint-1800/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
+  }
+}

Math_QA/group_01/checkpoints/checkpoint-1800/tokenizer_config.json

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

Math_QA/group_01/checkpoints/checkpoint-1800/trainer_state.json

@@ -0,0 +1,2561 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 450.0,
+  "eval_steps": 500,
+  "global_step": 1800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 10.180441856384277,
+      "learning_rate": 0.0,
+      "loss": 1.8305,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 6.451148509979248,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.8074,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 3.347440481185913,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.6091,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 1.9289507865905762,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 1.1842,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.8556746244430542,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.8199,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.7173905372619629,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.6794,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.57694011926651,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.601,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.5361317992210388,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.518,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.821795701980591,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.5037,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.5809462666511536,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.3551,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 0.6679601669311523,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.3027,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 1.0066516399383545,
+      "learning_rate": 0.0001,
+      "loss": 0.2053,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 2.1689505577087402,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1499,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 1.3551698923110962,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.0919,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 0.8636834025382996,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0684,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 1.1933852434158325,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0497,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.142573118209839,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.0413,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.4700527787208557,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0385,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 0.343295693397522,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.033,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.22979414463043213,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.029,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.3299155533313751,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0299,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.13267530500888824,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0261,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.11862046271562576,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0269,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.1212410181760788,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.0271,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.4221489727497101,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0277,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.1887303739786148,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.028,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.06632087379693985,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0292,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.06920741498470306,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.0266,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.20255975425243378,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.0252,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.06548365205526352,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0262,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.3841380774974823,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0266,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.14380377531051636,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0264,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.1875791698694229,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0272,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.0587279237806797,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.026,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.1045636460185051,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0258,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.1214262992143631,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0258,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.15483546257019043,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0258,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.05430334061384201,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0249,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.059528253972530365,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0252,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.08998366445302963,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0256,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.1713639348745346,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0261,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.15917673707008362,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.026,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.06540960818529129,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.0249,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.28250637650489807,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0257,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.21159835159778595,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0252,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.17774927616119385,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0243,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.09880783408880234,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.0256,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.22325387597084045,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0348,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.18399597704410553,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0277,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.07885713130235672,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0244,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.3227796256542206,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0278,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.15556609630584717,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0298,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.21505486965179443,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0267,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.05085480958223343,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0252,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.05251656472682953,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0265,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.15204979479312897,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0245,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.12058636546134949,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0244,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.04826376959681511,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.0236,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.038287319242954254,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.0235,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.045909084379673004,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0253,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.07804425060749054,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.0237,
+      "step": 300
+    },
+    {
+      "epoch": 76.32,
+      "grad_norm": 0.04439236596226692,
+      "learning_rate": 8.56815578465063e-05,
+      "loss": 0.0241,
+      "step": 305
+    },
+    {
+      "epoch": 77.64,
+      "grad_norm": 0.0510355643928051,
+      "learning_rate": 8.539518900343643e-05,
+      "loss": 0.0247,
+      "step": 310
+    },
+    {
+      "epoch": 78.96,
+      "grad_norm": 0.04283309355378151,
+      "learning_rate": 8.510882016036655e-05,
+      "loss": 0.0244,
+      "step": 315
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.08130446821451187,
+      "learning_rate": 8.482245131729668e-05,
+      "loss": 0.0236,
+      "step": 320
+    },
+    {
+      "epoch": 81.32,
+      "grad_norm": 0.03965280205011368,
+      "learning_rate": 8.453608247422681e-05,
+      "loss": 0.0233,
+      "step": 325
+    },
+    {
+      "epoch": 82.64,
+      "grad_norm": 0.036928094923496246,
+      "learning_rate": 8.424971363115693e-05,
+      "loss": 0.0247,
+      "step": 330
+    },
+    {
+      "epoch": 83.96,
+      "grad_norm": 0.03514806181192398,
+      "learning_rate": 8.396334478808706e-05,
+      "loss": 0.0232,
+      "step": 335
+    },
+    {
+      "epoch": 85.0,
+      "grad_norm": 0.13447487354278564,
+      "learning_rate": 8.367697594501719e-05,
+      "loss": 0.0247,
+      "step": 340
+    },
+    {
+      "epoch": 86.32,
+      "grad_norm": 0.048798318952322006,
+      "learning_rate": 8.339060710194731e-05,
+      "loss": 0.0238,
+      "step": 345
+    },
+    {
+      "epoch": 87.64,
+      "grad_norm": 0.04126816615462303,
