Upload 114 files

.gitattributes

@@ -39,3 +39,11 @@ Llama-3.1-8B-Instruct-lora/checkpoint-93/tokenizer.json filter=lfs diff=lfs merg
 Llama-3.1-8B-Instruct-lora/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Llama3.1-8B-Chinese-Chat-lora/checkpoint-93/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Llama3.1-8B-Chinese-Chat-lora/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct-lora-2/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct-lora-2/checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct-lora-2/checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct-lora-2/checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct-lora-2/checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct-lora-2/checkpoint-3036/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct-lora-2/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct-lora-2/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Qwen2.5-7B-Instruct-lora-2/README.md

@@ -0,0 +1,59 @@
+---
+library_name: peft
+license: other
+base_model: /data/zhaoguoyu/Experiments/mgtd-sys/detector/ckpt/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: Qwen2.5-7B-Instruct-lora-2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Qwen2.5-7B-Instruct-lora-2
+
+This model is a fine-tuned version of [/data/zhaoguoyu/Experiments/mgtd-sys/detector/ckpt/Qwen2.5-7B-Instruct](https://huggingface.co//data/zhaoguoyu/Experiments/mgtd-sys/detector/ckpt/Qwen2.5-7B-Instruct) on the nlpcc25_task1_train dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.0
+- Transformers 4.50.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.4.1
+- Tokenizers 0.21.0

Qwen2.5-7B-Instruct-lora-2/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/zhaoguoyu/Experiments/mgtd-sys/detector/ckpt/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

Qwen2.5-7B-Instruct-lora-2/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8402ed41b02a34fcdc1ecd7ce937af493a89532e451516627b0222e9652253e
+size 80792096

Qwen2.5-7B-Instruct-lora-2/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
+}

Qwen2.5-7B-Instruct-lora-2/all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.9975308641975307,
+    "eval_nlpcc25_task1_dev_accuracy": 0.9996825396825397,
+    "eval_nlpcc25_task1_dev_loss": 0.0018848935142159462,
+    "eval_nlpcc25_task1_dev_runtime": 2528.4122,
+    "eval_nlpcc25_task1_dev_samples_per_second": 1.107,
+    "eval_nlpcc25_task1_dev_steps_per_second": 0.277,
+    "total_flos": 1.7445311627903631e+18,
+    "train_loss": 0.07892912521831204,
+    "train_runtime": 224440.5917,
+    "train_samples_per_second": 0.433,
+    "train_steps_per_second": 0.014
+}

Qwen2.5-7B-Instruct-lora-2/checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /data/zhaoguoyu/Experiments/mgtd-sys/detector/ckpt/Qwen2.5-7B-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 0.15.0

Qwen2.5-7B-Instruct-lora-2/checkpoint-1000/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/zhaoguoyu/Experiments/mgtd-sys/detector/ckpt/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

Qwen2.5-7B-Instruct-lora-2/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07a0cd322b506ab56eb0a762c21b8071538ab563c1e744e68e713c7801acee0d
+size 80792096

Qwen2.5-7B-Instruct-lora-2/checkpoint-1000/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
+}

Qwen2.5-7B-Instruct-lora-2/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b492af21df6ec85d758309ada19101d73ff7e6a41717161ed0e54a0a43da2426
+size 161810282

Qwen2.5-7B-Instruct-lora-2/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

Qwen2.5-7B-Instruct-lora-2/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5918d346fe9060e659615446cea815a9b715c8fa69cf77cf3b71de31c3c3de85
+size 1064

Qwen2.5-7B-Instruct-lora-2/checkpoint-1000/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
+  }
+}

Qwen2.5-7B-Instruct-lora-2/checkpoint-1000/tokenizer.json

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

Qwen2.5-7B-Instruct-lora-2/checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

