Add files using upload-large-folder tool

Competition_Math/group_00/adapter/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
+}

Competition_Math/group_00/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

Competition_Math/group_00/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": [
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Competition_Math/group_00/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
+}

Competition_Math/group_00/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 %}

Competition_Math/group_00/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
+  }
+}

Competition_Math/group_00/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
+}

Competition_Math/group_00/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": 4.598043441772461,
+      "learning_rate": 0.0,
+      "loss": 0.9577,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 3.2691659927368164,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.914,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.4407647848129272,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.87,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 0.873967170715332,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 0.7194,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.5684808492660522,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.485,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.31015607714653015,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.4448,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.2658279538154602,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.4004,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.24357278645038605,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.3975,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.7138969302177429,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.3541,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.3199204206466675,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.2981,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 0.3794819414615631,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.2975,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 0.6489832997322083,
+      "learning_rate": 0.0001,
+      "loss": 0.2113,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.9405580759048462,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1426,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 0.5083445310592651,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.1212,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 0.4943920969963074,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0843,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 0.7678825259208679,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0484,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 1.9925947189331055,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.0444,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.2645427882671356,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0288,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 0.1064828559756279,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.0301,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.12416807562112808,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.0196,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.2526699900627136,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0203,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.09203815460205078,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0201,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.07873351126909256,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0162,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.10604001581668854,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.0191,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 1.7986263036727905,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0198,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.07677727192640305,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.0158,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.1571263074874878,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0152,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.06132940948009491,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.0137,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.09364927560091019,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.016,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.04978128522634506,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0161,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.03882812336087227,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0154,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.04475203529000282,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0164,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.13846606016159058,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0161,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.033312492072582245,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.0135,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.041062209755182266,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0135,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.032531533390283585,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0135,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.1364850103855133,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0149,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.042139116674661636,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0136,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.03540545701980591,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0132,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.04514731466770172,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0175,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.14643007516860962,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0152,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.03208281844854355,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.0144,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.03130023553967476,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.0168,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.03348194435238838,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0141,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.05507143586874008,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0149,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.019802691414952278,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0149,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.025274671614170074,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.016,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.0396709069609642,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0156,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.11217641085386276,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0165,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.03045077621936798,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0154,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.030307715758681297,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0149,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.028285281732678413,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0139,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.1250770390033722,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0187,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.025621576234698296,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0135,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.021983368322253227,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0149,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.02598453126847744,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0139,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.08075019717216492,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0148,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.0245928093791008,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.0159,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.026031415909528732,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.0144,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.02940714731812477,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0146,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.0966266617178917,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.014,
+      "step": 300
+    },
+    {
+      "epoch": 76.32,
+      "grad_norm": 0.028764601796865463,
+      "learning_rate": 8.56815578465063e-05,
+      "loss": 0.0132,
+      "step": 305
+    },
+    {
+      "epoch": 77.64,
+      "grad_norm": 0.027627065777778625,
+      "learning_rate": 8.539518900343643e-05,
+      "loss": 0.0166,
+      "step": 310
+    },
+    {
+      "epoch": 78.96,
+      "grad_norm": 0.026004405692219734,
+      "learning_rate": 8.510882016036655e-05,
+      "loss": 0.0148,
+      "step": 315
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.08327600359916687,
+      "learning_rate": 8.482245131729668e-05,
+      "loss": 0.016,
+      "step": 320
+    },
+    {
+      "epoch": 81.32,
+      "grad_norm": 0.025960935279726982,
+      "learning_rate": 8.453608247422681e-05,
+      "loss": 0.0143,
+      "step": 325
+    },
+    {
+      "epoch": 82.64,
+      "grad_norm": 0.025417521595954895,
+      "learning_rate": 8.424971363115693e-05,
+      "loss": 0.014,
+      "step": 330
+    },
+    {
+      "epoch": 83.96,
+      "grad_norm": 0.025654327124357224,
+      "learning_rate": 8.396334478808706e-05,
+      "loss": 0.0128,
+      "step": 335
+    },
+    {
+      "epoch": 85.0,
+      "grad_norm": 0.10201112926006317,
+      "learning_rate": 8.367697594501719e-05,
+      "loss": 0.0142,
+      "step": 340
+    },
+    {
+      "epoch": 86.32,
+      "grad_norm": 0.02470439113676548,
+      "learning_rate": 8.339060710194731e-05,
+      "loss": 0.0127,
+      "step": 345
+    },
+    {
+      "epoch": 87.64,
+      "grad_norm": 0.0236374419182539,
+      "learning_rate": 8.310423825887744e-05,
+      "loss": 0.0153,
+      "step": 350
+    },
+    {
+      "epoch": 88.96,
+      "grad_norm": 0.03599975258111954,
+      "learning_rate": 8.281786941580757e-05,
+      "loss": 0.0133,
+      "step": 355
+    },
+    {
+      "epoch": 90.0,
+      "grad_norm": 0.08355200290679932,
+      "learning_rate": 8.253150057273768e-05,
+      "loss": 0.0144,
+      "step": 360
+    },
+    {
+      "epoch": 91.32,
+      "grad_norm": 0.020355794578790665,
+      "learning_rate": 8.224513172966782e-05,
+      "loss": 0.014,
+      "step": 365
+    },
+    {
+      "epoch": 92.64,
+      "grad_norm": 0.021856721490621567,
+      "learning_rate": 8.195876288659795e-05,
+      "loss": 0.0166,
+      "step": 370
+    },
+    {
+      "epoch": 93.96,
+      "grad_norm": 0.03352021053433418,
+      "learning_rate": 8.167239404352807e-05,
+      "loss": 0.0133,
+      "step": 375
+    },
+    {
+      "epoch": 95.0,
+      "grad_norm": 0.050965987145900726,
+      "learning_rate": 8.13860252004582e-05,
+      "loss": 0.0111,
+      "step": 380
+    },
+    {
+      "epoch": 96.32,
+      "grad_norm": 0.01907683163881302,
+      "learning_rate": 8.109965635738833e-05,
+      "loss": 0.0123,
+      "step": 385
+    },
+    {
+      "epoch": 97.64,
+      "grad_norm": 0.017776427790522575,
+      "learning_rate": 8.081328751431845e-05,
+      "loss": 0.0141,
+      "step": 390
+    },
+    {
+      "epoch": 98.96,
+      "grad_norm": 0.02410067617893219,
+      "learning_rate": 8.052691867124858e-05,
+      "loss": 0.0147,
+      "step": 395
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.11242590099573135,
+      "learning_rate": 8.02405498281787e-05,
+      "loss": 0.0164,
+      "step": 400
+    },
+    {
+      "epoch": 101.32,
+      "grad_norm": 0.024096814915537834,
+      "learning_rate": 7.995418098510883e-05,
+      "loss": 0.0143,
+      "step": 405
+    },
+    {
+      "epoch": 102.64,
+      "grad_norm": 0.02899334393441677,
+      "learning_rate": 7.966781214203894e-05,
+      "loss": 0.0155,
+      "step": 410
+    },
+    {
+      "epoch": 103.96,
+      "grad_norm": 0.023235289379954338,
+      "learning_rate": 7.938144329896907e-05,
+      "loss": 0.0124,
+      "step": 415
+    },
+    {
+      "epoch": 105.0,
+      "grad_norm": 0.0693734735250473,
+      "learning_rate": 7.90950744558992e-05,
+      "loss": 0.0137,
+      "step": 420
+    },
+    {
+      "epoch": 106.32,
+      "grad_norm": 0.019512519240379333,
+      "learning_rate": 7.880870561282932e-05,
+      "loss": 0.0142,
+      "step": 425
+    },
+    {
+      "epoch": 107.64,
+      "grad_norm": 0.02140176109969616,
+      "learning_rate": 7.852233676975945e-05,
+      "loss": 0.0141,
+      "step": 430
+    },
+    {
+      "epoch": 108.96,
+      "grad_norm": 0.022468585520982742,
+      "learning_rate": 7.823596792668958e-05,
+      "loss": 0.0122,
+      "step": 435
+    },
+    {
+      "epoch": 110.0,
+      "grad_norm": 0.0380476713180542,
+      "learning_rate": 7.79495990836197e-05,
+      "loss": 0.0136,
+      "step": 440
+    },
+    {
+      "epoch": 111.32,
+      "grad_norm": 0.018203549087047577,
+      "learning_rate": 7.766323024054983e-05,
+      "loss": 0.0119,
+      "step": 445
+    },
+    {
+      "epoch": 112.64,
+      "grad_norm": 0.02083701454102993,
+      "learning_rate": 7.737686139747996e-05,
+      "loss": 0.0159,
+      "step": 450
+    },
+    {
+      "epoch": 113.96,
+      "grad_norm": 0.02744678594172001,
+      "learning_rate": 7.709049255441008e-05,
+      "loss": 0.0138,
+      "step": 455
+    },
+    {
+      "epoch": 115.0,
+      "grad_norm": 0.05891157686710358,
+      "learning_rate": 7.680412371134021e-05,
+      "loss": 0.0123,
+      "step": 460
+    },
+    {
+      "epoch": 116.32,
+      "grad_norm": 0.02845454029738903,
+      "learning_rate": 7.651775486827034e-05,
+      "loss": 0.0139,
+      "step": 465
+    },
+    {
+      "epoch": 117.64,
+      "grad_norm": 0.020904691889882088,
+      "learning_rate": 7.623138602520046e-05,
+      "loss": 0.013,
+      "step": 470
+    },
+    {
+      "epoch": 118.96,
+      "grad_norm": 0.020568421110510826,
+      "learning_rate": 7.594501718213059e-05,
+      "loss": 0.0126,
+      "step": 475
+    },
+    {
+      "epoch": 120.0,
+      "grad_norm": 0.11525513231754303,
+      "learning_rate": 7.565864833906071e-05,
+      "loss": 0.0149,
+      "step": 480
+    },
+    {
+      "epoch": 121.32,
+      "grad_norm": 0.02282075583934784,
+      "learning_rate": 7.537227949599084e-05,
+      "loss": 0.0145,
+      "step": 485
+    },
+    {
+      "epoch": 122.64,
+      "grad_norm": 0.021044986322522163,
+      "learning_rate": 7.508591065292097e-05,
+      "loss": 0.0118,
+      "step": 490
+    },
+    {
+      "epoch": 123.96,
+      "grad_norm": 0.026140881702303886,
+      "learning_rate": 7.47995418098511e-05,
+      "loss": 0.0134,
+      "step": 495
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 0.08347874134778976,
+      "learning_rate": 7.451317296678122e-05,
+      "loss": 0.0134,
+      "step": 500
+    },
+    {
+      "epoch": 126.32,
+      "grad_norm": 0.021540338173508644,
+      "learning_rate": 7.422680412371135e-05,
+      "loss": 0.0124,
+      "step": 505
+    },
+    {
+      "epoch": 127.64,
+      "grad_norm": 0.018244560807943344,
+      "learning_rate": 7.394043528064147e-05,
+      "loss": 0.0133,
+      "step": 510
+    },
+    {
+      "epoch": 128.96,
+      "grad_norm": 0.0179904717952013,
+      "learning_rate": 7.36540664375716e-05,
+      "loss": 0.0131,
+      "step": 515
+    },
+    {
+      "epoch": 130.0,
+      "grad_norm": 0.0700739249587059,
+      "learning_rate": 7.336769759450171e-05,
+      "loss": 0.0151,
+      "step": 520
+    },
+    {
+      "epoch": 131.32,
+      "grad_norm": 0.02473938651382923,
+      "learning_rate": 7.308132875143184e-05,
+      "loss": 0.0139,
+      "step": 525
+    },
+    {
+      "epoch": 132.64,
+      "grad_norm": 0.016669029369950294,
+      "learning_rate": 7.279495990836197e-05,
+      "loss": 0.0129,
+      "step": 530
+    },
+    {
+      "epoch": 133.96,
+      "grad_norm": 0.0206622127443552,
+      "learning_rate": 7.250859106529209e-05,
+      "loss": 0.0131,
+      "step": 535
+    },
+    {
+      "epoch": 135.0,
+      "grad_norm": 0.1013081893324852,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.0141,
+      "step": 540
+    },
+    {
+      "epoch": 136.32,
+      "grad_norm": 0.02413194440305233,
+      "learning_rate": 7.193585337915235e-05,
+      "loss": 0.0136,
+      "step": 545
+    },
+    {
+      "epoch": 137.64,
+      "grad_norm": 0.02023296430706978,
+      "learning_rate": 7.164948453608247e-05,
+      "loss": 0.0134,
+      "step": 550
+    },
+    {
+      "epoch": 138.96,
+      "grad_norm": 0.018895283341407776,
+      "learning_rate": 7.136311569301261e-05,
+      "loss": 0.012,
+      "step": 555
+    },
+    {
+      "epoch": 140.0,
+      "grad_norm": 0.08102845400571823,
+      "learning_rate": 7.107674684994274e-05,
+      "loss": 0.0142,
+      "step": 560
+    },
+    {
+      "epoch": 141.32,
+      "grad_norm": 0.019933724775910378,
+      "learning_rate": 7.079037800687286e-05,
+      "loss": 0.0143,
+      "step": 565
+    },
+    {
+      "epoch": 142.64,
+      "grad_norm": 0.02834722027182579,
+      "learning_rate": 7.050400916380299e-05,
+      "loss": 0.0136,
+      "step": 570
+    },
+    {
+      "epoch": 143.96,
+      "grad_norm": 0.02353634126484394,
+      "learning_rate": 7.02176403207331e-05,
+      "loss": 0.0139,
+      "step": 575
+    },
+    {
+      "epoch": 145.0,
+      "grad_norm": 0.042016856372356415,
+      "learning_rate": 6.993127147766323e-05,
+      "loss": 0.0151,
+      "step": 580
+    },
+    {
+      "epoch": 146.32,
+      "grad_norm": 0.020217517390847206,
+      "learning_rate": 6.964490263459336e-05,
+      "loss": 0.0131,
+      "step": 585
+    },
+    {
+      "epoch": 147.64,
+      "grad_norm": 0.019066426903009415,
+      "learning_rate": 6.935853379152348e-05,
+      "loss": 0.0138,
+      "step": 590
+    },
+    {
+      "epoch": 148.96,
+      "grad_norm": 0.023700350895524025,
+      "learning_rate": 6.907216494845361e-05,
+      "loss": 0.0157,
+      "step": 595
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 0.10881764441728592,
+      "learning_rate": 6.878579610538374e-05,
+      "loss": 0.0145,
+      "step": 600
+    },
+    {
+      "epoch": 151.32,
+      "grad_norm": 0.01735377125442028,
+      "learning_rate": 6.849942726231386e-05,
+      "loss": 0.0149,
+      "step": 605
+    },
+    {
+      "epoch": 152.64,
+      "grad_norm": 0.02352583408355713,
+      "learning_rate": 6.821305841924399e-05,
+      "loss": 0.0133,
+      "step": 610
+    },
+    {
+      "epoch": 153.96,
+      "grad_norm": 0.020118385553359985,
+      "learning_rate": 6.792668957617412e-05,
+      "loss": 0.013,
+      "step": 615
+    },
+    {
+      "epoch": 155.0,
+      "grad_norm": 0.06744980812072754,
+      "learning_rate": 6.764032073310424e-05,
+      "loss": 0.0132,
+      "step": 620
+    },
+    {
+      "epoch": 156.32,
+      "grad_norm": 0.016874659806489944,
+      "learning_rate": 6.735395189003437e-05,