+      "learning_rate": 8.310423825887744e-05,
+      "loss": 0.0222,
+      "step": 350
+    },
+    {
+      "epoch": 88.96,
+      "grad_norm": 0.04224137216806412,
+      "learning_rate": 8.281786941580757e-05,
+      "loss": 0.0234,
+      "step": 355
+    },
+    {
+      "epoch": 90.0,
+      "grad_norm": 0.10610926151275635,
+      "learning_rate": 8.253150057273768e-05,
+      "loss": 0.0245,
+      "step": 360
+    },
+    {
+      "epoch": 91.32,
+      "grad_norm": 0.050110042095184326,
+      "learning_rate": 8.224513172966782e-05,
+      "loss": 0.0243,
+      "step": 365
+    },
+    {
+      "epoch": 92.64,
+      "grad_norm": 0.04875118285417557,
+      "learning_rate": 8.195876288659795e-05,
+      "loss": 0.0236,
+      "step": 370
+    },
+    {
+      "epoch": 93.96,
+      "grad_norm": 0.04443453252315521,
+      "learning_rate": 8.167239404352807e-05,
+      "loss": 0.0254,
+      "step": 375
+    },
+    {
+      "epoch": 95.0,
+      "grad_norm": 0.12320202589035034,
+      "learning_rate": 8.13860252004582e-05,
+      "loss": 0.0233,
+      "step": 380
+    },
+    {
+      "epoch": 96.32,
+      "grad_norm": 0.049856845289468765,
+      "learning_rate": 8.109965635738833e-05,
+      "loss": 0.0235,
+      "step": 385
+    },
+    {
+      "epoch": 97.64,
+      "grad_norm": 0.052503034472465515,
+      "learning_rate": 8.081328751431845e-05,
+      "loss": 0.0239,
+      "step": 390
+    },
+    {
+      "epoch": 98.96,
+      "grad_norm": 0.03616590052843094,
+      "learning_rate": 8.052691867124858e-05,
+      "loss": 0.024,
+      "step": 395
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.1246335357427597,
+      "learning_rate": 8.02405498281787e-05,
+      "loss": 0.0229,
+      "step": 400
+    },
+    {
+      "epoch": 101.32,
+      "grad_norm": 0.03999874368309975,
+      "learning_rate": 7.995418098510883e-05,
+      "loss": 0.0242,
+      "step": 405
+    },
+    {
+      "epoch": 102.64,
+      "grad_norm": 0.043219417333602905,
+      "learning_rate": 7.966781214203894e-05,
+      "loss": 0.0238,
+      "step": 410
+    },
+    {
+      "epoch": 103.96,
+      "grad_norm": 0.045299362391233444,
+      "learning_rate": 7.938144329896907e-05,
+      "loss": 0.0234,
+      "step": 415
+    },
+    {
+      "epoch": 105.0,
+      "grad_norm": 0.1272430568933487,
+      "learning_rate": 7.90950744558992e-05,
+      "loss": 0.025,
+      "step": 420
+    },
+    {
+      "epoch": 106.32,
+      "grad_norm": 0.03369831666350365,
+      "learning_rate": 7.880870561282932e-05,
+      "loss": 0.0232,
+      "step": 425
+    },
+    {
+      "epoch": 107.64,
+      "grad_norm": 0.03566688671708107,
+      "learning_rate": 7.852233676975945e-05,
+      "loss": 0.024,
+      "step": 430
+    },
+    {
+      "epoch": 108.96,
+      "grad_norm": 0.039571139961481094,
+      "learning_rate": 7.823596792668958e-05,
+      "loss": 0.0224,
+      "step": 435
+    },
+    {
+      "epoch": 110.0,
+      "grad_norm": 0.13205471634864807,
+      "learning_rate": 7.79495990836197e-05,
+      "loss": 0.025,
+      "step": 440
+    },
+    {
+      "epoch": 111.32,
+      "grad_norm": 0.038404062390327454,
+      "learning_rate": 7.766323024054983e-05,
+      "loss": 0.0239,
+      "step": 445
+    },
+    {
+      "epoch": 112.64,
+      "grad_norm": 0.038733795285224915,
+      "learning_rate": 7.737686139747996e-05,
+      "loss": 0.0235,
+      "step": 450
+    },
+    {
+      "epoch": 113.96,
+      "grad_norm": 0.04340984299778938,
+      "learning_rate": 7.709049255441008e-05,
+      "loss": 0.0237,
+      "step": 455
+    },
+    {
+      "epoch": 115.0,
+      "grad_norm": 0.1490347683429718,
+      "learning_rate": 7.680412371134021e-05,
+      "loss": 0.026,
+      "step": 460
+    },
+    {
+      "epoch": 116.32,
+      "grad_norm": 0.04450232908129692,
+      "learning_rate": 7.651775486827034e-05,
+      "loss": 0.0248,
+      "step": 465
+    },
+    {
+      "epoch": 117.64,
+      "grad_norm": 0.03861455246806145,
+      "learning_rate": 7.623138602520046e-05,
+      "loss": 0.0245,
+      "step": 470
+    },
+    {
+      "epoch": 118.96,
+      "grad_norm": 0.03502120077610016,
+      "learning_rate": 7.594501718213059e-05,
+      "loss": 0.0254,
+      "step": 475
+    },
+    {
+      "epoch": 120.0,
+      "grad_norm": 0.092933788895607,
+      "learning_rate": 7.565864833906071e-05,
+      "loss": 0.0242,
+      "step": 480
+    },
+    {
+      "epoch": 121.32,
+      "grad_norm": 0.03522248566150665,
+      "learning_rate": 7.537227949599084e-05,
+      "loss": 0.0232,
+      "step": 485
+    },
+    {
+      "epoch": 122.64,
+      "grad_norm": 0.030242981389164925,
+      "learning_rate": 7.508591065292097e-05,
+      "loss": 0.0229,
+      "step": 490
+    },
+    {
+      "epoch": 123.96,
+      "grad_norm": 0.03727824613451958,
+      "learning_rate": 7.47995418098511e-05,
+      "loss": 0.0239,
+      "step": 495
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 0.11968818306922913,
+      "learning_rate": 7.451317296678122e-05,
+      "loss": 0.0234,
+      "step": 500
+    },
+    {
+      "epoch": 126.32,
+      "grad_norm": 0.032707035541534424,
+      "learning_rate": 7.422680412371135e-05,
+      "loss": 0.0221,
+      "step": 505
+    },
+    {
+      "epoch": 127.64,
+      "grad_norm": 0.03655603528022766,
+      "learning_rate": 7.394043528064147e-05,
+      "loss": 0.0243,
+      "step": 510
+    },
+    {
+      "epoch": 128.96,
+      "grad_norm": 0.03384123370051384,
+      "learning_rate": 7.36540664375716e-05,
+      "loss": 0.0217,
+      "step": 515
+    },
+    {
+      "epoch": 130.0,
+      "grad_norm": 0.11020781844854355,
+      "learning_rate": 7.336769759450171e-05,
+      "loss": 0.0237,
+      "step": 520
+    },
+    {
+      "epoch": 131.32,
+      "grad_norm": 0.038297172635793686,
+      "learning_rate": 7.308132875143184e-05,
+      "loss": 0.0232,
+      "step": 525
+    },
+    {
+      "epoch": 132.64,
+      "grad_norm": 0.03700310364365578,
+      "learning_rate": 7.279495990836197e-05,
+      "loss": 0.0229,
+      "step": 530
+    },
+    {
+      "epoch": 133.96,
+      "grad_norm": 0.0338885597884655,
+      "learning_rate": 7.250859106529209e-05,
+      "loss": 0.0229,
+      "step": 535
+    },
+    {
+      "epoch": 135.0,
+      "grad_norm": 0.10868728905916214,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.0224,
+      "step": 540
+    },
+    {
+      "epoch": 136.32,
+      "grad_norm": 0.035598840564489365,
+      "learning_rate": 7.193585337915235e-05,
+      "loss": 0.0255,
+      "step": 545
+    },
+    {
+      "epoch": 137.64,
+      "grad_norm": 0.031226877123117447,
+      "learning_rate": 7.164948453608247e-05,
+      "loss": 0.0233,
+      "step": 550
+    },
+    {
+      "epoch": 138.96,
+      "grad_norm": 0.03582902252674103,
+      "learning_rate": 7.136311569301261e-05,
+      "loss": 0.0229,
+      "step": 555
+    },
+    {
+      "epoch": 140.0,
+      "grad_norm": 0.11769143491983414,
+      "learning_rate": 7.107674684994274e-05,
+      "loss": 0.0245,
+      "step": 560
+    },
+    {
+      "epoch": 141.32,
+      "grad_norm": 0.030704690143465996,
+      "learning_rate": 7.079037800687286e-05,
+      "loss": 0.0242,
+      "step": 565
+    },
+    {
+      "epoch": 142.64,
+      "grad_norm": 0.03247276693582535,
+      "learning_rate": 7.050400916380299e-05,
+      "loss": 0.0239,
+      "step": 570
+    },
+    {
+      "epoch": 143.96,
+      "grad_norm": 0.03496946021914482,
+      "learning_rate": 7.02176403207331e-05,
+      "loss": 0.0251,
+      "step": 575
+    },
+    {
+      "epoch": 145.0,
+      "grad_norm": 0.08276615291833878,
+      "learning_rate": 6.993127147766323e-05,
+      "loss": 0.0221,
+      "step": 580
+    },
+    {
+      "epoch": 146.32,
+      "grad_norm": 0.040135324001312256,
+      "learning_rate": 6.964490263459336e-05,
+      "loss": 0.0233,
+      "step": 585
+    },
+    {
+      "epoch": 147.64,
+      "grad_norm": 0.0358579121530056,
+      "learning_rate": 6.935853379152348e-05,
+      "loss": 0.0245,
+      "step": 590
+    },
+    {
+      "epoch": 148.96,
+      "grad_norm": 0.04078257456421852,
+      "learning_rate": 6.907216494845361e-05,
+      "loss": 0.0246,
+      "step": 595
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 0.07422423362731934,
+      "learning_rate": 6.878579610538374e-05,
+      "loss": 0.0217,
+      "step": 600
+    },
+    {
+      "epoch": 151.32,
+      "grad_norm": 0.036644842475652695,
+      "learning_rate": 6.849942726231386e-05,
+      "loss": 0.0234,
+      "step": 605
+    },
+    {
+      "epoch": 152.64,
+      "grad_norm": 0.03300880640745163,
+      "learning_rate": 6.821305841924399e-05,
+      "loss": 0.0228,
+      "step": 610
+    },
+    {
+      "epoch": 153.96,
+      "grad_norm": 0.03661232069134712,
+      "learning_rate": 6.792668957617412e-05,
+      "loss": 0.0237,
+      "step": 615
+    },
+    {
+      "epoch": 155.0,
+      "grad_norm": 0.12643153965473175,
+      "learning_rate": 6.764032073310424e-05,
+      "loss": 0.024,
+      "step": 620
+    },
+    {
+      "epoch": 156.32,
+      "grad_norm": 0.03363413363695145,
+      "learning_rate": 6.735395189003437e-05,
+      "loss": 0.0224,
+      "step": 625
+    },
+    {
+      "epoch": 157.64,
+      "grad_norm": 0.03167325258255005,
+      "learning_rate": 6.706758304696448e-05,
+      "loss": 0.0223,
+      "step": 630
+    },
+    {
+      "epoch": 158.96,
+      "grad_norm": 0.029550231993198395,
+      "learning_rate": 6.678121420389462e-05,
+      "loss": 0.0235,
+      "step": 635
+    },
+    {
+      "epoch": 160.0,
+      "grad_norm": 0.09065394103527069,
+      "learning_rate": 6.649484536082475e-05,
+      "loss": 0.024,
+      "step": 640
+    },
+    {
+      "epoch": 161.32,
+      "grad_norm": 0.03413796424865723,
+      "learning_rate": 6.620847651775487e-05,