Qwen2.5-7B-Instruct-lora-2/checkpoint-1000/trainer_state.json

@@ -0,0 +1,752 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9876543209876543,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009876543209876543,
+      "grad_norm": 7.599112033843994,
+      "learning_rate": 1.6447368421052632e-06,
+      "loss": 4.2059,
+      "step": 10
+    },
+    {
+      "epoch": 0.019753086419753086,
+      "grad_norm": 6.403433322906494,
+      "learning_rate": 3.2894736842105265e-06,
+      "loss": 4.1463,
+      "step": 20
+    },
+    {
+      "epoch": 0.02962962962962963,
+      "grad_norm": 9.776185989379883,
+      "learning_rate": 4.9342105263157895e-06,
+      "loss": 4.1087,
+      "step": 30
+    },
+    {
+      "epoch": 0.03950617283950617,
+      "grad_norm": 5.836405277252197,
+      "learning_rate": 6.578947368421053e-06,
+      "loss": 3.7657,
+      "step": 40
+    },
+    {
+      "epoch": 0.04938271604938271,
+      "grad_norm": 4.362349033355713,
+      "learning_rate": 8.223684210526317e-06,
+      "loss": 3.2134,
+      "step": 50
+    },
+    {
+      "epoch": 0.05925925925925926,
+      "grad_norm": 5.1398701667785645,
+      "learning_rate": 9.868421052631579e-06,
+      "loss": 2.6238,
+      "step": 60
+    },
+    {
+      "epoch": 0.0691358024691358,
+      "grad_norm": 8.642521858215332,
+      "learning_rate": 1.1513157894736843e-05,
+      "loss": 1.5929,
+      "step": 70
+    },
+    {
+      "epoch": 0.07901234567901234,
+      "grad_norm": 1.0219271183013916,
+      "learning_rate": 1.3157894736842106e-05,
+      "loss": 0.1491,
+      "step": 80
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.4035845100879669,
+      "learning_rate": 1.4802631578947368e-05,
+      "loss": 0.0206,
+      "step": 90
+    },
+    {
+      "epoch": 0.09876543209876543,
+      "grad_norm": 0.6767832636833191,
+      "learning_rate": 1.6447368421052635e-05,
+      "loss": 0.0073,
+      "step": 100
+    },
+    {
+      "epoch": 0.10864197530864197,
+      "grad_norm": 0.014764077961444855,
+      "learning_rate": 1.8092105263157896e-05,
+      "loss": 0.0011,
+      "step": 110
+    },
+    {
+      "epoch": 0.11851851851851852,
+      "grad_norm": 0.15152056515216827,
+      "learning_rate": 1.9736842105263158e-05,
+      "loss": 0.0005,
+      "step": 120
+    },
+    {
+      "epoch": 0.12839506172839507,
+      "grad_norm": 0.06782546639442444,
+      "learning_rate": 2.1381578947368423e-05,
+      "loss": 0.0014,
+      "step": 130
+    },
+    {
+      "epoch": 0.1382716049382716,
+      "grad_norm": 0.03198217228055,
+      "learning_rate": 2.3026315789473685e-05,
+      "loss": 0.0009,
+      "step": 140
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.02691480703651905,
+      "learning_rate": 2.4671052631578947e-05,
+      "loss": 0.0024,
+      "step": 150
+    },
+    {
+      "epoch": 0.1580246913580247,
+      "grad_norm": 0.0057847509160637856,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 0.0001,
+      "step": 160
+    },
+    {
+      "epoch": 0.16790123456790124,
+      "grad_norm": 0.003663571085780859,
+      "learning_rate": 2.7960526315789477e-05,
+      "loss": 0.0002,
+      "step": 170
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.004447426181286573,
+      "learning_rate": 2.9605263157894735e-05,
+      "loss": 0.0003,
+      "step": 180
+    },
+    {
+      "epoch": 0.18765432098765433,
+      "grad_norm": 0.10373878479003906,
+      "learning_rate": 3.125e-05,
+      "loss": 0.0006,
+      "step": 190
+    },
+    {
+      "epoch": 0.19753086419753085,
+      "grad_norm": 0.002619905164465308,
+      "learning_rate": 3.289473684210527e-05,
+      "loss": 0.0006,
+      "step": 200
+    },
+    {
+      "epoch": 0.2074074074074074,
+      "grad_norm": 0.007042820565402508,
+      "learning_rate": 3.4539473684210524e-05,
+      "loss": 0.0015,
+      "step": 210
+    },
+    {
+      "epoch": 0.21728395061728395,
+      "grad_norm": 0.0016206403961405158,
+      "learning_rate": 3.618421052631579e-05,
+      "loss": 0.0049,
+      "step": 220
+    },
+    {
+      "epoch": 0.2271604938271605,
+      "grad_norm": 0.001877307309769094,
+      "learning_rate": 3.7828947368421054e-05,
+      "loss": 0.0001,
+      "step": 230
+    },
+    {
+      "epoch": 0.23703703703703705,
+      "grad_norm": 0.003795365337282419,
+      "learning_rate": 3.9473684210526316e-05,
+      "loss": 0.0001,
+      "step": 240
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 0.008357529528439045,
+      "learning_rate": 4.111842105263158e-05,
+      "loss": 0.004,
+      "step": 250
+    },
+    {
+      "epoch": 0.25679012345679014,
+      "grad_norm": 0.026294540613889694,
+      "learning_rate": 4.2763157894736847e-05,
+      "loss": 0.0002,
+      "step": 260
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.08903225511312485,
+      "learning_rate": 4.440789473684211e-05,
+      "loss": 0.0005,
+      "step": 270
+    },
+    {
+      "epoch": 0.2765432098765432,
+      "grad_norm": 0.05173858627676964,
+      "learning_rate": 4.605263157894737e-05,
+      "loss": 0.0003,
+      "step": 280
+    },
+    {
+      "epoch": 0.28641975308641976,
+      "grad_norm": 0.036562711000442505,
+      "learning_rate": 4.769736842105263e-05,
+      "loss": 0.0012,
+      "step": 290
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.008022695779800415,
+      "learning_rate": 4.9342105263157894e-05,
+      "loss": 0.0036,
+      "step": 300
+    },
+    {
+      "epoch": 0.30617283950617286,
+      "grad_norm": 0.0021413813810795546,
+      "learning_rate": 4.999940495590975e-05,
+      "loss": 0.0006,
+      "step": 310
+    },
+    {
+      "epoch": 0.3160493827160494,
+      "grad_norm": 0.015379426069557667,
+      "learning_rate": 4.999576867793816e-05,
+      "loss": 0.0092,
+      "step": 320
+    },
+    {
+      "epoch": 0.32592592592592595,
+      "grad_norm": 0.003894766792654991,
+      "learning_rate": 4.9988827182291254e-05,
+      "loss": 0.001,
+      "step": 330
+    },
+    {
+      "epoch": 0.3358024691358025,
+      "grad_norm": 0.0016231742920354009,
+      "learning_rate": 4.997858138685056e-05,
+      "loss": 0.0001,