+      "loss": 0.0139,
+      "step": 625
+    },
+    {
+      "epoch": 157.64,
+      "grad_norm": 0.01467908825725317,
+      "learning_rate": 6.706758304696448e-05,
+      "loss": 0.0137,
+      "step": 630
+    },
+    {
+      "epoch": 158.96,
+      "grad_norm": 0.015406169928610325,
+      "learning_rate": 6.678121420389462e-05,
+      "loss": 0.0127,
+      "step": 635
+    },
+    {
+      "epoch": 160.0,
+      "grad_norm": 0.12341684848070145,
+      "learning_rate": 6.649484536082475e-05,
+      "loss": 0.015,
+      "step": 640
+    },
+    {
+      "epoch": 161.32,
+      "grad_norm": 0.019478783011436462,
+      "learning_rate": 6.620847651775487e-05,
+      "loss": 0.014,
+      "step": 645
+    },
+    {
+      "epoch": 162.64,
+      "grad_norm": 0.019468264654278755,
+      "learning_rate": 6.5922107674685e-05,
+      "loss": 0.0137,
+      "step": 650
+    },
+    {
+      "epoch": 163.96,
+      "grad_norm": 0.01982899010181427,
+      "learning_rate": 6.563573883161513e-05,
+      "loss": 0.0133,
+      "step": 655
+    },
+    {
+      "epoch": 165.0,
+      "grad_norm": 0.06181833893060684,
+      "learning_rate": 6.534936998854525e-05,
+      "loss": 0.0174,
+      "step": 660
+    },
+    {
+      "epoch": 166.32,
+      "grad_norm": 0.017229964956641197,
+      "learning_rate": 6.506300114547538e-05,
+      "loss": 0.0137,
+      "step": 665
+    },
+    {
+      "epoch": 167.64,
+      "grad_norm": 0.020293107256293297,
+      "learning_rate": 6.477663230240551e-05,
+      "loss": 0.0162,
+      "step": 670
+    },
+    {
+      "epoch": 168.96,
+      "grad_norm": 0.01984878070652485,
+      "learning_rate": 6.449026345933563e-05,
+      "loss": 0.0118,
+      "step": 675
+    },
+    {
+      "epoch": 170.0,
+      "grad_norm": 0.05648861452937126,
+      "learning_rate": 6.420389461626576e-05,
+      "loss": 0.0153,
+      "step": 680
+    },
+    {
+      "epoch": 171.32,
+      "grad_norm": 0.016714531928300858,
+      "learning_rate": 6.391752577319587e-05,
+      "loss": 0.0155,
+      "step": 685
+    },
+    {
+      "epoch": 172.64,
+      "grad_norm": 0.016303598880767822,
+      "learning_rate": 6.3631156930126e-05,
+      "loss": 0.0154,
+      "step": 690
+    },
+    {
+      "epoch": 173.96,
+      "grad_norm": 0.019211357459425926,
+      "learning_rate": 6.334478808705613e-05,
+      "loss": 0.015,
+      "step": 695
+    },
+    {
+      "epoch": 175.0,
+      "grad_norm": 0.06923225522041321,
+      "learning_rate": 6.305841924398625e-05,
+      "loss": 0.0151,
+      "step": 700
+    },
+    {
+      "epoch": 176.32,
+      "grad_norm": 0.0212013591080904,
+      "learning_rate": 6.277205040091638e-05,
+      "loss": 0.0137,
+      "step": 705
+    },
+    {
+      "epoch": 177.64,
+      "grad_norm": 0.019212843850255013,
+      "learning_rate": 6.24856815578465e-05,
+      "loss": 0.013,
+      "step": 710
+    },
+    {
+      "epoch": 178.96,
+      "grad_norm": 0.01936633512377739,
+      "learning_rate": 6.219931271477663e-05,
+      "loss": 0.0124,
+      "step": 715
+    },
+    {
+      "epoch": 180.0,
+      "grad_norm": 0.03678485378623009,
+      "learning_rate": 6.191294387170676e-05,
+      "loss": 0.0128,
+      "step": 720
+    },
+    {
+      "epoch": 181.32,
+      "grad_norm": 0.01613820530474186,
+      "learning_rate": 6.162657502863689e-05,
+      "loss": 0.013,
+      "step": 725
+    },
+    {
+      "epoch": 182.64,
+      "grad_norm": 0.014102709479629993,
+      "learning_rate": 6.134020618556701e-05,
+      "loss": 0.0122,
+      "step": 730
+    },
+    {
+      "epoch": 183.96,
+      "grad_norm": 0.019725633785128593,
+      "learning_rate": 6.105383734249714e-05,
+      "loss": 0.0136,
+      "step": 735
+    },
+    {
+      "epoch": 185.0,
+      "grad_norm": 0.02554723620414734,
+      "learning_rate": 6.076746849942726e-05,
+      "loss": 0.0106,
+      "step": 740
+    },
+    {
+      "epoch": 186.32,
+      "grad_norm": 0.017536187544465065,
+      "learning_rate": 6.0481099656357384e-05,
+      "loss": 0.0126,
+      "step": 745
+    },
+    {
+      "epoch": 187.64,
+      "grad_norm": 0.014839887619018555,
+      "learning_rate": 6.019473081328752e-05,
+      "loss": 0.0147,
+      "step": 750
+    },
+    {
+      "epoch": 188.96,
+      "grad_norm": 0.015652010217308998,
+      "learning_rate": 5.9908361970217644e-05,
+      "loss": 0.0122,
+      "step": 755
+    },
+    {
+      "epoch": 190.0,
+      "grad_norm": 0.07570195943117142,
+      "learning_rate": 5.962199312714777e-05,
+      "loss": 0.0156,
+      "step": 760
+    },
+    {
+      "epoch": 191.32,
+      "grad_norm": 0.01712140068411827,
+      "learning_rate": 5.93356242840779e-05,
+      "loss": 0.0144,
+      "step": 765
+    },
+    {
+      "epoch": 192.64,
+      "grad_norm": 0.018935920670628548,
+      "learning_rate": 5.904925544100802e-05,
+      "loss": 0.0137,
+      "step": 770
+    },
+    {
+      "epoch": 193.96,
+      "grad_norm": 0.018975302577018738,
+      "learning_rate": 5.876288659793815e-05,
+      "loss": 0.0139,
+      "step": 775
+    },
+    {
+      "epoch": 195.0,
+      "grad_norm": 0.06302426010370255,
+      "learning_rate": 5.8476517754868276e-05,
+      "loss": 0.0124,
+      "step": 780
+    },
+    {
+      "epoch": 196.32,
+      "grad_norm": 0.017456602305173874,
+      "learning_rate": 5.81901489117984e-05,
+      "loss": 0.0157,
+      "step": 785
+    },
+    {
+      "epoch": 197.64,
+      "grad_norm": 0.017395246773958206,
+      "learning_rate": 5.790378006872853e-05,
+      "loss": 0.0137,
+      "step": 790
+    },
+    {
+      "epoch": 198.96,
+      "grad_norm": 0.01904039829969406,
+      "learning_rate": 5.761741122565865e-05,
+      "loss": 0.0149,
+      "step": 795
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 0.05075971782207489,
+      "learning_rate": 5.7331042382588775e-05,
+      "loss": 0.0133,
+      "step": 800
+    },
+    {
+      "epoch": 201.32,
+      "grad_norm": 0.017711862921714783,
+      "learning_rate": 5.70446735395189e-05,
+      "loss": 0.0132,
+      "step": 805
+    },
+    {
+      "epoch": 202.64,
+      "grad_norm": 0.01479764562100172,
+      "learning_rate": 5.675830469644903e-05,
+      "loss": 0.0159,
+      "step": 810
+    },
+    {
+      "epoch": 203.96,
+      "grad_norm": 0.014561891555786133,
+      "learning_rate": 5.6471935853379155e-05,
+      "loss": 0.0134,
+      "step": 815
+    },
+    {
+      "epoch": 205.0,
+      "grad_norm": 0.07381083816289902,
+      "learning_rate": 5.618556701030928e-05,
+      "loss": 0.0125,
+      "step": 820
+    },
+    {
+      "epoch": 206.32,
+      "grad_norm": 0.016206586733460426,
+      "learning_rate": 5.589919816723941e-05,
+      "loss": 0.0147,
+      "step": 825
+    },
+    {
+      "epoch": 207.64,
+      "grad_norm": 0.017128223553299904,
+      "learning_rate": 5.5612829324169534e-05,
+      "loss": 0.0138,
+      "step": 830
+    },
+    {
+      "epoch": 208.96,
+      "grad_norm": 0.025427645072340965,
+      "learning_rate": 5.532646048109966e-05,
+      "loss": 0.0162,
+      "step": 835
+    },
+    {
+      "epoch": 210.0,
+      "grad_norm": 0.08378550410270691,
+      "learning_rate": 5.504009163802979e-05,
+      "loss": 0.0157,
+      "step": 840
+    },
+    {
+      "epoch": 211.32,
+      "grad_norm": 0.015921575948596,
+      "learning_rate": 5.4753722794959914e-05,
+      "loss": 0.0125,
+      "step": 845
+    },
+    {
+      "epoch": 212.64,
+      "grad_norm": 0.01416046917438507,
+      "learning_rate": 5.4467353951890033e-05,
+      "loss": 0.0125,
+      "step": 850
+    },
+    {
+      "epoch": 213.96,
+      "grad_norm": 0.015747040510177612,
+      "learning_rate": 5.418098510882016e-05,
+      "loss": 0.0134,
+      "step": 855
+    },
+    {
+      "epoch": 215.0,
+      "grad_norm": 0.024801790714263916,
+      "learning_rate": 5.3894616265750286e-05,
+      "loss": 0.0122,
+      "step": 860
+    },
+    {
+      "epoch": 216.32,
+      "grad_norm": 0.017852013930678368,
+      "learning_rate": 5.360824742268041e-05,
+      "loss": 0.0142,
+      "step": 865
+    },
+    {
+      "epoch": 217.64,
+      "grad_norm": 0.0136189516633749,
+      "learning_rate": 5.332187857961054e-05,
+      "loss": 0.0137,
+      "step": 870
+    },
+    {
+      "epoch": 218.96,
+      "grad_norm": 0.01580929383635521,
+      "learning_rate": 5.3035509736540666e-05,
+      "loss": 0.0136,
+      "step": 875
+    },
+    {
+      "epoch": 220.0,
+      "grad_norm": 0.02904467284679413,
+      "learning_rate": 5.274914089347079e-05,
+      "loss": 0.0119,
+      "step": 880
+    },
+    {
+      "epoch": 221.32,
+      "grad_norm": 0.0184769406914711,
+      "learning_rate": 5.246277205040092e-05,
+      "loss": 0.0135,
+      "step": 885
+    },
+    {
+      "epoch": 222.64,
+      "grad_norm": 0.014274867251515388,
+      "learning_rate": 5.2176403207331045e-05,
+      "loss": 0.0134,
+      "step": 890
+    },
+    {
+      "epoch": 223.96,
+      "grad_norm": 0.014355281367897987,
+      "learning_rate": 5.189003436426118e-05,
+      "loss": 0.0129,
+      "step": 895
+    },
+    {
+      "epoch": 225.0,
+      "grad_norm": 0.0977749451994896,
+      "learning_rate": 5.1603665521191305e-05,
+      "loss": 0.0159,
+      "step": 900
+    },
+    {
+      "epoch": 226.32,
+      "grad_norm": 0.016206488013267517,
+      "learning_rate": 5.131729667812142e-05,
+      "loss": 0.0127,
+      "step": 905
+    },
+    {
+      "epoch": 227.64,
+      "grad_norm": 0.015327920205891132,
+      "learning_rate": 5.1030927835051544e-05,
+      "loss": 0.012,
+      "step": 910
+    },
+    {
+      "epoch": 228.96,
+      "grad_norm": 0.018427951261401176,
+      "learning_rate": 5.074455899198167e-05,
+      "loss": 0.0136,
+      "step": 915
+    },
+    {
+      "epoch": 230.0,
+      "grad_norm": 0.07962764799594879,
+      "learning_rate": 5.04581901489118e-05,
+      "loss": 0.0147,
+      "step": 920
+    },
+    {
+      "epoch": 231.32,
+      "grad_norm": 0.016093431040644646,
+      "learning_rate": 5.0171821305841924e-05,
+      "loss": 0.0148,
+      "step": 925
+    },
+    {
+      "epoch": 232.64,
+      "grad_norm": 0.01602271758019924,
+      "learning_rate": 4.988545246277205e-05,
+      "loss": 0.0121,
+      "step": 930
+    },
+    {
+      "epoch": 233.96,
+      "grad_norm": 0.017893284559249878,
+      "learning_rate": 4.9599083619702184e-05,
+      "loss": 0.0161,
+      "step": 935
+    },
+    {
+      "epoch": 235.0,
+      "grad_norm": 0.09273411333560944,
+      "learning_rate": 4.931271477663231e-05,
+      "loss": 0.0159,
+      "step": 940
+    },
+    {
+      "epoch": 236.32,
+      "grad_norm": 0.015418586321175098,
+      "learning_rate": 4.902634593356243e-05,
+      "loss": 0.0133,
+      "step": 945
+    },
+    {
+      "epoch": 237.64,
+      "grad_norm": 0.01846655271947384,
+      "learning_rate": 4.8739977090492556e-05,
+      "loss": 0.014,
+      "step": 950
+    },
+    {
+      "epoch": 238.96,
+      "grad_norm": 0.020013106986880302,
+      "learning_rate": 4.845360824742268e-05,
+      "loss": 0.0119,
+      "step": 955
+    },
+    {
+      "epoch": 240.0,
+      "grad_norm": 0.08002018183469772,
+      "learning_rate": 4.816723940435281e-05,
+      "loss": 0.0138,
+      "step": 960
+    },
+    {
+      "epoch": 241.32,
+      "grad_norm": 0.018113132566213608,
+      "learning_rate": 4.7880870561282936e-05,
+      "loss": 0.0147,
+      "step": 965
+    },
+    {
+      "epoch": 242.64,
+      "grad_norm": 0.016398336738348007,
+      "learning_rate": 4.7594501718213055e-05,
+      "loss": 0.0133,
+      "step": 970
+    },
+    {
+      "epoch": 243.96,
+      "grad_norm": 0.014641818590462208,
+      "learning_rate": 4.730813287514318e-05,
+      "loss": 0.0149,
+      "step": 975
+    },
+    {
+      "epoch": 245.0,
+      "grad_norm": 0.051146481186151505,
+      "learning_rate": 4.7021764032073315e-05,
+      "loss": 0.015,
+      "step": 980
+    },
+    {
+      "epoch": 246.32,
+      "grad_norm": 0.017207512632012367,
+      "learning_rate": 4.673539518900344e-05,
+      "loss": 0.0132,
+      "step": 985
+    },
+    {
+      "epoch": 247.64,
+      "grad_norm": 0.01419247966259718,
+      "learning_rate": 4.644902634593357e-05,
+      "loss": 0.0115,
+      "step": 990
+    },
+    {
+      "epoch": 248.96,
+      "grad_norm": 0.019387872889637947,
+      "learning_rate": 4.6162657502863694e-05,
+      "loss": 0.0147,
+      "step": 995
+    },
+    {
+      "epoch": 250.0,
+      "grad_norm": 0.04106825590133667,
+      "learning_rate": 4.5876288659793814e-05,
+      "loss": 0.0143,
+      "step": 1000
+    },
+    {
+      "epoch": 251.32,
+      "grad_norm": 0.014324587769806385,
+      "learning_rate": 4.558991981672394e-05,
+      "loss": 0.0123,
+      "step": 1005
+    },
+    {
+      "epoch": 252.64,
+      "grad_norm": 0.01592319644987583,
+      "learning_rate": 4.530355097365407e-05,
+      "loss": 0.0138,
+      "step": 1010
+    },
+    {
+      "epoch": 253.96,
+      "grad_norm": 0.012997015379369259,
+      "learning_rate": 4.5017182130584194e-05,
+      "loss": 0.0126,
+      "step": 1015
+    },
+    {
+      "epoch": 255.0,
+      "grad_norm": 0.028852175921201706,
+      "learning_rate": 4.473081328751432e-05,
+      "loss": 0.0113,
+      "step": 1020
+    },
+    {
+      "epoch": 256.32,
+      "grad_norm": 0.014631297439336777,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.0127,
+      "step": 1025
+    },
+    {
+      "epoch": 257.64,
+      "grad_norm": 0.013913788832724094,
+      "learning_rate": 4.415807560137457e-05,
+      "loss": 0.0143,
+      "step": 1030
+    },
+    {
+      "epoch": 258.96,
+      "grad_norm": 0.014716614969074726,
+      "learning_rate": 4.38717067583047e-05,
+      "loss": 0.0122,
+      "step": 1035
+    },
+    {
+      "epoch": 260.0,
+      "grad_norm": 0.04596526920795441,
+      "learning_rate": 4.3585337915234826e-05,
+      "loss": 0.0144,
+      "step": 1040
+    },
+    {
+      "epoch": 261.32,
+      "grad_norm": 0.016867341473698616,
+      "learning_rate": 4.329896907216495e-05,
+      "loss": 0.0136,
+      "step": 1045
+    },
+    {
+      "epoch": 262.64,
+      "grad_norm": 0.014432119205594063,
+      "learning_rate": 4.301260022909508e-05,
+      "loss": 0.0133,
+      "step": 1050
+    },
+    {
+      "epoch": 263.96,
+      "grad_norm": 0.015816187486052513,
+      "learning_rate": 4.27262313860252e-05,
+      "loss": 0.0141,
+      "step": 1055
+    },
+    {
+      "epoch": 265.0,
+      "grad_norm": 0.0827472060918808,
+      "learning_rate": 4.2439862542955325e-05,
+      "loss": 0.015,
+      "step": 1060
+    },
+    {
+      "epoch": 266.32,
+      "grad_norm": 0.015457245521247387,
+      "learning_rate": 4.215349369988545e-05,
+      "loss": 0.0158,
+      "step": 1065
+    },
+    {
+      "epoch": 267.64,
+      "grad_norm": 0.014881868846714497,
+      "learning_rate": 4.1867124856815585e-05,
+      "loss": 0.0138,
+      "step": 1070
+    },
+    {
+      "epoch": 268.96,
+      "grad_norm": 0.016008669510483742,
+      "learning_rate": 4.158075601374571e-05,
+      "loss": 0.0152,
+      "step": 1075
+    },
+    {
+      "epoch": 270.0,
+      "grad_norm": 0.06517193466424942,
+      "learning_rate": 4.129438717067583e-05,
+      "loss": 0.0149,
+      "step": 1080
+    },
+    {
+      "epoch": 271.32,
+      "grad_norm": 0.016941051930189133,
+      "learning_rate": 4.100801832760596e-05,
+      "loss": 0.0143,
+      "step": 1085
+    },
+    {
+      "epoch": 272.64,
+      "grad_norm": 0.01699843816459179,
+      "learning_rate": 4.0721649484536084e-05,
+      "loss": 0.0122,
+      "step": 1090
+    },
+    {
+      "epoch": 273.96,
+      "grad_norm": 0.015007564797997475,
+      "learning_rate": 4.043528064146621e-05,
+      "loss": 0.0132,
+      "step": 1095
+    },
+    {
+      "epoch": 275.0,
+      "grad_norm": 0.044932473450899124,
+      "learning_rate": 4.014891179839634e-05,
+      "loss": 0.0158,
+      "step": 1100
+    },
+    {
+      "epoch": 276.32,
+      "grad_norm": 0.015588543377816677,
+      "learning_rate": 3.9862542955326463e-05,
+      "loss": 0.0154,
+      "step": 1105
+    },
+    {
+      "epoch": 277.64,
+      "grad_norm": 0.016450706869363785,
+      "learning_rate": 3.957617411225659e-05,
+      "loss": 0.0131,
+      "step": 1110
+    },
+    {
+      "epoch": 278.96,
+      "grad_norm": 0.014836867339909077,
+      "learning_rate": 3.9289805269186716e-05,
+      "loss": 0.0136,
+      "step": 1115
+    },
+    {
+      "epoch": 280.0,
+      "grad_norm": 0.05053675174713135,
+      "learning_rate": 3.900343642611684e-05,
+      "loss": 0.0155,
+      "step": 1120
+    },
+    {
+      "epoch": 281.32,
+      "grad_norm": 0.014328036457300186,
+      "learning_rate": 3.871706758304697e-05,
+      "loss": 0.0137,
+      "step": 1125
+    },
+    {
+      "epoch": 282.64,
+      "grad_norm": 0.014809757471084595,
+      "learning_rate": 3.8430698739977096e-05,
+      "loss": 0.0148,
+      "step": 1130
+    },
+    {
+      "epoch": 283.96,
+      "grad_norm": 0.015511567704379559,
+      "learning_rate": 3.8144329896907216e-05,
+      "loss": 0.0118,
+      "step": 1135
+    },
+    {
+      "epoch": 285.0,
+      "grad_norm": 0.059976644814014435,
+      "learning_rate": 3.785796105383734e-05,
+      "loss": 0.0131,
+      "step": 1140
+    },
+    {
+      "epoch": 286.32,
+      "grad_norm": 0.0156101631000638,
+      "learning_rate": 3.757159221076747e-05,
+      "loss": 0.0132,
+      "step": 1145
+    },
+    {
+      "epoch": 287.64,
+      "grad_norm": 0.014046646654605865,
+      "learning_rate": 3.7285223367697595e-05,
+      "loss": 0.0132,
+      "step": 1150
+    },
+    {
+      "epoch": 288.96,
+      "grad_norm": 0.018160076811909676,
+      "learning_rate": 3.699885452462772e-05,
+      "loss": 0.0118,
+      "step": 1155
+    },
+    {
+      "epoch": 290.0,
+      "grad_norm": 0.04931604117155075,
+      "learning_rate": 3.671248568155785e-05,
+      "loss": 0.014,
+      "step": 1160
+    },
+    {
+      "epoch": 291.32,
+      "grad_norm": 0.01428920030593872,
+      "learning_rate": 3.6426116838487974e-05,
+      "loss": 0.0148,
+      "step": 1165
+    },
+    {
+      "epoch": 292.64,
+      "grad_norm": 0.015592087060213089,
+      "learning_rate": 3.61397479954181e-05,
+      "loss": 0.0122,
+      "step": 1170
+    },
+    {
+      "epoch": 293.96,
+      "grad_norm": 0.013092358596622944,
+      "learning_rate": 3.585337915234823e-05,
+      "loss": 0.0142,
+      "step": 1175
+    },
+    {
+      "epoch": 295.0,
+      "grad_norm": 0.038132186979055405,
+      "learning_rate": 3.5567010309278354e-05,
+      "loss": 0.0132,
+      "step": 1180
+    },
+    {
+      "epoch": 296.32,
+      "grad_norm": 0.01834624819457531,
+      "learning_rate": 3.528064146620848e-05,
+      "loss": 0.0162,
+      "step": 1185
+    },
+    {
+      "epoch": 297.64,
+      "grad_norm": 0.018859442323446274,
+      "learning_rate": 3.49942726231386e-05,
+      "loss": 0.0135,
+      "step": 1190
+    },
+    {
+      "epoch": 298.96,
+      "grad_norm": 0.016382131725549698,
+      "learning_rate": 3.4707903780068726e-05,
+      "loss": 0.0125,
+      "step": 1195
+    },
+    {
+      "epoch": 300.0,
+      "grad_norm": 0.05285535380244255,
+      "learning_rate": 3.442153493699885e-05,
+      "loss": 0.0135,
+      "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
+}