+      "loss": 0.0238,
+      "step": 645
+    },
+    {
+      "epoch": 162.64,
+      "grad_norm": 0.03629285842180252,
+      "learning_rate": 6.5922107674685e-05,
+      "loss": 0.0228,
+      "step": 650
+    },
+    {
+      "epoch": 163.96,
+      "grad_norm": 0.030809171497821808,
+      "learning_rate": 6.563573883161513e-05,
+      "loss": 0.0237,
+      "step": 655
+    },
+    {
+      "epoch": 165.0,
+      "grad_norm": 0.12004661560058594,
+      "learning_rate": 6.534936998854525e-05,
+      "loss": 0.024,
+      "step": 660
+    },
+    {
+      "epoch": 166.32,
+      "grad_norm": 0.03047570399940014,
+      "learning_rate": 6.506300114547538e-05,
+      "loss": 0.0241,
+      "step": 665
+    },
+    {
+      "epoch": 167.64,
+      "grad_norm": 0.02905591018497944,
+      "learning_rate": 6.477663230240551e-05,
+      "loss": 0.0237,
+      "step": 670
+    },
+    {
+      "epoch": 168.96,
+      "grad_norm": 0.034070760011672974,
+      "learning_rate": 6.449026345933563e-05,
+      "loss": 0.0238,
+      "step": 675
+    },
+    {
+      "epoch": 170.0,
+      "grad_norm": 0.1274733990430832,
+      "learning_rate": 6.420389461626576e-05,
+      "loss": 0.0243,
+      "step": 680
+    },
+    {
+      "epoch": 171.32,
+      "grad_norm": 0.03325100615620613,
+      "learning_rate": 6.391752577319587e-05,
+      "loss": 0.0232,
+      "step": 685
+    },
+    {
+      "epoch": 172.64,
+      "grad_norm": 0.03404676914215088,
+      "learning_rate": 6.3631156930126e-05,
+      "loss": 0.0242,
+      "step": 690
+    },
+    {
+      "epoch": 173.96,
+      "grad_norm": 0.029422307386994362,
+      "learning_rate": 6.334478808705613e-05,
+      "loss": 0.0223,
+      "step": 695
+    },
+    {
+      "epoch": 175.0,
+      "grad_norm": 0.06759767234325409,
+      "learning_rate": 6.305841924398625e-05,
+      "loss": 0.0216,
+      "step": 700
+    },
+    {
+      "epoch": 176.32,
+      "grad_norm": 0.03126778081059456,
+      "learning_rate": 6.277205040091638e-05,
+      "loss": 0.0234,
+      "step": 705
+    },
+    {
+      "epoch": 177.64,
+      "grad_norm": 0.025731679052114487,
+      "learning_rate": 6.24856815578465e-05,
+      "loss": 0.0234,
+      "step": 710
+    },
+    {
+      "epoch": 178.96,
+      "grad_norm": 0.028922362253069878,
+      "learning_rate": 6.219931271477663e-05,
+      "loss": 0.0229,
+      "step": 715
+    },
+    {
+      "epoch": 180.0,
+      "grad_norm": 0.12048332393169403,
+      "learning_rate": 6.191294387170676e-05,
+      "loss": 0.023,
+      "step": 720
+    },
+    {
+      "epoch": 181.32,
+      "grad_norm": 0.033701252192258835,
+      "learning_rate": 6.162657502863689e-05,
+      "loss": 0.0253,
+      "step": 725
+    },
+    {
+      "epoch": 182.64,
+      "grad_norm": 0.034988295286893845,
+      "learning_rate": 6.134020618556701e-05,
+      "loss": 0.022,
+      "step": 730
+    },
+    {
+      "epoch": 183.96,
+      "grad_norm": 0.04288899898529053,
+      "learning_rate": 6.105383734249714e-05,
+      "loss": 0.0223,
+      "step": 735
+    },
+    {
+      "epoch": 185.0,
+      "grad_norm": 0.07889136672019958,
+      "learning_rate": 6.076746849942726e-05,
+      "loss": 0.0253,
+      "step": 740
+    },
+    {
+      "epoch": 186.32,
+      "grad_norm": 0.03613121807575226,
+      "learning_rate": 6.0481099656357384e-05,
+      "loss": 0.0231,
+      "step": 745
+    },
+    {
+      "epoch": 187.64,
+      "grad_norm": 0.029085509479045868,
+      "learning_rate": 6.019473081328752e-05,
+      "loss": 0.0243,
+      "step": 750
+    },
+    {
+      "epoch": 188.96,
+      "grad_norm": 0.029132477939128876,
+      "learning_rate": 5.9908361970217644e-05,
+      "loss": 0.0225,
+      "step": 755
+    },
+    {
+      "epoch": 190.0,
+      "grad_norm": 0.05503055825829506,
+      "learning_rate": 5.962199312714777e-05,
+      "loss": 0.0214,
+      "step": 760
+    },
+    {
+      "epoch": 191.32,
+      "grad_norm": 0.02779143489897251,
+      "learning_rate": 5.93356242840779e-05,
+      "loss": 0.023,
+      "step": 765
+    },
+    {
+      "epoch": 192.64,
+      "grad_norm": 0.03147861734032631,
+      "learning_rate": 5.904925544100802e-05,
+      "loss": 0.024,
+      "step": 770
+    },
+    {
+      "epoch": 193.96,
+      "grad_norm": 0.032027844339609146,
+      "learning_rate": 5.876288659793815e-05,
+      "loss": 0.0237,
+      "step": 775
+    },
+    {
+      "epoch": 195.0,
+      "grad_norm": 0.08647307753562927,
+      "learning_rate": 5.8476517754868276e-05,
+      "loss": 0.0229,
+      "step": 780
+    },
+    {
+      "epoch": 196.32,
+      "grad_norm": 0.03443491831421852,
+      "learning_rate": 5.81901489117984e-05,
+      "loss": 0.0225,
+      "step": 785
+    },
+    {
+      "epoch": 197.64,
+      "grad_norm": 0.03234897553920746,
+      "learning_rate": 5.790378006872853e-05,
+      "loss": 0.0226,
+      "step": 790
+    },
+    {
+      "epoch": 198.96,
+      "grad_norm": 0.033941544592380524,
+      "learning_rate": 5.761741122565865e-05,
+      "loss": 0.0236,
+      "step": 795
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 0.08900703489780426,
+      "learning_rate": 5.7331042382588775e-05,
+      "loss": 0.024,
+      "step": 800
+    },
+    {
+      "epoch": 201.32,
+      "grad_norm": 0.02964199334383011,
+      "learning_rate": 5.70446735395189e-05,
+      "loss": 0.0237,
+      "step": 805
+    },
+    {
+      "epoch": 202.64,
+      "grad_norm": 0.032776352018117905,
+      "learning_rate": 5.675830469644903e-05,
+      "loss": 0.0227,
+      "step": 810
+    },
+    {
+      "epoch": 203.96,
+      "grad_norm": 0.02906695567071438,
+      "learning_rate": 5.6471935853379155e-05,
+      "loss": 0.0247,
+      "step": 815
+    },
+    {
+      "epoch": 205.0,
+      "grad_norm": 0.10413157194852829,
+      "learning_rate": 5.618556701030928e-05,
+      "loss": 0.0231,
+      "step": 820
+    },
+    {
+      "epoch": 206.32,
+      "grad_norm": 0.027301495894789696,
+      "learning_rate": 5.589919816723941e-05,
+      "loss": 0.0235,
+      "step": 825
+    },
+    {
+      "epoch": 207.64,
+      "grad_norm": 0.02905373089015484,
+      "learning_rate": 5.5612829324169534e-05,
+      "loss": 0.0235,
+      "step": 830
+    },
+    {
+      "epoch": 208.96,
+      "grad_norm": 0.02877797745168209,
+      "learning_rate": 5.532646048109966e-05,
+      "loss": 0.0224,
+      "step": 835
+    },
+    {
+      "epoch": 210.0,
+      "grad_norm": 0.0836072713136673,
+      "learning_rate": 5.504009163802979e-05,
+      "loss": 0.0233,
+      "step": 840
+    },
+    {
+      "epoch": 211.32,
+      "grad_norm": 0.030773388221859932,
+      "learning_rate": 5.4753722794959914e-05,
+      "loss": 0.0243,
+      "step": 845
+    },
+    {
+      "epoch": 212.64,
+      "grad_norm": 0.028844933956861496,
+      "learning_rate": 5.4467353951890033e-05,
+      "loss": 0.0224,
+      "step": 850
+    },
+    {
+      "epoch": 213.96,
+      "grad_norm": 0.032330844551324844,
+      "learning_rate": 5.418098510882016e-05,
+      "loss": 0.023,
+      "step": 855
+    },
+    {
+      "epoch": 215.0,
+      "grad_norm": 0.13418708741664886,
+      "learning_rate": 5.3894616265750286e-05,
+      "loss": 0.0229,
+      "step": 860
+    },
+    {
+      "epoch": 216.32,
+      "grad_norm": 0.0328691340982914,
+      "learning_rate": 5.360824742268041e-05,
+      "loss": 0.0237,
+      "step": 865
+    },
+    {
+      "epoch": 217.64,
+      "grad_norm": 0.030551306903362274,
+      "learning_rate": 5.332187857961054e-05,
+      "loss": 0.0226,
+      "step": 870
+    },
+    {
+      "epoch": 218.96,
+      "grad_norm": 0.03350970149040222,
+      "learning_rate": 5.3035509736540666e-05,
+      "loss": 0.0234,
+      "step": 875
+    },
+    {
+      "epoch": 220.0,
+      "grad_norm": 0.08607557415962219,
+      "learning_rate": 5.274914089347079e-05,
+      "loss": 0.0235,
+      "step": 880
+    },
+    {
+      "epoch": 221.32,
+      "grad_norm": 0.028927354142069817,
+      "learning_rate": 5.246277205040092e-05,
+      "loss": 0.0244,
+      "step": 885
+    },
+    {
+      "epoch": 222.64,
+      "grad_norm": 0.02603020891547203,
+      "learning_rate": 5.2176403207331045e-05,
+      "loss": 0.0223,
+      "step": 890
+    },
+    {
+      "epoch": 223.96,
+      "grad_norm": 0.025388307869434357,
+      "learning_rate": 5.189003436426118e-05,
+      "loss": 0.0238,
+      "step": 895
+    },
+    {
+      "epoch": 225.0,
+      "grad_norm": 0.08444017916917801,
+      "learning_rate": 5.1603665521191305e-05,
+      "loss": 0.0239,
+      "step": 900
+    },
+    {
+      "epoch": 226.32,
+      "grad_norm": 0.02715456858277321,
+      "learning_rate": 5.131729667812142e-05,
+      "loss": 0.0242,
+      "step": 905
+    },
+    {
+      "epoch": 227.64,
+      "grad_norm": 0.0326889231801033,
+      "learning_rate": 5.1030927835051544e-05,
+      "loss": 0.0216,
+      "step": 910
+    },
+    {
+      "epoch": 228.96,
+      "grad_norm": 0.03151186928153038,
+      "learning_rate": 5.074455899198167e-05,
+      "loss": 0.0232,
+      "step": 915
+    },
+    {
+      "epoch": 230.0,
+      "grad_norm": 0.1081857904791832,
+      "learning_rate": 5.04581901489118e-05,
+      "loss": 0.0243,
+      "step": 920
+    },
+    {
+      "epoch": 231.32,
+      "grad_norm": 0.02827647142112255,
+      "learning_rate": 5.0171821305841924e-05,
+      "loss": 0.0234,
+      "step": 925
+    },
+    {
+      "epoch": 232.64,
+      "grad_norm": 0.027565542608499527,
+      "learning_rate": 4.988545246277205e-05,
+      "loss": 0.023,
+      "step": 930
+    },
+    {
+      "epoch": 233.96,
+      "grad_norm": 0.03328179195523262,
+      "learning_rate": 4.9599083619702184e-05,
+      "loss": 0.0234,
+      "step": 935
+    },
+    {
+      "epoch": 235.0,
+      "grad_norm": 0.14499929547309875,