+      "step": 340
+    },
+    {
+      "epoch": 0.345679012345679,
+      "grad_norm": 0.0015260468935593963,
+      "learning_rate": 4.996503264642876e-05,
+      "loss": 0.0016,
+      "step": 350
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.03330058977007866,
+      "learning_rate": 4.994818275259052e-05,
+      "loss": 0.0013,
+      "step": 360
+    },
+    {
+      "epoch": 0.3654320987654321,
+      "grad_norm": 0.002741268603131175,
+      "learning_rate": 4.992803393341563e-05,
+      "loss": 0.0017,
+      "step": 370
+    },
+    {
+      "epoch": 0.37530864197530867,
+      "grad_norm": 0.004990574903786182,
+      "learning_rate": 4.9904588853204365e-05,
+      "loss": 0.0001,
+      "step": 380
+    },
+    {
+      "epoch": 0.3851851851851852,
+      "grad_norm": 0.013514043763279915,
+      "learning_rate": 4.9877850612125173e-05,
+      "loss": 0.0001,
+      "step": 390
+    },
+    {
+      "epoch": 0.3950617283950617,
+      "grad_norm": 0.0015880317660048604,
+      "learning_rate": 4.984782274580476e-05,
+      "loss": 0.0001,
+      "step": 400
+    },
+    {
+      "epoch": 0.4049382716049383,
+      "grad_norm": 0.002702023135498166,
+      "learning_rate": 4.981450922486053e-05,
+      "loss": 0.0001,
+      "step": 410
+    },
+    {
+      "epoch": 0.4148148148148148,
+      "grad_norm": 0.0020927605219185352,
+      "learning_rate": 4.977791445437559e-05,
+      "loss": 0.0001,
+      "step": 420
+    },
+    {
+      "epoch": 0.4246913580246914,
+      "grad_norm": 0.0007626357255503535,
+      "learning_rate": 4.973804327331625e-05,
+      "loss": 0.0002,
+      "step": 430
+    },
+    {
+      "epoch": 0.4345679012345679,
+      "grad_norm": 0.0026151000056415796,
+      "learning_rate": 4.969490095389213e-05,
+      "loss": 0.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.0007740291184745729,
+      "learning_rate": 4.964849320085905e-05,
+      "loss": 0.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.454320987654321,
+      "grad_norm": 0.0005287025705911219,
+      "learning_rate": 4.9598826150764656e-05,
+      "loss": 0.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.4641975308641975,
+      "grad_norm": 0.0004778858565259725,
+      "learning_rate": 4.9545906371137e-05,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.4740740740740741,
+      "grad_norm": 0.0007034554146230221,
+      "learning_rate": 4.9489740859616094e-05,
+      "loss": 0.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.4839506172839506,
+      "grad_norm": 0.0006262129172682762,
+      "learning_rate": 4.9430337043028604e-05,
+      "loss": 0.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.00045443352428264916,
+      "learning_rate": 4.9367702776405806e-05,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "eval_nlpcc25_task1_dev_accuracy": 0.9995238095238096,
+      "eval_nlpcc25_task1_dev_loss": 0.0022831459064036608,
+      "eval_nlpcc25_task1_dev_runtime": 2528.8573,
+      "eval_nlpcc25_task1_dev_samples_per_second": 1.107,
+      "eval_nlpcc25_task1_dev_steps_per_second": 0.277,
+      "step": 500
+    },
+    {
+      "epoch": 0.5037037037037037,
+      "grad_norm": 0.0003733730991370976,
+      "learning_rate": 4.930184634194488e-05,
+      "loss": 0.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.5135802469135803,
+      "grad_norm": 0.0003028757928404957,
+      "learning_rate": 4.923277644791378e-05,
+      "loss": 0.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.5234567901234568,
+      "grad_norm": 0.00028728952747769654,
+      "learning_rate": 4.9160502227499704e-05,
+      "loss": 0.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.0003644278913270682,
+      "learning_rate": 4.908503323760143e-05,
+      "loss": 0.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.5432098765432098,
+      "grad_norm": 0.0005966073367744684,
+      "learning_rate": 4.900637945756554e-05,
+      "loss": 0.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.5530864197530864,
+      "grad_norm": 0.000367969973012805,
+      "learning_rate": 4.892455128786692e-05,
+      "loss": 0.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.562962962962963,
+      "grad_norm": 0.0002780740906018764,
+      "learning_rate": 4.8839559548733436e-05,
+      "loss": 0.0077,
+      "step": 570
+    },
+    {
+      "epoch": 0.5728395061728395,
+      "grad_norm": 0.00031342540751211345,
+      "learning_rate": 4.875141547871519e-05,
+      "loss": 0.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.582716049382716,
+      "grad_norm": 0.000353014562278986,
+      "learning_rate": 4.866013073319841e-05,
+      "loss": 0.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.00029066085699014366,
+      "learning_rate": 4.856571738286426e-05,
+      "loss": 0.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.6024691358024692,
+      "grad_norm": 0.00024000390840228647,
+      "learning_rate": 4.8468187912092744e-05,
+      "loss": 0.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.6123456790123457,
+      "grad_norm": 0.0003632376901805401,
+      "learning_rate": 4.836755521731183e-05,
+      "loss": 0.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.00029751085094176233,
+      "learning_rate": 4.826383260529221e-05,
+      "loss": 0.0002,
+      "step": 630
+    },
+    {
+      "epoch": 0.6320987654320988,
+      "grad_norm": 3.190973997116089,
+      "learning_rate": 4.815703379138765e-05,
+      "loss": 0.0017,
+      "step": 640
+    },
+    {
+      "epoch": 0.6419753086419753,
+      "grad_norm": 0.18289895355701447,
+      "learning_rate": 4.804717289772147e-05,
+      "loss": 0.0043,
+      "step": 650
+    },
+    {
+      "epoch": 0.6518518518518519,
+      "grad_norm": 0.2459922581911087,
+      "learning_rate": 4.7934264451319105e-05,
+      "loss": 0.003,
+      "step": 660
+    },
+    {
+      "epoch": 0.6617283950617284,
+      "grad_norm": 0.004725860431790352,
+      "learning_rate": 4.7818323382187214e-05,
+      "loss": 0.0002,
+      "step": 670
+    },
+    {
+      "epoch": 0.671604938271605,
+      "grad_norm": 0.004160716664046049,
+      "learning_rate": 4.769936502133946e-05,