Competition_Math/group_00/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

Competition_Math/group_00/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": [
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Competition_Math/group_00/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
+}

Competition_Math/group_00/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 %}

Competition_Math/group_00/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
+  }
+}

Competition_Math/group_00/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
+}

Competition_Math/group_00/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": 4.598043441772461,
+      "learning_rate": 0.0,
+      "loss": 0.9577,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 3.2691659927368164,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.914,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.4407647848129272,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.87,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 0.873967170715332,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 0.7194,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.5684808492660522,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.485,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.31015607714653015,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.4448,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.2658279538154602,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.4004,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.24357278645038605,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.3975,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.7138969302177429,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.3541,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.3199204206466675,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.2981,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 0.3794819414615631,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.2975,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 0.6489832997322083,
+      "learning_rate": 0.0001,
+      "loss": 0.2113,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.9405580759048462,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1426,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 0.5083445310592651,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.1212,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 0.4943920969963074,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0843,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 0.7678825259208679,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0484,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 1.9925947189331055,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.0444,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.2645427882671356,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0288,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 0.1064828559756279,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.0301,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.12416807562112808,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.0196,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.2526699900627136,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0203,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.09203815460205078,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0201,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.07873351126909256,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0162,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.10604001581668854,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.0191,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 1.7986263036727905,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0198,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.07677727192640305,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.0158,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.1571263074874878,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0152,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.06132940948009491,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.0137,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.09364927560091019,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.016,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.04978128522634506,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0161,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.03882812336087227,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0154,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.04475203529000282,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0164,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.13846606016159058,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0161,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.033312492072582245,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.0135,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.041062209755182266,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0135,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.032531533390283585,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0135,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.1364850103855133,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0149,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.042139116674661636,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0136,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.03540545701980591,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0132,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.04514731466770172,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0175,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.14643007516860962,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0152,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.03208281844854355,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.0144,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.03130023553967476,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.0168,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.03348194435238838,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0141,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.05507143586874008,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0149,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.019802691414952278,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0149,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.025274671614170074,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.016,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.0396709069609642,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0156,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.11217641085386276,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0165,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.03045077621936798,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0154,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.030307715758681297,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0149,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.028285281732678413,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0139,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.1250770390033722,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0187,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.025621576234698296,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0135,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.021983368322253227,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0149,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.02598453126847744,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0139,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.08075019717216492,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0148,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.0245928093791008,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.0159,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.026031415909528732,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.0144,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.02940714731812477,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0146,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.0966266617178917,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.014,
+      "step": 300
+    },
+    {
+      "epoch": 76.32,
+      "grad_norm": 0.028764601796865463,
+      "learning_rate": 8.56815578465063e-05,
+      "loss": 0.0132,
+      "step": 305
+    },
+    {
+      "epoch": 77.64,
+      "grad_norm": 0.027627065777778625,
+      "learning_rate": 8.539518900343643e-05,
+      "loss": 0.0166,
+      "step": 310
+    },
+    {
+      "epoch": 78.96,
+      "grad_norm": 0.026004405692219734,
+      "learning_rate": 8.510882016036655e-05,
+      "loss": 0.0148,
+      "step": 315
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.08327600359916687,
+      "learning_rate": 8.482245131729668e-05,
+      "loss": 0.016,
+      "step": 320
+    },
+    {
+      "epoch": 81.32,
+      "grad_norm": 0.025960935279726982,
+      "learning_rate": 8.453608247422681e-05,
+      "loss": 0.0143,
+      "step": 325
+    },
+    {
+      "epoch": 82.64,
+      "grad_norm": 0.025417521595954895,
+      "learning_rate": 8.424971363115693e-05,
+      "loss": 0.014,
+      "step": 330
+    },
+    {
+      "epoch": 83.96,
+      "grad_norm": 0.025654327124357224,
+      "learning_rate": 8.396334478808706e-05,
+      "loss": 0.0128,
+      "step": 335
+    },
+    {
+      "epoch": 85.0,
+      "grad_norm": 0.10201112926006317,
+      "learning_rate": 8.367697594501719e-05,
+      "loss": 0.0142,
+      "step": 340
+    },
+    {
+      "epoch": 86.32,
+      "grad_norm": 0.02470439113676548,
+      "learning_rate": 8.339060710194731e-05,
+      "loss": 0.0127,
+      "step": 345
+    },
+    {
+      "epoch": 87.64,
+      "grad_norm": 0.0236374419182539,
+      "learning_rate": 8.310423825887744e-05,
+      "loss": 0.0153,
+      "step": 350
+    },
+    {
+      "epoch": 88.96,
+      "grad_norm": 0.03599975258111954,
+      "learning_rate": 8.281786941580757e-05,
+      "loss": 0.0133,
+      "step": 355
+    },
+    {
+      "epoch": 90.0,
+      "grad_norm": 0.08355200290679932,
+      "learning_rate": 8.253150057273768e-05,
+      "loss": 0.0144,
+      "step": 360
+    },
+    {
+      "epoch": 91.32,
+      "grad_norm": 0.020355794578790665,
+      "learning_rate": 8.224513172966782e-05,
+      "loss": 0.014,
+      "step": 365
+    },
+    {
+      "epoch": 92.64,
+      "grad_norm": 0.021856721490621567,
+      "learning_rate": 8.195876288659795e-05,
+      "loss": 0.0166,
+      "step": 370
+    },
+    {
+      "epoch": 93.96,
+      "grad_norm": 0.03352021053433418,
+      "learning_rate": 8.167239404352807e-05,
+      "loss": 0.0133,
+      "step": 375
+    },
+    {
+      "epoch": 95.0,
+      "grad_norm": 0.050965987145900726,
+      "learning_rate": 8.13860252004582e-05,
+      "loss": 0.0111,
+      "step": 380
+    },
+    {
+      "epoch": 96.32,
+      "grad_norm": 0.01907683163881302,
+      "learning_rate": 8.109965635738833e-05,
+      "loss": 0.0123,
+      "step": 385
+    },
+    {
+      "epoch": 97.64,
+      "grad_norm": 0.017776427790522575,
+      "learning_rate": 8.081328751431845e-05,
+      "loss": 0.0141,
+      "step": 390
+    },
+    {
+      "epoch": 98.96,
+      "grad_norm": 0.02410067617893219,
+      "learning_rate": 8.052691867124858e-05,
+      "loss": 0.0147,
+      "step": 395
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.11242590099573135,
+      "learning_rate": 8.02405498281787e-05,
+      "loss": 0.0164,
+      "step": 400
+    },
+    {
+      "epoch": 101.32,
+      "grad_norm": 0.024096814915537834,
+      "learning_rate": 7.995418098510883e-05,
+      "loss": 0.0143,
+      "step": 405
+    },
+    {
+      "epoch": 102.64,
+      "grad_norm": 0.02899334393441677,
+      "learning_rate": 7.966781214203894e-05,
+      "loss": 0.0155,
+      "step": 410
+    },
+    {
+      "epoch": 103.96,
+      "grad_norm": 0.023235289379954338,
+      "learning_rate": 7.938144329896907e-05,
+      "loss": 0.0124,
+      "step": 415
+    },
+    {
+      "epoch": 105.0,
+      "grad_norm": 0.0693734735250473,
+      "learning_rate": 7.90950744558992e-05,
+      "loss": 0.0137,
+      "step": 420
+    },
+    {
+      "epoch": 106.32,
+      "grad_norm": 0.019512519240379333,
+      "learning_rate": 7.880870561282932e-05,
+      "loss": 0.0142,
+      "step": 425
+    },
+    {
+      "epoch": 107.64,
+      "grad_norm": 0.02140176109969616,
+      "learning_rate": 7.852233676975945e-05,
+      "loss": 0.0141,
+      "step": 430
+    },
+    {
+      "epoch": 108.96,
+      "grad_norm": 0.022468585520982742,
+      "learning_rate": 7.823596792668958e-05,
+      "loss": 0.0122,
+      "step": 435
+    },
+    {
+      "epoch": 110.0,
+      "grad_norm": 0.0380476713180542,
+      "learning_rate": 7.79495990836197e-05,
+      "loss": 0.0136,
+      "step": 440
+    },
+    {
+      "epoch": 111.32,
+      "grad_norm": 0.018203549087047577,
+      "learning_rate": 7.766323024054983e-05,
+      "loss": 0.0119,
+      "step": 445
+    },
+    {
+      "epoch": 112.64,
+      "grad_norm": 0.02083701454102993,
+      "learning_rate": 7.737686139747996e-05,
+      "loss": 0.0159,
+      "step": 450
+    },
+    {
+      "epoch": 113.96,
+      "grad_norm": 0.02744678594172001,
+      "learning_rate": 7.709049255441008e-05,
+      "loss": 0.0138,
+      "step": 455
+    },
+    {
+      "epoch": 115.0,
+      "grad_norm": 0.05891157686710358,
+      "learning_rate": 7.680412371134021e-05,
+      "loss": 0.0123,
+      "step": 460
+    },
+    {
+      "epoch": 116.32,
+      "grad_norm": 0.02845454029738903,
+      "learning_rate": 7.651775486827034e-05,
+      "loss": 0.0139,
+      "step": 465
+    },
+    {
+      "epoch": 117.64,
+      "grad_norm": 0.020904691889882088,
+      "learning_rate": 7.623138602520046e-05,
+      "loss": 0.013,
+      "step": 470
+    },
+    {
+      "epoch": 118.96,
+      "grad_norm": 0.020568421110510826,
+      "learning_rate": 7.594501718213059e-05,
+      "loss": 0.0126,
+      "step": 475
+    },
+    {
+      "epoch": 120.0,
+      "grad_norm": 0.11525513231754303,
+      "learning_rate": 7.565864833906071e-05,
+      "loss": 0.0149,
+      "step": 480
+    },
+    {
+      "epoch": 121.32,
+      "grad_norm": 0.02282075583934784,
+      "learning_rate": 7.537227949599084e-05,
+      "loss": 0.0145,
+      "step": 485
+    },
+    {
+      "epoch": 122.64,
+      "grad_norm": 0.021044986322522163,
+      "learning_rate": 7.508591065292097e-05,
+      "loss": 0.0118,
+      "step": 490
+    },
+    {
+      "epoch": 123.96,
+      "grad_norm": 0.026140881702303886,
+      "learning_rate": 7.47995418098511e-05,
+      "loss": 0.0134,
+      "step": 495
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 0.08347874134778976,
+      "learning_rate": 7.451317296678122e-05,
+      "loss": 0.0134,
+      "step": 500
+    },
+    {
+      "epoch": 126.32,
+      "grad_norm": 0.021540338173508644,
+      "learning_rate": 7.422680412371135e-05,
+      "loss": 0.0124,
+      "step": 505
+    },
+    {
+      "epoch": 127.64,
+      "grad_norm": 0.018244560807943344,
+      "learning_rate": 7.394043528064147e-05,
+      "loss": 0.0133,
+      "step": 510
+    },
+    {
+      "epoch": 128.96,
+      "grad_norm": 0.0179904717952013,
+      "learning_rate": 7.36540664375716e-05,
+      "loss": 0.0131,
+      "step": 515
+    },
+    {
+      "epoch": 130.0,
+      "grad_norm": 0.0700739249587059,
+      "learning_rate": 7.336769759450171e-05,
+      "loss": 0.0151,
+      "step": 520
+    },
+    {
+      "epoch": 131.32,
+      "grad_norm": 0.02473938651382923,
+      "learning_rate": 7.308132875143184e-05,
+      "loss": 0.0139,
+      "step": 525
+    },
+    {
+      "epoch": 132.64,
+      "grad_norm": 0.016669029369950294,
+      "learning_rate": 7.279495990836197e-05,
+      "loss": 0.0129,
+      "step": 530
+    },
+    {
+      "epoch": 133.96,
+      "grad_norm": 0.0206622127443552,
+      "learning_rate": 7.250859106529209e-05,
+      "loss": 0.0131,
+      "step": 535
+    },
+    {
+      "epoch": 135.0,
+      "grad_norm": 0.1013081893324852,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.0141,
+      "step": 540
+    },
+    {
+      "epoch": 136.32,
+      "grad_norm": 0.02413194440305233,
+      "learning_rate": 7.193585337915235e-05,
+      "loss": 0.0136,
+      "step": 545
+    },
+    {
+      "epoch": 137.64,
+      "grad_norm": 0.02023296430706978,
+      "learning_rate": 7.164948453608247e-05,
+      "loss": 0.0134,
+      "step": 550
+    },
+    {
+      "epoch": 138.96,
+      "grad_norm": 0.018895283341407776,
+      "learning_rate": 7.136311569301261e-05,
+      "loss": 0.012,
+      "step": 555
+    },
+    {
+      "epoch": 140.0,
+      "grad_norm": 0.08102845400571823,
+      "learning_rate": 7.107674684994274e-05,
+      "loss": 0.0142,
+      "step": 560
+    },
+    {
+      "epoch": 141.32,
+      "grad_norm": 0.019933724775910378,
+      "learning_rate": 7.079037800687286e-05,
+      "loss": 0.0143,
+      "step": 565
+    },
+    {
+      "epoch": 142.64,
+      "grad_norm": 0.02834722027182579,
+      "learning_rate": 7.050400916380299e-05,
+      "loss": 0.0136,
+      "step": 570
+    },
+    {
+      "epoch": 143.96,
+      "grad_norm": 0.02353634126484394,
+      "learning_rate": 7.02176403207331e-05,
+      "loss": 0.0139,
+      "step": 575
+    },
+    {
+      "epoch": 145.0,
+      "grad_norm": 0.042016856372356415,
+      "learning_rate": 6.993127147766323e-05,
+      "loss": 0.0151,
+      "step": 580
+    },
+    {
+      "epoch": 146.32,
+      "grad_norm": 0.020217517390847206,
+      "learning_rate": 6.964490263459336e-05,
+      "loss": 0.0131,
+      "step": 585
+    },
+    {
+      "epoch": 147.64,
+      "grad_norm": 0.019066426903009415,
+      "learning_rate": 6.935853379152348e-05,
+      "loss": 0.0138,
+      "step": 590
+    },
+    {
+      "epoch": 148.96,
+      "grad_norm": 0.023700350895524025,
+      "learning_rate": 6.907216494845361e-05,
+      "loss": 0.0157,
+      "step": 595
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 0.10881764441728592,
+      "learning_rate": 6.878579610538374e-05,
+      "loss": 0.0145,
+      "step": 600
+    },
+    {
+      "epoch": 151.32,
+      "grad_norm": 0.01735377125442028,
+      "learning_rate": 6.849942726231386e-05,
+      "loss": 0.0149,
+      "step": 605
+    },
+    {
+      "epoch": 152.64,
+      "grad_norm": 0.02352583408355713,
+      "learning_rate": 6.821305841924399e-05,
+      "loss": 0.0133,
+      "step": 610
+    },
+    {
+      "epoch": 153.96,
+      "grad_norm": 0.020118385553359985,
+      "learning_rate": 6.792668957617412e-05,
+      "loss": 0.013,
+      "step": 615
+    },
+    {
+      "epoch": 155.0,
+      "grad_norm": 0.06744980812072754,
+      "learning_rate": 6.764032073310424e-05,
+      "loss": 0.0132,
+      "step": 620
+    },
+    {
+      "epoch": 156.32,
+      "grad_norm": 0.016874659806489944,
+      "learning_rate": 6.735395189003437e-05,
+      "loss": 0.0139,
+      "step": 625
+    },
+    {
+      "epoch": 157.64,
+      "grad_norm": 0.01467908825725317,
+      "learning_rate": 6.706758304696448e-05,
+      "loss": 0.0137,
+      "step": 630
+    },
+    {
+      "epoch": 158.96,
+      "grad_norm": 0.015406169928610325,
+      "learning_rate": 6.678121420389462e-05,
+      "loss": 0.0127,
+      "step": 635
+    },
+    {
+      "epoch": 160.0,
+      "grad_norm": 0.12341684848070145,
+      "learning_rate": 6.649484536082475e-05,
+      "loss": 0.015,
+      "step": 640
+    },
+    {
+      "epoch": 161.32,
+      "grad_norm": 0.019478783011436462,
+      "learning_rate": 6.620847651775487e-05,
+      "loss": 0.014,
+      "step": 645
+    },
+    {
+      "epoch": 162.64,
+      "grad_norm": 0.019468264654278755,
+      "learning_rate": 6.5922107674685e-05,
+      "loss": 0.0137,
+      "step": 650
+    },
+    {
+      "epoch": 163.96,
+      "grad_norm": 0.01982899010181427,
+      "learning_rate": 6.563573883161513e-05,
+      "loss": 0.0133,
+      "step": 655
+    },
+    {
+      "epoch": 165.0,
+      "grad_norm": 0.06181833893060684,
+      "learning_rate": 6.534936998854525e-05,
+      "loss": 0.0174,
+      "step": 660
+    },
+    {
+      "epoch": 166.32,
+      "grad_norm": 0.017229964956641197,
+      "learning_rate": 6.506300114547538e-05,
+      "loss": 0.0137,
+      "step": 665
+    },
+    {
+      "epoch": 167.64,
+      "grad_norm": 0.020293107256293297,
+      "learning_rate": 6.477663230240551e-05,
+      "loss": 0.0162,
+      "step": 670
+    },
+    {
+      "epoch": 168.96,
+      "grad_norm": 0.01984878070652485,
+      "learning_rate": 6.449026345933563e-05,
+      "loss": 0.0118,
+      "step": 675
+    },
+    {
+      "epoch": 170.0,
+      "grad_norm": 0.05648861452937126,
+      "learning_rate": 6.420389461626576e-05,
+      "loss": 0.0153,
+      "step": 680
+    },
+    {
+      "epoch": 171.32,
+      "grad_norm": 0.016714531928300858,
+      "learning_rate": 6.391752577319587e-05,
+      "loss": 0.0155,
+      "step": 685
+    },
+    {
+      "epoch": 172.64,
+      "grad_norm": 0.016303598880767822,
+      "learning_rate": 6.3631156930126e-05,
+      "loss": 0.0154,
+      "step": 690
+    },
+    {
+      "epoch": 173.96,
+      "grad_norm": 0.019211357459425926,
+      "learning_rate": 6.334478808705613e-05,
+      "loss": 0.015,
+      "step": 695
+    },
+    {
+      "epoch": 175.0,
+      "grad_norm": 0.06923225522041321,
+      "learning_rate": 6.305841924398625e-05,
+      "loss": 0.0151,
+      "step": 700
+    },
+    {
+      "epoch": 176.32,
+      "grad_norm": 0.0212013591080904,
+      "learning_rate": 6.277205040091638e-05,
+      "loss": 0.0137,
+      "step": 705
+    },
+    {
+      "epoch": 177.64,
+      "grad_norm": 0.019212843850255013,
+      "learning_rate": 6.24856815578465e-05,
+      "loss": 0.013,
+      "step": 710
+    },
+    {
+      "epoch": 178.96,
+      "grad_norm": 0.01936633512377739,
+      "learning_rate": 6.219931271477663e-05,
+      "loss": 0.0124,
+      "step": 715
+    },
+    {
+      "epoch": 180.0,
+      "grad_norm": 0.03678485378623009,
+      "learning_rate": 6.191294387170676e-05,
+      "loss": 0.0128,
+      "step": 720
+    },
+    {
+      "epoch": 181.32,
+      "grad_norm": 0.01613820530474186,
+      "learning_rate": 6.162657502863689e-05,
+      "loss": 0.013,
+      "step": 725
+    },
+    {
+      "epoch": 182.64,
+      "grad_norm": 0.014102709479629993,
+      "learning_rate": 6.134020618556701e-05,
+      "loss": 0.0122,
+      "step": 730
+    },
+    {
+      "epoch": 183.96,
+      "grad_norm": 0.019725633785128593,
+      "learning_rate": 6.105383734249714e-05,
+      "loss": 0.0136,
+      "step": 735
+    },
+    {
+      "epoch": 185.0,
+      "grad_norm": 0.02554723620414734,
+      "learning_rate": 6.076746849942726e-05,
+      "loss": 0.0106,
+      "step": 740
+    },
+    {
+      "epoch": 186.32,
+      "grad_norm": 0.017536187544465065,
+      "learning_rate": 6.0481099656357384e-05,
+      "loss": 0.0126,
+      "step": 745
+    },
+    {
+      "epoch": 187.64,
+      "grad_norm": 0.014839887619018555,
+      "learning_rate": 6.019473081328752e-05,
+      "loss": 0.0147,
+      "step": 750
+    },
+    {
+      "epoch": 188.96,
+      "grad_norm": 0.015652010217308998,
+      "learning_rate": 5.9908361970217644e-05,
+      "loss": 0.0122,
+      "step": 755
+    },
+    {
+      "epoch": 190.0,
+      "grad_norm": 0.07570195943117142,
+      "learning_rate": 5.962199312714777e-05,
+      "loss": 0.0156,
+      "step": 760
+    },
+    {
+      "epoch": 191.32,
+      "grad_norm": 0.01712140068411827,
+      "learning_rate": 5.93356242840779e-05,
+      "loss": 0.0144,
+      "step": 765
+    },
+    {
+      "epoch": 192.64,
+      "grad_norm": 0.018935920670628548,
+      "learning_rate": 5.904925544100802e-05,
+      "loss": 0.0137,
+      "step": 770
+    },
+    {
+      "epoch": 193.96,
+      "grad_norm": 0.018975302577018738,
+      "learning_rate": 5.876288659793815e-05,
+      "loss": 0.0139,
+      "step": 775
+    },
+    {
+      "epoch": 195.0,
+      "grad_norm": 0.06302426010370255,