+      "learning_rate": 4.931271477663231e-05,
+      "loss": 0.0241,
+      "step": 940
+    },
+    {
+      "epoch": 236.32,
+      "grad_norm": 0.025718634948134422,
+      "learning_rate": 4.902634593356243e-05,
+      "loss": 0.0229,
+      "step": 945
+    },
+    {
+      "epoch": 237.64,
+      "grad_norm": 0.03075622022151947,
+      "learning_rate": 4.8739977090492556e-05,
+      "loss": 0.0233,
+      "step": 950
+    },
+    {
+      "epoch": 238.96,
+      "grad_norm": 0.03137879818677902,
+      "learning_rate": 4.845360824742268e-05,
+      "loss": 0.0243,
+      "step": 955
+    },
+    {
+      "epoch": 240.0,
+      "grad_norm": 0.08810659497976303,
+      "learning_rate": 4.816723940435281e-05,
+      "loss": 0.0227,
+      "step": 960
+    },
+    {
+      "epoch": 241.32,
+      "grad_norm": 0.030054708942770958,
+      "learning_rate": 4.7880870561282936e-05,
+      "loss": 0.0234,
+      "step": 965
+    },
+    {
+      "epoch": 242.64,
+      "grad_norm": 0.028709901496767998,
+      "learning_rate": 4.7594501718213055e-05,
+      "loss": 0.0228,
+      "step": 970
+    },
+    {
+      "epoch": 243.96,
+      "grad_norm": 0.027529578655958176,
+      "learning_rate": 4.730813287514318e-05,
+      "loss": 0.0224,
+      "step": 975
+    },
+    {
+      "epoch": 245.0,
+      "grad_norm": 0.10843145102262497,
+      "learning_rate": 4.7021764032073315e-05,
+      "loss": 0.0244,
+      "step": 980
+    },
+    {
+      "epoch": 246.32,
+      "grad_norm": 0.028441136702895164,
+      "learning_rate": 4.673539518900344e-05,
+      "loss": 0.0244,
+      "step": 985
+    },
+    {
+      "epoch": 247.64,
+      "grad_norm": 0.027241505682468414,
+      "learning_rate": 4.644902634593357e-05,
+      "loss": 0.0223,
+      "step": 990
+    },
+    {
+      "epoch": 248.96,
+      "grad_norm": 0.029671119526028633,
+      "learning_rate": 4.6162657502863694e-05,
+      "loss": 0.0236,
+      "step": 995
+    },
+    {
+      "epoch": 250.0,
+      "grad_norm": 0.10153710842132568,
+      "learning_rate": 4.5876288659793814e-05,
+      "loss": 0.0243,
+      "step": 1000
+    },
+    {
+      "epoch": 251.32,
+      "grad_norm": 0.03248867765069008,
+      "learning_rate": 4.558991981672394e-05,
+      "loss": 0.0239,
+      "step": 1005
+    },
+    {
+      "epoch": 252.64,
+      "grad_norm": 0.03408573195338249,
+      "learning_rate": 4.530355097365407e-05,
+      "loss": 0.023,
+      "step": 1010
+    },
+    {
+      "epoch": 253.96,
+      "grad_norm": 0.027460109442472458,
+      "learning_rate": 4.5017182130584194e-05,
+      "loss": 0.0228,
+      "step": 1015
+    },
+    {
+      "epoch": 255.0,
+      "grad_norm": 0.0669630840420723,
+      "learning_rate": 4.473081328751432e-05,
+      "loss": 0.0231,
+      "step": 1020
+    },
+    {
+      "epoch": 256.32,
+      "grad_norm": 0.026929493993520737,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.022,
+      "step": 1025
+    },
+    {
+      "epoch": 257.64,
+      "grad_norm": 0.026157841086387634,
+      "learning_rate": 4.415807560137457e-05,
+      "loss": 0.0232,
+      "step": 1030
+    },
+    {
+      "epoch": 258.96,
+      "grad_norm": 0.03178902342915535,
+      "learning_rate": 4.38717067583047e-05,
+      "loss": 0.0235,
+      "step": 1035
+    },
+    {
+      "epoch": 260.0,
+      "grad_norm": 0.09565325826406479,
+      "learning_rate": 4.3585337915234826e-05,
+      "loss": 0.0244,
+      "step": 1040
+    },
+    {
+      "epoch": 261.32,
+      "grad_norm": 0.028645526617765427,
+      "learning_rate": 4.329896907216495e-05,
+      "loss": 0.0229,
+      "step": 1045
+    },
+    {
+      "epoch": 262.64,
+      "grad_norm": 0.02763913758099079,
+      "learning_rate": 4.301260022909508e-05,
+      "loss": 0.0235,
+      "step": 1050
+    },
+    {
+      "epoch": 263.96,
+      "grad_norm": 0.02442869544029236,
+      "learning_rate": 4.27262313860252e-05,
+      "loss": 0.023,
+      "step": 1055
+    },
+    {
+      "epoch": 265.0,
+      "grad_norm": 0.07956762611865997,
+      "learning_rate": 4.2439862542955325e-05,
+      "loss": 0.0228,
+      "step": 1060
+    },
+    {
+      "epoch": 266.32,
+      "grad_norm": 0.027121301740407944,
+      "learning_rate": 4.215349369988545e-05,
+      "loss": 0.0231,
+      "step": 1065
+    },
+    {
+      "epoch": 267.64,
+      "grad_norm": 0.028464002534747124,
+      "learning_rate": 4.1867124856815585e-05,
+      "loss": 0.0216,
+      "step": 1070
+    },
+    {
+      "epoch": 268.96,
+      "grad_norm": 0.028463657945394516,
+      "learning_rate": 4.158075601374571e-05,
+      "loss": 0.0235,
+      "step": 1075
+    },
+    {
+      "epoch": 270.0,
+      "grad_norm": 0.11043697595596313,
+      "learning_rate": 4.129438717067583e-05,
+      "loss": 0.0238,
+      "step": 1080
+    },
+    {
+      "epoch": 271.32,
+      "grad_norm": 0.028240198269486427,
+      "learning_rate": 4.100801832760596e-05,
+      "loss": 0.0228,
+      "step": 1085
+    },
+    {
+      "epoch": 272.64,
+      "grad_norm": 0.03129616379737854,
+      "learning_rate": 4.0721649484536084e-05,
+      "loss": 0.0236,
+      "step": 1090
+    },
+    {
+      "epoch": 273.96,
+      "grad_norm": 0.02936883457005024,
+      "learning_rate": 4.043528064146621e-05,
+      "loss": 0.0219,
+      "step": 1095
+    },
+    {
+      "epoch": 275.0,
+      "grad_norm": 0.08938605338335037,
+      "learning_rate": 4.014891179839634e-05,
+      "loss": 0.0234,
+      "step": 1100
+    },
+    {
+      "epoch": 276.32,
+      "grad_norm": 0.031886886805295944,
+      "learning_rate": 3.9862542955326463e-05,
+      "loss": 0.022,
+      "step": 1105
+    },
+    {
+      "epoch": 277.64,
+      "grad_norm": 0.027169784530997276,
+      "learning_rate": 3.957617411225659e-05,
+      "loss": 0.0231,
+      "step": 1110
+    },
+    {
+      "epoch": 278.96,
+      "grad_norm": 0.030490893870592117,
+      "learning_rate": 3.9289805269186716e-05,
+      "loss": 0.0225,
+      "step": 1115
+    },
+    {
+      "epoch": 280.0,
+      "grad_norm": 0.10452266782522202,
+      "learning_rate": 3.900343642611684e-05,
+      "loss": 0.0229,
+      "step": 1120
+    },
+    {
+      "epoch": 281.32,
+      "grad_norm": 0.031348999589681625,
+      "learning_rate": 3.871706758304697e-05,
+      "loss": 0.0225,
+      "step": 1125
+    },
+    {
+      "epoch": 282.64,
+      "grad_norm": 0.025815803557634354,
+      "learning_rate": 3.8430698739977096e-05,
+      "loss": 0.0224,
+      "step": 1130
+    },
+    {
+      "epoch": 283.96,
+      "grad_norm": 0.026555614545941353,
+      "learning_rate": 3.8144329896907216e-05,
+      "loss": 0.0218,
+      "step": 1135
+    },
+    {
+      "epoch": 285.0,
+      "grad_norm": 0.11624571681022644,
+      "learning_rate": 3.785796105383734e-05,
+      "loss": 0.0251,
+      "step": 1140
+    },
+    {
+      "epoch": 286.32,
+      "grad_norm": 0.03565097600221634,
+      "learning_rate": 3.757159221076747e-05,
+      "loss": 0.0225,
+      "step": 1145
+    },
+    {
+      "epoch": 287.64,
+      "grad_norm": 0.02672787383198738,
+      "learning_rate": 3.7285223367697595e-05,
+      "loss": 0.0217,
+      "step": 1150
+    },
+    {
+      "epoch": 288.96,
+      "grad_norm": 0.02724423073232174,
+      "learning_rate": 3.699885452462772e-05,
+      "loss": 0.0231,
+      "step": 1155
+    },
+    {
+      "epoch": 290.0,
+      "grad_norm": 0.10171245783567429,
+      "learning_rate": 3.671248568155785e-05,
+      "loss": 0.0236,
+      "step": 1160
+    },
+    {
+      "epoch": 291.32,
+      "grad_norm": 0.02749449387192726,
+      "learning_rate": 3.6426116838487974e-05,
+      "loss": 0.0227,
+      "step": 1165
+    },
+    {
+      "epoch": 292.64,
+      "grad_norm": 0.02680155821144581,
+      "learning_rate": 3.61397479954181e-05,
+      "loss": 0.0234,
+      "step": 1170
+    },
+    {
+      "epoch": 293.96,
+      "grad_norm": 0.025701116770505905,
+      "learning_rate": 3.585337915234823e-05,
+      "loss": 0.0228,
+      "step": 1175
+    },
+    {
+      "epoch": 295.0,
+      "grad_norm": 0.0642700269818306,
+      "learning_rate": 3.5567010309278354e-05,
+      "loss": 0.0211,
+      "step": 1180
+    },
+    {
+      "epoch": 296.32,
+      "grad_norm": 0.025475211441516876,
+      "learning_rate": 3.528064146620848e-05,
+      "loss": 0.0224,
+      "step": 1185
+    },
+    {
+      "epoch": 297.64,
+      "grad_norm": 0.028312934562563896,
+      "learning_rate": 3.49942726231386e-05,
+      "loss": 0.0234,
+      "step": 1190
+    },
+    {
+      "epoch": 298.96,
+      "grad_norm": 0.026962120085954666,
+      "learning_rate": 3.4707903780068726e-05,
+      "loss": 0.0223,
+      "step": 1195
+    },
+    {
+      "epoch": 300.0,
+      "grad_norm": 0.08954183757305145,
+      "learning_rate": 3.442153493699885e-05,
+      "loss": 0.0226,
+      "step": 1200
+    },
+    {
+      "epoch": 301.32,
+      "grad_norm": 0.027179185301065445,
+      "learning_rate": 3.4135166093928986e-05,
+      "loss": 0.0224,
+      "step": 1205
+    },
+    {
+      "epoch": 302.64,
+      "grad_norm": 0.026793546974658966,
+      "learning_rate": 3.384879725085911e-05,
+      "loss": 0.0222,
+      "step": 1210
+    },
+    {
+      "epoch": 303.96,
+      "grad_norm": 0.029869597405195236,
+      "learning_rate": 3.356242840778923e-05,
+      "loss": 0.0232,
+      "step": 1215
+    },
+    {
+      "epoch": 305.0,
+      "grad_norm": 0.12393646687269211,
+      "learning_rate": 3.327605956471936e-05,
+      "loss": 0.0229,
+      "step": 1220
+    },
+    {
+      "epoch": 306.32,
+      "grad_norm": 0.029647044837474823,
+      "learning_rate": 3.2989690721649485e-05,
+      "loss": 0.0229,
+      "step": 1225
+    },
+    {
+      "epoch": 307.64,
+      "grad_norm": 0.02922012098133564,
+      "learning_rate": 3.270332187857961e-05,