+      "loss": 0.0002,
+      "step": 680
+    },
+    {
+      "epoch": 0.6814814814814815,
+      "grad_norm": 0.002101948019117117,
+      "learning_rate": 4.7577405098769256e-05,
+      "loss": 0.0001,
+      "step": 690
+    },
+    {
+      "epoch": 0.691358024691358,
+      "grad_norm": 0.0015966896899044514,
+      "learning_rate": 4.74524597413698e-05,
+      "loss": 0.0001,
+      "step": 700
+    },
+    {
+      "epoch": 0.7012345679012346,
+      "grad_norm": 0.0010343171888962388,
+      "learning_rate": 4.732454547080159e-05,
+      "loss": 0.0,
+      "step": 710
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.0007301874575205147,
+      "learning_rate": 4.7193679201307705e-05,
+      "loss": 0.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.7209876543209877,
+      "grad_norm": 0.0008054127101786435,
+      "learning_rate": 4.705987823747731e-05,
+      "loss": 0.0,
+      "step": 730
+    },
+    {
+      "epoch": 0.7308641975308642,
+      "grad_norm": 0.0006862932350486517,
+      "learning_rate": 4.692316027195733e-05,
+      "loss": 0.0001,
+      "step": 740
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.0005865858984179795,
+      "learning_rate": 4.678354338311306e-05,
+      "loss": 0.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.7506172839506173,
+      "grad_norm": 0.0004720942524727434,
+      "learning_rate": 4.6641046032637516e-05,
+      "loss": 0.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.7604938271604939,
+      "grad_norm": 0.0004310516524128616,
+      "learning_rate": 4.6495687063110325e-05,
+      "loss": 0.0,
+      "step": 770
+    },
+    {
+      "epoch": 0.7703703703703704,
+      "grad_norm": 0.00043949694372713566,
+      "learning_rate": 4.634748569550612e-05,
+      "loss": 0.0,
+      "step": 780
+    },
+    {
+      "epoch": 0.7802469135802469,
+      "grad_norm": 0.0004090226429980248,
+      "learning_rate": 4.61964615266529e-05,
+      "loss": 0.0,
+      "step": 790
+    },
+    {
+      "epoch": 0.7901234567901234,
+      "grad_norm": 0.00037527765380218625,
+      "learning_rate": 4.6042634526640755e-05,
+      "loss": 0.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.0162104368209839,
+      "learning_rate": 4.588602503618118e-05,
+      "loss": 0.0021,
+      "step": 810
+    },
+    {
+      "epoch": 0.8098765432098766,
+      "grad_norm": 1.3063777685165405,
+      "learning_rate": 4.572665376391741e-05,
+      "loss": 0.0006,
+      "step": 820
+    },
+    {
+      "epoch": 0.8197530864197531,
+      "grad_norm": 0.9236663579940796,
+      "learning_rate": 4.55645417836861e-05,
+      "loss": 0.0058,
+      "step": 830
+    },
+    {
+      "epoch": 0.8296296296296296,
+      "grad_norm": 0.01748817227780819,
+      "learning_rate": 4.5399710531730685e-05,
+      "loss": 0.0025,
+      "step": 840
+    },
+    {
+      "epoch": 0.8395061728395061,
+      "grad_norm": 0.003460384439677,
+      "learning_rate": 4.5232181803866886e-05,
+      "loss": 0.0005,
+      "step": 850
+    },
+    {
+      "epoch": 0.8493827160493828,
+      "grad_norm": 0.0013236172962933779,
+      "learning_rate": 4.506197775260055e-05,
+      "loss": 0.0001,
+      "step": 860
+    },
+    {
+      "epoch": 0.8592592592592593,
+      "grad_norm": 0.0011838016798719764,
+      "learning_rate": 4.4889120884198495e-05,
+      "loss": 0.0,
+      "step": 870
+    },
+    {
+      "epoch": 0.8691358024691358,
+      "grad_norm": 0.0007675419910810888,
+      "learning_rate": 4.47136340557124e-05,
+      "loss": 0.0,
+      "step": 880
+    },
+    {
+      "epoch": 0.8790123456790123,
+      "grad_norm": 0.0007905301754362881,
+      "learning_rate": 4.453554047195644e-05,
+      "loss": 0.0,
+      "step": 890
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.0005061720148660243,
+      "learning_rate": 4.435486368243888e-05,
+      "loss": 0.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.8987654320987655,
+      "grad_norm": 0.0005205022753216326,
+      "learning_rate": 4.417162757824808e-05,
+      "loss": 0.0,
+      "step": 910
+    },
+    {
+      "epoch": 0.908641975308642,
+      "grad_norm": 0.0004827196535188705,
+      "learning_rate": 4.398585638889335e-05,
+      "loss": 0.0,
+      "step": 920
+    },
+    {
+      "epoch": 0.9185185185185185,
+      "grad_norm": 0.000379192759282887,
+      "learning_rate": 4.379757467910113e-05,
+      "loss": 0.0,
+      "step": 930
+    },
+    {
+      "epoch": 0.928395061728395,
+      "grad_norm": 0.00045221165055409074,
+      "learning_rate": 4.3606807345566616e-05,
+      "loss": 0.0,
+      "step": 940
+    },
+    {
+      "epoch": 0.9382716049382716,
+      "grad_norm": 0.0005233365809544921,
+      "learning_rate": 4.341357961366181e-05,
+      "loss": 0.0,
+      "step": 950
+    },
+    {
+      "epoch": 0.9481481481481482,
+      "grad_norm": 0.0002833159815054387,
+      "learning_rate": 4.3217917034099823e-05,
+      "loss": 0.0,
+      "step": 960
+    },
+    {
+      "epoch": 0.9580246913580247,
+      "grad_norm": 0.00043191161239519715,
+      "learning_rate": 4.301984547955635e-05,
+      "loss": 0.0,
+      "step": 970
+    },
+    {
+      "epoch": 0.9679012345679012,
+      "grad_norm": 0.0004523663374129683,
+      "learning_rate": 4.281939114124843e-05,
+      "loss": 0.0,
+      "step": 980
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.00025242462288588285,
+      "learning_rate": 4.261658052547124e-05,
+      "loss": 0.0,
+      "step": 990
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.0006344653083942831,
+      "learning_rate": 4.241144045009304e-05,
+      "loss": 0.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "eval_nlpcc25_task1_dev_accuracy": 0.9996031746031745,
+      "eval_nlpcc25_task1_dev_loss": 0.002990948036313057,
+      "eval_nlpcc25_task1_dev_runtime": 2528.4874,
+      "eval_nlpcc25_task1_dev_samples_per_second": 1.107,
+      "eval_nlpcc25_task1_dev_steps_per_second": 0.277,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3036,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.748493428351959e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