+      "learning_rate": 5.8476517754868276e-05,
+      "loss": 0.0124,
+      "step": 780
+    },
+    {
+      "epoch": 196.32,
+      "grad_norm": 0.017456602305173874,
+      "learning_rate": 5.81901489117984e-05,
+      "loss": 0.0157,
+      "step": 785
+    },
+    {
+      "epoch": 197.64,
+      "grad_norm": 0.017395246773958206,
+      "learning_rate": 5.790378006872853e-05,
+      "loss": 0.0137,
+      "step": 790
+    },
+    {
+      "epoch": 198.96,
+      "grad_norm": 0.01904039829969406,
+      "learning_rate": 5.761741122565865e-05,
+      "loss": 0.0149,
+      "step": 795
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 0.05075971782207489,
+      "learning_rate": 5.7331042382588775e-05,
+      "loss": 0.0133,
+      "step": 800
+    },
+    {
+      "epoch": 201.32,
+      "grad_norm": 0.017711862921714783,
+      "learning_rate": 5.70446735395189e-05,
+      "loss": 0.0132,
+      "step": 805
+    },
+    {
+      "epoch": 202.64,
+      "grad_norm": 0.01479764562100172,
+      "learning_rate": 5.675830469644903e-05,
+      "loss": 0.0159,
+      "step": 810
+    },
+    {
+      "epoch": 203.96,
+      "grad_norm": 0.014561891555786133,
+      "learning_rate": 5.6471935853379155e-05,
+      "loss": 0.0134,
+      "step": 815
+    },
+    {
+      "epoch": 205.0,
+      "grad_norm": 0.07381083816289902,
+      "learning_rate": 5.618556701030928e-05,
+      "loss": 0.0125,
+      "step": 820
+    },
+    {
+      "epoch": 206.32,
+      "grad_norm": 0.016206586733460426,
+      "learning_rate": 5.589919816723941e-05,
+      "loss": 0.0147,
+      "step": 825
+    },
+    {
+      "epoch": 207.64,
+      "grad_norm": 0.017128223553299904,
+      "learning_rate": 5.5612829324169534e-05,
+      "loss": 0.0138,
+      "step": 830
+    },
+    {
+      "epoch": 208.96,
+      "grad_norm": 0.025427645072340965,
+      "learning_rate": 5.532646048109966e-05,
+      "loss": 0.0162,
+      "step": 835
+    },
+    {
+      "epoch": 210.0,
+      "grad_norm": 0.08378550410270691,
+      "learning_rate": 5.504009163802979e-05,
+      "loss": 0.0157,
+      "step": 840
+    },
+    {
+      "epoch": 211.32,
+      "grad_norm": 0.015921575948596,
+      "learning_rate": 5.4753722794959914e-05,
+      "loss": 0.0125,
+      "step": 845
+    },
+    {
+      "epoch": 212.64,
+      "grad_norm": 0.01416046917438507,
+      "learning_rate": 5.4467353951890033e-05,
+      "loss": 0.0125,
+      "step": 850
+    },
+    {
+      "epoch": 213.96,
+      "grad_norm": 0.015747040510177612,
+      "learning_rate": 5.418098510882016e-05,
+      "loss": 0.0134,
+      "step": 855
+    },
+    {
+      "epoch": 215.0,
+      "grad_norm": 0.024801790714263916,
+      "learning_rate": 5.3894616265750286e-05,
+      "loss": 0.0122,
+      "step": 860
+    },
+    {
+      "epoch": 216.32,
+      "grad_norm": 0.017852013930678368,
+      "learning_rate": 5.360824742268041e-05,
+      "loss": 0.0142,
+      "step": 865
+    },
+    {
+      "epoch": 217.64,
+      "grad_norm": 0.0136189516633749,
+      "learning_rate": 5.332187857961054e-05,
+      "loss": 0.0137,
+      "step": 870
+    },
+    {
+      "epoch": 218.96,
+      "grad_norm": 0.01580929383635521,
+      "learning_rate": 5.3035509736540666e-05,
+      "loss": 0.0136,
+      "step": 875
+    },
+    {
+      "epoch": 220.0,
+      "grad_norm": 0.02904467284679413,
+      "learning_rate": 5.274914089347079e-05,
+      "loss": 0.0119,
+      "step": 880
+    },
+    {
+      "epoch": 221.32,
+      "grad_norm": 0.0184769406914711,
+      "learning_rate": 5.246277205040092e-05,
+      "loss": 0.0135,
+      "step": 885
+    },
+    {
+      "epoch": 222.64,
+      "grad_norm": 0.014274867251515388,
+      "learning_rate": 5.2176403207331045e-05,
+      "loss": 0.0134,
+      "step": 890
+    },
+    {
+      "epoch": 223.96,
+      "grad_norm": 0.014355281367897987,
+      "learning_rate": 5.189003436426118e-05,
+      "loss": 0.0129,
+      "step": 895
+    },
+    {
+      "epoch": 225.0,
+      "grad_norm": 0.0977749451994896,
+      "learning_rate": 5.1603665521191305e-05,
+      "loss": 0.0159,
+      "step": 900
+    },
+    {
+      "epoch": 226.32,
+      "grad_norm": 0.016206488013267517,
+      "learning_rate": 5.131729667812142e-05,
+      "loss": 0.0127,
+      "step": 905
+    },
+    {
+      "epoch": 227.64,
+      "grad_norm": 0.015327920205891132,
+      "learning_rate": 5.1030927835051544e-05,
+      "loss": 0.012,
+      "step": 910
+    },
+    {
+      "epoch": 228.96,
+      "grad_norm": 0.018427951261401176,
+      "learning_rate": 5.074455899198167e-05,
+      "loss": 0.0136,
+      "step": 915
+    },
+    {
+      "epoch": 230.0,
+      "grad_norm": 0.07962764799594879,
+      "learning_rate": 5.04581901489118e-05,
+      "loss": 0.0147,
+      "step": 920
+    },
+    {
+      "epoch": 231.32,
+      "grad_norm": 0.016093431040644646,
+      "learning_rate": 5.0171821305841924e-05,
+      "loss": 0.0148,
+      "step": 925
+    },
+    {
+      "epoch": 232.64,
+      "grad_norm": 0.01602271758019924,
+      "learning_rate": 4.988545246277205e-05,
+      "loss": 0.0121,
+      "step": 930
+    },
+    {
+      "epoch": 233.96,
+      "grad_norm": 0.017893284559249878,
+      "learning_rate": 4.9599083619702184e-05,
+      "loss": 0.0161,
+      "step": 935
+    },
+    {
+      "epoch": 235.0,
+      "grad_norm": 0.09273411333560944,
+      "learning_rate": 4.931271477663231e-05,
+      "loss": 0.0159,
+      "step": 940
+    },
+    {
+      "epoch": 236.32,
+      "grad_norm": 0.015418586321175098,
+      "learning_rate": 4.902634593356243e-05,
+      "loss": 0.0133,
+      "step": 945
+    },
+    {
+      "epoch": 237.64,
+      "grad_norm": 0.01846655271947384,
+      "learning_rate": 4.8739977090492556e-05,
+      "loss": 0.014,
+      "step": 950
+    },
+    {
+      "epoch": 238.96,
+      "grad_norm": 0.020013106986880302,
+      "learning_rate": 4.845360824742268e-05,
+      "loss": 0.0119,
+      "step": 955
+    },
+    {
+      "epoch": 240.0,
+      "grad_norm": 0.08002018183469772,
+      "learning_rate": 4.816723940435281e-05,
+      "loss": 0.0138,
+      "step": 960
+    },
+    {
+      "epoch": 241.32,
+      "grad_norm": 0.018113132566213608,
+      "learning_rate": 4.7880870561282936e-05,
+      "loss": 0.0147,
+      "step": 965
+    },
+    {
+      "epoch": 242.64,
+      "grad_norm": 0.016398336738348007,
+      "learning_rate": 4.7594501718213055e-05,
+      "loss": 0.0133,
+      "step": 970
+    },
+    {
+      "epoch": 243.96,
+      "grad_norm": 0.014641818590462208,
+      "learning_rate": 4.730813287514318e-05,
+      "loss": 0.0149,
+      "step": 975
+    },
+    {
+      "epoch": 245.0,
+      "grad_norm": 0.051146481186151505,
+      "learning_rate": 4.7021764032073315e-05,
+      "loss": 0.015,
+      "step": 980
+    },
+    {
+      "epoch": 246.32,
+      "grad_norm": 0.017207512632012367,
+      "learning_rate": 4.673539518900344e-05,
+      "loss": 0.0132,
+      "step": 985
+    },
+    {
+      "epoch": 247.64,
+      "grad_norm": 0.01419247966259718,
+      "learning_rate": 4.644902634593357e-05,
+      "loss": 0.0115,
+      "step": 990
+    },
+    {
+      "epoch": 248.96,
+      "grad_norm": 0.019387872889637947,
+      "learning_rate": 4.6162657502863694e-05,
+      "loss": 0.0147,
+      "step": 995
+    },
+    {
+      "epoch": 250.0,
+      "grad_norm": 0.04106825590133667,
+      "learning_rate": 4.5876288659793814e-05,
+      "loss": 0.0143,
+      "step": 1000
+    },
+    {
+      "epoch": 251.32,
+      "grad_norm": 0.014324587769806385,
+      "learning_rate": 4.558991981672394e-05,
+      "loss": 0.0123,
+      "step": 1005
+    },
+    {
+      "epoch": 252.64,
+      "grad_norm": 0.01592319644987583,
+      "learning_rate": 4.530355097365407e-05,
+      "loss": 0.0138,
+      "step": 1010
+    },
+    {
+      "epoch": 253.96,
+      "grad_norm": 0.012997015379369259,
+      "learning_rate": 4.5017182130584194e-05,
+      "loss": 0.0126,
+      "step": 1015
+    },
+    {
+      "epoch": 255.0,
+      "grad_norm": 0.028852175921201706,
+      "learning_rate": 4.473081328751432e-05,
+      "loss": 0.0113,
+      "step": 1020
+    },
+    {
+      "epoch": 256.32,
+      "grad_norm": 0.014631297439336777,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.0127,
+      "step": 1025
+    },
+    {
+      "epoch": 257.64,
+      "grad_norm": 0.013913788832724094,
+      "learning_rate": 4.415807560137457e-05,
+      "loss": 0.0143,
+      "step": 1030
+    },
+    {
+      "epoch": 258.96,
+      "grad_norm": 0.014716614969074726,
+      "learning_rate": 4.38717067583047e-05,
+      "loss": 0.0122,
+      "step": 1035
+    },
+    {
+      "epoch": 260.0,
+      "grad_norm": 0.04596526920795441,
+      "learning_rate": 4.3585337915234826e-05,
+      "loss": 0.0144,
+      "step": 1040
+    },
+    {
+      "epoch": 261.32,
+      "grad_norm": 0.016867341473698616,
+      "learning_rate": 4.329896907216495e-05,
+      "loss": 0.0136,
+      "step": 1045
+    },
+    {
+      "epoch": 262.64,
+      "grad_norm": 0.014432119205594063,
+      "learning_rate": 4.301260022909508e-05,
+      "loss": 0.0133,
+      "step": 1050
+    },
+    {
+      "epoch": 263.96,
+      "grad_norm": 0.015816187486052513,
+      "learning_rate": 4.27262313860252e-05,
+      "loss": 0.0141,
+      "step": 1055
+    },
+    {
+      "epoch": 265.0,
+      "grad_norm": 0.0827472060918808,
+      "learning_rate": 4.2439862542955325e-05,
+      "loss": 0.015,
+      "step": 1060
+    },
+    {
+      "epoch": 266.32,
+      "grad_norm": 0.015457245521247387,
+      "learning_rate": 4.215349369988545e-05,
+      "loss": 0.0158,
+      "step": 1065
+    },
+    {
+      "epoch": 267.64,
+      "grad_norm": 0.014881868846714497,
+      "learning_rate": 4.1867124856815585e-05,
+      "loss": 0.0138,
+      "step": 1070
+    },
+    {
+      "epoch": 268.96,
+      "grad_norm": 0.016008669510483742,
+      "learning_rate": 4.158075601374571e-05,
+      "loss": 0.0152,
+      "step": 1075
+    },
+    {
+      "epoch": 270.0,
+      "grad_norm": 0.06517193466424942,
+      "learning_rate": 4.129438717067583e-05,
+      "loss": 0.0149,
+      "step": 1080
+    },
+    {
+      "epoch": 271.32,
+      "grad_norm": 0.016941051930189133,
+      "learning_rate": 4.100801832760596e-05,
+      "loss": 0.0143,
+      "step": 1085
+    },
+    {
+      "epoch": 272.64,
+      "grad_norm": 0.01699843816459179,
+      "learning_rate": 4.0721649484536084e-05,
+      "loss": 0.0122,
+      "step": 1090
+    },
+    {
+      "epoch": 273.96,
+      "grad_norm": 0.015007564797997475,
+      "learning_rate": 4.043528064146621e-05,
+      "loss": 0.0132,
+      "step": 1095
+    },
+    {
+      "epoch": 275.0,
+      "grad_norm": 0.044932473450899124,
+      "learning_rate": 4.014891179839634e-05,
+      "loss": 0.0158,
+      "step": 1100
+    },
+    {
+      "epoch": 276.32,
+      "grad_norm": 0.015588543377816677,
+      "learning_rate": 3.9862542955326463e-05,
+      "loss": 0.0154,
+      "step": 1105
+    },
+    {
+      "epoch": 277.64,
+      "grad_norm": 0.016450706869363785,
+      "learning_rate": 3.957617411225659e-05,
+      "loss": 0.0131,
+      "step": 1110
+    },
+    {
+      "epoch": 278.96,
+      "grad_norm": 0.014836867339909077,
+      "learning_rate": 3.9289805269186716e-05,
+      "loss": 0.0136,
+      "step": 1115
+    },
+    {
+      "epoch": 280.0,
+      "grad_norm": 0.05053675174713135,
+      "learning_rate": 3.900343642611684e-05,
+      "loss": 0.0155,
+      "step": 1120
+    },
+    {
+      "epoch": 281.32,
+      "grad_norm": 0.014328036457300186,
+      "learning_rate": 3.871706758304697e-05,
+      "loss": 0.0137,
+      "step": 1125
+    },
+    {
+      "epoch": 282.64,
+      "grad_norm": 0.014809757471084595,
+      "learning_rate": 3.8430698739977096e-05,
+      "loss": 0.0148,
+      "step": 1130
+    },
+    {
+      "epoch": 283.96,
+      "grad_norm": 0.015511567704379559,
+      "learning_rate": 3.8144329896907216e-05,
+      "loss": 0.0118,
+      "step": 1135
+    },
+    {
+      "epoch": 285.0,
+      "grad_norm": 0.059976644814014435,
+      "learning_rate": 3.785796105383734e-05,
+      "loss": 0.0131,
+      "step": 1140
+    },
+    {
+      "epoch": 286.32,
+      "grad_norm": 0.0156101631000638,
+      "learning_rate": 3.757159221076747e-05,
+      "loss": 0.0132,
+      "step": 1145
+    },
+    {
+      "epoch": 287.64,
+      "grad_norm": 0.014046646654605865,
+      "learning_rate": 3.7285223367697595e-05,
+      "loss": 0.0132,
+      "step": 1150
+    },
+    {
+      "epoch": 288.96,
+      "grad_norm": 0.018160076811909676,
+      "learning_rate": 3.699885452462772e-05,
+      "loss": 0.0118,
+      "step": 1155
+    },
+    {
+      "epoch": 290.0,
+      "grad_norm": 0.04931604117155075,
+      "learning_rate": 3.671248568155785e-05,
+      "loss": 0.014,
+      "step": 1160
+    },
+    {
+      "epoch": 291.32,
+      "grad_norm": 0.01428920030593872,
+      "learning_rate": 3.6426116838487974e-05,
+      "loss": 0.0148,
+      "step": 1165
+    },
+    {
+      "epoch": 292.64,
+      "grad_norm": 0.015592087060213089,
+      "learning_rate": 3.61397479954181e-05,
+      "loss": 0.0122,
+      "step": 1170
+    },
+    {
+      "epoch": 293.96,
+      "grad_norm": 0.013092358596622944,
+      "learning_rate": 3.585337915234823e-05,
+      "loss": 0.0142,
+      "step": 1175
+    },
+    {
+      "epoch": 295.0,
+      "grad_norm": 0.038132186979055405,
+      "learning_rate": 3.5567010309278354e-05,
+      "loss": 0.0132,
+      "step": 1180
+    },
+    {
+      "epoch": 296.32,
+      "grad_norm": 0.01834624819457531,
+      "learning_rate": 3.528064146620848e-05,
+      "loss": 0.0162,
+      "step": 1185
+    },
+    {
+      "epoch": 297.64,
+      "grad_norm": 0.018859442323446274,
+      "learning_rate": 3.49942726231386e-05,
+      "loss": 0.0135,
+      "step": 1190
+    },
+    {
+      "epoch": 298.96,
+      "grad_norm": 0.016382131725549698,
+      "learning_rate": 3.4707903780068726e-05,
+      "loss": 0.0125,
+      "step": 1195
+    },
+    {
+      "epoch": 300.0,
+      "grad_norm": 0.05285535380244255,
+      "learning_rate": 3.442153493699885e-05,
+      "loss": 0.0135,
+      "step": 1200
+    },
+    {
+      "epoch": 301.32,
+      "grad_norm": 0.015993736684322357,
+      "learning_rate": 3.4135166093928986e-05,
+      "loss": 0.0139,
+      "step": 1205
+    },
+    {
+      "epoch": 302.64,
+      "grad_norm": 0.017096402123570442,
+      "learning_rate": 3.384879725085911e-05,
+      "loss": 0.0133,
+      "step": 1210
+    },
+    {
+      "epoch": 303.96,
+      "grad_norm": 0.013847332447767258,
+      "learning_rate": 3.356242840778923e-05,
+      "loss": 0.0122,
+      "step": 1215
+    },
+    {
+      "epoch": 305.0,
+      "grad_norm": 0.026308810338377953,
+      "learning_rate": 3.327605956471936e-05,
+      "loss": 0.0114,
+      "step": 1220
+    },
+    {
+      "epoch": 306.32,
+      "grad_norm": 0.012427975423634052,
+      "learning_rate": 3.2989690721649485e-05,
+      "loss": 0.0126,
+      "step": 1225
+    },
+    {
+      "epoch": 307.64,
+      "grad_norm": 0.01535365916788578,
+      "learning_rate": 3.270332187857961e-05,
+      "loss": 0.0143,
+      "step": 1230
+    },
+    {
+      "epoch": 308.96,
+      "grad_norm": 0.013711849227547646,
+      "learning_rate": 3.241695303550974e-05,
+      "loss": 0.0135,
+      "step": 1235
+    },
+    {
+      "epoch": 310.0,
+      "grad_norm": 0.037382978945970535,
+      "learning_rate": 3.2130584192439865e-05,
+      "loss": 0.013,
+      "step": 1240
+    },
+    {
+      "epoch": 311.32,
+      "grad_norm": 0.017702355980873108,
+      "learning_rate": 3.184421534936999e-05,
+      "loss": 0.0135,
+      "step": 1245
+    },
+    {
+      "epoch": 312.64,
+      "grad_norm": 0.015050322748720646,
+      "learning_rate": 3.155784650630012e-05,
+      "loss": 0.013,
+      "step": 1250
+    },
+    {
+      "epoch": 313.96,
+      "grad_norm": 0.01236819103360176,
+      "learning_rate": 3.1271477663230244e-05,
+      "loss": 0.0149,
+      "step": 1255
+    },
+    {
+      "epoch": 315.0,
+      "grad_norm": 0.09097390621900558,
+      "learning_rate": 3.098510882016037e-05,
+      "loss": 0.0166,
+      "step": 1260
+    },
+    {
+      "epoch": 316.32,
+      "grad_norm": 0.01699104905128479,
+      "learning_rate": 3.06987399770905e-05,
+      "loss": 0.0132,
+      "step": 1265
+    },
+    {
+      "epoch": 317.64,
+      "grad_norm": 0.016667397692799568,
+      "learning_rate": 3.0412371134020617e-05,
+      "loss": 0.0128,
+      "step": 1270
+    },
+    {
+      "epoch": 318.96,
+      "grad_norm": 0.014088712632656097,
+      "learning_rate": 3.0126002290950743e-05,
+      "loss": 0.0139,
+      "step": 1275
+    },
+    {
+      "epoch": 320.0,
+      "grad_norm": 0.071391761302948,
+      "learning_rate": 2.983963344788087e-05,
+      "loss": 0.0143,
+      "step": 1280
+    },
+    {
+      "epoch": 321.32,
+      "grad_norm": 0.013555712066590786,
+      "learning_rate": 2.9553264604811e-05,
+      "loss": 0.0131,
+      "step": 1285
+    },
+    {
+      "epoch": 322.64,
+      "grad_norm": 0.01849992945790291,
+      "learning_rate": 2.9266895761741126e-05,
+      "loss": 0.0141,
+      "step": 1290
+    },
+    {
+      "epoch": 323.96,
+      "grad_norm": 0.017192630097270012,
+      "learning_rate": 2.8980526918671253e-05,
+      "loss": 0.0135,
+      "step": 1295
+    },
+    {
+      "epoch": 325.0,
+      "grad_norm": 0.05855363979935646,
+      "learning_rate": 2.8694158075601372e-05,
+      "loss": 0.0115,
+      "step": 1300
+    },
+    {
+      "epoch": 326.32,
+      "grad_norm": 0.0140520129352808,
+      "learning_rate": 2.8407789232531502e-05,
+      "loss": 0.0121,
+      "step": 1305
+    },
+    {
+      "epoch": 327.64,
+      "grad_norm": 0.015486122108995914,
+      "learning_rate": 2.812142038946163e-05,
+      "loss": 0.0131,
+      "step": 1310
+    },
+    {
+      "epoch": 328.96,
+      "grad_norm": 0.014222219586372375,
+      "learning_rate": 2.7835051546391755e-05,
+      "loss": 0.0138,
+      "step": 1315
+    },
+    {
+      "epoch": 330.0,
+      "grad_norm": 0.0894969180226326,
+      "learning_rate": 2.754868270332188e-05,
+      "loss": 0.0149,
+      "step": 1320
+    },
+    {
+      "epoch": 331.32,
+      "grad_norm": 0.015103315934538841,
+      "learning_rate": 2.7262313860252005e-05,
+      "loss": 0.0126,
+      "step": 1325
+    },
+    {
+      "epoch": 332.64,
+      "grad_norm": 0.015136363916099072,
+      "learning_rate": 2.697594501718213e-05,
+      "loss": 0.0135,
+      "step": 1330
+    },
+    {
+      "epoch": 333.96,
+      "grad_norm": 0.019810238853096962,
+      "learning_rate": 2.6689576174112258e-05,
+      "loss": 0.0139,
+      "step": 1335
+    },
+    {
+      "epoch": 335.0,
+      "grad_norm": 0.0372529998421669,
+      "learning_rate": 2.6403207331042384e-05,
+      "loss": 0.0107,
+      "step": 1340
+    },
+    {
+      "epoch": 336.32,
+      "grad_norm": 0.015268836170434952,
+      "learning_rate": 2.611683848797251e-05,
+      "loss": 0.0119,
+      "step": 1345
+    },
+    {
+      "epoch": 337.64,
+      "grad_norm": 0.016926297917962074,
+      "learning_rate": 2.5830469644902637e-05,
+      "loss": 0.0149,
+      "step": 1350
+    },
+    {
+      "epoch": 338.96,
+      "grad_norm": 0.016032274812459946,
+      "learning_rate": 2.554410080183276e-05,
+      "loss": 0.0127,
+      "step": 1355
+    },
+    {
+      "epoch": 340.0,
+      "grad_norm": 0.0720982775092125,
+      "learning_rate": 2.5257731958762887e-05,
+      "loss": 0.0146,
+      "step": 1360
+    },
+    {
+      "epoch": 341.32,
+      "grad_norm": 0.016808465123176575,
+      "learning_rate": 2.4971363115693013e-05,
+      "loss": 0.0144,
+      "step": 1365
+    },
+    {
+      "epoch": 342.64,
+      "grad_norm": 0.013908334076404572,
+      "learning_rate": 2.468499427262314e-05,
+      "loss": 0.0129,
+      "step": 1370
+    },
+    {
+      "epoch": 343.96,
+      "grad_norm": 0.01524080615490675,
+      "learning_rate": 2.4398625429553266e-05,
+      "loss": 0.0132,
+      "step": 1375
+    },
+    {
+      "epoch": 345.0,
+      "grad_norm": 0.08049940317869186,
+      "learning_rate": 2.4112256586483393e-05,
+      "loss": 0.0144,
+      "step": 1380
+    },
+    {
+      "epoch": 346.32,
+      "grad_norm": 0.0138388155028224,
+      "learning_rate": 2.3825887743413516e-05,
+      "loss": 0.0117,
+      "step": 1385
+    },
+    {
+      "epoch": 347.64,
+      "grad_norm": 0.015177235938608646,
+      "learning_rate": 2.3539518900343642e-05,
+      "loss": 0.0127,
+      "step": 1390
+    },
+    {
+      "epoch": 348.96,
+      "grad_norm": 0.012481410056352615,
+      "learning_rate": 2.3253150057273772e-05,
+      "loss": 0.0126,
+      "step": 1395
+    },
+    {
+      "epoch": 350.0,
+      "grad_norm": 0.03498537838459015,
+      "learning_rate": 2.2966781214203895e-05,
+      "loss": 0.0117,
+      "step": 1400
+    },
+    {
+      "epoch": 351.32,
+      "grad_norm": 0.013234886340796947,
+      "learning_rate": 2.268041237113402e-05,
+      "loss": 0.012,
+      "step": 1405
+    },
+    {
+      "epoch": 352.64,
+      "grad_norm": 0.01700565218925476,
+      "learning_rate": 2.2394043528064148e-05,
+      "loss": 0.0136,
+      "step": 1410
+    },
+    {
+      "epoch": 353.96,
+      "grad_norm": 0.016031507402658463,
+      "learning_rate": 2.210767468499427e-05,
+      "loss": 0.0135,
+      "step": 1415
+    },
+    {
+      "epoch": 355.0,
+      "grad_norm": 0.06468836218118668,
+      "learning_rate": 2.18213058419244e-05,
+      "loss": 0.0146,
+      "step": 1420
+    },
+    {
+      "epoch": 356.32,
+      "grad_norm": 0.016307266429066658,
+      "learning_rate": 2.1534936998854528e-05,
+      "loss": 0.0129,
+      "step": 1425
+    },
+    {
+      "epoch": 357.64,
+      "grad_norm": 0.01452616136521101,
+      "learning_rate": 2.124856815578465e-05,
+      "loss": 0.0115,
+      "step": 1430
+    },
+    {
+      "epoch": 358.96,
+      "grad_norm": 0.015597185119986534,
+      "learning_rate": 2.0962199312714777e-05,
+      "loss": 0.0133,
+      "step": 1435
+    },
+    {
+      "epoch": 360.0,
+      "grad_norm": 0.09148745238780975,
+      "learning_rate": 2.0675830469644904e-05,
+      "loss": 0.0137,
+      "step": 1440
+    },
+    {
+      "epoch": 361.32,
+      "grad_norm": 0.01317733246833086,
+      "learning_rate": 2.038946162657503e-05,
+      "loss": 0.0126,
+      "step": 1445
+    },
+    {
+      "epoch": 362.64,
+      "grad_norm": 0.01985546387732029,
+      "learning_rate": 2.0103092783505157e-05,
+      "loss": 0.0127,
+      "step": 1450
+    },
+    {
+      "epoch": 363.96,
+      "grad_norm": 0.013473625294864178,
+      "learning_rate": 1.981672394043528e-05,
+      "loss": 0.0139,
+      "step": 1455
+    },
+    {
+      "epoch": 365.0,
+      "grad_norm": 0.09046448022127151,
+      "learning_rate": 1.9530355097365406e-05,
+      "loss": 0.0158,
+      "step": 1460
+    },
+    {
+      "epoch": 366.32,
+      "grad_norm": 0.02008042298257351,
+      "learning_rate": 1.9243986254295536e-05,
+      "loss": 0.0145,
+      "step": 1465
+    },
+    {
+      "epoch": 367.64,
+      "grad_norm": 0.013885478489100933,
+      "learning_rate": 1.895761741122566e-05,
+      "loss": 0.0121,
+      "step": 1470
+    },
+    {
+      "epoch": 368.96,
+      "grad_norm": 0.01947566121816635,
+      "learning_rate": 1.8671248568155786e-05,
+      "loss": 0.0135,
+      "step": 1475
+    },
+    {
+      "epoch": 370.0,
+      "grad_norm": 0.11254226416349411,
+      "learning_rate": 1.8384879725085912e-05,
+      "loss": 0.0161,
+      "step": 1480
+    },
+    {
+      "epoch": 371.32,
+      "grad_norm": 0.01628114841878414,
+      "learning_rate": 1.809851088201604e-05,
+      "loss": 0.012,
+      "step": 1485
+    },
+    {
+      "epoch": 372.64,
+      "grad_norm": 0.01649070717394352,
+      "learning_rate": 1.7812142038946165e-05,
+      "loss": 0.0133,
+      "step": 1490
+    },
+    {
+      "epoch": 373.96,
+      "grad_norm": 0.01745239645242691,
+      "learning_rate": 1.7525773195876288e-05,
+      "loss": 0.0119,
+      "step": 1495
+    },
+    {
+      "epoch": 375.0,
+      "grad_norm": 0.02520393580198288,
+      "learning_rate": 1.7239404352806415e-05,
+      "loss": 0.0114,
+      "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
+}