+      "loss": 0.0228,
+      "step": 1230
+    },
+    {
+      "epoch": 308.96,
+      "grad_norm": 0.028046652674674988,
+      "learning_rate": 3.241695303550974e-05,
+      "loss": 0.0218,
+      "step": 1235
+    },
+    {
+      "epoch": 310.0,
+      "grad_norm": 0.09626638144254684,
+      "learning_rate": 3.2130584192439865e-05,
+      "loss": 0.0241,
+      "step": 1240
+    },
+    {
+      "epoch": 311.32,
+      "grad_norm": 0.025637533515691757,
+      "learning_rate": 3.184421534936999e-05,
+      "loss": 0.0247,
+      "step": 1245
+    },
+    {
+      "epoch": 312.64,
+      "grad_norm": 0.0269307903945446,
+      "learning_rate": 3.155784650630012e-05,
+      "loss": 0.024,
+      "step": 1250
+    },
+    {
+      "epoch": 313.96,
+      "grad_norm": 0.025975301861763,
+      "learning_rate": 3.1271477663230244e-05,
+      "loss": 0.0232,
+      "step": 1255
+    },
+    {
+      "epoch": 315.0,
+      "grad_norm": 0.10530711710453033,
+      "learning_rate": 3.098510882016037e-05,
+      "loss": 0.0242,
+      "step": 1260
+    },
+    {
+      "epoch": 316.32,
+      "grad_norm": 0.026885682716965675,
+      "learning_rate": 3.06987399770905e-05,
+      "loss": 0.0225,
+      "step": 1265
+    },
+    {
+      "epoch": 317.64,
+      "grad_norm": 0.027477962896227837,
+      "learning_rate": 3.0412371134020617e-05,
+      "loss": 0.0233,
+      "step": 1270
+    },
+    {
+      "epoch": 318.96,
+      "grad_norm": 0.031309112906455994,
+      "learning_rate": 3.0126002290950743e-05,
+      "loss": 0.0226,
+      "step": 1275
+    },
+    {
+      "epoch": 320.0,
+      "grad_norm": 0.0752459242939949,
+      "learning_rate": 2.983963344788087e-05,
+      "loss": 0.0209,
+      "step": 1280
+    },
+    {
+      "epoch": 321.32,
+      "grad_norm": 0.029426634311676025,
+      "learning_rate": 2.9553264604811e-05,
+      "loss": 0.0219,
+      "step": 1285
+    },
+    {
+      "epoch": 322.64,
+      "grad_norm": 0.02936774678528309,
+      "learning_rate": 2.9266895761741126e-05,
+      "loss": 0.0228,
+      "step": 1290
+    },
+    {
+      "epoch": 323.96,
+      "grad_norm": 0.028937801718711853,
+      "learning_rate": 2.8980526918671253e-05,
+      "loss": 0.022,
+      "step": 1295
+    },
+    {
+      "epoch": 325.0,
+      "grad_norm": 0.09840500354766846,
+      "learning_rate": 2.8694158075601372e-05,
+      "loss": 0.023,
+      "step": 1300
+    },
+    {
+      "epoch": 326.32,
+      "grad_norm": 0.03570740297436714,
+      "learning_rate": 2.8407789232531502e-05,
+      "loss": 0.0248,
+      "step": 1305
+    },
+    {
+      "epoch": 327.64,
+      "grad_norm": 0.02928864397108555,
+      "learning_rate": 2.812142038946163e-05,
+      "loss": 0.0223,
+      "step": 1310
+    },
+    {
+      "epoch": 328.96,
+      "grad_norm": 0.026148077100515366,
+      "learning_rate": 2.7835051546391755e-05,
+      "loss": 0.0216,
+      "step": 1315
+    },
+    {
+      "epoch": 330.0,
+      "grad_norm": 0.08714782446622849,
+      "learning_rate": 2.754868270332188e-05,
+      "loss": 0.0224,
+      "step": 1320
+    },
+    {
+      "epoch": 331.32,
+      "grad_norm": 0.027646895498037338,
+      "learning_rate": 2.7262313860252005e-05,
+      "loss": 0.022,
+      "step": 1325
+    },
+    {
+      "epoch": 332.64,
+      "grad_norm": 0.02741863578557968,
+      "learning_rate": 2.697594501718213e-05,
+      "loss": 0.0238,
+      "step": 1330
+    },
+    {
+      "epoch": 333.96,
+      "grad_norm": 0.031554851680994034,
+      "learning_rate": 2.6689576174112258e-05,
+      "loss": 0.0238,
+      "step": 1335
+    },
+    {
+      "epoch": 335.0,
+      "grad_norm": 0.10320069640874863,
+      "learning_rate": 2.6403207331042384e-05,
+      "loss": 0.0247,
+      "step": 1340
+    },
+    {
+      "epoch": 336.32,
+      "grad_norm": 0.027910800650715828,
+      "learning_rate": 2.611683848797251e-05,
+      "loss": 0.0218,
+      "step": 1345
+    },
+    {
+      "epoch": 337.64,
+      "grad_norm": 0.0307508185505867,
+      "learning_rate": 2.5830469644902637e-05,
+      "loss": 0.0227,
+      "step": 1350
+    },
+    {
+      "epoch": 338.96,
+      "grad_norm": 0.028163570910692215,
+      "learning_rate": 2.554410080183276e-05,
+      "loss": 0.0228,
+      "step": 1355
+    },
+    {
+      "epoch": 340.0,
+      "grad_norm": 0.07637765258550644,
+      "learning_rate": 2.5257731958762887e-05,
+      "loss": 0.0214,
+      "step": 1360
+    },
+    {
+      "epoch": 341.32,
+      "grad_norm": 0.028695199638605118,
+      "learning_rate": 2.4971363115693013e-05,
+      "loss": 0.0227,
+      "step": 1365
+    },
+    {
+      "epoch": 342.64,
+      "grad_norm": 0.026736624538898468,
+      "learning_rate": 2.468499427262314e-05,
+      "loss": 0.0218,
+      "step": 1370
+    },
+    {
+      "epoch": 343.96,
+      "grad_norm": 0.02612302638590336,
+      "learning_rate": 2.4398625429553266e-05,
+      "loss": 0.0233,
+      "step": 1375
+    },
+    {
+      "epoch": 345.0,
+      "grad_norm": 0.11723119765520096,
+      "learning_rate": 2.4112256586483393e-05,
+      "loss": 0.0242,
+      "step": 1380
+    },
+    {
+      "epoch": 346.32,
+      "grad_norm": 0.028947005048394203,
+      "learning_rate": 2.3825887743413516e-05,
+      "loss": 0.0224,
+      "step": 1385
+    },
+    {
+      "epoch": 347.64,
+      "grad_norm": 0.027752472087740898,
+      "learning_rate": 2.3539518900343642e-05,
+      "loss": 0.0232,
+      "step": 1390
+    },
+    {
+      "epoch": 348.96,
+      "grad_norm": 0.02834869734942913,
+      "learning_rate": 2.3253150057273772e-05,
+      "loss": 0.0219,
+      "step": 1395
+    },
+    {
+      "epoch": 350.0,
+      "grad_norm": 0.11914043128490448,
+      "learning_rate": 2.2966781214203895e-05,
+      "loss": 0.0219,
+      "step": 1400
+    },
+    {
+      "epoch": 351.32,
+      "grad_norm": 0.026326792314648628,
+      "learning_rate": 2.268041237113402e-05,
+      "loss": 0.0231,
+      "step": 1405
+    },
+    {
+      "epoch": 352.64,
+      "grad_norm": 0.027006076648831367,
+      "learning_rate": 2.2394043528064148e-05,
+      "loss": 0.0242,
+      "step": 1410
+    },
+    {
+      "epoch": 353.96,
+      "grad_norm": 0.026360318064689636,
+      "learning_rate": 2.210767468499427e-05,
+      "loss": 0.0236,
+      "step": 1415
+    },
+    {
+      "epoch": 355.0,
+      "grad_norm": 0.0959874838590622,
+      "learning_rate": 2.18213058419244e-05,
+      "loss": 0.0221,
+      "step": 1420
+    },
+    {
+      "epoch": 356.32,
+      "grad_norm": 0.026437407359480858,
+      "learning_rate": 2.1534936998854528e-05,
+      "loss": 0.0231,
+      "step": 1425
+    },
+    {
+      "epoch": 357.64,
+      "grad_norm": 0.028155773878097534,
+      "learning_rate": 2.124856815578465e-05,
+      "loss": 0.0234,
+      "step": 1430
+    },
+    {
+      "epoch": 358.96,
+      "grad_norm": 0.03281427174806595,
+      "learning_rate": 2.0962199312714777e-05,
+      "loss": 0.023,
+      "step": 1435
+    },
+    {
+      "epoch": 360.0,
+      "grad_norm": 0.07536535710096359,
+      "learning_rate": 2.0675830469644904e-05,
+      "loss": 0.0228,
+      "step": 1440
+    },
+    {
+      "epoch": 361.32,
+      "grad_norm": 0.028682468459010124,
+      "learning_rate": 2.038946162657503e-05,
+      "loss": 0.024,
+      "step": 1445
+    },
+    {
+      "epoch": 362.64,
+      "grad_norm": 0.026450011879205704,
+      "learning_rate": 2.0103092783505157e-05,
+      "loss": 0.0236,
+      "step": 1450
+    },
+    {
+      "epoch": 363.96,
+      "grad_norm": 0.02757578156888485,
+      "learning_rate": 1.981672394043528e-05,
+      "loss": 0.0227,
+      "step": 1455
+    },
+    {
+      "epoch": 365.0,
+      "grad_norm": 0.09330349415540695,
+      "learning_rate": 1.9530355097365406e-05,
+      "loss": 0.0228,
+      "step": 1460
+    },
+    {
+      "epoch": 366.32,
+      "grad_norm": 0.02596072480082512,
+      "learning_rate": 1.9243986254295536e-05,
+      "loss": 0.0225,
+      "step": 1465
+    },
+    {
+      "epoch": 367.64,
+      "grad_norm": 0.025059539824724197,
+      "learning_rate": 1.895761741122566e-05,
+      "loss": 0.0226,
+      "step": 1470
+    },
+    {
+      "epoch": 368.96,
+      "grad_norm": 0.029328053817152977,
+      "learning_rate": 1.8671248568155786e-05,
+      "loss": 0.0242,
+      "step": 1475
+    },
+    {
+      "epoch": 370.0,
+      "grad_norm": 0.09089489281177521,
+      "learning_rate": 1.8384879725085912e-05,
+      "loss": 0.0226,
+      "step": 1480
+    },
+    {
+      "epoch": 371.32,
+      "grad_norm": 0.026843125000596046,
+      "learning_rate": 1.809851088201604e-05,
+      "loss": 0.0228,
+      "step": 1485
+    },
+    {
+      "epoch": 372.64,
+      "grad_norm": 0.025317925959825516,
+      "learning_rate": 1.7812142038946165e-05,
+      "loss": 0.0223,
+      "step": 1490
+    },
+    {
+      "epoch": 373.96,
+      "grad_norm": 0.02977876551449299,
+      "learning_rate": 1.7525773195876288e-05,
+      "loss": 0.025,
+      "step": 1495
+    },
+    {
+      "epoch": 375.0,
+      "grad_norm": 0.09727901220321655,
+      "learning_rate": 1.7239404352806415e-05,
+      "loss": 0.0231,
+      "step": 1500
+    },
+    {
+      "epoch": 376.32,
+      "grad_norm": 0.02707320638000965,
+      "learning_rate": 1.695303550973654e-05,
+      "loss": 0.0222,
+      "step": 1505
+    },
+    {
+      "epoch": 377.64,
+      "grad_norm": 0.02679339610040188,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.0242,
+      "step": 1510
+    },
+    {
+      "epoch": 378.96,
+      "grad_norm": 0.0271786879748106,
+      "learning_rate": 1.6380297823596794e-05,
+      "loss": 0.0227,
+      "step": 1515
+    },
+    {
+      "epoch": 380.0,
+      "grad_norm": 0.101263627409935,
+      "learning_rate": 1.609392898052692e-05,
+      "loss": 0.0234,
+      "step": 1520
+    },
+    {