Qwen2.5-7B-Instruct-lora-2/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc27925817800cee3170b92f598d1cfe9fce4b0491f781c2f4977cfd2644a9a
+size 5752

Qwen2.5-7B-Instruct-lora-2/checkpoint-1500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /data/zhaoguoyu/Experiments/mgtd-sys/detector/ckpt/Qwen2.5-7B-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 0.15.0

Qwen2.5-7B-Instruct-lora-2/checkpoint-1500/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/zhaoguoyu/Experiments/mgtd-sys/detector/ckpt/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

Qwen2.5-7B-Instruct-lora-2/checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c877e7641cfb911f52d81ab8deed742e74675d10712bded6183a4bf14b29d766
+size 80792096

Qwen2.5-7B-Instruct-lora-2/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
+}

Qwen2.5-7B-Instruct-lora-2/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3b1b723e6fd339e9e095bcbf19a1ac51ea4c7e763b1f9ab0bbde16b569e9f2e
+size 161810282

Qwen2.5-7B-Instruct-lora-2/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
+size 14244

Qwen2.5-7B-Instruct-lora-2/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae0eb18432ecf0cfb9a0f275643de304875ad2c2d898c212c522cc3e221f35f
+size 1064

Qwen2.5-7B-Instruct-lora-2/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
+  }
+}