Competition_Math/group_00/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

Competition_Math/group_00/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
+  }
+}

Competition_Math/group_00/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": 4.598043441772461,
+      "learning_rate": 0.0,
+      "loss": 0.9577,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 3.2691659927368164,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.914,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.4407647848129272,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.87,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 0.873967170715332,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 0.7194,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.5684808492660522,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.485,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.31015607714653015,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.4448,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.2658279538154602,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.4004,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.24357278645038605,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.3975,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.7138969302177429,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.3541,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.3199204206466675,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.2981,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 0.3794819414615631,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.2975,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 0.6489832997322083,
+      "learning_rate": 0.0001,
+      "loss": 0.2113,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.9405580759048462,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1426,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 0.5083445310592651,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.1212,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 0.4943920969963074,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0843,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 0.7678825259208679,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0484,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 1.9925947189331055,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.0444,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.2645427882671356,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0288,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 0.1064828559756279,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.0301,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.12416807562112808,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.0196,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.2526699900627136,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0203,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.09203815460205078,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0201,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.07873351126909256,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0162,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.10604001581668854,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.0191,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 1.7986263036727905,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0198,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.07677727192640305,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.0158,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.1571263074874878,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0152,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.06132940948009491,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.0137,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.09364927560091019,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.016,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.04978128522634506,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0161,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.03882812336087227,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0154,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.04475203529000282,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0164,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.13846606016159058,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0161,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.033312492072582245,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.0135,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.041062209755182266,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0135,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.032531533390283585,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0135,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.1364850103855133,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0149,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.042139116674661636,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0136,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.03540545701980591,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0132,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.04514731466770172,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0175,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.14643007516860962,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0152,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.03208281844854355,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.0144,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.03130023553967476,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.0168,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.03348194435238838,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0141,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.05507143586874008,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0149,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.019802691414952278,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0149,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.025274671614170074,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.016,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.0396709069609642,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0156,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.11217641085386276,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0165,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.03045077621936798,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0154,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.030307715758681297,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0149,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.028285281732678413,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0139,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.1250770390033722,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0187,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.025621576234698296,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0135,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.021983368322253227,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0149,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.02598453126847744,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0139,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.08075019717216492,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0148,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.0245928093791008,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.0159,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.026031415909528732,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.0144,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.02940714731812477,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0146,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.0966266617178917,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.014,
+      "step": 300
+    },
+    {
+      "epoch": 76.32,
+      "grad_norm": 0.028764601796865463,
+      "learning_rate": 8.56815578465063e-05,
+      "loss": 0.0132,
+      "step": 305
+    },
+    {
+      "epoch": 77.64,
+      "grad_norm": 0.027627065777778625,
+      "learning_rate": 8.539518900343643e-05,
+      "loss": 0.0166,
+      "step": 310
+    },
+    {
+      "epoch": 78.96,
+      "grad_norm": 0.026004405692219734,
+      "learning_rate": 8.510882016036655e-05,
+      "loss": 0.0148,
+      "step": 315
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.08327600359916687,
+      "learning_rate": 8.482245131729668e-05,
+      "loss": 0.016,
+      "step": 320
+    },
+    {
+      "epoch": 81.32,
+      "grad_norm": 0.025960935279726982,
+      "learning_rate": 8.453608247422681e-05,
+      "loss": 0.0143,
+      "step": 325
+    },
+    {
+      "epoch": 82.64,
+      "grad_norm": 0.025417521595954895,
+      "learning_rate": 8.424971363115693e-05,
+      "loss": 0.014,
+      "step": 330
+    },
+    {
+      "epoch": 83.96,
+      "grad_norm": 0.025654327124357224,
+      "learning_rate": 8.396334478808706e-05,
+      "loss": 0.0128,
+      "step": 335
+    },
+    {
+      "epoch": 85.0,
+      "grad_norm": 0.10201112926006317,
+      "learning_rate": 8.367697594501719e-05,
+      "loss": 0.0142,
+      "step": 340
+    },
+    {
+      "epoch": 86.32,
+      "grad_norm": 0.02470439113676548,
+      "learning_rate": 8.339060710194731e-05,
+      "loss": 0.0127,
+      "step": 345
+    },
+    {
+      "epoch": 87.64,
+      "grad_norm": 0.0236374419182539,
+      "learning_rate": 8.310423825887744e-05,
+      "loss": 0.0153,
+      "step": 350
+    },
+    {
+      "epoch": 88.96,
+      "grad_norm": 0.03599975258111954,
+      "learning_rate": 8.281786941580757e-05,
+      "loss": 0.0133,
+      "step": 355
+    },
+    {
+      "epoch": 90.0,
+      "grad_norm": 0.08355200290679932,
+      "learning_rate": 8.253150057273768e-05,
+      "loss": 0.0144,
+      "step": 360
+    },
+    {
+      "epoch": 91.32,
+      "grad_norm": 0.020355794578790665,
+      "learning_rate": 8.224513172966782e-05,
+      "loss": 0.014,
+      "step": 365
+    },
+    {
+      "epoch": 92.64,
+      "grad_norm": 0.021856721490621567,
+      "learning_rate": 8.195876288659795e-05,
+      "loss": 0.0166,
+      "step": 370
+    },
+    {
+      "epoch": 93.96,
+      "grad_norm": 0.03352021053433418,
+      "learning_rate": 8.167239404352807e-05,
+      "loss": 0.0133,
+      "step": 375
+    },
+    {
+      "epoch": 95.0,
+      "grad_norm": 0.050965987145900726,
+      "learning_rate": 8.13860252004582e-05,
+      "loss": 0.0111,
+      "step": 380
+    },
+    {
+      "epoch": 96.32,
+      "grad_norm": 0.01907683163881302,
+      "learning_rate": 8.109965635738833e-05,
+      "loss": 0.0123,
+      "step": 385
+    },
+    {
+      "epoch": 97.64,
+      "grad_norm": 0.017776427790522575,
+      "learning_rate": 8.081328751431845e-05,
+      "loss": 0.0141,
+      "step": 390
+    },
+    {
+      "epoch": 98.96,
+      "grad_norm": 0.02410067617893219,
+      "learning_rate": 8.052691867124858e-05,
+      "loss": 0.0147,
+      "step": 395
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.11242590099573135,
+      "learning_rate": 8.02405498281787e-05,
+      "loss": 0.0164,
+      "step": 400
+    },
+    {
+      "epoch": 101.32,
+      "grad_norm": 0.024096814915537834,
+      "learning_rate": 7.995418098510883e-05,
+      "loss": 0.0143,
+      "step": 405
+    },
+    {
+      "epoch": 102.64,
+      "grad_norm": 0.02899334393441677,
+      "learning_rate": 7.966781214203894e-05,
+      "loss": 0.0155,
+      "step": 410
+    },
+    {
+      "epoch": 103.96,
+      "grad_norm": 0.023235289379954338,
+      "learning_rate": 7.938144329896907e-05,
+      "loss": 0.0124,
+      "step": 415
+    },
+    {
+      "epoch": 105.0,
+      "grad_norm": 0.0693734735250473,
+      "learning_rate": 7.90950744558992e-05,
+      "loss": 0.0137,
+      "step": 420
+    },
+    {
+      "epoch": 106.32,
+      "grad_norm": 0.019512519240379333,
+      "learning_rate": 7.880870561282932e-05,
+      "loss": 0.0142,
+      "step": 425
+    },
+    {
+      "epoch": 107.64,
+      "grad_norm": 0.02140176109969616,
+      "learning_rate": 7.852233676975945e-05,
+      "loss": 0.0141,
+      "step": 430
+    },
+    {
+      "epoch": 108.96,
+      "grad_norm": 0.022468585520982742,
+      "learning_rate": 7.823596792668958e-05,
+      "loss": 0.0122,
+      "step": 435
+    },
+    {
+      "epoch": 110.0,
+      "grad_norm": 0.0380476713180542,
+      "learning_rate": 7.79495990836197e-05,
+      "loss": 0.0136,
+      "step": 440
+    },
+    {
+      "epoch": 111.32,
+      "grad_norm": 0.018203549087047577,
+      "learning_rate": 7.766323024054983e-05,
+      "loss": 0.0119,
+      "step": 445
+    },
+    {
+      "epoch": 112.64,
+      "grad_norm": 0.02083701454102993,
+      "learning_rate": 7.737686139747996e-05,
+      "loss": 0.0159,
+      "step": 450
+    },
+    {
+      "epoch": 113.96,
+      "grad_norm": 0.02744678594172001,
+      "learning_rate": 7.709049255441008e-05,
+      "loss": 0.0138,
+      "step": 455
+    },
+    {
+      "epoch": 115.0,
+      "grad_norm": 0.05891157686710358,
+      "learning_rate": 7.680412371134021e-05,
+      "loss": 0.0123,
+      "step": 460
+    },
+    {
+      "epoch": 116.32,
+      "grad_norm": 0.02845454029738903,
+      "learning_rate": 7.651775486827034e-05,
+      "loss": 0.0139,
+      "step": 465
+    },
+    {
+      "epoch": 117.64,
+      "grad_norm": 0.020904691889882088,
+      "learning_rate": 7.623138602520046e-05,
+      "loss": 0.013,
+      "step": 470
+    },
+    {
+      "epoch": 118.96,
+      "grad_norm": 0.020568421110510826,
+      "learning_rate": 7.594501718213059e-05,
+      "loss": 0.0126,
+      "step": 475
+    },
+    {
+      "epoch": 120.0,
+      "grad_norm": 0.11525513231754303,
+      "learning_rate": 7.565864833906071e-05,
+      "loss": 0.0149,
+      "step": 480
+    },
+    {
+      "epoch": 121.32,
+      "grad_norm": 0.02282075583934784,
+      "learning_rate": 7.537227949599084e-05,
+      "loss": 0.0145,
+      "step": 485
+    },
+    {
+      "epoch": 122.64,
+      "grad_norm": 0.021044986322522163,
+      "learning_rate": 7.508591065292097e-05,
+      "loss": 0.0118,
+      "step": 490
+    },
+    {
+      "epoch": 123.96,
+      "grad_norm": 0.026140881702303886,
+      "learning_rate": 7.47995418098511e-05,
+      "loss": 0.0134,
+      "step": 495
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 0.08347874134778976,
+      "learning_rate": 7.451317296678122e-05,
+      "loss": 0.0134,
+      "step": 500
+    },
+    {
+      "epoch": 126.32,
+      "grad_norm": 0.021540338173508644,
+      "learning_rate": 7.422680412371135e-05,
+      "loss": 0.0124,
+      "step": 505
+    },
+    {
+      "epoch": 127.64,
+      "grad_norm": 0.018244560807943344,
+      "learning_rate": 7.394043528064147e-05,
+      "loss": 0.0133,
+      "step": 510
+    },
+    {
+      "epoch": 128.96,
+      "grad_norm": 0.0179904717952013,
+      "learning_rate": 7.36540664375716e-05,
+      "loss": 0.0131,
+      "step": 515
+    },
+    {
+      "epoch": 130.0,
+      "grad_norm": 0.0700739249587059,
+      "learning_rate": 7.336769759450171e-05,
+      "loss": 0.0151,
+      "step": 520
+    },
+    {
+      "epoch": 131.32,
+      "grad_norm": 0.02473938651382923,
+      "learning_rate": 7.308132875143184e-05,
+      "loss": 0.0139,
+      "step": 525
+    },
+    {
+      "epoch": 132.64,
+      "grad_norm": 0.016669029369950294,
+      "learning_rate": 7.279495990836197e-05,
+      "loss": 0.0129,
+      "step": 530
+    },
+    {
+      "epoch": 133.96,
+      "grad_norm": 0.0206622127443552,
+      "learning_rate": 7.250859106529209e-05,
+      "loss": 0.0131,
+      "step": 535
+    },
+    {
+      "epoch": 135.0,
+      "grad_norm": 0.1013081893324852,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.0141,
+      "step": 540
+    },
+    {
+      "epoch": 136.32,
+      "grad_norm": 0.02413194440305233,
+      "learning_rate": 7.193585337915235e-05,
+      "loss": 0.0136,
+      "step": 545
+    },
+    {
+      "epoch": 137.64,
+      "grad_norm": 0.02023296430706978,
+      "learning_rate": 7.164948453608247e-05,
+      "loss": 0.0134,
+      "step": 550
+    },
+    {
+      "epoch": 138.96,
+      "grad_norm": 0.018895283341407776,
+      "learning_rate": 7.136311569301261e-05,
+      "loss": 0.012,
+      "step": 555
+    },
+    {
+      "epoch": 140.0,
+      "grad_norm": 0.08102845400571823,
+      "learning_rate": 7.107674684994274e-05,
+      "loss": 0.0142,
+      "step": 560
+    },
+    {
+      "epoch": 141.32,
+      "grad_norm": 0.019933724775910378,
+      "learning_rate": 7.079037800687286e-05,
+      "loss": 0.0143,
+      "step": 565
+    },
+    {
+      "epoch": 142.64,
+      "grad_norm": 0.02834722027182579,
+      "learning_rate": 7.050400916380299e-05,
+      "loss": 0.0136,
+      "step": 570
+    },
+    {
+      "epoch": 143.96,
+      "grad_norm": 0.02353634126484394,
+      "learning_rate": 7.02176403207331e-05,
+      "loss": 0.0139,
+      "step": 575
+    },
+    {
+      "epoch": 145.0,
+      "grad_norm": 0.042016856372356415,
+      "learning_rate": 6.993127147766323e-05,
+      "loss": 0.0151,
+      "step": 580
+    },
+    {
+      "epoch": 146.32,
+      "grad_norm": 0.020217517390847206,
+      "learning_rate": 6.964490263459336e-05,
+      "loss": 0.0131,
+      "step": 585
+    },
+    {
+      "epoch": 147.64,
+      "grad_norm": 0.019066426903009415,
+      "learning_rate": 6.935853379152348e-05,
+      "loss": 0.0138,
+      "step": 590
+    },
+    {
+      "epoch": 148.96,
+      "grad_norm": 0.023700350895524025,
+      "learning_rate": 6.907216494845361e-05,
+      "loss": 0.0157,
+      "step": 595
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 0.10881764441728592,
+      "learning_rate": 6.878579610538374e-05,
+      "loss": 0.0145,
+      "step": 600
+    },
+    {
+      "epoch": 151.32,
+      "grad_norm": 0.01735377125442028,
+      "learning_rate": 6.849942726231386e-05,
+      "loss": 0.0149,
+      "step": 605
+    },
+    {
+      "epoch": 152.64,
+      "grad_norm": 0.02352583408355713,
+      "learning_rate": 6.821305841924399e-05,
+      "loss": 0.0133,
+      "step": 610
+    },
+    {
+      "epoch": 153.96,
+      "grad_norm": 0.020118385553359985,
+      "learning_rate": 6.792668957617412e-05,
+      "loss": 0.013,
+      "step": 615
+    },
+    {
+      "epoch": 155.0,
+      "grad_norm": 0.06744980812072754,
+      "learning_rate": 6.764032073310424e-05,
+      "loss": 0.0132,
+      "step": 620
+    },
+    {
+      "epoch": 156.32,
+      "grad_norm": 0.016874659806489944,
+      "learning_rate": 6.735395189003437e-05,
+      "loss": 0.0139,
+      "step": 625
+    },
+    {
+      "epoch": 157.64,
+      "grad_norm": 0.01467908825725317,
+      "learning_rate": 6.706758304696448e-05,
+      "loss": 0.0137,
+      "step": 630
+    },
+    {
+      "epoch": 158.96,
+      "grad_norm": 0.015406169928610325,
+      "learning_rate": 6.678121420389462e-05,
+      "loss": 0.0127,
+      "step": 635
+    },
+    {
+      "epoch": 160.0,
+      "grad_norm": 0.12341684848070145,
+      "learning_rate": 6.649484536082475e-05,
+      "loss": 0.015,
+      "step": 640
+    },
+    {
+      "epoch": 161.32,
+      "grad_norm": 0.019478783011436462,
+      "learning_rate": 6.620847651775487e-05,
+      "loss": 0.014,
+      "step": 645
+    },
+    {
+      "epoch": 162.64,
+      "grad_norm": 0.019468264654278755,
+      "learning_rate": 6.5922107674685e-05,
+      "loss": 0.0137,
+      "step": 650
+    },
+    {
+      "epoch": 163.96,
+      "grad_norm": 0.01982899010181427,
+      "learning_rate": 6.563573883161513e-05,
+      "loss": 0.0133,
+      "step": 655
+    },
+    {
+      "epoch": 165.0,
+      "grad_norm": 0.06181833893060684,
+      "learning_rate": 6.534936998854525e-05,
+      "loss": 0.0174,
+      "step": 660
+    },
+    {
+      "epoch": 166.32,
+      "grad_norm": 0.017229964956641197,
+      "learning_rate": 6.506300114547538e-05,
+      "loss": 0.0137,
+      "step": 665
+    },
+    {
+      "epoch": 167.64,
+      "grad_norm": 0.020293107256293297,
+      "learning_rate": 6.477663230240551e-05,
+      "loss": 0.0162,
+      "step": 670
+    },
+    {
+      "epoch": 168.96,
+      "grad_norm": 0.01984878070652485,
+      "learning_rate": 6.449026345933563e-05,
+      "loss": 0.0118,
+      "step": 675
+    },
+    {
+      "epoch": 170.0,
+      "grad_norm": 0.05648861452937126,
+      "learning_rate": 6.420389461626576e-05,
+      "loss": 0.0153,
+      "step": 680
+    },
+    {
+      "epoch": 171.32,
+      "grad_norm": 0.016714531928300858,
+      "learning_rate": 6.391752577319587e-05,
+      "loss": 0.0155,
+      "step": 685
+    },
+    {
+      "epoch": 172.64,
+      "grad_norm": 0.016303598880767822,
+      "learning_rate": 6.3631156930126e-05,
+      "loss": 0.0154,
+      "step": 690
+    },
+    {
+      "epoch": 173.96,
+      "grad_norm": 0.019211357459425926,
+      "learning_rate": 6.334478808705613e-05,
+      "loss": 0.015,
+      "step": 695
+    },
+    {
+      "epoch": 175.0,
+      "grad_norm": 0.06923225522041321,
+      "learning_rate": 6.305841924398625e-05,
+      "loss": 0.0151,
+      "step": 700
+    },
+    {
+      "epoch": 176.32,
+      "grad_norm": 0.0212013591080904,
+      "learning_rate": 6.277205040091638e-05,
+      "loss": 0.0137,
+      "step": 705
+    },
+    {
+      "epoch": 177.64,
+      "grad_norm": 0.019212843850255013,
+      "learning_rate": 6.24856815578465e-05,
+      "loss": 0.013,
+      "step": 710
+    },
+    {
+      "epoch": 178.96,
+      "grad_norm": 0.01936633512377739,
+      "learning_rate": 6.219931271477663e-05,
+      "loss": 0.0124,
+      "step": 715
+    },
+    {
+      "epoch": 180.0,
+      "grad_norm": 0.03678485378623009,
+      "learning_rate": 6.191294387170676e-05,
+      "loss": 0.0128,
+      "step": 720
+    },
+    {
+      "epoch": 181.32,
+      "grad_norm": 0.01613820530474186,
+      "learning_rate": 6.162657502863689e-05,
+      "loss": 0.013,
+      "step": 725
+    },
+    {
+      "epoch": 182.64,
+      "grad_norm": 0.014102709479629993,
+      "learning_rate": 6.134020618556701e-05,
+      "loss": 0.0122,
+      "step": 730
+    },
+    {
+      "epoch": 183.96,
+      "grad_norm": 0.019725633785128593,
+      "learning_rate": 6.105383734249714e-05,
+      "loss": 0.0136,
+      "step": 735
+    },
+    {
+      "epoch": 185.0,
+      "grad_norm": 0.02554723620414734,
+      "learning_rate": 6.076746849942726e-05,
+      "loss": 0.0106,
+      "step": 740
+    },
+    {
+      "epoch": 186.32,
+      "grad_norm": 0.017536187544465065,
+      "learning_rate": 6.0481099656357384e-05,
+      "loss": 0.0126,
+      "step": 745
+    },
+    {
+      "epoch": 187.64,
+      "grad_norm": 0.014839887619018555,
+      "learning_rate": 6.019473081328752e-05,
+      "loss": 0.0147,
+      "step": 750
+    },
+    {
+      "epoch": 188.96,
+      "grad_norm": 0.015652010217308998,
+      "learning_rate": 5.9908361970217644e-05,
+      "loss": 0.0122,
+      "step": 755
+    },
+    {
+      "epoch": 190.0,
+      "grad_norm": 0.07570195943117142,
+      "learning_rate": 5.962199312714777e-05,
+      "loss": 0.0156,
+      "step": 760
+    },
+    {
+      "epoch": 191.32,
+      "grad_norm": 0.01712140068411827,
+      "learning_rate": 5.93356242840779e-05,
+      "loss": 0.0144,
+      "step": 765
+    },
+    {
+      "epoch": 192.64,
+      "grad_norm": 0.018935920670628548,
+      "learning_rate": 5.904925544100802e-05,
+      "loss": 0.0137,
+      "step": 770
+    },
+    {
+      "epoch": 193.96,
+      "grad_norm": 0.018975302577018738,
+      "learning_rate": 5.876288659793815e-05,
+      "loss": 0.0139,
+      "step": 775
+    },
+    {
+      "epoch": 195.0,
+      "grad_norm": 0.06302426010370255,
+      "learning_rate": 5.8476517754868276e-05,
+      "loss": 0.0124,
+      "step": 780
+    },
+    {
+      "epoch": 196.32,
+      "grad_norm": 0.017456602305173874,
+      "learning_rate": 5.81901489117984e-05,
+      "loss": 0.0157,
+      "step": 785
+    },
+    {
+      "epoch": 197.64,
+      "grad_norm": 0.017395246773958206,
+      "learning_rate": 5.790378006872853e-05,
+      "loss": 0.0137,
+      "step": 790
+    },
+    {
+      "epoch": 198.96,
+      "grad_norm": 0.01904039829969406,
+      "learning_rate": 5.761741122565865e-05,
+      "loss": 0.0149,
+      "step": 795
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 0.05075971782207489,
+      "learning_rate": 5.7331042382588775e-05,
+      "loss": 0.0133,
+      "step": 800
+    },
+    {
+      "epoch": 201.32,
+      "grad_norm": 0.017711862921714783,
+      "learning_rate": 5.70446735395189e-05,
+      "loss": 0.0132,
+      "step": 805
+    },
+    {
+      "epoch": 202.64,
+      "grad_norm": 0.01479764562100172,
+      "learning_rate": 5.675830469644903e-05,
+      "loss": 0.0159,
+      "step": 810
+    },
+    {
+      "epoch": 203.96,
+      "grad_norm": 0.014561891555786133,
+      "learning_rate": 5.6471935853379155e-05,
+      "loss": 0.0134,
+      "step": 815
+    },
+    {
+      "epoch": 205.0,
+      "grad_norm": 0.07381083816289902,
+      "learning_rate": 5.618556701030928e-05,
+      "loss": 0.0125,
+      "step": 820
+    },
+    {
+      "epoch": 206.32,
+      "grad_norm": 0.016206586733460426,
+      "learning_rate": 5.589919816723941e-05,
+      "loss": 0.0147,
+      "step": 825
+    },
+    {
+      "epoch": 207.64,
+      "grad_norm": 0.017128223553299904,
+      "learning_rate": 5.5612829324169534e-05,
+      "loss": 0.0138,
+      "step": 830
+    },
+    {
+      "epoch": 208.96,
+      "grad_norm": 0.025427645072340965,
+      "learning_rate": 5.532646048109966e-05,
+      "loss": 0.0162,
+      "step": 835
+    },
+    {
+      "epoch": 210.0,
+      "grad_norm": 0.08378550410270691,
+      "learning_rate": 5.504009163802979e-05,
+      "loss": 0.0157,
+      "step": 840
+    },
+    {
+      "epoch": 211.32,
+      "grad_norm": 0.015921575948596,
+      "learning_rate": 5.4753722794959914e-05,
+      "loss": 0.0125,
+      "step": 845
+    },
+    {
+      "epoch": 212.64,
+      "grad_norm": 0.01416046917438507,
+      "learning_rate": 5.4467353951890033e-05,
+      "loss": 0.0125,
+      "step": 850
+    },
+    {
+      "epoch": 213.96,
+      "grad_norm": 0.015747040510177612,
+      "learning_rate": 5.418098510882016e-05,
+      "loss": 0.0134,
+      "step": 855
+    },
+    {
+      "epoch": 215.0,
+      "grad_norm": 0.024801790714263916,
+      "learning_rate": 5.3894616265750286e-05,
+      "loss": 0.0122,
+      "step": 860
+    },
+    {
+      "epoch": 216.32,
+      "grad_norm": 0.017852013930678368,
+      "learning_rate": 5.360824742268041e-05,
+      "loss": 0.0142,
+      "step": 865
+    },
+    {
+      "epoch": 217.64,
+      "grad_norm": 0.0136189516633749,
+      "learning_rate": 5.332187857961054e-05,
+      "loss": 0.0137,
+      "step": 870
+    },
+    {
+      "epoch": 218.96,
+      "grad_norm": 0.01580929383635521,
+      "learning_rate": 5.3035509736540666e-05,
+      "loss": 0.0136,
+      "step": 875
+    },
+    {
+      "epoch": 220.0,
+      "grad_norm": 0.02904467284679413,
+      "learning_rate": 5.274914089347079e-05,
+      "loss": 0.0119,
+      "step": 880
+    },
+    {
+      "epoch": 221.32,
+      "grad_norm": 0.0184769406914711,
+      "learning_rate": 5.246277205040092e-05,
+      "loss": 0.0135,
+      "step": 885
+    },
+    {
+      "epoch": 222.64,
+      "grad_norm": 0.014274867251515388,
+      "learning_rate": 5.2176403207331045e-05,
+      "loss": 0.0134,
+      "step": 890
+    },
+    {
+      "epoch": 223.96,
+      "grad_norm": 0.014355281367897987,
+      "learning_rate": 5.189003436426118e-05,
+      "loss": 0.0129,
+      "step": 895
+    },
+    {
+      "epoch": 225.0,
+      "grad_norm": 0.0977749451994896,
+      "learning_rate": 5.1603665521191305e-05,
+      "loss": 0.0159,
+      "step": 900
+    },
+    {
+      "epoch": 226.32,
+      "grad_norm": 0.016206488013267517,
+      "learning_rate": 5.131729667812142e-05,
+      "loss": 0.0127,
+      "step": 905
+    },
+    {
+      "epoch": 227.64,
+      "grad_norm": 0.015327920205891132,
+      "learning_rate": 5.1030927835051544e-05,
+      "loss": 0.012,
+      "step": 910
+    },
+    {
+      "epoch": 228.96,
+      "grad_norm": 0.018427951261401176,
+      "learning_rate": 5.074455899198167e-05,
+      "loss": 0.0136,
+      "step": 915
+    },
+    {
+      "epoch": 230.0,
+      "grad_norm": 0.07962764799594879,
+      "learning_rate": 5.04581901489118e-05,
+      "loss": 0.0147,
+      "step": 920
+    },
+    {
+      "epoch": 231.32,
+      "grad_norm": 0.016093431040644646,
+      "learning_rate": 5.0171821305841924e-05,
+      "loss": 0.0148,
+      "step": 925
+    },
+    {
+      "epoch": 232.64,
+      "grad_norm": 0.01602271758019924,
+      "learning_rate": 4.988545246277205e-05,
+      "loss": 0.0121,
+      "step": 930
+    },
+    {
+      "epoch": 233.96,
+      "grad_norm": 0.017893284559249878,
+      "learning_rate": 4.9599083619702184e-05,
+      "loss": 0.0161,