+      "epoch": 381.32,
+      "grad_norm": 0.027572425082325935,
+      "learning_rate": 1.5807560137457044e-05,
+      "loss": 0.0226,
+      "step": 1525
+    },
+    {
+      "epoch": 382.64,
+      "grad_norm": 0.028548145666718483,
+      "learning_rate": 1.5521191294387173e-05,
+      "loss": 0.0239,
+      "step": 1530
+    },
+    {
+      "epoch": 383.96,
+      "grad_norm": 0.02758699469268322,
+      "learning_rate": 1.5234822451317298e-05,
+      "loss": 0.0221,
+      "step": 1535
+    },
+    {
+      "epoch": 385.0,
+      "grad_norm": 0.09393903613090515,
+      "learning_rate": 1.4948453608247423e-05,
+      "loss": 0.024,
+      "step": 1540
+    },
+    {
+      "epoch": 386.32,
+      "grad_norm": 0.0290912464261055,
+      "learning_rate": 1.466208476517755e-05,
+      "loss": 0.0213,
+      "step": 1545
+    },
+    {
+      "epoch": 387.64,
+      "grad_norm": 0.028691260144114494,
+      "learning_rate": 1.4375715922107674e-05,
+      "loss": 0.0224,
+      "step": 1550
+    },
+    {
+      "epoch": 388.96,
+      "grad_norm": 0.026655474677681923,
+      "learning_rate": 1.40893470790378e-05,
+      "loss": 0.0231,
+      "step": 1555
+    },
+    {
+      "epoch": 390.0,
+      "grad_norm": 0.08629110455513,
+      "learning_rate": 1.3802978235967929e-05,
+      "loss": 0.0214,
+      "step": 1560
+    },
+    {
+      "epoch": 391.32,
+      "grad_norm": 0.024232706055045128,
+      "learning_rate": 1.3516609392898052e-05,
+      "loss": 0.0225,
+      "step": 1565
+    },
+    {
+      "epoch": 392.64,
+      "grad_norm": 0.026552241295576096,
+      "learning_rate": 1.323024054982818e-05,
+      "loss": 0.0231,
+      "step": 1570
+    },
+    {
+      "epoch": 393.96,
+      "grad_norm": 0.02248690277338028,
+      "learning_rate": 1.2943871706758307e-05,
+      "loss": 0.0226,
+      "step": 1575
+    },
+    {
+      "epoch": 395.0,
+      "grad_norm": 0.08844082802534103,
+      "learning_rate": 1.2657502863688431e-05,
+      "loss": 0.0238,
+      "step": 1580
+    },
+    {
+      "epoch": 396.32,
+      "grad_norm": 0.028189977630972862,
+      "learning_rate": 1.2371134020618558e-05,
+      "loss": 0.0227,
+      "step": 1585
+    },
+    {
+      "epoch": 397.64,
+      "grad_norm": 0.030216960236430168,
+      "learning_rate": 1.2084765177548683e-05,
+      "loss": 0.0236,
+      "step": 1590
+    },
+    {
+      "epoch": 398.96,
+      "grad_norm": 0.027676530182361603,
+      "learning_rate": 1.1798396334478809e-05,
+      "loss": 0.0218,
+      "step": 1595
+    },
+    {
+      "epoch": 400.0,
+      "grad_norm": 0.10360432416200638,
+      "learning_rate": 1.1512027491408934e-05,
+      "loss": 0.0228,
+      "step": 1600
+    },
+    {
+      "epoch": 401.32,
+      "grad_norm": 0.027776524424552917,
+      "learning_rate": 1.1225658648339062e-05,
+      "loss": 0.0235,
+      "step": 1605
+    },
+    {
+      "epoch": 402.64,
+      "grad_norm": 0.02695218101143837,
+      "learning_rate": 1.0939289805269187e-05,
+      "loss": 0.023,
+      "step": 1610
+    },
+    {
+      "epoch": 403.96,
+      "grad_norm": 0.029759282246232033,
+      "learning_rate": 1.0652920962199313e-05,
+      "loss": 0.0237,
+      "step": 1615
+    },
+    {
+      "epoch": 405.0,
+      "grad_norm": 0.08746307343244553,
+      "learning_rate": 1.036655211912944e-05,
+      "loss": 0.0225,
+      "step": 1620
+    },
+    {
+      "epoch": 406.32,
+      "grad_norm": 0.02580684795975685,
+      "learning_rate": 1.0080183276059566e-05,
+      "loss": 0.0226,
+      "step": 1625
+    },
+    {
+      "epoch": 407.64,
+      "grad_norm": 0.026979517191648483,
+      "learning_rate": 9.793814432989691e-06,
+      "loss": 0.0228,
+      "step": 1630
+    },
+    {
+      "epoch": 408.96,
+      "grad_norm": 0.02724551595747471,
+      "learning_rate": 9.507445589919818e-06,
+      "loss": 0.0228,
+      "step": 1635
+    },
+    {
+      "epoch": 410.0,
+      "grad_norm": 0.08738246560096741,
+      "learning_rate": 9.221076746849944e-06,
+      "loss": 0.0213,
+      "step": 1640
+    },
+    {
+      "epoch": 411.32,
+      "grad_norm": 0.028775516897439957,
+      "learning_rate": 8.934707903780069e-06,
+      "loss": 0.0226,
+      "step": 1645
+    },
+    {
+      "epoch": 412.64,
+      "grad_norm": 0.02923266589641571,
+      "learning_rate": 8.648339060710195e-06,
+      "loss": 0.0229,
+      "step": 1650
+    },
+    {
+      "epoch": 413.96,
+      "grad_norm": 0.027875343337655067,
+      "learning_rate": 8.36197021764032e-06,
+      "loss": 0.023,
+      "step": 1655
+    },
+    {
+      "epoch": 415.0,
+      "grad_norm": 0.10546427220106125,
+      "learning_rate": 8.075601374570448e-06,
+      "loss": 0.0222,
+      "step": 1660
+    },
+    {
+      "epoch": 416.32,
+      "grad_norm": 0.02529430203139782,
+      "learning_rate": 7.789232531500573e-06,
+      "loss": 0.0225,
+      "step": 1665
+    },
+    {
+      "epoch": 417.64,
+      "grad_norm": 0.028874307870864868,
+      "learning_rate": 7.502863688430699e-06,
+      "loss": 0.023,
+      "step": 1670
+    },
+    {
+      "epoch": 418.96,
+      "grad_norm": 0.026649517938494682,
+      "learning_rate": 7.216494845360824e-06,
+      "loss": 0.023,
+      "step": 1675
+    },
+    {
+      "epoch": 420.0,
+      "grad_norm": 0.08407299220561981,
+      "learning_rate": 6.930126002290952e-06,
+      "loss": 0.0218,
+      "step": 1680
+    },
+    {
+      "epoch": 421.32,
+      "grad_norm": 0.028949715197086334,
+      "learning_rate": 6.643757159221077e-06,
+      "loss": 0.0217,
+      "step": 1685
+    },
+    {
+      "epoch": 422.64,
+      "grad_norm": 0.02620142698287964,
+      "learning_rate": 6.357388316151203e-06,
+      "loss": 0.0212,
+      "step": 1690
+    },
+    {
+      "epoch": 423.96,
+      "grad_norm": 0.027563657611608505,
+      "learning_rate": 6.071019473081329e-06,
+      "loss": 0.0227,
+      "step": 1695
+    },
+    {
+      "epoch": 425.0,
+      "grad_norm": 0.09733061492443085,
+      "learning_rate": 5.784650630011455e-06,
+      "loss": 0.0228,
+      "step": 1700
+    },
+    {
+      "epoch": 426.32,
+      "grad_norm": 0.026252230629324913,
+      "learning_rate": 5.498281786941581e-06,
+      "loss": 0.0226,
+      "step": 1705
+    },
+    {
+      "epoch": 427.64,
+      "grad_norm": 0.025463592261075974,
+      "learning_rate": 5.211912943871707e-06,
+      "loss": 0.0223,
+      "step": 1710
+    },
+    {
+      "epoch": 428.96,
+      "grad_norm": 0.028576774522662163,
+      "learning_rate": 4.925544100801833e-06,
+      "loss": 0.024,
+      "step": 1715
+    },
+    {
+      "epoch": 430.0,
+      "grad_norm": 0.09522772580385208,
+      "learning_rate": 4.639175257731959e-06,
+      "loss": 0.0218,
+      "step": 1720
+    },
+    {
+      "epoch": 431.32,
+      "grad_norm": 0.0282877329736948,
+      "learning_rate": 4.352806414662085e-06,
+      "loss": 0.0218,
+      "step": 1725
+    },
+    {
+      "epoch": 432.64,
+      "grad_norm": 0.028195489197969437,
+      "learning_rate": 4.066437571592211e-06,
+      "loss": 0.0222,
+      "step": 1730
+    },
+    {
+      "epoch": 433.96,
+      "grad_norm": 0.026181157678365707,
+      "learning_rate": 3.7800687285223365e-06,
+      "loss": 0.022,
+      "step": 1735
+    },
+    {
+      "epoch": 435.0,
+      "grad_norm": 0.10222843289375305,
+      "learning_rate": 3.493699885452463e-06,
+      "loss": 0.0224,
+      "step": 1740
+    },
+    {
+      "epoch": 436.32,
+      "grad_norm": 0.0255801510065794,
+      "learning_rate": 3.2073310423825886e-06,
+      "loss": 0.0226,
+      "step": 1745
+    },
+    {
+      "epoch": 437.64,
+      "grad_norm": 0.026890140026807785,
+      "learning_rate": 2.920962199312715e-06,
+      "loss": 0.0227,
+      "step": 1750
+    },
+    {
+      "epoch": 438.96,
+      "grad_norm": 0.026494432240724564,
+      "learning_rate": 2.6345933562428407e-06,
+      "loss": 0.0236,
+      "step": 1755
+    },
+    {
+      "epoch": 440.0,
+      "grad_norm": 0.11536001414060593,
+      "learning_rate": 2.3482245131729668e-06,
+      "loss": 0.0243,
+      "step": 1760
+    },
+    {
+      "epoch": 441.32,
+      "grad_norm": 0.027686437591910362,
+      "learning_rate": 2.061855670103093e-06,
+      "loss": 0.0236,
+      "step": 1765
+    },
+    {
+      "epoch": 442.64,
+      "grad_norm": 0.028341075405478477,
+      "learning_rate": 1.7754868270332189e-06,
+      "loss": 0.0235,
+      "step": 1770
+    },
+    {
+      "epoch": 443.96,
+      "grad_norm": 0.029025057330727577,
+      "learning_rate": 1.4891179839633447e-06,
+      "loss": 0.0223,
+      "step": 1775
+    },
+    {
+      "epoch": 445.0,
+      "grad_norm": 0.08899275958538055,
+      "learning_rate": 1.202749140893471e-06,
+      "loss": 0.0214,
+      "step": 1780
+    },
+    {
+      "epoch": 446.32,
+      "grad_norm": 0.029170271009206772,
+      "learning_rate": 9.163802978235968e-07,
+      "loss": 0.0225,
+      "step": 1785
+    },
+    {
+      "epoch": 447.64,
+      "grad_norm": 0.028448564931750298,
+      "learning_rate": 6.300114547537229e-07,
+      "loss": 0.0235,
+      "step": 1790
+    },
+    {
+      "epoch": 448.96,
+      "grad_norm": 0.029456494376063347,
+      "learning_rate": 3.436426116838488e-07,
+      "loss": 0.0235,
+      "step": 1795
+    },
+    {
+      "epoch": 450.0,
+      "grad_norm": 0.06313438713550568,
+      "learning_rate": 5.72737686139748e-08,
+      "loss": 0.0217,
+      "step": 1800
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 450,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5308141101056e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Math_QA/group_01/checkpoints/checkpoint-300/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/不冻结Qwen训练/models/Qwen2.5-1.5B-Instruct
+library_name: peft
+---
+
+# 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 0.12.0