Qwen2.5-7B-Instruct-lora-2/checkpoint-1500/tokenizer.json

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

Qwen2.5-7B-Instruct-lora-2/checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

Qwen2.5-7B-Instruct-lora-2/checkpoint-1500/trainer_state.json

@@ -0,0 +1,1111 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4809876543209877,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009876543209876543,
+      "grad_norm": 7.599112033843994,
+      "learning_rate": 1.6447368421052632e-06,
+      "loss": 4.2059,
+      "step": 10
+    },
+    {
+      "epoch": 0.019753086419753086,
+      "grad_norm": 6.403433322906494,
+      "learning_rate": 3.2894736842105265e-06,
+      "loss": 4.1463,
+      "step": 20
+    },
+    {
+      "epoch": 0.02962962962962963,
+      "grad_norm": 9.776185989379883,
+      "learning_rate": 4.9342105263157895e-06,
+      "loss": 4.1087,
+      "step": 30
+    },
+    {
+      "epoch": 0.03950617283950617,
+      "grad_norm": 5.836405277252197,
+      "learning_rate": 6.578947368421053e-06,
+      "loss": 3.7657,
+      "step": 40
+    },
+    {
+      "epoch": 0.04938271604938271,
+      "grad_norm": 4.362349033355713,
+      "learning_rate": 8.223684210526317e-06,
+      "loss": 3.2134,
+      "step": 50
+    },
+    {
+      "epoch": 0.05925925925925926,
+      "grad_norm": 5.1398701667785645,
+      "learning_rate": 9.868421052631579e-06,
+      "loss": 2.6238,
+      "step": 60
+    },
+    {
+      "epoch": 0.0691358024691358,
+      "grad_norm": 8.642521858215332,
+      "learning_rate": 1.1513157894736843e-05,
+      "loss": 1.5929,
+      "step": 70
+    },
+    {
+      "epoch": 0.07901234567901234,
+      "grad_norm": 1.0219271183013916,
+      "learning_rate": 1.3157894736842106e-05,
+      "loss": 0.1491,
+      "step": 80
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.4035845100879669,
+      "learning_rate": 1.4802631578947368e-05,
+      "loss": 0.0206,
+      "step": 90
+    },
+    {
+      "epoch": 0.09876543209876543,
+      "grad_norm": 0.6767832636833191,
+      "learning_rate": 1.6447368421052635e-05,
+      "loss": 0.0073,
+      "step": 100
+    },
+    {
+      "epoch": 0.10864197530864197,
+      "grad_norm": 0.014764077961444855,
+      "learning_rate": 1.8092105263157896e-05,
+      "loss": 0.0011,
+      "step": 110
+    },
+    {
+      "epoch": 0.11851851851851852,
+      "grad_norm": 0.15152056515216827,
+      "learning_rate": 1.9736842105263158e-05,
+      "loss": 0.0005,
+      "step": 120
+    },
+    {
+      "epoch": 0.12839506172839507,
+      "grad_norm": 0.06782546639442444,
+      "learning_rate": 2.1381578947368423e-05,
+      "loss": 0.0014,
+      "step": 130
+    },
+    {
+      "epoch": 0.1382716049382716,
+      "grad_norm": 0.03198217228055,
+      "learning_rate": 2.3026315789473685e-05,
+      "loss": 0.0009,
+      "step": 140
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.02691480703651905,
+      "learning_rate": 2.4671052631578947e-05,
+      "loss": 0.0024,
+      "step": 150
+    },
+    {
+      "epoch": 0.1580246913580247,
+      "grad_norm": 0.0057847509160637856,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 0.0001,
+      "step": 160
+    },
+    {
+      "epoch": 0.16790123456790124,
+      "grad_norm": 0.003663571085780859,
+      "learning_rate": 2.7960526315789477e-05,
+      "loss": 0.0002,
+      "step": 170
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.004447426181286573,
+      "learning_rate": 2.9605263157894735e-05,
+      "loss": 0.0003,
+      "step": 180
+    },
+    {
+      "epoch": 0.18765432098765433,
+      "grad_norm": 0.10373878479003906,
+      "learning_rate": 3.125e-05,
+      "loss": 0.0006,
+      "step": 190
+    },
+    {
+      "epoch": 0.19753086419753085,
+      "grad_norm": 0.002619905164465308,
+      "learning_rate": 3.289473684210527e-05,
+      "loss": 0.0006,
+      "step": 200
+    },
+    {
+      "epoch": 0.2074074074074074,
+      "grad_norm": 0.007042820565402508,
+      "learning_rate": 3.4539473684210524e-05,
+      "loss": 0.0015,
+      "step": 210
+    },
+    {
+      "epoch": 0.21728395061728395,
+      "grad_norm": 0.0016206403961405158,
+      "learning_rate": 3.618421052631579e-05,
+      "loss": 0.0049,
+      "step": 220
+    },
+    {
+      "epoch": 0.2271604938271605,
+      "grad_norm": 0.001877307309769094,
+      "learning_rate": 3.7828947368421054e-05,
+      "loss": 0.0001,
+      "step": 230
+    },
+    {
+      "epoch": 0.23703703703703705,
+      "grad_norm": 0.003795365337282419,
+      "learning_rate": 3.9473684210526316e-05,
+      "loss": 0.0001,
+      "step": 240
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 0.008357529528439045,
+      "learning_rate": 4.111842105263158e-05,
+      "loss": 0.004,
+      "step": 250
+    },
+    {
+      "epoch": 0.25679012345679014,
+      "grad_norm": 0.026294540613889694,
+      "learning_rate": 4.2763157894736847e-05,
+      "loss": 0.0002,
+      "step": 260
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.08903225511312485,
+      "learning_rate": 4.440789473684211e-05,
+      "loss": 0.0005,
+      "step": 270
+    },
+    {
+      "epoch": 0.2765432098765432,
+      "grad_norm": 0.05173858627676964,
+      "learning_rate": 4.605263157894737e-05,
+      "loss": 0.0003,
+      "step": 280
+    },
+    {
+      "epoch": 0.28641975308641976,
+      "grad_norm": 0.036562711000442505,
+      "learning_rate": 4.769736842105263e-05,
+      "loss": 0.0012,
+      "step": 290
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.008022695779800415,
+      "learning_rate": 4.9342105263157894e-05,
+      "loss": 0.0036,
+      "step": 300
+    },
+    {
+      "epoch": 0.30617283950617286,
+      "grad_norm": 0.0021413813810795546,
+      "learning_rate": 4.999940495590975e-05,
+      "loss": 0.0006,
+      "step": 310
+    },
+    {
+      "epoch": 0.3160493827160494,
+      "grad_norm": 0.015379426069557667,
+      "learning_rate": 4.999576867793816e-05,
+      "loss": 0.0092,
+      "step": 320
+    },
+    {
+      "epoch": 0.32592592592592595,
+      "grad_norm": 0.003894766792654991,
+      "learning_rate": 4.9988827182291254e-05,
+      "loss": 0.001,
+      "step": 330
+    },
+    {
+      "epoch": 0.3358024691358025,
+      "grad_norm": 0.0016231742920354009,
+      "learning_rate": 4.997858138685056e-05,
+      "loss": 0.0001,
+      "step": 340
+    },
+    {
+      "epoch": 0.345679012345679,
+      "grad_norm": 0.0015260468935593963,
+      "learning_rate": 4.996503264642876e-05,
+      "loss": 0.0016,
+      "step": 350
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.03330058977007866,
+      "learning_rate": 4.994818275259052e-05,
+      "loss": 0.0013,
+      "step": 360
+    },
+    {
+      "epoch": 0.3654320987654321,
+      "grad_norm": 0.002741268603131175,
+      "learning_rate": 4.992803393341563e-05,
+      "loss": 0.0017,
+      "step": 370
+    },
+    {
+      "epoch": 0.37530864197530867,
+      "grad_norm": 0.004990574903786182,
+      "learning_rate": 4.9904588853204365e-05,
+      "loss": 0.0001,
+      "step": 380
+    },
+    {
+      "epoch": 0.3851851851851852,
+      "grad_norm": 0.013514043763279915,
+      "learning_rate": 4.9877850612125173e-05,
+      "loss": 0.0001,
+      "step": 390
+    },
+    {
+      "epoch": 0.3950617283950617,
+      "grad_norm": 0.0015880317660048604,
+      "learning_rate": 4.984782274580476e-05,
+      "loss": 0.0001,
+      "step": 400
+    },
+    {
+      "epoch": 0.4049382716049383,
+      "grad_norm": 0.002702023135498166,
+      "learning_rate": 4.981450922486053e-05,
+      "loss": 0.0001,
+      "step": 410
+    },
+    {
+      "epoch": 0.4148148148148148,
+      "grad_norm": 0.0020927605219185352,
+      "learning_rate": 4.977791445437559e-05,
+      "loss": 0.0001,
+      "step": 420
+    },
+    {
+      "epoch": 0.4246913580246914,
+      "grad_norm": 0.0007626357255503535,
+      "learning_rate": 4.973804327331625e-05,