+      "step": 935
+    },
+    {
+      "epoch": 235.0,
+      "grad_norm": 0.09273411333560944,
+      "learning_rate": 4.931271477663231e-05,
+      "loss": 0.0159,
+      "step": 940
+    },
+    {
+      "epoch": 236.32,
+      "grad_norm": 0.015418586321175098,
+      "learning_rate": 4.902634593356243e-05,
+      "loss": 0.0133,
+      "step": 945
+    },
+    {
+      "epoch": 237.64,
+      "grad_norm": 0.01846655271947384,
+      "learning_rate": 4.8739977090492556e-05,
+      "loss": 0.014,
+      "step": 950
+    },
+    {
+      "epoch": 238.96,
+      "grad_norm": 0.020013106986880302,
+      "learning_rate": 4.845360824742268e-05,
+      "loss": 0.0119,
+      "step": 955
+    },
+    {
+      "epoch": 240.0,
+      "grad_norm": 0.08002018183469772,
+      "learning_rate": 4.816723940435281e-05,
+      "loss": 0.0138,
+      "step": 960
+    },
+    {
+      "epoch": 241.32,
+      "grad_norm": 0.018113132566213608,
+      "learning_rate": 4.7880870561282936e-05,
+      "loss": 0.0147,
+      "step": 965
+    },
+    {
+      "epoch": 242.64,
+      "grad_norm": 0.016398336738348007,
+      "learning_rate": 4.7594501718213055e-05,
+      "loss": 0.0133,
+      "step": 970
+    },
+    {
+      "epoch": 243.96,
+      "grad_norm": 0.014641818590462208,
+      "learning_rate": 4.730813287514318e-05,
+      "loss": 0.0149,
+      "step": 975
+    },
+    {
+      "epoch": 245.0,
+      "grad_norm": 0.051146481186151505,
+      "learning_rate": 4.7021764032073315e-05,
+      "loss": 0.015,
+      "step": 980
+    },
+    {
+      "epoch": 246.32,
+      "grad_norm": 0.017207512632012367,
+      "learning_rate": 4.673539518900344e-05,
+      "loss": 0.0132,
+      "step": 985
+    },
+    {
+      "epoch": 247.64,
+      "grad_norm": 0.01419247966259718,
+      "learning_rate": 4.644902634593357e-05,
+      "loss": 0.0115,
+      "step": 990
+    },
+    {
+      "epoch": 248.96,
+      "grad_norm": 0.019387872889637947,
+      "learning_rate": 4.6162657502863694e-05,
+      "loss": 0.0147,
+      "step": 995
+    },
+    {
+      "epoch": 250.0,
+      "grad_norm": 0.04106825590133667,
+      "learning_rate": 4.5876288659793814e-05,
+      "loss": 0.0143,
+      "step": 1000
+    },
+    {
+      "epoch": 251.32,
+      "grad_norm": 0.014324587769806385,
+      "learning_rate": 4.558991981672394e-05,
+      "loss": 0.0123,
+      "step": 1005
+    },
+    {
+      "epoch": 252.64,
+      "grad_norm": 0.01592319644987583,
+      "learning_rate": 4.530355097365407e-05,
+      "loss": 0.0138,
+      "step": 1010
+    },
+    {
+      "epoch": 253.96,
+      "grad_norm": 0.012997015379369259,
+      "learning_rate": 4.5017182130584194e-05,
+      "loss": 0.0126,
+      "step": 1015
+    },
+    {
+      "epoch": 255.0,
+      "grad_norm": 0.028852175921201706,
+      "learning_rate": 4.473081328751432e-05,
+      "loss": 0.0113,
+      "step": 1020
+    },
+    {
+      "epoch": 256.32,
+      "grad_norm": 0.014631297439336777,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.0127,
+      "step": 1025
+    },
+    {
+      "epoch": 257.64,
+      "grad_norm": 0.013913788832724094,
+      "learning_rate": 4.415807560137457e-05,
+      "loss": 0.0143,
+      "step": 1030
+    },
+    {
+      "epoch": 258.96,
+      "grad_norm": 0.014716614969074726,
+      "learning_rate": 4.38717067583047e-05,
+      "loss": 0.0122,
+      "step": 1035
+    },
+    {
+      "epoch": 260.0,
+      "grad_norm": 0.04596526920795441,
+      "learning_rate": 4.3585337915234826e-05,
+      "loss": 0.0144,
+      "step": 1040
+    },
+    {
+      "epoch": 261.32,
+      "grad_norm": 0.016867341473698616,
+      "learning_rate": 4.329896907216495e-05,
+      "loss": 0.0136,
+      "step": 1045
+    },
+    {
+      "epoch": 262.64,
+      "grad_norm": 0.014432119205594063,
+      "learning_rate": 4.301260022909508e-05,
+      "loss": 0.0133,
+      "step": 1050
+    },
+    {
+      "epoch": 263.96,
+      "grad_norm": 0.015816187486052513,
+      "learning_rate": 4.27262313860252e-05,
+      "loss": 0.0141,
+      "step": 1055
+    },
+    {
+      "epoch": 265.0,
+      "grad_norm": 0.0827472060918808,
+      "learning_rate": 4.2439862542955325e-05,
+      "loss": 0.015,
+      "step": 1060
+    },
+    {
+      "epoch": 266.32,
+      "grad_norm": 0.015457245521247387,
+      "learning_rate": 4.215349369988545e-05,
+      "loss": 0.0158,
+      "step": 1065
+    },
+    {
+      "epoch": 267.64,
+      "grad_norm": 0.014881868846714497,
+      "learning_rate": 4.1867124856815585e-05,
+      "loss": 0.0138,
+      "step": 1070
+    },
+    {
+      "epoch": 268.96,
+      "grad_norm": 0.016008669510483742,
+      "learning_rate": 4.158075601374571e-05,
+      "loss": 0.0152,
+      "step": 1075
+    },
+    {
+      "epoch": 270.0,
+      "grad_norm": 0.06517193466424942,
+      "learning_rate": 4.129438717067583e-05,
+      "loss": 0.0149,
+      "step": 1080
+    },
+    {
+      "epoch": 271.32,
+      "grad_norm": 0.016941051930189133,
+      "learning_rate": 4.100801832760596e-05,
+      "loss": 0.0143,
+      "step": 1085
+    },
+    {
+      "epoch": 272.64,
+      "grad_norm": 0.01699843816459179,
+      "learning_rate": 4.0721649484536084e-05,
+      "loss": 0.0122,
+      "step": 1090
+    },
+    {
+      "epoch": 273.96,
+      "grad_norm": 0.015007564797997475,
+      "learning_rate": 4.043528064146621e-05,
+      "loss": 0.0132,
+      "step": 1095
+    },
+    {
+      "epoch": 275.0,
+      "grad_norm": 0.044932473450899124,
+      "learning_rate": 4.014891179839634e-05,
+      "loss": 0.0158,
+      "step": 1100
+    },
+    {
+      "epoch": 276.32,
+      "grad_norm": 0.015588543377816677,
+      "learning_rate": 3.9862542955326463e-05,
+      "loss": 0.0154,
+      "step": 1105
+    },
+    {
+      "epoch": 277.64,
+      "grad_norm": 0.016450706869363785,
+      "learning_rate": 3.957617411225659e-05,
+      "loss": 0.0131,
+      "step": 1110
+    },
+    {
+      "epoch": 278.96,
+      "grad_norm": 0.014836867339909077,
+      "learning_rate": 3.9289805269186716e-05,
+      "loss": 0.0136,
+      "step": 1115
+    },
+    {
+      "epoch": 280.0,
+      "grad_norm": 0.05053675174713135,
+      "learning_rate": 3.900343642611684e-05,
+      "loss": 0.0155,
+      "step": 1120
+    },
+    {
+      "epoch": 281.32,
+      "grad_norm": 0.014328036457300186,
+      "learning_rate": 3.871706758304697e-05,
+      "loss": 0.0137,
+      "step": 1125
+    },
+    {
+      "epoch": 282.64,
+      "grad_norm": 0.014809757471084595,
+      "learning_rate": 3.8430698739977096e-05,
+      "loss": 0.0148,
+      "step": 1130
+    },
+    {
+      "epoch": 283.96,
+      "grad_norm": 0.015511567704379559,
+      "learning_rate": 3.8144329896907216e-05,
+      "loss": 0.0118,
+      "step": 1135
+    },
+    {
+      "epoch": 285.0,
+      "grad_norm": 0.059976644814014435,
+      "learning_rate": 3.785796105383734e-05,
+      "loss": 0.0131,
+      "step": 1140
+    },
+    {
+      "epoch": 286.32,
+      "grad_norm": 0.0156101631000638,
+      "learning_rate": 3.757159221076747e-05,
+      "loss": 0.0132,
+      "step": 1145
+    },
+    {
+      "epoch": 287.64,
+      "grad_norm": 0.014046646654605865,
+      "learning_rate": 3.7285223367697595e-05,
+      "loss": 0.0132,
+      "step": 1150
+    },
+    {
+      "epoch": 288.96,
+      "grad_norm": 0.018160076811909676,
+      "learning_rate": 3.699885452462772e-05,
+      "loss": 0.0118,
+      "step": 1155
+    },
+    {
+      "epoch": 290.0,
+      "grad_norm": 0.04931604117155075,
+      "learning_rate": 3.671248568155785e-05,
+      "loss": 0.014,
+      "step": 1160
+    },
+    {
+      "epoch": 291.32,
+      "grad_norm": 0.01428920030593872,
+      "learning_rate": 3.6426116838487974e-05,
+      "loss": 0.0148,
+      "step": 1165
+    },
+    {
+      "epoch": 292.64,
+      "grad_norm": 0.015592087060213089,
+      "learning_rate": 3.61397479954181e-05,
+      "loss": 0.0122,
+      "step": 1170
+    },
+    {
+      "epoch": 293.96,
+      "grad_norm": 0.013092358596622944,
+      "learning_rate": 3.585337915234823e-05,
+      "loss": 0.0142,
+      "step": 1175
+    },
+    {
+      "epoch": 295.0,
+      "grad_norm": 0.038132186979055405,
+      "learning_rate": 3.5567010309278354e-05,
+      "loss": 0.0132,
+      "step": 1180
+    },
+    {
+      "epoch": 296.32,
+      "grad_norm": 0.01834624819457531,
+      "learning_rate": 3.528064146620848e-05,
+      "loss": 0.0162,
+      "step": 1185
+    },
+    {
+      "epoch": 297.64,
+      "grad_norm": 0.018859442323446274,
+      "learning_rate": 3.49942726231386e-05,
+      "loss": 0.0135,
+      "step": 1190
+    },
+    {
+      "epoch": 298.96,
+      "grad_norm": 0.016382131725549698,
+      "learning_rate": 3.4707903780068726e-05,
+      "loss": 0.0125,
+      "step": 1195
+    },
+    {
+      "epoch": 300.0,
+      "grad_norm": 0.05285535380244255,
+      "learning_rate": 3.442153493699885e-05,
+      "loss": 0.0135,
+      "step": 1200
+    },
+    {
+      "epoch": 301.32,
+      "grad_norm": 0.015993736684322357,
+      "learning_rate": 3.4135166093928986e-05,
+      "loss": 0.0139,
+      "step": 1205
+    },
+    {
+      "epoch": 302.64,
+      "grad_norm": 0.017096402123570442,
+      "learning_rate": 3.384879725085911e-05,
+      "loss": 0.0133,
+      "step": 1210
+    },
+    {
+      "epoch": 303.96,
+      "grad_norm": 0.013847332447767258,
+      "learning_rate": 3.356242840778923e-05,
+      "loss": 0.0122,
+      "step": 1215
+    },
+    {
+      "epoch": 305.0,
+      "grad_norm": 0.026308810338377953,
+      "learning_rate": 3.327605956471936e-05,
+      "loss": 0.0114,
+      "step": 1220
+    },
+    {
+      "epoch": 306.32,
+      "grad_norm": 0.012427975423634052,
+      "learning_rate": 3.2989690721649485e-05,
+      "loss": 0.0126,
+      "step": 1225
+    },
+    {
+      "epoch": 307.64,
+      "grad_norm": 0.01535365916788578,
+      "learning_rate": 3.270332187857961e-05,
+      "loss": 0.0143,
+      "step": 1230
+    },
+    {
+      "epoch": 308.96,
+      "grad_norm": 0.013711849227547646,
+      "learning_rate": 3.241695303550974e-05,
+      "loss": 0.0135,
+      "step": 1235
+    },
+    {
+      "epoch": 310.0,
+      "grad_norm": 0.037382978945970535,
+      "learning_rate": 3.2130584192439865e-05,
+      "loss": 0.013,
+      "step": 1240
+    },
+    {
+      "epoch": 311.32,
+      "grad_norm": 0.017702355980873108,
+      "learning_rate": 3.184421534936999e-05,
+      "loss": 0.0135,
+      "step": 1245
+    },
+    {
+      "epoch": 312.64,
+      "grad_norm": 0.015050322748720646,
+      "learning_rate": 3.155784650630012e-05,
+      "loss": 0.013,
+      "step": 1250
+    },
+    {
+      "epoch": 313.96,
+      "grad_norm": 0.01236819103360176,
+      "learning_rate": 3.1271477663230244e-05,
+      "loss": 0.0149,
+      "step": 1255
+    },
+    {
+      "epoch": 315.0,
+      "grad_norm": 0.09097390621900558,
+      "learning_rate": 3.098510882016037e-05,
+      "loss": 0.0166,
+      "step": 1260
+    },
+    {
+      "epoch": 316.32,
+      "grad_norm": 0.01699104905128479,
+      "learning_rate": 3.06987399770905e-05,
+      "loss": 0.0132,
+      "step": 1265
+    },
+    {
+      "epoch": 317.64,
+      "grad_norm": 0.016667397692799568,
+      "learning_rate": 3.0412371134020617e-05,
+      "loss": 0.0128,
+      "step": 1270
+    },
+    {
+      "epoch": 318.96,
+      "grad_norm": 0.014088712632656097,
+      "learning_rate": 3.0126002290950743e-05,
+      "loss": 0.0139,
+      "step": 1275
+    },
+    {
+      "epoch": 320.0,
+      "grad_norm": 0.071391761302948,
+      "learning_rate": 2.983963344788087e-05,
+      "loss": 0.0143,
+      "step": 1280
+    },
+    {
+      "epoch": 321.32,
+      "grad_norm": 0.013555712066590786,
+      "learning_rate": 2.9553264604811e-05,
+      "loss": 0.0131,
+      "step": 1285
+    },
+    {
+      "epoch": 322.64,
+      "grad_norm": 0.01849992945790291,
+      "learning_rate": 2.9266895761741126e-05,
+      "loss": 0.0141,
+      "step": 1290
+    },
+    {
+      "epoch": 323.96,
+      "grad_norm": 0.017192630097270012,
+      "learning_rate": 2.8980526918671253e-05,
+      "loss": 0.0135,
+      "step": 1295
+    },
+    {
+      "epoch": 325.0,
+      "grad_norm": 0.05855363979935646,
+      "learning_rate": 2.8694158075601372e-05,
+      "loss": 0.0115,
+      "step": 1300
+    },
+    {
+      "epoch": 326.32,
+      "grad_norm": 0.0140520129352808,
+      "learning_rate": 2.8407789232531502e-05,
+      "loss": 0.0121,
+      "step": 1305
+    },
+    {
+      "epoch": 327.64,
+      "grad_norm": 0.015486122108995914,
+      "learning_rate": 2.812142038946163e-05,
+      "loss": 0.0131,
+      "step": 1310
+    },
+    {
+      "epoch": 328.96,
+      "grad_norm": 0.014222219586372375,
+      "learning_rate": 2.7835051546391755e-05,
+      "loss": 0.0138,
+      "step": 1315
+    },
+    {
+      "epoch": 330.0,
+      "grad_norm": 0.0894969180226326,
+      "learning_rate": 2.754868270332188e-05,
+      "loss": 0.0149,
+      "step": 1320
+    },
+    {
+      "epoch": 331.32,
+      "grad_norm": 0.015103315934538841,
+      "learning_rate": 2.7262313860252005e-05,
+      "loss": 0.0126,
+      "step": 1325
+    },
+    {
+      "epoch": 332.64,
+      "grad_norm": 0.015136363916099072,
+      "learning_rate": 2.697594501718213e-05,
+      "loss": 0.0135,
+      "step": 1330
+    },
+    {
+      "epoch": 333.96,
+      "grad_norm": 0.019810238853096962,
+      "learning_rate": 2.6689576174112258e-05,
+      "loss": 0.0139,
+      "step": 1335
+    },
+    {
+      "epoch": 335.0,
+      "grad_norm": 0.0372529998421669,
+      "learning_rate": 2.6403207331042384e-05,
+      "loss": 0.0107,
+      "step": 1340
+    },
+    {
+      "epoch": 336.32,
+      "grad_norm": 0.015268836170434952,
+      "learning_rate": 2.611683848797251e-05,
+      "loss": 0.0119,
+      "step": 1345
+    },
+    {
+      "epoch": 337.64,
+      "grad_norm": 0.016926297917962074,
+      "learning_rate": 2.5830469644902637e-05,
+      "loss": 0.0149,
+      "step": 1350
+    },
+    {
+      "epoch": 338.96,
+      "grad_norm": 0.016032274812459946,
+      "learning_rate": 2.554410080183276e-05,
+      "loss": 0.0127,
+      "step": 1355
+    },
+    {
+      "epoch": 340.0,
+      "grad_norm": 0.0720982775092125,
+      "learning_rate": 2.5257731958762887e-05,
+      "loss": 0.0146,
+      "step": 1360
+    },
+    {
+      "epoch": 341.32,
+      "grad_norm": 0.016808465123176575,
+      "learning_rate": 2.4971363115693013e-05,
+      "loss": 0.0144,
+      "step": 1365
+    },
+    {
+      "epoch": 342.64,
+      "grad_norm": 0.013908334076404572,
+      "learning_rate": 2.468499427262314e-05,
+      "loss": 0.0129,
+      "step": 1370
+    },
+    {
+      "epoch": 343.96,
+      "grad_norm": 0.01524080615490675,
+      "learning_rate": 2.4398625429553266e-05,
+      "loss": 0.0132,
+      "step": 1375
+    },
+    {
+      "epoch": 345.0,
+      "grad_norm": 0.08049940317869186,
+      "learning_rate": 2.4112256586483393e-05,
+      "loss": 0.0144,
+      "step": 1380
+    },
+    {
+      "epoch": 346.32,
+      "grad_norm": 0.0138388155028224,
+      "learning_rate": 2.3825887743413516e-05,
+      "loss": 0.0117,
+      "step": 1385
+    },
+    {
+      "epoch": 347.64,
+      "grad_norm": 0.015177235938608646,
+      "learning_rate": 2.3539518900343642e-05,
+      "loss": 0.0127,
+      "step": 1390
+    },
+    {
+      "epoch": 348.96,
+      "grad_norm": 0.012481410056352615,
+      "learning_rate": 2.3253150057273772e-05,
+      "loss": 0.0126,
+      "step": 1395
+    },
+    {
+      "epoch": 350.0,
+      "grad_norm": 0.03498537838459015,
+      "learning_rate": 2.2966781214203895e-05,
+      "loss": 0.0117,
+      "step": 1400
+    },
+    {
+      "epoch": 351.32,
+      "grad_norm": 0.013234886340796947,
+      "learning_rate": 2.268041237113402e-05,
+      "loss": 0.012,
+      "step": 1405
+    },
+    {
+      "epoch": 352.64,
+      "grad_norm": 0.01700565218925476,
+      "learning_rate": 2.2394043528064148e-05,
+      "loss": 0.0136,
+      "step": 1410
+    },
+    {
+      "epoch": 353.96,
+      "grad_norm": 0.016031507402658463,
+      "learning_rate": 2.210767468499427e-05,
+      "loss": 0.0135,
+      "step": 1415
+    },
+    {
+      "epoch": 355.0,
+      "grad_norm": 0.06468836218118668,
+      "learning_rate": 2.18213058419244e-05,
+      "loss": 0.0146,
+      "step": 1420
+    },
+    {
+      "epoch": 356.32,
+      "grad_norm": 0.016307266429066658,
+      "learning_rate": 2.1534936998854528e-05,
+      "loss": 0.0129,
+      "step": 1425
+    },
+    {
+      "epoch": 357.64,
+      "grad_norm": 0.01452616136521101,
+      "learning_rate": 2.124856815578465e-05,
+      "loss": 0.0115,
+      "step": 1430
+    },
+    {
+      "epoch": 358.96,
+      "grad_norm": 0.015597185119986534,
+      "learning_rate": 2.0962199312714777e-05,
+      "loss": 0.0133,
+      "step": 1435
+    },
+    {
+      "epoch": 360.0,
+      "grad_norm": 0.09148745238780975,
+      "learning_rate": 2.0675830469644904e-05,
+      "loss": 0.0137,
+      "step": 1440
+    },
+    {
+      "epoch": 361.32,
+      "grad_norm": 0.01317733246833086,
+      "learning_rate": 2.038946162657503e-05,
+      "loss": 0.0126,
+      "step": 1445
+    },
+    {
+      "epoch": 362.64,
+      "grad_norm": 0.01985546387732029,
+      "learning_rate": 2.0103092783505157e-05,
+      "loss": 0.0127,
+      "step": 1450
+    },
+    {
+      "epoch": 363.96,
+      "grad_norm": 0.013473625294864178,
+      "learning_rate": 1.981672394043528e-05,
+      "loss": 0.0139,
+      "step": 1455
+    },
+    {
+      "epoch": 365.0,
+      "grad_norm": 0.09046448022127151,
+      "learning_rate": 1.9530355097365406e-05,
+      "loss": 0.0158,
+      "step": 1460
+    },
+    {
+      "epoch": 366.32,
+      "grad_norm": 0.02008042298257351,
+      "learning_rate": 1.9243986254295536e-05,
+      "loss": 0.0145,
+      "step": 1465
+    },
+    {
+      "epoch": 367.64,
+      "grad_norm": 0.013885478489100933,
+      "learning_rate": 1.895761741122566e-05,
+      "loss": 0.0121,
+      "step": 1470
+    },
+    {
+      "epoch": 368.96,
+      "grad_norm": 0.01947566121816635,
+      "learning_rate": 1.8671248568155786e-05,
+      "loss": 0.0135,
+      "step": 1475
+    },
+    {
+      "epoch": 370.0,
+      "grad_norm": 0.11254226416349411,
+      "learning_rate": 1.8384879725085912e-05,
+      "loss": 0.0161,
+      "step": 1480
+    },
+    {
+      "epoch": 371.32,
+      "grad_norm": 0.01628114841878414,
+      "learning_rate": 1.809851088201604e-05,
+      "loss": 0.012,
+      "step": 1485
+    },
+    {
+      "epoch": 372.64,
+      "grad_norm": 0.01649070717394352,
+      "learning_rate": 1.7812142038946165e-05,
+      "loss": 0.0133,
+      "step": 1490
+    },
+    {
+      "epoch": 373.96,
+      "grad_norm": 0.01745239645242691,
+      "learning_rate": 1.7525773195876288e-05,
+      "loss": 0.0119,
+      "step": 1495
+    },
+    {
+      "epoch": 375.0,
+      "grad_norm": 0.02520393580198288,
+      "learning_rate": 1.7239404352806415e-05,
+      "loss": 0.0114,
+      "step": 1500
+    },
+    {
+      "epoch": 376.32,
+      "grad_norm": 0.017253026366233826,
+      "learning_rate": 1.695303550973654e-05,
+      "loss": 0.0126,
+      "step": 1505
+    },
+    {
+      "epoch": 377.64,
+      "grad_norm": 0.014182883314788342,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.012,
+      "step": 1510
+    },
+    {
+      "epoch": 378.96,
+      "grad_norm": 0.01444864273071289,
+      "learning_rate": 1.6380297823596794e-05,
+      "loss": 0.0142,
+      "step": 1515
+    },
+    {
+      "epoch": 380.0,
+      "grad_norm": 0.10569846630096436,
+      "learning_rate": 1.609392898052692e-05,
+      "loss": 0.0141,
+      "step": 1520
+    },
+    {
+      "epoch": 381.32,
+      "grad_norm": 0.015410926192998886,
+      "learning_rate": 1.5807560137457044e-05,
+      "loss": 0.0149,
+      "step": 1525
+    },
+    {
+      "epoch": 382.64,
+      "grad_norm": 0.014263981021940708,
+      "learning_rate": 1.5521191294387173e-05,
+      "loss": 0.0125,
+      "step": 1530
+    },
+    {
+      "epoch": 383.96,
+      "grad_norm": 0.0157818291336298,
+      "learning_rate": 1.5234822451317298e-05,
+      "loss": 0.0133,
+      "step": 1535
+    },
+    {
+      "epoch": 385.0,
+      "grad_norm": 0.046719539910554886,
+      "learning_rate": 1.4948453608247423e-05,
+      "loss": 0.0131,
+      "step": 1540
+    },
+    {
+      "epoch": 386.32,
+      "grad_norm": 0.013704204931855202,
+      "learning_rate": 1.466208476517755e-05,
+      "loss": 0.0125,
+      "step": 1545
+    },
+    {
+      "epoch": 387.64,
+      "grad_norm": 0.015599510632455349,
+      "learning_rate": 1.4375715922107674e-05,
+      "loss": 0.0129,
+      "step": 1550
+    },
+    {
+      "epoch": 388.96,
+      "grad_norm": 0.015263325534760952,
+      "learning_rate": 1.40893470790378e-05,
+      "loss": 0.0121,
+      "step": 1555
+    },
+    {
+      "epoch": 390.0,
+      "grad_norm": 0.03270559385418892,
+      "learning_rate": 1.3802978235967929e-05,
+      "loss": 0.0136,
+      "step": 1560
+    },
+    {
+      "epoch": 391.32,
+      "grad_norm": 0.01386338286101818,
+      "learning_rate": 1.3516609392898052e-05,
+      "loss": 0.0122,
+      "step": 1565
+    },
+    {
+      "epoch": 392.64,
+      "grad_norm": 0.015721846371889114,
+      "learning_rate": 1.323024054982818e-05,
+      "loss": 0.0139,
+      "step": 1570
+    },
+    {
+      "epoch": 393.96,
+      "grad_norm": 0.01901036873459816,
+      "learning_rate": 1.2943871706758307e-05,
+      "loss": 0.0121,
+      "step": 1575
+    },
+    {
+      "epoch": 395.0,
+      "grad_norm": 0.06953398138284683,
+      "learning_rate": 1.2657502863688431e-05,
+      "loss": 0.0148,
+      "step": 1580
+    },
+    {
+      "epoch": 396.32,
+      "grad_norm": 0.014572130516171455,
+      "learning_rate": 1.2371134020618558e-05,
+      "loss": 0.0123,
+      "step": 1585
+    },
+    {
+      "epoch": 397.64,
+      "grad_norm": 0.013791495934128761,
+      "learning_rate": 1.2084765177548683e-05,
+      "loss": 0.0129,
+      "step": 1590
+    },
+    {
+      "epoch": 398.96,
+      "grad_norm": 0.014808098785579205,
+      "learning_rate": 1.1798396334478809e-05,
+      "loss": 0.0129,
+      "step": 1595
+    },
+    {
+      "epoch": 400.0,
+      "grad_norm": 0.08156128972768784,
+      "learning_rate": 1.1512027491408934e-05,
+      "loss": 0.0138,
+      "step": 1600
+    },
+    {
+      "epoch": 401.32,
+      "grad_norm": 0.011896721087396145,
+      "learning_rate": 1.1225658648339062e-05,
+      "loss": 0.0122,
+      "step": 1605
+    },
+    {
+      "epoch": 402.64,
+      "grad_norm": 0.013838461600244045,
+      "learning_rate": 1.0939289805269187e-05,
+      "loss": 0.015,
+      "step": 1610
+    },
+    {
+      "epoch": 403.96,
+      "grad_norm": 0.016724299639463425,
+      "learning_rate": 1.0652920962199313e-05,
+      "loss": 0.0142,
+      "step": 1615
+    },
+    {
+      "epoch": 405.0,
+      "grad_norm": 0.08658616989850998,
+      "learning_rate": 1.036655211912944e-05,
+      "loss": 0.0142,
+      "step": 1620
+    },
+    {
+      "epoch": 406.32,
+      "grad_norm": 0.019461670890450478,
+      "learning_rate": 1.0080183276059566e-05,
+      "loss": 0.0153,
+      "step": 1625
+    },
+    {
+      "epoch": 407.64,
+      "grad_norm": 0.013831749558448792,
+      "learning_rate": 9.793814432989691e-06,
+      "loss": 0.0127,
+      "step": 1630
+    },
+    {
+      "epoch": 408.96,
+      "grad_norm": 0.017337650060653687,
+      "learning_rate": 9.507445589919818e-06,
+      "loss": 0.0127,
+      "step": 1635
+    },
+    {
+      "epoch": 410.0,
+      "grad_norm": 0.05681740120053291,
+      "learning_rate": 9.221076746849944e-06,
+      "loss": 0.0122,
+      "step": 1640
+    },
+    {
+      "epoch": 411.32,
+      "grad_norm": 0.012636670842766762,
+      "learning_rate": 8.934707903780069e-06,
+      "loss": 0.0129,
+      "step": 1645
+    },
+    {
+      "epoch": 412.64,
+      "grad_norm": 0.01840255968272686,
+      "learning_rate": 8.648339060710195e-06,
+      "loss": 0.0137,
+      "step": 1650
+    },
+    {
+      "epoch": 413.96,
+      "grad_norm": 0.017703307792544365,
+      "learning_rate": 8.36197021764032e-06,
+      "loss": 0.014,
+      "step": 1655
+    },
+    {
+      "epoch": 415.0,
+      "grad_norm": 0.042530808597803116,
+      "learning_rate": 8.075601374570448e-06,
+      "loss": 0.0119,
+      "step": 1660
+    },
+    {
+      "epoch": 416.32,
+      "grad_norm": 0.019621506333351135,
+      "learning_rate": 7.789232531500573e-06,
+      "loss": 0.0147,
+      "step": 1665
+    },
+    {
+      "epoch": 417.64,
+      "grad_norm": 0.013771059922873974,
+      "learning_rate": 7.502863688430699e-06,
+      "loss": 0.0126,
+      "step": 1670
+    },
+    {
+      "epoch": 418.96,
+      "grad_norm": 0.013901861384510994,
+      "learning_rate": 7.216494845360824e-06,
+      "loss": 0.0122,
+      "step": 1675
+    },
+    {
+      "epoch": 420.0,
+      "grad_norm": 0.0342877171933651,
+      "learning_rate": 6.930126002290952e-06,
+      "loss": 0.0116,
+      "step": 1680
+    },
+    {
+      "epoch": 421.32,
+      "grad_norm": 0.016494231298565865,
+      "learning_rate": 6.643757159221077e-06,
+      "loss": 0.0126,
+      "step": 1685
+    },
+    {
+      "epoch": 422.64,
+      "grad_norm": 0.01748238503932953,
+      "learning_rate": 6.357388316151203e-06,
+      "loss": 0.0117,
+      "step": 1690
+    },
+    {
+      "epoch": 423.96,
+      "grad_norm": 0.01810644380748272,
+      "learning_rate": 6.071019473081329e-06,
+      "loss": 0.0124,
+      "step": 1695
+    },
+    {
+      "epoch": 425.0,
+      "grad_norm": 0.08766311407089233,
+      "learning_rate": 5.784650630011455e-06,
+      "loss": 0.0162,
+      "step": 1700
+    },
+    {
+      "epoch": 426.32,
+      "grad_norm": 0.01534106582403183,
+      "learning_rate": 5.498281786941581e-06,
+      "loss": 0.0117,
+      "step": 1705
+    },
+    {
+      "epoch": 427.64,
+      "grad_norm": 0.01711273193359375,
+      "learning_rate": 5.211912943871707e-06,
+      "loss": 0.0127,
+      "step": 1710
+    },
+    {
+      "epoch": 428.96,
+      "grad_norm": 0.013884472660720348,
+      "learning_rate": 4.925544100801833e-06,
+      "loss": 0.0127,
+      "step": 1715
+    },
+    {
+      "epoch": 430.0,
+      "grad_norm": 0.04232710972428322,
+      "learning_rate": 4.639175257731959e-06,
+      "loss": 0.0114,
+      "step": 1720
+    },
+    {
+      "epoch": 431.32,
+      "grad_norm": 0.014072608202695847,
+      "learning_rate": 4.352806414662085e-06,
+      "loss": 0.0126,
+      "step": 1725
+    },
+    {
+      "epoch": 432.64,
+      "grad_norm": 0.016274895519018173,
+      "learning_rate": 4.066437571592211e-06,
+      "loss": 0.013,
+      "step": 1730
+    },
+    {
+      "epoch": 433.96,
+      "grad_norm": 0.014604011550545692,
+      "learning_rate": 3.7800687285223365e-06,
+      "loss": 0.0124,
+      "step": 1735
+    },
+    {
+      "epoch": 435.0,
+      "grad_norm": 0.10355663299560547,
+      "learning_rate": 3.493699885452463e-06,
+      "loss": 0.0146,
+      "step": 1740
+    },
+    {
+      "epoch": 436.32,
+      "grad_norm": 0.01530387345701456,
+      "learning_rate": 3.2073310423825886e-06,
+      "loss": 0.0144,
+      "step": 1745
+    },
+    {
+      "epoch": 437.64,
+      "grad_norm": 0.01776758022606373,
+      "learning_rate": 2.920962199312715e-06,
+      "loss": 0.0123,
+      "step": 1750
+    },
+    {
+      "epoch": 438.96,
+      "grad_norm": 0.02176729030907154,
+      "learning_rate": 2.6345933562428407e-06,
+      "loss": 0.0143,
+      "step": 1755
+    },
+    {
+      "epoch": 440.0,
+      "grad_norm": 0.08045906573534012,
+      "learning_rate": 2.3482245131729668e-06,
+      "loss": 0.0144,
+      "step": 1760
+    },
+    {
+      "epoch": 441.32,
+      "grad_norm": 0.01481122337281704,
+      "learning_rate": 2.061855670103093e-06,
+      "loss": 0.0139,
+      "step": 1765
+    },
+    {
+      "epoch": 442.64,
+      "grad_norm": 0.016810059547424316,
+      "learning_rate": 1.7754868270332189e-06,
+      "loss": 0.014,
+      "step": 1770
+    },
+    {
+      "epoch": 443.96,
+      "grad_norm": 0.014532101340591908,
+      "learning_rate": 1.4891179839633447e-06,
+      "loss": 0.0116,
+      "step": 1775
+    },
+    {
+      "epoch": 445.0,
+      "grad_norm": 0.03813250735402107,
+      "learning_rate": 1.202749140893471e-06,
+      "loss": 0.0128,
+      "step": 1780
+    },
+    {
+      "epoch": 446.32,
+      "grad_norm": 0.014029953628778458,
+      "learning_rate": 9.163802978235968e-07,
+      "loss": 0.0145,
+      "step": 1785
+    },
+    {
+      "epoch": 447.64,
+      "grad_norm": 0.01374804973602295,
+      "learning_rate": 6.300114547537229e-07,
+      "loss": 0.0137,
+      "step": 1790
+    },
+    {
+      "epoch": 448.96,
+      "grad_norm": 0.014675168320536613,
+      "learning_rate": 3.436426116838488e-07,
+      "loss": 0.0126,
+      "step": 1795
+    },
+    {
+      "epoch": 450.0,
+      "grad_norm": 0.04528183490037918,
+      "learning_rate": 5.72737686139748e-08,
+      "loss": 0.0139,
+      "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
+}