Math_QA/group_01/checkpoints/checkpoint-300/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/\u4e0d\u51bb\u7ed3Qwen\u8bad\u7ec3/models/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "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": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Math_QA/group_01/checkpoints/checkpoint-300/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
+}

Math_QA/group_01/checkpoints/checkpoint-300/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 %}

Math_QA/group_01/checkpoints/checkpoint-300/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
+  }
+}

Math_QA/group_01/checkpoints/checkpoint-300/tokenizer_config.json

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

Math_QA/group_01/checkpoints/checkpoint-300/trainer_state.json

@@ -0,0 +1,461 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 75.0,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 10.180441856384277,
+      "learning_rate": 0.0,
+      "loss": 1.8305,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 6.451148509979248,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.8074,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 3.347440481185913,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.6091,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 1.9289507865905762,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 1.1842,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.8556746244430542,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.8199,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.7173905372619629,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.6794,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.57694011926651,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.601,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.5361317992210388,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.518,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.821795701980591,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.5037,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.5809462666511536,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.3551,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 0.6679601669311523,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.3027,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 1.0066516399383545,
+      "learning_rate": 0.0001,
+      "loss": 0.2053,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 2.1689505577087402,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1499,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 1.3551698923110962,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.0919,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 0.8636834025382996,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0684,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 1.1933852434158325,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0497,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.142573118209839,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.0413,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.4700527787208557,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0385,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 0.343295693397522,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.033,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.22979414463043213,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.029,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.3299155533313751,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0299,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.13267530500888824,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0261,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.11862046271562576,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0269,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.1212410181760788,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.0271,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.4221489727497101,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0277,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.1887303739786148,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.028,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.06632087379693985,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0292,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.06920741498470306,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.0266,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.20255975425243378,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.0252,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.06548365205526352,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0262,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.3841380774974823,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0266,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.14380377531051636,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0264,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.1875791698694229,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0272,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.0587279237806797,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.026,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.1045636460185051,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0258,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.1214262992143631,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0258,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.15483546257019043,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0258,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.05430334061384201,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0249,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.059528253972530365,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0252,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.08998366445302963,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0256,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.1713639348745346,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0261,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.15917673707008362,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.026,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.06540960818529129,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.0249,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.28250637650489807,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0257,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.21159835159778595,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0252,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.17774927616119385,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0243,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.09880783408880234,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.0256,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.22325387597084045,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0348,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.18399597704410553,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0277,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.07885713130235672,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0244,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.3227796256542206,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0278,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.15556609630584717,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0298,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.21505486965179443,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0267,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.05085480958223343,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0252,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.05251656472682953,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0265,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.15204979479312897,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0245,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.12058636546134949,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0244,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.04826376959681511,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.0236,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.038287319242954254,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.0235,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.045909084379673004,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0253,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.07804425060749054,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.0237,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 450,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.551356850176e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Math_QA/group_01/checkpoints/checkpoint-600/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/不冻结Qwen训练/models/Qwen2.5-1.5B-Instruct
+library_name: peft
+---
+
+# 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 0.12.0

Math_QA/group_01/checkpoints/checkpoint-600/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/\u4e0d\u51bb\u7ed3Qwen\u8bad\u7ec3/models/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "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": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Math_QA/group_01/checkpoints/checkpoint-600/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
+}

Math_QA/group_01/checkpoints/checkpoint-600/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 %}

Math_QA/group_01/checkpoints/checkpoint-600/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
+  }
+}