+      "loss": 0.0002,
+      "step": 430
+    },
+    {
+      "epoch": 0.4345679012345679,
+      "grad_norm": 0.0026151000056415796,
+      "learning_rate": 4.969490095389213e-05,
+      "loss": 0.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.0007740291184745729,
+      "learning_rate": 4.964849320085905e-05,
+      "loss": 0.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.454320987654321,
+      "grad_norm": 0.0005287025705911219,
+      "learning_rate": 4.9598826150764656e-05,
+      "loss": 0.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.4641975308641975,
+      "grad_norm": 0.0004778858565259725,
+      "learning_rate": 4.9545906371137e-05,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.4740740740740741,
+      "grad_norm": 0.0007034554146230221,
+      "learning_rate": 4.9489740859616094e-05,
+      "loss": 0.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.4839506172839506,
+      "grad_norm": 0.0006262129172682762,
+      "learning_rate": 4.9430337043028604e-05,
+      "loss": 0.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.00045443352428264916,
+      "learning_rate": 4.9367702776405806e-05,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "eval_nlpcc25_task1_dev_accuracy": 0.9995238095238096,
+      "eval_nlpcc25_task1_dev_loss": 0.0022831459064036608,
+      "eval_nlpcc25_task1_dev_runtime": 2528.8573,
+      "eval_nlpcc25_task1_dev_samples_per_second": 1.107,
+      "eval_nlpcc25_task1_dev_steps_per_second": 0.277,
+      "step": 500
+    },
+    {
+      "epoch": 0.5037037037037037,
+      "grad_norm": 0.0003733730991370976,
+      "learning_rate": 4.930184634194488e-05,
+      "loss": 0.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.5135802469135803,
+      "grad_norm": 0.0003028757928404957,
+      "learning_rate": 4.923277644791378e-05,
+      "loss": 0.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.5234567901234568,
+      "grad_norm": 0.00028728952747769654,
+      "learning_rate": 4.9160502227499704e-05,
+      "loss": 0.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.0003644278913270682,
+      "learning_rate": 4.908503323760143e-05,
+      "loss": 0.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.5432098765432098,
+      "grad_norm": 0.0005966073367744684,
+      "learning_rate": 4.900637945756554e-05,
+      "loss": 0.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.5530864197530864,
+      "grad_norm": 0.000367969973012805,
+      "learning_rate": 4.892455128786692e-05,
+      "loss": 0.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.562962962962963,
+      "grad_norm": 0.0002780740906018764,
+      "learning_rate": 4.8839559548733436e-05,
+      "loss": 0.0077,
+      "step": 570
+    },
+    {
+      "epoch": 0.5728395061728395,
+      "grad_norm": 0.00031342540751211345,
+      "learning_rate": 4.875141547871519e-05,
+      "loss": 0.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.582716049382716,
+      "grad_norm": 0.000353014562278986,
+      "learning_rate": 4.866013073319841e-05,
+      "loss": 0.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.00029066085699014366,
+      "learning_rate": 4.856571738286426e-05,
+      "loss": 0.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.6024691358024692,
+      "grad_norm": 0.00024000390840228647,
+      "learning_rate": 4.8468187912092744e-05,
+      "loss": 0.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.6123456790123457,
+      "grad_norm": 0.0003632376901805401,
+      "learning_rate": 4.836755521731183e-05,
+      "loss": 0.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.00029751085094176233,
+      "learning_rate": 4.826383260529221e-05,
+      "loss": 0.0002,
+      "step": 630
+    },
+    {
+      "epoch": 0.6320987654320988,
+      "grad_norm": 3.190973997116089,
+      "learning_rate": 4.815703379138765e-05,
+      "loss": 0.0017,
+      "step": 640
+    },
+    {
+      "epoch": 0.6419753086419753,
+      "grad_norm": 0.18289895355701447,
+      "learning_rate": 4.804717289772147e-05,
+      "loss": 0.0043,
+      "step": 650
+    },
+    {
+      "epoch": 0.6518518518518519,
+      "grad_norm": 0.2459922581911087,
+      "learning_rate": 4.7934264451319105e-05,
+      "loss": 0.003,
+      "step": 660
+    },
+    {
+      "epoch": 0.6617283950617284,
+      "grad_norm": 0.004725860431790352,
+      "learning_rate": 4.7818323382187214e-05,
+      "loss": 0.0002,
+      "step": 670
+    },
+    {
+      "epoch": 0.671604938271605,
+      "grad_norm": 0.004160716664046049,
+      "learning_rate": 4.769936502133946e-05,
+      "loss": 0.0002,
+      "step": 680
+    },
+    {
+      "epoch": 0.6814814814814815,
+      "grad_norm": 0.002101948019117117,
+      "learning_rate": 4.7577405098769256e-05,
+      "loss": 0.0001,
+      "step": 690
+    },
+    {
+      "epoch": 0.691358024691358,
+      "grad_norm": 0.0015966896899044514,
+      "learning_rate": 4.74524597413698e-05,
+      "loss": 0.0001,
+      "step": 700
+    },
+    {
+      "epoch": 0.7012345679012346,
+      "grad_norm": 0.0010343171888962388,
+      "learning_rate": 4.732454547080159e-05,
+      "loss": 0.0,
+      "step": 710
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.0007301874575205147,
+      "learning_rate": 4.7193679201307705e-05,
+      "loss": 0.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.7209876543209877,
+      "grad_norm": 0.0008054127101786435,
+      "learning_rate": 4.705987823747731e-05,
+      "loss": 0.0,
+      "step": 730
+    },
+    {
+      "epoch": 0.7308641975308642,
+      "grad_norm": 0.0006862932350486517,
+      "learning_rate": 4.692316027195733e-05,
+      "loss": 0.0001,
+      "step": 740
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.0005865858984179795,
+      "learning_rate": 4.678354338311306e-05,
+      "loss": 0.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.7506172839506173,
+      "grad_norm": 0.0004720942524727434,
+      "learning_rate": 4.6641046032637516e-05,
+      "loss": 0.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.7604938271604939,
+      "grad_norm": 0.0004310516524128616,
+      "learning_rate": 4.6495687063110325e-05,
+      "loss": 0.0,
+      "step": 770
+    },
+    {
+      "epoch": 0.7703703703703704,
+      "grad_norm": 0.00043949694372713566,
+      "learning_rate": 4.634748569550612e-05,
+      "loss": 0.0,
+      "step": 780
+    },
+    {
+      "epoch": 0.7802469135802469,
+      "grad_norm": 0.0004090226429980248,
+      "learning_rate": 4.61964615266529e-05,
+      "loss": 0.0,
+      "step": 790
+    },
+    {
+      "epoch": 0.7901234567901234,
+      "grad_norm": 0.00037527765380218625,
+      "learning_rate": 4.6042634526640755e-05,
+      "loss": 0.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.0162104368209839,
+      "learning_rate": 4.588602503618118e-05,
+      "loss": 0.0021,
+      "step": 810
+    },
+    {
+      "epoch": 0.8098765432098766,
+      "grad_norm": 1.3063777685165405,
+      "learning_rate": 4.572665376391741e-05,
+      "loss": 0.0006,
+      "step": 820
+    },
+    {
+      "epoch": 0.8197530864197531,
+      "grad_norm": 0.9236663579940796,
+      "learning_rate": 4.55645417836861e-05,
+      "loss": 0.0058,
+      "step": 830
+    },
+    {
+      "epoch": 0.8296296296296296,
+      "grad_norm": 0.01748817227780819,
+      "learning_rate": 4.5399710531730685e-05,
+      "loss": 0.0025,
+      "step": 840
+    },
+    {
+      "epoch": 0.8395061728395061,
+      "grad_norm": 0.003460384439677,
+      "learning_rate": 4.5232181803866886e-05,
+      "loss": 0.0005,
+      "step": 850
+    },
+    {
+      "epoch": 0.8493827160493828,
+      "grad_norm": 0.0013236172962933779,
+      "learning_rate": 4.506197775260055e-05,
+      "loss": 0.0001,
+      "step": 860
+    },
+    {
+      "epoch": 0.8592592592592593,
+      "grad_norm": 0.0011838016798719764,
+      "learning_rate": 4.4889120884198495e-05,