Competition_Math/group_00/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

Competition_Math/group_00/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": [
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Competition_Math/group_00/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
+}

Competition_Math/group_00/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 %}

Competition_Math/group_00/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
+  }
+}

Competition_Math/group_00/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
+}

Competition_Math/group_00/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": 4.598043441772461,
+      "learning_rate": 0.0,
+      "loss": 0.9577,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 3.2691659927368164,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.914,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.4407647848129272,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.87,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 0.873967170715332,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 0.7194,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.5684808492660522,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.485,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.31015607714653015,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.4448,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.2658279538154602,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.4004,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.24357278645038605,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.3975,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.7138969302177429,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.3541,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.3199204206466675,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.2981,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 0.3794819414615631,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.2975,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 0.6489832997322083,
+      "learning_rate": 0.0001,
+      "loss": 0.2113,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.9405580759048462,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1426,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 0.5083445310592651,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.1212,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 0.4943920969963074,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0843,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 0.7678825259208679,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0484,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 1.9925947189331055,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.0444,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.2645427882671356,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0288,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 0.1064828559756279,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.0301,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.12416807562112808,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.0196,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.2526699900627136,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0203,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.09203815460205078,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0201,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.07873351126909256,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0162,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.10604001581668854,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.0191,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 1.7986263036727905,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0198,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.07677727192640305,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.0158,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.1571263074874878,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0152,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.06132940948009491,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.0137,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.09364927560091019,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.016,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.04978128522634506,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0161,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.03882812336087227,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0154,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.04475203529000282,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0164,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.13846606016159058,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0161,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.033312492072582245,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.0135,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.041062209755182266,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0135,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.032531533390283585,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0135,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.1364850103855133,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0149,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.042139116674661636,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0136,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.03540545701980591,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0132,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.04514731466770172,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0175,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.14643007516860962,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0152,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.03208281844854355,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.0144,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.03130023553967476,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.0168,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.03348194435238838,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0141,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.05507143586874008,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0149,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.019802691414952278,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0149,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.025274671614170074,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.016,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.0396709069609642,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0156,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.11217641085386276,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0165,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.03045077621936798,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0154,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.030307715758681297,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0149,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.028285281732678413,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0139,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.1250770390033722,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0187,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.025621576234698296,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0135,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.021983368322253227,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0149,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.02598453126847744,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0139,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.08075019717216492,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0148,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.0245928093791008,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.0159,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.026031415909528732,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.0144,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.02940714731812477,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0146,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.0966266617178917,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.014,
+      "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
+}

Competition_Math/group_00/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

Competition_Math/group_00/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": [
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Competition_Math/group_00/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
+}

Competition_Math/group_00/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 %}

Competition_Math/group_00/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
+  }
+}

Competition_Math/group_00/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
+}

Competition_Math/group_00/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": 4.598043441772461,
+      "learning_rate": 0.0,
+      "loss": 0.9577,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 3.2691659927368164,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.914,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.4407647848129272,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.87,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 0.873967170715332,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 0.7194,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.5684808492660522,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.485,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.31015607714653015,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.4448,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.2658279538154602,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.4004,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.24357278645038605,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.3975,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.7138969302177429,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.3541,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.3199204206466675,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.2981,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 0.3794819414615631,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.2975,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 0.6489832997322083,
+      "learning_rate": 0.0001,
+      "loss": 0.2113,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.9405580759048462,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1426,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 0.5083445310592651,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.1212,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 0.4943920969963074,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0843,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 0.7678825259208679,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0484,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 1.9925947189331055,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.0444,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.2645427882671356,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0288,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 0.1064828559756279,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.0301,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.12416807562112808,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.0196,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.2526699900627136,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0203,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.09203815460205078,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0201,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.07873351126909256,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0162,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.10604001581668854,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.0191,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 1.7986263036727905,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0198,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.07677727192640305,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.0158,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.1571263074874878,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0152,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.06132940948009491,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.0137,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.09364927560091019,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.016,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.04978128522634506,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0161,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.03882812336087227,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0154,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.04475203529000282,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0164,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.13846606016159058,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0161,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.033312492072582245,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.0135,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.041062209755182266,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0135,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.032531533390283585,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0135,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.1364850103855133,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0149,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.042139116674661636,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0136,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.03540545701980591,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0132,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.04514731466770172,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0175,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.14643007516860962,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0152,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.03208281844854355,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.0144,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.03130023553967476,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.0168,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.03348194435238838,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0141,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.05507143586874008,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0149,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.019802691414952278,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0149,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.025274671614170074,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.016,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.0396709069609642,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0156,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.11217641085386276,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0165,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.03045077621936798,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0154,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.030307715758681297,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0149,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.028285281732678413,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0139,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.1250770390033722,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0187,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.025621576234698296,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0135,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.021983368322253227,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0149,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.02598453126847744,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0139,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.08075019717216492,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0148,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.0245928093791008,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.0159,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.026031415909528732,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.0144,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.02940714731812477,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0146,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.0966266617178917,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.014,
+      "step": 300
+    },
+    {
+      "epoch": 76.32,
+      "grad_norm": 0.028764601796865463,
+      "learning_rate": 8.56815578465063e-05,
+      "loss": 0.0132,
+      "step": 305
+    },
+    {
+      "epoch": 77.64,
+      "grad_norm": 0.027627065777778625,
+      "learning_rate": 8.539518900343643e-05,
+      "loss": 0.0166,
+      "step": 310
+    },
+    {
+      "epoch": 78.96,
+      "grad_norm": 0.026004405692219734,
+      "learning_rate": 8.510882016036655e-05,
+      "loss": 0.0148,
+      "step": 315
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.08327600359916687,
+      "learning_rate": 8.482245131729668e-05,
+      "loss": 0.016,
+      "step": 320
+    },
+    {
+      "epoch": 81.32,
+      "grad_norm": 0.025960935279726982,
+      "learning_rate": 8.453608247422681e-05,
+      "loss": 0.0143,
+      "step": 325
+    },
+    {
+      "epoch": 82.64,
+      "grad_norm": 0.025417521595954895,
+      "learning_rate": 8.424971363115693e-05,
+      "loss": 0.014,
+      "step": 330
+    },
+    {
+      "epoch": 83.96,
+      "grad_norm": 0.025654327124357224,
+      "learning_rate": 8.396334478808706e-05,
+      "loss": 0.0128,
+      "step": 335
+    },
+    {
+      "epoch": 85.0,
+      "grad_norm": 0.10201112926006317,
+      "learning_rate": 8.367697594501719e-05,
+      "loss": 0.0142,
+      "step": 340
+    },
+    {
+      "epoch": 86.32,
+      "grad_norm": 0.02470439113676548,
+      "learning_rate": 8.339060710194731e-05,
+      "loss": 0.0127,
+      "step": 345
+    },
+    {
+      "epoch": 87.64,
+      "grad_norm": 0.0236374419182539,
+      "learning_rate": 8.310423825887744e-05,
+      "loss": 0.0153,
+      "step": 350
+    },
+    {
+      "epoch": 88.96,
+      "grad_norm": 0.03599975258111954,
+      "learning_rate": 8.281786941580757e-05,
+      "loss": 0.0133,
+      "step": 355
+    },
+    {
+      "epoch": 90.0,
+      "grad_norm": 0.08355200290679932,
+      "learning_rate": 8.253150057273768e-05,
+      "loss": 0.0144,
+      "step": 360
+    },
+    {
+      "epoch": 91.32,
+      "grad_norm": 0.020355794578790665,
+      "learning_rate": 8.224513172966782e-05,
+      "loss": 0.014,
+      "step": 365
+    },
+    {
+      "epoch": 92.64,
+      "grad_norm": 0.021856721490621567,
+      "learning_rate": 8.195876288659795e-05,
+      "loss": 0.0166,
+      "step": 370
+    },
+    {
+      "epoch": 93.96,
+      "grad_norm": 0.03352021053433418,
+      "learning_rate": 8.167239404352807e-05,
+      "loss": 0.0133,
+      "step": 375
+    },
+    {
+      "epoch": 95.0,
+      "grad_norm": 0.050965987145900726,
+      "learning_rate": 8.13860252004582e-05,
+      "loss": 0.0111,
+      "step": 380
+    },
+    {
+      "epoch": 96.32,
+      "grad_norm": 0.01907683163881302,
+      "learning_rate": 8.109965635738833e-05,
+      "loss": 0.0123,
+      "step": 385
+    },
+    {
+      "epoch": 97.64,
+      "grad_norm": 0.017776427790522575,
+      "learning_rate": 8.081328751431845e-05,
+      "loss": 0.0141,
+      "step": 390
+    },
+    {
+      "epoch": 98.96,
+      "grad_norm": 0.02410067617893219,
+      "learning_rate": 8.052691867124858e-05,
+      "loss": 0.0147,
+      "step": 395
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.11242590099573135,
+      "learning_rate": 8.02405498281787e-05,
+      "loss": 0.0164,
+      "step": 400
+    },
+    {
+      "epoch": 101.32,
+      "grad_norm": 0.024096814915537834,
+      "learning_rate": 7.995418098510883e-05,
+      "loss": 0.0143,
+      "step": 405
+    },
+    {
+      "epoch": 102.64,
+      "grad_norm": 0.02899334393441677,
+      "learning_rate": 7.966781214203894e-05,
+      "loss": 0.0155,
+      "step": 410
+    },
+    {
+      "epoch": 103.96,
+      "grad_norm": 0.023235289379954338,
+      "learning_rate": 7.938144329896907e-05,
+      "loss": 0.0124,
+      "step": 415
+    },
+    {
+      "epoch": 105.0,
+      "grad_norm": 0.0693734735250473,
+      "learning_rate": 7.90950744558992e-05,
+      "loss": 0.0137,
+      "step": 420
+    },
+    {
+      "epoch": 106.32,
+      "grad_norm": 0.019512519240379333,
+      "learning_rate": 7.880870561282932e-05,
+      "loss": 0.0142,
+      "step": 425
+    },
+    {
+      "epoch": 107.64,
+      "grad_norm": 0.02140176109969616,
+      "learning_rate": 7.852233676975945e-05,
+      "loss": 0.0141,
+      "step": 430
+    },
+    {
+      "epoch": 108.96,
+      "grad_norm": 0.022468585520982742,
+      "learning_rate": 7.823596792668958e-05,
+      "loss": 0.0122,
+      "step": 435
+    },
+    {
+      "epoch": 110.0,
+      "grad_norm": 0.0380476713180542,
+      "learning_rate": 7.79495990836197e-05,
+      "loss": 0.0136,
+      "step": 440
+    },
+    {
+      "epoch": 111.32,
+      "grad_norm": 0.018203549087047577,
+      "learning_rate": 7.766323024054983e-05,
+      "loss": 0.0119,
+      "step": 445
+    },
+    {
+      "epoch": 112.64,
+      "grad_norm": 0.02083701454102993,
+      "learning_rate": 7.737686139747996e-05,
+      "loss": 0.0159,
+      "step": 450
+    },
+    {
+      "epoch": 113.96,
+      "grad_norm": 0.02744678594172001,
+      "learning_rate": 7.709049255441008e-05,
+      "loss": 0.0138,
+      "step": 455
+    },
+    {
+      "epoch": 115.0,
+      "grad_norm": 0.05891157686710358,
+      "learning_rate": 7.680412371134021e-05,
+      "loss": 0.0123,
+      "step": 460
+    },
+    {
+      "epoch": 116.32,
+      "grad_norm": 0.02845454029738903,
+      "learning_rate": 7.651775486827034e-05,
+      "loss": 0.0139,
+      "step": 465
+    },
+    {
+      "epoch": 117.64,
+      "grad_norm": 0.020904691889882088,
+      "learning_rate": 7.623138602520046e-05,
+      "loss": 0.013,
+      "step": 470
+    },
+    {
+      "epoch": 118.96,
+      "grad_norm": 0.020568421110510826,
+      "learning_rate": 7.594501718213059e-05,
+      "loss": 0.0126,
+      "step": 475
+    },
+    {
+      "epoch": 120.0,
+      "grad_norm": 0.11525513231754303,
+      "learning_rate": 7.565864833906071e-05,
+      "loss": 0.0149,
+      "step": 480
+    },
+    {
+      "epoch": 121.32,
+      "grad_norm": 0.02282075583934784,
+      "learning_rate": 7.537227949599084e-05,
+      "loss": 0.0145,
+      "step": 485
+    },
+    {
+      "epoch": 122.64,
+      "grad_norm": 0.021044986322522163,
+      "learning_rate": 7.508591065292097e-05,
+      "loss": 0.0118,
+      "step": 490
+    },
+    {
+      "epoch": 123.96,
+      "grad_norm": 0.026140881702303886,
+      "learning_rate": 7.47995418098511e-05,
+      "loss": 0.0134,
+      "step": 495
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 0.08347874134778976,
+      "learning_rate": 7.451317296678122e-05,
+      "loss": 0.0134,
+      "step": 500
+    },
+    {
+      "epoch": 126.32,
+      "grad_norm": 0.021540338173508644,
+      "learning_rate": 7.422680412371135e-05,
+      "loss": 0.0124,
+      "step": 505
+    },
+    {
+      "epoch": 127.64,
+      "grad_norm": 0.018244560807943344,
+      "learning_rate": 7.394043528064147e-05,
+      "loss": 0.0133,
+      "step": 510
+    },
+    {
+      "epoch": 128.96,
+      "grad_norm": 0.0179904717952013,
+      "learning_rate": 7.36540664375716e-05,
+      "loss": 0.0131,
+      "step": 515
+    },
+    {
+      "epoch": 130.0,
+      "grad_norm": 0.0700739249587059,
+      "learning_rate": 7.336769759450171e-05,
+      "loss": 0.0151,
+      "step": 520
+    },
+    {
+      "epoch": 131.32,
+      "grad_norm": 0.02473938651382923,
+      "learning_rate": 7.308132875143184e-05,
+      "loss": 0.0139,
+      "step": 525
+    },
+    {
+      "epoch": 132.64,
+      "grad_norm": 0.016669029369950294,
+      "learning_rate": 7.279495990836197e-05,
+      "loss": 0.0129,
+      "step": 530
+    },
+    {
+      "epoch": 133.96,
+      "grad_norm": 0.0206622127443552,
+      "learning_rate": 7.250859106529209e-05,
+      "loss": 0.0131,
+      "step": 535
+    },
+    {
+      "epoch": 135.0,
+      "grad_norm": 0.1013081893324852,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.0141,
+      "step": 540
+    },
+    {
+      "epoch": 136.32,
+      "grad_norm": 0.02413194440305233,
+      "learning_rate": 7.193585337915235e-05,
+      "loss": 0.0136,
+      "step": 545
+    },
+    {
+      "epoch": 137.64,
+      "grad_norm": 0.02023296430706978,
+      "learning_rate": 7.164948453608247e-05,
+      "loss": 0.0134,
+      "step": 550
+    },
+    {
+      "epoch": 138.96,
+      "grad_norm": 0.018895283341407776,
+      "learning_rate": 7.136311569301261e-05,
+      "loss": 0.012,
+      "step": 555
+    },
+    {
+      "epoch": 140.0,
+      "grad_norm": 0.08102845400571823,
+      "learning_rate": 7.107674684994274e-05,
+      "loss": 0.0142,
+      "step": 560
+    },
+    {
+      "epoch": 141.32,
+      "grad_norm": 0.019933724775910378,
+      "learning_rate": 7.079037800687286e-05,
+      "loss": 0.0143,
+      "step": 565
+    },
+    {
+      "epoch": 142.64,
+      "grad_norm": 0.02834722027182579,
+      "learning_rate": 7.050400916380299e-05,
+      "loss": 0.0136,
+      "step": 570
+    },
+    {
+      "epoch": 143.96,
+      "grad_norm": 0.02353634126484394,
+      "learning_rate": 7.02176403207331e-05,
+      "loss": 0.0139,
+      "step": 575
+    },
+    {
+      "epoch": 145.0,
+      "grad_norm": 0.042016856372356415,
+      "learning_rate": 6.993127147766323e-05,
+      "loss": 0.0151,
+      "step": 580
+    },
+    {
+      "epoch": 146.32,
+      "grad_norm": 0.020217517390847206,
+      "learning_rate": 6.964490263459336e-05,
+      "loss": 0.0131,
+      "step": 585
+    },
+    {
+      "epoch": 147.64,
+      "grad_norm": 0.019066426903009415,
+      "learning_rate": 6.935853379152348e-05,
+      "loss": 0.0138,
+      "step": 590
+    },
+    {
+      "epoch": 148.96,
+      "grad_norm": 0.023700350895524025,
+      "learning_rate": 6.907216494845361e-05,
+      "loss": 0.0157,
+      "step": 595
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 0.10881764441728592,
+      "learning_rate": 6.878579610538374e-05,
+      "loss": 0.0145,
+      "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
+}

Competition_Math/group_00/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

Competition_Math/group_00/checkpoints/checkpoint-900/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": [
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Competition_Math/group_00/checkpoints/checkpoint-900/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
+}

Competition_Math/group_00/checkpoints/checkpoint-900/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 %}

Competition_Math/group_00/checkpoints/checkpoint-900/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
+  }
+}

Competition_Math/group_00/checkpoints/checkpoint-900/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
+}