Math_QA/group_01/checkpoints/checkpoint-600/tokenizer_config.json

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

Math_QA/group_01/checkpoints/checkpoint-600/trainer_state.json

@@ -0,0 +1,881 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 150.0,
+  "eval_steps": 500,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 10.180441856384277,
+      "learning_rate": 0.0,
+      "loss": 1.8305,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 6.451148509979248,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.8074,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 3.347440481185913,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.6091,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 1.9289507865905762,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 1.1842,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.8556746244430542,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.8199,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.7173905372619629,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.6794,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.57694011926651,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.601,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.5361317992210388,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.518,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.821795701980591,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.5037,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.5809462666511536,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.3551,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 0.6679601669311523,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.3027,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 1.0066516399383545,
+      "learning_rate": 0.0001,
+      "loss": 0.2053,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 2.1689505577087402,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1499,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 1.3551698923110962,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.0919,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 0.8636834025382996,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0684,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 1.1933852434158325,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0497,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.142573118209839,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.0413,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.4700527787208557,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0385,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 0.343295693397522,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.033,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.22979414463043213,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.029,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.3299155533313751,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0299,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.13267530500888824,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0261,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.11862046271562576,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0269,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.1212410181760788,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.0271,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.4221489727497101,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0277,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.1887303739786148,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.028,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.06632087379693985,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0292,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.06920741498470306,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.0266,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.20255975425243378,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.0252,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.06548365205526352,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0262,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.3841380774974823,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0266,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.14380377531051636,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0264,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.1875791698694229,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0272,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.0587279237806797,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.026,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.1045636460185051,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0258,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.1214262992143631,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0258,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.15483546257019043,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0258,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.05430334061384201,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0249,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.059528253972530365,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0252,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.08998366445302963,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0256,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.1713639348745346,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0261,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.15917673707008362,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.026,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.06540960818529129,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.0249,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.28250637650489807,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0257,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.21159835159778595,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0252,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.17774927616119385,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0243,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.09880783408880234,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.0256,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.22325387597084045,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0348,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.18399597704410553,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0277,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.07885713130235672,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0244,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.3227796256542206,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0278,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.15556609630584717,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0298,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.21505486965179443,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0267,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.05085480958223343,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0252,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.05251656472682953,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0265,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.15204979479312897,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0245,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.12058636546134949,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0244,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.04826376959681511,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.0236,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.038287319242954254,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.0235,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.045909084379673004,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0253,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.07804425060749054,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.0237,
+      "step": 300
+    },
+    {
+      "epoch": 76.32,
+      "grad_norm": 0.04439236596226692,
+      "learning_rate": 8.56815578465063e-05,
+      "loss": 0.0241,
+      "step": 305
+    },
+    {
+      "epoch": 77.64,
+      "grad_norm": 0.0510355643928051,
+      "learning_rate": 8.539518900343643e-05,
+      "loss": 0.0247,
+      "step": 310
+    },
+    {
+      "epoch": 78.96,
+      "grad_norm": 0.04283309355378151,
+      "learning_rate": 8.510882016036655e-05,
+      "loss": 0.0244,
+      "step": 315
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.08130446821451187,
+      "learning_rate": 8.482245131729668e-05,
+      "loss": 0.0236,
+      "step": 320
+    },
+    {
+      "epoch": 81.32,
+      "grad_norm": 0.03965280205011368,
+      "learning_rate": 8.453608247422681e-05,
+      "loss": 0.0233,
+      "step": 325
+    },
+    {
+      "epoch": 82.64,
+      "grad_norm": 0.036928094923496246,
+      "learning_rate": 8.424971363115693e-05,
+      "loss": 0.0247,
+      "step": 330
+    },
+    {
+      "epoch": 83.96,
+      "grad_norm": 0.03514806181192398,
+      "learning_rate": 8.396334478808706e-05,
+      "loss": 0.0232,
+      "step": 335
+    },
+    {
+      "epoch": 85.0,
+      "grad_norm": 0.13447487354278564,
+      "learning_rate": 8.367697594501719e-05,
+      "loss": 0.0247,
+      "step": 340
+    },
+    {
+      "epoch": 86.32,
+      "grad_norm": 0.048798318952322006,
+      "learning_rate": 8.339060710194731e-05,
+      "loss": 0.0238,
+      "step": 345
+    },
+    {
+      "epoch": 87.64,
+      "grad_norm": 0.04126816615462303,
+      "learning_rate": 8.310423825887744e-05,
+      "loss": 0.0222,
+      "step": 350
+    },
+    {
+      "epoch": 88.96,
+      "grad_norm": 0.04224137216806412,
+      "learning_rate": 8.281786941580757e-05,
+      "loss": 0.0234,
+      "step": 355
+    },
+    {
+      "epoch": 90.0,
+      "grad_norm": 0.10610926151275635,
+      "learning_rate": 8.253150057273768e-05,
+      "loss": 0.0245,
+      "step": 360
+    },
+    {
+      "epoch": 91.32,
+      "grad_norm": 0.050110042095184326,
+      "learning_rate": 8.224513172966782e-05,
+      "loss": 0.0243,
+      "step": 365
+    },
+    {
+      "epoch": 92.64,
+      "grad_norm": 0.04875118285417557,
+      "learning_rate": 8.195876288659795e-05,
+      "loss": 0.0236,
+      "step": 370
+    },
+    {
+      "epoch": 93.96,
+      "grad_norm": 0.04443453252315521,
+      "learning_rate": 8.167239404352807e-05,
+      "loss": 0.0254,
+      "step": 375
+    },
+    {
+      "epoch": 95.0,
+      "grad_norm": 0.12320202589035034,
+      "learning_rate": 8.13860252004582e-05,
+      "loss": 0.0233,
+      "step": 380
+    },
+    {
+      "epoch": 96.32,
+      "grad_norm": 0.049856845289468765,
+      "learning_rate": 8.109965635738833e-05,
+      "loss": 0.0235,
+      "step": 385
+    },
+    {
+      "epoch": 97.64,
+      "grad_norm": 0.052503034472465515,
+      "learning_rate": 8.081328751431845e-05,
+      "loss": 0.0239,
+      "step": 390
+    },
+    {
+      "epoch": 98.96,
+      "grad_norm": 0.03616590052843094,
+      "learning_rate": 8.052691867124858e-05,
+      "loss": 0.024,
+      "step": 395
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.1246335357427597,
+      "learning_rate": 8.02405498281787e-05,
+      "loss": 0.0229,
+      "step": 400
+    },
+    {
+      "epoch": 101.32,
+      "grad_norm": 0.03999874368309975,
+      "learning_rate": 7.995418098510883e-05,
+      "loss": 0.0242,
+      "step": 405
+    },
+    {
+      "epoch": 102.64,
+      "grad_norm": 0.043219417333602905,
+      "learning_rate": 7.966781214203894e-05,
+      "loss": 0.0238,
+      "step": 410
+    },
+    {
+      "epoch": 103.96,
+      "grad_norm": 0.045299362391233444,
+      "learning_rate": 7.938144329896907e-05,
+      "loss": 0.0234,
+      "step": 415
+    },
+    {
+      "epoch": 105.0,
+      "grad_norm": 0.1272430568933487,
+      "learning_rate": 7.90950744558992e-05,
+      "loss": 0.025,
+      "step": 420
+    },
+    {
+      "epoch": 106.32,
+      "grad_norm": 0.03369831666350365,
+      "learning_rate": 7.880870561282932e-05,
+      "loss": 0.0232,
+      "step": 425
+    },
+    {
+      "epoch": 107.64,
+      "grad_norm": 0.03566688671708107,
+      "learning_rate": 7.852233676975945e-05,
+      "loss": 0.024,
+      "step": 430
+    },
+    {
+      "epoch": 108.96,
+      "grad_norm": 0.039571139961481094,
+      "learning_rate": 7.823596792668958e-05,
+      "loss": 0.0224,
+      "step": 435
+    },
+    {
+      "epoch": 110.0,
+      "grad_norm": 0.13205471634864807,
+      "learning_rate": 7.79495990836197e-05,
+      "loss": 0.025,
+      "step": 440
+    },
+    {
+      "epoch": 111.32,
+      "grad_norm": 0.038404062390327454,
+      "learning_rate": 7.766323024054983e-05,
+      "loss": 0.0239,
+      "step": 445
+    },
+    {
+      "epoch": 112.64,
+      "grad_norm": 0.038733795285224915,
+      "learning_rate": 7.737686139747996e-05,
+      "loss": 0.0235,
+      "step": 450
+    },
+    {
+      "epoch": 113.96,
+      "grad_norm": 0.04340984299778938,
+      "learning_rate": 7.709049255441008e-05,
+      "loss": 0.0237,
+      "step": 455
+    },
+    {
+      "epoch": 115.0,
+      "grad_norm": 0.1490347683429718,
+      "learning_rate": 7.680412371134021e-05,
+      "loss": 0.026,
+      "step": 460
+    },
+    {
+      "epoch": 116.32,
+      "grad_norm": 0.04450232908129692,
+      "learning_rate": 7.651775486827034e-05,
+      "loss": 0.0248,
+      "step": 465
+    },
+    {
+      "epoch": 117.64,
+      "grad_norm": 0.03861455246806145,
+      "learning_rate": 7.623138602520046e-05,
+      "loss": 0.0245,
+      "step": 470
+    },
+    {
+      "epoch": 118.96,
+      "grad_norm": 0.03502120077610016,
+      "learning_rate": 7.594501718213059e-05,
+      "loss": 0.0254,
+      "step": 475
+    },
+    {
+      "epoch": 120.0,
+      "grad_norm": 0.092933788895607,
+      "learning_rate": 7.565864833906071e-05,
+      "loss": 0.0242,
+      "step": 480
+    },
+    {
+      "epoch": 121.32,
+      "grad_norm": 0.03522248566150665,
+      "learning_rate": 7.537227949599084e-05,
+      "loss": 0.0232,
+      "step": 485
+    },
+    {
+      "epoch": 122.64,
+      "grad_norm": 0.030242981389164925,
+      "learning_rate": 7.508591065292097e-05,
+      "loss": 0.0229,
+      "step": 490
+    },
+    {
+      "epoch": 123.96,
+      "grad_norm": 0.03727824613451958,
+      "learning_rate": 7.47995418098511e-05,
+      "loss": 0.0239,
+      "step": 495
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 0.11968818306922913,
+      "learning_rate": 7.451317296678122e-05,
+      "loss": 0.0234,
+      "step": 500
+    },
+    {
+      "epoch": 126.32,
+      "grad_norm": 0.032707035541534424,
+      "learning_rate": 7.422680412371135e-05,
+      "loss": 0.0221,
+      "step": 505
+    },
+    {
+      "epoch": 127.64,
+      "grad_norm": 0.03655603528022766,
+      "learning_rate": 7.394043528064147e-05,
+      "loss": 0.0243,
+      "step": 510
+    },
+    {
+      "epoch": 128.96,
+      "grad_norm": 0.03384123370051384,
+      "learning_rate": 7.36540664375716e-05,
+      "loss": 0.0217,
+      "step": 515
+    },
+    {
+      "epoch": 130.0,
+      "grad_norm": 0.11020781844854355,
+      "learning_rate": 7.336769759450171e-05,
+      "loss": 0.0237,
+      "step": 520
+    },
+    {
+      "epoch": 131.32,
+      "grad_norm": 0.038297172635793686,
+      "learning_rate": 7.308132875143184e-05,
+      "loss": 0.0232,
+      "step": 525
+    },
+    {
+      "epoch": 132.64,
+      "grad_norm": 0.03700310364365578,
+      "learning_rate": 7.279495990836197e-05,
+      "loss": 0.0229,
+      "step": 530
+    },
+    {
+      "epoch": 133.96,
+      "grad_norm": 0.0338885597884655,
+      "learning_rate": 7.250859106529209e-05,
+      "loss": 0.0229,
+      "step": 535
+    },
+    {
+      "epoch": 135.0,
+      "grad_norm": 0.10868728905916214,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.0224,
+      "step": 540
+    },
+    {
+      "epoch": 136.32,
+      "grad_norm": 0.035598840564489365,
+      "learning_rate": 7.193585337915235e-05,
+      "loss": 0.0255,
+      "step": 545
+    },
+    {
+      "epoch": 137.64,
+      "grad_norm": 0.031226877123117447,
+      "learning_rate": 7.164948453608247e-05,
+      "loss": 0.0233,
+      "step": 550
+    },
+    {
+      "epoch": 138.96,
+      "grad_norm": 0.03582902252674103,
+      "learning_rate": 7.136311569301261e-05,
+      "loss": 0.0229,
+      "step": 555
+    },
+    {
+      "epoch": 140.0,
+      "grad_norm": 0.11769143491983414,
+      "learning_rate": 7.107674684994274e-05,
+      "loss": 0.0245,
+      "step": 560
+    },
+    {
+      "epoch": 141.32,
+      "grad_norm": 0.030704690143465996,
+      "learning_rate": 7.079037800687286e-05,
+      "loss": 0.0242,
+      "step": 565
+    },
+    {
+      "epoch": 142.64,
+      "grad_norm": 0.03247276693582535,
+      "learning_rate": 7.050400916380299e-05,
+      "loss": 0.0239,
+      "step": 570
+    },
+    {
+      "epoch": 143.96,
+      "grad_norm": 0.03496946021914482,
+      "learning_rate": 7.02176403207331e-05,
+      "loss": 0.0251,
+      "step": 575
+    },
+    {
+      "epoch": 145.0,
+      "grad_norm": 0.08276615291833878,
+      "learning_rate": 6.993127147766323e-05,
+      "loss": 0.0221,
+      "step": 580
+    },
+    {
+      "epoch": 146.32,
+      "grad_norm": 0.040135324001312256,
+      "learning_rate": 6.964490263459336e-05,
+      "loss": 0.0233,
+      "step": 585
+    },
+    {
+      "epoch": 147.64,
+      "grad_norm": 0.0358579121530056,
+      "learning_rate": 6.935853379152348e-05,
+      "loss": 0.0245,
+      "step": 590
+    },
+    {
+      "epoch": 148.96,
+      "grad_norm": 0.04078257456421852,
+      "learning_rate": 6.907216494845361e-05,
+      "loss": 0.0246,
+      "step": 595
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 0.07422423362731934,
+      "learning_rate": 6.878579610538374e-05,
+      "loss": 0.0217,
+      "step": 600
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 450,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.102713700352e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Math_QA/group_01/checkpoints/checkpoint-900/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hkfs/work/workspace/scratch/tum_fmp0582-dndworkspace/不冻结Qwen训练/models/Qwen2.5-1.5B-Instruct
+library_name: peft
+---
+
+# 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 0.12.0