Competition_Math/group_00/checkpoints/checkpoint-900/trainer_state.json

@@ -0,0 +1,1301 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 225.0,
+  "eval_steps": 500,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.598043441772461,
+      "learning_rate": 0.0,
+      "loss": 0.9577,
+      "step": 1
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 3.2691659927368164,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.914,
+      "step": 5
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.4407647848129272,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.87,
+      "step": 10
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 0.873967170715332,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 0.7194,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.5684808492660522,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.485,
+      "step": 20
+    },
+    {
+      "epoch": 6.32,
+      "grad_norm": 0.31015607714653015,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.4448,
+      "step": 25
+    },
+    {
+      "epoch": 7.64,
+      "grad_norm": 0.2658279538154602,
+      "learning_rate": 5.370370370370371e-05,
+      "loss": 0.4004,
+      "step": 30
+    },
+    {
+      "epoch": 8.96,
+      "grad_norm": 0.24357278645038605,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.3975,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.7138969302177429,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.3541,
+      "step": 40
+    },
+    {
+      "epoch": 11.32,
+      "grad_norm": 0.3199204206466675,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.2981,
+      "step": 45
+    },
+    {
+      "epoch": 12.64,
+      "grad_norm": 0.3794819414615631,
+      "learning_rate": 9.074074074074075e-05,
+      "loss": 0.2975,
+      "step": 50
+    },
+    {
+      "epoch": 13.96,
+      "grad_norm": 0.6489832997322083,
+      "learning_rate": 0.0001,
+      "loss": 0.2113,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.9405580759048462,
+      "learning_rate": 9.971363115693013e-05,
+      "loss": 0.1426,
+      "step": 60
+    },
+    {
+      "epoch": 16.32,
+      "grad_norm": 0.5083445310592651,
+      "learning_rate": 9.942726231386026e-05,
+      "loss": 0.1212,
+      "step": 65
+    },
+    {
+      "epoch": 17.64,
+      "grad_norm": 0.4943920969963074,
+      "learning_rate": 9.914089347079038e-05,
+      "loss": 0.0843,
+      "step": 70
+    },
+    {
+      "epoch": 18.96,
+      "grad_norm": 0.7678825259208679,
+      "learning_rate": 9.885452462772051e-05,
+      "loss": 0.0484,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 1.9925947189331055,
+      "learning_rate": 9.856815578465064e-05,
+      "loss": 0.0444,
+      "step": 80
+    },
+    {
+      "epoch": 21.32,
+      "grad_norm": 0.2645427882671356,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 0.0288,
+      "step": 85
+    },
+    {
+      "epoch": 22.64,
+      "grad_norm": 0.1064828559756279,
+      "learning_rate": 9.799541809851088e-05,
+      "loss": 0.0301,
+      "step": 90
+    },
+    {
+      "epoch": 23.96,
+      "grad_norm": 0.12416807562112808,
+      "learning_rate": 9.7709049255441e-05,
+      "loss": 0.0196,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.2526699900627136,
+      "learning_rate": 9.742268041237114e-05,
+      "loss": 0.0203,
+      "step": 100
+    },
+    {
+      "epoch": 26.32,
+      "grad_norm": 0.09203815460205078,
+      "learning_rate": 9.713631156930127e-05,
+      "loss": 0.0201,
+      "step": 105
+    },
+    {
+      "epoch": 27.64,
+      "grad_norm": 0.07873351126909256,
+      "learning_rate": 9.68499427262314e-05,
+      "loss": 0.0162,
+      "step": 110
+    },
+    {
+      "epoch": 28.96,
+      "grad_norm": 0.10604001581668854,
+      "learning_rate": 9.656357388316152e-05,
+      "loss": 0.0191,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 1.7986263036727905,
+      "learning_rate": 9.627720504009165e-05,
+      "loss": 0.0198,
+      "step": 120
+    },
+    {
+      "epoch": 31.32,
+      "grad_norm": 0.07677727192640305,
+      "learning_rate": 9.599083619702178e-05,
+      "loss": 0.0158,
+      "step": 125
+    },
+    {
+      "epoch": 32.64,
+      "grad_norm": 0.1571263074874878,
+      "learning_rate": 9.57044673539519e-05,
+      "loss": 0.0152,
+      "step": 130
+    },
+    {
+      "epoch": 33.96,
+      "grad_norm": 0.06132940948009491,
+      "learning_rate": 9.541809851088203e-05,
+      "loss": 0.0137,
+      "step": 135
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 0.09364927560091019,
+      "learning_rate": 9.513172966781214e-05,
+      "loss": 0.016,
+      "step": 140
+    },
+    {
+      "epoch": 36.32,
+      "grad_norm": 0.04978128522634506,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.0161,
+      "step": 145
+    },
+    {
+      "epoch": 37.64,
+      "grad_norm": 0.03882812336087227,
+      "learning_rate": 9.45589919816724e-05,
+      "loss": 0.0154,
+      "step": 150
+    },
+    {
+      "epoch": 38.96,
+      "grad_norm": 0.04475203529000282,
+      "learning_rate": 9.427262313860252e-05,
+      "loss": 0.0164,
+      "step": 155
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.13846606016159058,
+      "learning_rate": 9.398625429553265e-05,
+      "loss": 0.0161,
+      "step": 160
+    },
+    {
+      "epoch": 41.32,
+      "grad_norm": 0.033312492072582245,
+      "learning_rate": 9.369988545246277e-05,
+      "loss": 0.0135,
+      "step": 165
+    },
+    {
+      "epoch": 42.64,
+      "grad_norm": 0.041062209755182266,
+      "learning_rate": 9.34135166093929e-05,
+      "loss": 0.0135,
+      "step": 170
+    },
+    {
+      "epoch": 43.96,
+      "grad_norm": 0.032531533390283585,
+      "learning_rate": 9.312714776632303e-05,
+      "loss": 0.0135,
+      "step": 175
+    },
+    {
+      "epoch": 45.0,
+      "grad_norm": 0.1364850103855133,
+      "learning_rate": 9.284077892325315e-05,
+      "loss": 0.0149,
+      "step": 180
+    },
+    {
+      "epoch": 46.32,
+      "grad_norm": 0.042139116674661636,
+      "learning_rate": 9.255441008018328e-05,
+      "loss": 0.0136,
+      "step": 185
+    },
+    {
+      "epoch": 47.64,
+      "grad_norm": 0.03540545701980591,
+      "learning_rate": 9.22680412371134e-05,
+      "loss": 0.0132,
+      "step": 190
+    },
+    {
+      "epoch": 48.96,
+      "grad_norm": 0.04514731466770172,
+      "learning_rate": 9.198167239404353e-05,
+      "loss": 0.0175,
+      "step": 195
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 0.14643007516860962,
+      "learning_rate": 9.169530355097366e-05,
+      "loss": 0.0152,
+      "step": 200
+    },
+    {
+      "epoch": 51.32,
+      "grad_norm": 0.03208281844854355,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 0.0144,
+      "step": 205
+    },
+    {
+      "epoch": 52.64,
+      "grad_norm": 0.03130023553967476,
+      "learning_rate": 9.112256586483391e-05,
+      "loss": 0.0168,
+      "step": 210
+    },
+    {
+      "epoch": 53.96,
+      "grad_norm": 0.03348194435238838,
+      "learning_rate": 9.083619702176404e-05,
+      "loss": 0.0141,
+      "step": 215
+    },
+    {
+      "epoch": 55.0,
+      "grad_norm": 0.05507143586874008,
+      "learning_rate": 9.054982817869416e-05,
+      "loss": 0.0149,
+      "step": 220
+    },
+    {
+      "epoch": 56.32,
+      "grad_norm": 0.019802691414952278,
+      "learning_rate": 9.026345933562429e-05,
+      "loss": 0.0149,
+      "step": 225
+    },
+    {
+      "epoch": 57.64,
+      "grad_norm": 0.025274671614170074,
+      "learning_rate": 8.997709049255442e-05,
+      "loss": 0.016,
+      "step": 230
+    },
+    {
+      "epoch": 58.96,
+      "grad_norm": 0.0396709069609642,
+      "learning_rate": 8.969072164948454e-05,
+      "loss": 0.0156,
+      "step": 235
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.11217641085386276,
+      "learning_rate": 8.940435280641467e-05,
+      "loss": 0.0165,
+      "step": 240
+    },
+    {
+      "epoch": 61.32,
+      "grad_norm": 0.03045077621936798,
+      "learning_rate": 8.91179839633448e-05,
+      "loss": 0.0154,
+      "step": 245
+    },
+    {
+      "epoch": 62.64,
+      "grad_norm": 0.030307715758681297,
+      "learning_rate": 8.883161512027491e-05,
+      "loss": 0.0149,
+      "step": 250
+    },
+    {
+      "epoch": 63.96,
+      "grad_norm": 0.028285281732678413,
+      "learning_rate": 8.854524627720504e-05,
+      "loss": 0.0139,
+      "step": 255
+    },
+    {
+      "epoch": 65.0,
+      "grad_norm": 0.1250770390033722,
+      "learning_rate": 8.825887743413516e-05,
+      "loss": 0.0187,
+      "step": 260
+    },
+    {
+      "epoch": 66.32,
+      "grad_norm": 0.025621576234698296,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 0.0135,
+      "step": 265
+    },
+    {
+      "epoch": 67.64,
+      "grad_norm": 0.021983368322253227,
+      "learning_rate": 8.768613974799542e-05,
+      "loss": 0.0149,
+      "step": 270
+    },
+    {
+      "epoch": 68.96,
+      "grad_norm": 0.02598453126847744,
+      "learning_rate": 8.739977090492554e-05,
+      "loss": 0.0139,
+      "step": 275
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 0.08075019717216492,
+      "learning_rate": 8.711340206185567e-05,
+      "loss": 0.0148,
+      "step": 280
+    },
+    {
+      "epoch": 71.32,
+      "grad_norm": 0.0245928093791008,
+      "learning_rate": 8.682703321878581e-05,
+      "loss": 0.0159,
+      "step": 285
+    },
+    {
+      "epoch": 72.64,
+      "grad_norm": 0.026031415909528732,
+      "learning_rate": 8.654066437571594e-05,
+      "loss": 0.0144,
+      "step": 290
+    },
+    {
+      "epoch": 73.96,
+      "grad_norm": 0.02940714731812477,
+      "learning_rate": 8.625429553264606e-05,
+      "loss": 0.0146,
+      "step": 295
+    },
+    {
+      "epoch": 75.0,
+      "grad_norm": 0.0966266617178917,
+      "learning_rate": 8.596792668957619e-05,
+      "loss": 0.014,
+      "step": 300
+    },
+    {
+      "epoch": 76.32,
+      "grad_norm": 0.028764601796865463,
+      "learning_rate": 8.56815578465063e-05,
+      "loss": 0.0132,
+      "step": 305
+    },
+    {
+      "epoch": 77.64,
+      "grad_norm": 0.027627065777778625,
+      "learning_rate": 8.539518900343643e-05,
+      "loss": 0.0166,
+      "step": 310
+    },
+    {
+      "epoch": 78.96,
+      "grad_norm": 0.026004405692219734,
+      "learning_rate": 8.510882016036655e-05,
+      "loss": 0.0148,
+      "step": 315
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.08327600359916687,
+      "learning_rate": 8.482245131729668e-05,
+      "loss": 0.016,
+      "step": 320
+    },
+    {
+      "epoch": 81.32,
+      "grad_norm": 0.025960935279726982,
+      "learning_rate": 8.453608247422681e-05,
+      "loss": 0.0143,
+      "step": 325
+    },
+    {
+      "epoch": 82.64,
+      "grad_norm": 0.025417521595954895,
+      "learning_rate": 8.424971363115693e-05,
+      "loss": 0.014,
+      "step": 330
+    },
+    {
+      "epoch": 83.96,
+      "grad_norm": 0.025654327124357224,
+      "learning_rate": 8.396334478808706e-05,
+      "loss": 0.0128,
+      "step": 335
+    },
+    {
+      "epoch": 85.0,
+      "grad_norm": 0.10201112926006317,
+      "learning_rate": 8.367697594501719e-05,
+      "loss": 0.0142,
+      "step": 340
+    },
+    {
+      "epoch": 86.32,
+      "grad_norm": 0.02470439113676548,
+      "learning_rate": 8.339060710194731e-05,
+      "loss": 0.0127,
+      "step": 345
+    },
+    {
+      "epoch": 87.64,
+      "grad_norm": 0.0236374419182539,
+      "learning_rate": 8.310423825887744e-05,
+      "loss": 0.0153,
+      "step": 350
+    },
+    {
+      "epoch": 88.96,
+      "grad_norm": 0.03599975258111954,
+      "learning_rate": 8.281786941580757e-05,
+      "loss": 0.0133,
+      "step": 355
+    },
+    {
+      "epoch": 90.0,
+      "grad_norm": 0.08355200290679932,
+      "learning_rate": 8.253150057273768e-05,
+      "loss": 0.0144,
+      "step": 360
+    },
+    {
+      "epoch": 91.32,
+      "grad_norm": 0.020355794578790665,
+      "learning_rate": 8.224513172966782e-05,
+      "loss": 0.014,
+      "step": 365
+    },
+    {
+      "epoch": 92.64,
+      "grad_norm": 0.021856721490621567,
+      "learning_rate": 8.195876288659795e-05,
+      "loss": 0.0166,
+      "step": 370
+    },
+    {
+      "epoch": 93.96,
+      "grad_norm": 0.03352021053433418,
+      "learning_rate": 8.167239404352807e-05,
+      "loss": 0.0133,
+      "step": 375
+    },
+    {
+      "epoch": 95.0,
+      "grad_norm": 0.050965987145900726,
+      "learning_rate": 8.13860252004582e-05,
+      "loss": 0.0111,
+      "step": 380
+    },
+    {
+      "epoch": 96.32,
+      "grad_norm": 0.01907683163881302,
+      "learning_rate": 8.109965635738833e-05,
+      "loss": 0.0123,
+      "step": 385
+    },
+    {
+      "epoch": 97.64,
+      "grad_norm": 0.017776427790522575,
+      "learning_rate": 8.081328751431845e-05,
+      "loss": 0.0141,
+      "step": 390
+    },
+    {
+      "epoch": 98.96,
+      "grad_norm": 0.02410067617893219,
+      "learning_rate": 8.052691867124858e-05,
+      "loss": 0.0147,
+      "step": 395
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.11242590099573135,
+      "learning_rate": 8.02405498281787e-05,
+      "loss": 0.0164,
+      "step": 400
+    },
+    {
+      "epoch": 101.32,
+      "grad_norm": 0.024096814915537834,
+      "learning_rate": 7.995418098510883e-05,
+      "loss": 0.0143,
+      "step": 405
+    },
+    {
+      "epoch": 102.64,
+      "grad_norm": 0.02899334393441677,
+      "learning_rate": 7.966781214203894e-05,
+      "loss": 0.0155,
+      "step": 410
+    },
+    {
+      "epoch": 103.96,
+      "grad_norm": 0.023235289379954338,
+      "learning_rate": 7.938144329896907e-05,
+      "loss": 0.0124,
+      "step": 415
+    },
+    {
+      "epoch": 105.0,
+      "grad_norm": 0.0693734735250473,
+      "learning_rate": 7.90950744558992e-05,
+      "loss": 0.0137,
+      "step": 420
+    },
+    {
+      "epoch": 106.32,
+      "grad_norm": 0.019512519240379333,
+      "learning_rate": 7.880870561282932e-05,
+      "loss": 0.0142,
+      "step": 425
+    },
+    {
+      "epoch": 107.64,
+      "grad_norm": 0.02140176109969616,
+      "learning_rate": 7.852233676975945e-05,
+      "loss": 0.0141,
+      "step": 430
+    },
+    {
+      "epoch": 108.96,
+      "grad_norm": 0.022468585520982742,
+      "learning_rate": 7.823596792668958e-05,
+      "loss": 0.0122,
+      "step": 435
+    },
+    {
+      "epoch": 110.0,
+      "grad_norm": 0.0380476713180542,
+      "learning_rate": 7.79495990836197e-05,
+      "loss": 0.0136,
+      "step": 440
+    },
+    {
+      "epoch": 111.32,
+      "grad_norm": 0.018203549087047577,
+      "learning_rate": 7.766323024054983e-05,
+      "loss": 0.0119,
+      "step": 445
+    },
+    {
+      "epoch": 112.64,
+      "grad_norm": 0.02083701454102993,
+      "learning_rate": 7.737686139747996e-05,
+      "loss": 0.0159,
+      "step": 450
+    },
+    {
+      "epoch": 113.96,
+      "grad_norm": 0.02744678594172001,
+      "learning_rate": 7.709049255441008e-05,
+      "loss": 0.0138,
+      "step": 455
+    },
+    {
+      "epoch": 115.0,
+      "grad_norm": 0.05891157686710358,
+      "learning_rate": 7.680412371134021e-05,
+      "loss": 0.0123,
+      "step": 460
+    },
+    {
+      "epoch": 116.32,
+      "grad_norm": 0.02845454029738903,
+      "learning_rate": 7.651775486827034e-05,
+      "loss": 0.0139,
+      "step": 465
+    },
+    {
+      "epoch": 117.64,
+      "grad_norm": 0.020904691889882088,
+      "learning_rate": 7.623138602520046e-05,
+      "loss": 0.013,
+      "step": 470
+    },
+    {
+      "epoch": 118.96,
+      "grad_norm": 0.020568421110510826,
+      "learning_rate": 7.594501718213059e-05,
+      "loss": 0.0126,
+      "step": 475
+    },
+    {
+      "epoch": 120.0,
+      "grad_norm": 0.11525513231754303,
+      "learning_rate": 7.565864833906071e-05,
+      "loss": 0.0149,
+      "step": 480
+    },
+    {
+      "epoch": 121.32,
+      "grad_norm": 0.02282075583934784,
+      "learning_rate": 7.537227949599084e-05,
+      "loss": 0.0145,
+      "step": 485
+    },
+    {
+      "epoch": 122.64,
+      "grad_norm": 0.021044986322522163,
+      "learning_rate": 7.508591065292097e-05,
+      "loss": 0.0118,
+      "step": 490
+    },
+    {
+      "epoch": 123.96,
+      "grad_norm": 0.026140881702303886,
+      "learning_rate": 7.47995418098511e-05,
+      "loss": 0.0134,
+      "step": 495
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 0.08347874134778976,
+      "learning_rate": 7.451317296678122e-05,
+      "loss": 0.0134,
+      "step": 500
+    },
+    {
+      "epoch": 126.32,
+      "grad_norm": 0.021540338173508644,
+      "learning_rate": 7.422680412371135e-05,
+      "loss": 0.0124,
+      "step": 505
+    },
+    {
+      "epoch": 127.64,
+      "grad_norm": 0.018244560807943344,
+      "learning_rate": 7.394043528064147e-05,
+      "loss": 0.0133,
+      "step": 510
+    },
+    {
+      "epoch": 128.96,
+      "grad_norm": 0.0179904717952013,
+      "learning_rate": 7.36540664375716e-05,
+      "loss": 0.0131,
+      "step": 515
+    },
+    {
+      "epoch": 130.0,
+      "grad_norm": 0.0700739249587059,
+      "learning_rate": 7.336769759450171e-05,
+      "loss": 0.0151,
+      "step": 520
+    },
+    {
+      "epoch": 131.32,
+      "grad_norm": 0.02473938651382923,
+      "learning_rate": 7.308132875143184e-05,
+      "loss": 0.0139,
+      "step": 525
+    },
+    {
+      "epoch": 132.64,
+      "grad_norm": 0.016669029369950294,
+      "learning_rate": 7.279495990836197e-05,
+      "loss": 0.0129,
+      "step": 530
+    },
+    {
+      "epoch": 133.96,
+      "grad_norm": 0.0206622127443552,
+      "learning_rate": 7.250859106529209e-05,
+      "loss": 0.0131,
+      "step": 535
+    },
+    {
+      "epoch": 135.0,
+      "grad_norm": 0.1013081893324852,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 0.0141,
+      "step": 540
+    },
+    {
+      "epoch": 136.32,
+      "grad_norm": 0.02413194440305233,
+      "learning_rate": 7.193585337915235e-05,
+      "loss": 0.0136,
+      "step": 545
+    },
+    {
+      "epoch": 137.64,
+      "grad_norm": 0.02023296430706978,
+      "learning_rate": 7.164948453608247e-05,
+      "loss": 0.0134,
+      "step": 550
+    },
+    {
+      "epoch": 138.96,
+      "grad_norm": 0.018895283341407776,
+      "learning_rate": 7.136311569301261e-05,
+      "loss": 0.012,
+      "step": 555
+    },
+    {
+      "epoch": 140.0,
+      "grad_norm": 0.08102845400571823,
+      "learning_rate": 7.107674684994274e-05,
+      "loss": 0.0142,
+      "step": 560
+    },
+    {
+      "epoch": 141.32,
+      "grad_norm": 0.019933724775910378,
+      "learning_rate": 7.079037800687286e-05,
+      "loss": 0.0143,
+      "step": 565
+    },
+    {
+      "epoch": 142.64,
+      "grad_norm": 0.02834722027182579,
+      "learning_rate": 7.050400916380299e-05,
+      "loss": 0.0136,
+      "step": 570
+    },
+    {
+      "epoch": 143.96,
+      "grad_norm": 0.02353634126484394,
+      "learning_rate": 7.02176403207331e-05,
+      "loss": 0.0139,
+      "step": 575
+    },
+    {
+      "epoch": 145.0,
+      "grad_norm": 0.042016856372356415,
+      "learning_rate": 6.993127147766323e-05,
+      "loss": 0.0151,
+      "step": 580
+    },
+    {
+      "epoch": 146.32,
+      "grad_norm": 0.020217517390847206,
+      "learning_rate": 6.964490263459336e-05,
+      "loss": 0.0131,
+      "step": 585
+    },
+    {
+      "epoch": 147.64,
+      "grad_norm": 0.019066426903009415,
+      "learning_rate": 6.935853379152348e-05,
+      "loss": 0.0138,
+      "step": 590
+    },
+    {
+      "epoch": 148.96,
+      "grad_norm": 0.023700350895524025,
+      "learning_rate": 6.907216494845361e-05,
+      "loss": 0.0157,
+      "step": 595
+    },
+    {
+      "epoch": 150.0,
+      "grad_norm": 0.10881764441728592,
+      "learning_rate": 6.878579610538374e-05,
+      "loss": 0.0145,
+      "step": 600
+    },
+    {
+      "epoch": 151.32,
+      "grad_norm": 0.01735377125442028,
+      "learning_rate": 6.849942726231386e-05,
+      "loss": 0.0149,
+      "step": 605
+    },
+    {
+      "epoch": 152.64,
+      "grad_norm": 0.02352583408355713,
+      "learning_rate": 6.821305841924399e-05,
+      "loss": 0.0133,
+      "step": 610
+    },
+    {
+      "epoch": 153.96,
+      "grad_norm": 0.020118385553359985,
+      "learning_rate": 6.792668957617412e-05,
+      "loss": 0.013,
+      "step": 615
+    },
+    {
+      "epoch": 155.0,
+      "grad_norm": 0.06744980812072754,
+      "learning_rate": 6.764032073310424e-05,
+      "loss": 0.0132,
+      "step": 620
+    },
+    {
+      "epoch": 156.32,
+      "grad_norm": 0.016874659806489944,
+      "learning_rate": 6.735395189003437e-05,
+      "loss": 0.0139,
+      "step": 625
+    },
+    {
+      "epoch": 157.64,
+      "grad_norm": 0.01467908825725317,
+      "learning_rate": 6.706758304696448e-05,
+      "loss": 0.0137,
+      "step": 630
+    },
+    {
+      "epoch": 158.96,
+      "grad_norm": 0.015406169928610325,
+      "learning_rate": 6.678121420389462e-05,
+      "loss": 0.0127,
+      "step": 635
+    },
+    {
+      "epoch": 160.0,
+      "grad_norm": 0.12341684848070145,
+      "learning_rate": 6.649484536082475e-05,
+      "loss": 0.015,
+      "step": 640
+    },
+    {
+      "epoch": 161.32,
+      "grad_norm": 0.019478783011436462,
+      "learning_rate": 6.620847651775487e-05,
+      "loss": 0.014,
+      "step": 645
+    },
+    {
+      "epoch": 162.64,
+      "grad_norm": 0.019468264654278755,
+      "learning_rate": 6.5922107674685e-05,
+      "loss": 0.0137,
+      "step": 650
+    },
+    {
+      "epoch": 163.96,
+      "grad_norm": 0.01982899010181427,
+      "learning_rate": 6.563573883161513e-05,
+      "loss": 0.0133,
+      "step": 655
+    },
+    {
+      "epoch": 165.0,
+      "grad_norm": 0.06181833893060684,
+      "learning_rate": 6.534936998854525e-05,
+      "loss": 0.0174,
+      "step": 660
+    },
+    {
+      "epoch": 166.32,
+      "grad_norm": 0.017229964956641197,
+      "learning_rate": 6.506300114547538e-05,
+      "loss": 0.0137,
+      "step": 665
+    },
+    {
+      "epoch": 167.64,
+      "grad_norm": 0.020293107256293297,
+      "learning_rate": 6.477663230240551e-05,
+      "loss": 0.0162,
+      "step": 670
+    },
+    {
+      "epoch": 168.96,
+      "grad_norm": 0.01984878070652485,
+      "learning_rate": 6.449026345933563e-05,
+      "loss": 0.0118,
+      "step": 675
+    },
+    {
+      "epoch": 170.0,
+      "grad_norm": 0.05648861452937126,
+      "learning_rate": 6.420389461626576e-05,
+      "loss": 0.0153,
+      "step": 680
+    },
+    {
+      "epoch": 171.32,
+      "grad_norm": 0.016714531928300858,
+      "learning_rate": 6.391752577319587e-05,
+      "loss": 0.0155,
+      "step": 685
+    },
+    {
+      "epoch": 172.64,
+      "grad_norm": 0.016303598880767822,
+      "learning_rate": 6.3631156930126e-05,
+      "loss": 0.0154,
+      "step": 690
+    },
+    {
+      "epoch": 173.96,
+      "grad_norm": 0.019211357459425926,
+      "learning_rate": 6.334478808705613e-05,
+      "loss": 0.015,
+      "step": 695
+    },
+    {
+      "epoch": 175.0,
+      "grad_norm": 0.06923225522041321,
+      "learning_rate": 6.305841924398625e-05,
+      "loss": 0.0151,
+      "step": 700
+    },
+    {
+      "epoch": 176.32,
+      "grad_norm": 0.0212013591080904,
+      "learning_rate": 6.277205040091638e-05,
+      "loss": 0.0137,
+      "step": 705
+    },
+    {
+      "epoch": 177.64,
+      "grad_norm": 0.019212843850255013,
+      "learning_rate": 6.24856815578465e-05,
+      "loss": 0.013,
+      "step": 710
+    },
+    {
+      "epoch": 178.96,
+      "grad_norm": 0.01936633512377739,
+      "learning_rate": 6.219931271477663e-05,
+      "loss": 0.0124,
+      "step": 715
+    },
+    {
+      "epoch": 180.0,
+      "grad_norm": 0.03678485378623009,
+      "learning_rate": 6.191294387170676e-05,
+      "loss": 0.0128,
+      "step": 720
+    },
+    {
+      "epoch": 181.32,
+      "grad_norm": 0.01613820530474186,
+      "learning_rate": 6.162657502863689e-05,
+      "loss": 0.013,
+      "step": 725
+    },
+    {
+      "epoch": 182.64,
+      "grad_norm": 0.014102709479629993,
+      "learning_rate": 6.134020618556701e-05,
+      "loss": 0.0122,
+      "step": 730
+    },
+    {
+      "epoch": 183.96,
+      "grad_norm": 0.019725633785128593,
+      "learning_rate": 6.105383734249714e-05,
+      "loss": 0.0136,
+      "step": 735
+    },
+    {
+      "epoch": 185.0,
+      "grad_norm": 0.02554723620414734,
+      "learning_rate": 6.076746849942726e-05,
+      "loss": 0.0106,
+      "step": 740
+    },
+    {
+      "epoch": 186.32,
+      "grad_norm": 0.017536187544465065,
+      "learning_rate": 6.0481099656357384e-05,
+      "loss": 0.0126,
+      "step": 745
+    },
+    {
+      "epoch": 187.64,
+      "grad_norm": 0.014839887619018555,
+      "learning_rate": 6.019473081328752e-05,
+      "loss": 0.0147,
+      "step": 750
+    },
+    {
+      "epoch": 188.96,
+      "grad_norm": 0.015652010217308998,
+      "learning_rate": 5.9908361970217644e-05,
+      "loss": 0.0122,
+      "step": 755
+    },
+    {
+      "epoch": 190.0,
+      "grad_norm": 0.07570195943117142,
+      "learning_rate": 5.962199312714777e-05,
+      "loss": 0.0156,
+      "step": 760
+    },
+    {
+      "epoch": 191.32,
+      "grad_norm": 0.01712140068411827,
+      "learning_rate": 5.93356242840779e-05,
+      "loss": 0.0144,
+      "step": 765
+    },
+    {
+      "epoch": 192.64,
+      "grad_norm": 0.018935920670628548,
+      "learning_rate": 5.904925544100802e-05,
+      "loss": 0.0137,
+      "step": 770
+    },
+    {
+      "epoch": 193.96,
+      "grad_norm": 0.018975302577018738,
+      "learning_rate": 5.876288659793815e-05,
+      "loss": 0.0139,
+      "step": 775
+    },
+    {
+      "epoch": 195.0,
+      "grad_norm": 0.06302426010370255,
+      "learning_rate": 5.8476517754868276e-05,
+      "loss": 0.0124,
+      "step": 780
+    },
+    {
+      "epoch": 196.32,
+      "grad_norm": 0.017456602305173874,
+      "learning_rate": 5.81901489117984e-05,
+      "loss": 0.0157,
+      "step": 785
+    },
+    {
+      "epoch": 197.64,
+      "grad_norm": 0.017395246773958206,
+      "learning_rate": 5.790378006872853e-05,
+      "loss": 0.0137,
+      "step": 790
+    },
+    {
+      "epoch": 198.96,
+      "grad_norm": 0.01904039829969406,
+      "learning_rate": 5.761741122565865e-05,
+      "loss": 0.0149,
+      "step": 795
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 0.05075971782207489,
+      "learning_rate": 5.7331042382588775e-05,
+      "loss": 0.0133,
+      "step": 800
+    },
+    {
+      "epoch": 201.32,
+      "grad_norm": 0.017711862921714783,
+      "learning_rate": 5.70446735395189e-05,
+      "loss": 0.0132,
+      "step": 805
+    },
+    {
+      "epoch": 202.64,
+      "grad_norm": 0.01479764562100172,
+      "learning_rate": 5.675830469644903e-05,
+      "loss": 0.0159,
+      "step": 810
+    },
+    {
+      "epoch": 203.96,
+      "grad_norm": 0.014561891555786133,
+      "learning_rate": 5.6471935853379155e-05,
+      "loss": 0.0134,
+      "step": 815
+    },
+    {
+      "epoch": 205.0,
+      "grad_norm": 0.07381083816289902,
+      "learning_rate": 5.618556701030928e-05,
+      "loss": 0.0125,
+      "step": 820
+    },
+    {
+      "epoch": 206.32,
+      "grad_norm": 0.016206586733460426,
+      "learning_rate": 5.589919816723941e-05,
+      "loss": 0.0147,
+      "step": 825
+    },
+    {
+      "epoch": 207.64,
+      "grad_norm": 0.017128223553299904,
+      "learning_rate": 5.5612829324169534e-05,
+      "loss": 0.0138,
+      "step": 830
+    },
+    {
+      "epoch": 208.96,
+      "grad_norm": 0.025427645072340965,
+      "learning_rate": 5.532646048109966e-05,
+      "loss": 0.0162,
+      "step": 835
+    },
+    {
+      "epoch": 210.0,
+      "grad_norm": 0.08378550410270691,
+      "learning_rate": 5.504009163802979e-05,
+      "loss": 0.0157,
+      "step": 840
+    },
+    {
+      "epoch": 211.32,
+      "grad_norm": 0.015921575948596,
+      "learning_rate": 5.4753722794959914e-05,
+      "loss": 0.0125,
+      "step": 845
+    },
+    {
+      "epoch": 212.64,
+      "grad_norm": 0.01416046917438507,
+      "learning_rate": 5.4467353951890033e-05,
+      "loss": 0.0125,
+      "step": 850
+    },
+    {
+      "epoch": 213.96,
+      "grad_norm": 0.015747040510177612,
+      "learning_rate": 5.418098510882016e-05,
+      "loss": 0.0134,
+      "step": 855
+    },
+    {
+      "epoch": 215.0,
+      "grad_norm": 0.024801790714263916,
+      "learning_rate": 5.3894616265750286e-05,
+      "loss": 0.0122,
+      "step": 860
+    },
+    {
+      "epoch": 216.32,
+      "grad_norm": 0.017852013930678368,
+      "learning_rate": 5.360824742268041e-05,
+      "loss": 0.0142,
+      "step": 865
+    },
+    {
+      "epoch": 217.64,
+      "grad_norm": 0.0136189516633749,
+      "learning_rate": 5.332187857961054e-05,
+      "loss": 0.0137,
+      "step": 870
+    },
+    {
+      "epoch": 218.96,
+      "grad_norm": 0.01580929383635521,
+      "learning_rate": 5.3035509736540666e-05,
+      "loss": 0.0136,
+      "step": 875
+    },
+    {
+      "epoch": 220.0,
+      "grad_norm": 0.02904467284679413,
+      "learning_rate": 5.274914089347079e-05,
+      "loss": 0.0119,
+      "step": 880
+    },
+    {
+      "epoch": 221.32,
+      "grad_norm": 0.0184769406914711,
+      "learning_rate": 5.246277205040092e-05,
+      "loss": 0.0135,
+      "step": 885
+    },
+    {
+      "epoch": 222.64,
+      "grad_norm": 0.014274867251515388,
+      "learning_rate": 5.2176403207331045e-05,
+      "loss": 0.0134,
+      "step": 890
+    },
+    {
+      "epoch": 223.96,
+      "grad_norm": 0.014355281367897987,
+      "learning_rate": 5.189003436426118e-05,
+      "loss": 0.0129,
+      "step": 895
+    },
+    {
+      "epoch": 225.0,
+      "grad_norm": 0.0977749451994896,
+      "learning_rate": 5.1603665521191305e-05,
+      "loss": 0.0159,
+      "step": 900
+    }
+  ],
+  "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": 7.654070550528e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}