+      "loss": 0.0,
+      "step": 870
+    },
+    {
+      "epoch": 0.8691358024691358,
+      "grad_norm": 0.0007675419910810888,
+      "learning_rate": 4.47136340557124e-05,
+      "loss": 0.0,
+      "step": 880
+    },
+    {
+      "epoch": 0.8790123456790123,
+      "grad_norm": 0.0007905301754362881,
+      "learning_rate": 4.453554047195644e-05,
+      "loss": 0.0,
+      "step": 890
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.0005061720148660243,
+      "learning_rate": 4.435486368243888e-05,
+      "loss": 0.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.8987654320987655,
+      "grad_norm": 0.0005205022753216326,
+      "learning_rate": 4.417162757824808e-05,
+      "loss": 0.0,
+      "step": 910
+    },
+    {
+      "epoch": 0.908641975308642,
+      "grad_norm": 0.0004827196535188705,
+      "learning_rate": 4.398585638889335e-05,
+      "loss": 0.0,
+      "step": 920
+    },
+    {
+      "epoch": 0.9185185185185185,
+      "grad_norm": 0.000379192759282887,
+      "learning_rate": 4.379757467910113e-05,
+      "loss": 0.0,
+      "step": 930
+    },
+    {
+      "epoch": 0.928395061728395,
+      "grad_norm": 0.00045221165055409074,
+      "learning_rate": 4.3606807345566616e-05,
+      "loss": 0.0,
+      "step": 940
+    },
+    {
+      "epoch": 0.9382716049382716,
+      "grad_norm": 0.0005233365809544921,
+      "learning_rate": 4.341357961366181e-05,
+      "loss": 0.0,
+      "step": 950
+    },
+    {
+      "epoch": 0.9481481481481482,
+      "grad_norm": 0.0002833159815054387,
+      "learning_rate": 4.3217917034099823e-05,
+      "loss": 0.0,
+      "step": 960
+    },
+    {
+      "epoch": 0.9580246913580247,
+      "grad_norm": 0.00043191161239519715,
+      "learning_rate": 4.301984547955635e-05,
+      "loss": 0.0,
+      "step": 970
+    },
+    {
+      "epoch": 0.9679012345679012,
+      "grad_norm": 0.0004523663374129683,
+      "learning_rate": 4.281939114124843e-05,
+      "loss": 0.0,
+      "step": 980
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.00025242462288588285,
+      "learning_rate": 4.261658052547124e-05,
+      "loss": 0.0,
+      "step": 990
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.0006344653083942831,
+      "learning_rate": 4.241144045009304e-05,
+      "loss": 0.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "eval_nlpcc25_task1_dev_accuracy": 0.9996031746031745,
+      "eval_nlpcc25_task1_dev_loss": 0.002990948036313057,
+      "eval_nlpcc25_task1_dev_runtime": 2528.4874,
+      "eval_nlpcc25_task1_dev_samples_per_second": 1.107,
+      "eval_nlpcc25_task1_dev_steps_per_second": 0.277,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9975308641975309,
+      "grad_norm": 0.0005013208137825131,
+      "learning_rate": 4.22039980410091e-05,
+      "loss": 0.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.0069135802469136,
+      "grad_norm": 0.0003089129750151187,
+      "learning_rate": 4.199428072855476e-05,
+      "loss": 0.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.0167901234567902,
+      "grad_norm": 0.00048567031626589596,
+      "learning_rate": 4.1782316243878314e-05,
+      "loss": 0.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.0266666666666666,
+      "grad_norm": 0.0002530143829062581,
+      "learning_rate": 4.1568132615274094e-05,
+      "loss": 0.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.0365432098765432,
+      "grad_norm": 0.00028351074433885515,
+      "learning_rate": 4.1351758164476225e-05,
+      "loss": 0.0001,
+      "step": 1050
+    },
+    {
+      "epoch": 1.0464197530864197,
+      "grad_norm": 0.0005833515897393227,
+      "learning_rate": 4.113322150291365e-05,
+      "loss": 0.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.0562962962962963,
+      "grad_norm": 0.0011448035947978497,
+      "learning_rate": 4.091255152792678e-05,
+      "loss": 0.0028,
+      "step": 1070
+    },
+    {
+      "epoch": 1.066172839506173,
+      "grad_norm": 0.025126419961452484,
+      "learning_rate": 4.0689777418946394e-05,
+      "loss": 0.0002,
+      "step": 1080
+    },
+    {
+      "epoch": 1.0760493827160493,
+      "grad_norm": 0.0005254483548924327,
+      "learning_rate": 4.0464928633635196e-05,
+      "loss": 0.0006,
+      "step": 1090
+    },
+    {
+      "epoch": 1.085925925925926,
+      "grad_norm": 0.0009111575200222433,
+      "learning_rate": 4.023803490399258e-05,
+      "loss": 0.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0958024691358024,
+      "grad_norm": 0.000739308656193316,
+      "learning_rate": 4.000912623242318e-05,
+      "loss": 0.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.105679012345679,
+      "grad_norm": 0.0005893895868211985,
+      "learning_rate": 3.977823288776955e-05,
+      "loss": 0.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.1155555555555556,
+      "grad_norm": 0.00036915784585289657,
+      "learning_rate": 3.954538540130978e-05,
+      "loss": 0.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.125432098765432,
+      "grad_norm": 0.0005508523900061846,
+      "learning_rate": 3.9310614562720214e-05,
+      "loss": 0.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.1353086419753087,
+      "grad_norm": 0.0009192466968670487,
+      "learning_rate": 3.9073951416004143e-05,
+      "loss": 0.0002,
+      "step": 1150
+    },
+    {
+      "epoch": 1.145185185185185,
+      "grad_norm": 0.0004524670075625181,
+      "learning_rate": 3.8835427255386856e-05,
+      "loss": 0.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.1550617283950617,
+      "grad_norm": 0.000336712779244408,
+      "learning_rate": 3.859507362117748e-05,
+      "loss": 0.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.1649382716049383,
+      "grad_norm": 0.00038848226540721953,
+      "learning_rate": 3.8352922295598476e-05,
+      "loss": 0.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.1748148148148148,
+      "grad_norm": 0.0007016750751063228,
+      "learning_rate": 3.810900529858295e-05,
+      "loss": 0.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.1846913580246914,
+      "grad_norm": 0.00020055304048582911,
+      "learning_rate": 3.786335488354068e-05,
+      "loss": 0.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.194567901234568,
+      "grad_norm": 0.0006126250373199582,
+      "learning_rate": 3.7616003533093204e-05,
+      "loss": 0.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.2044444444444444,
+      "grad_norm": 0.00017670773377176374,
+      "learning_rate": 3.736698395477857e-05,
+      "loss": 0.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.214320987654321,
+      "grad_norm": 0.0001492701849201694,
+      "learning_rate": 3.7116329076726455e-05,
+      "loss": 0.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.2241975308641975,
+      "grad_norm": 0.0001376178115606308,
+      "learning_rate": 3.6864072043303945e-05,
+      "loss": 0.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.234074074074074,
+      "grad_norm": 0.0001676941174082458,
+      "learning_rate": 3.661024621073291e-05,
+      "loss": 0.0071,
+      "step": 1250
+    },
+    {
+      "epoch": 1.2439506172839505,
+      "grad_norm": 0.00019377398712094873,
+      "learning_rate": 3.635488514267923e-05,
+      "loss": 0.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.2538271604938271,
+      "grad_norm": 0.0001418793690390885,
+      "learning_rate": 3.609802260581464e-05,
+      "loss": 0.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.2637037037037038,
+      "grad_norm": 0.00016002310439944267,
+      "learning_rate": 3.583969256535172e-05,
+      "loss": 0.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.2735802469135802,
+      "grad_norm": 0.00014259129238780588,
+      "learning_rate": 3.5579929180552676e-05,
+      "loss": 0.0,
+      "step": 1290
+    },
+    {
+      "epoch": 1.2834567901234568,
+      "grad_norm": 0.000264517730101943,
+      "learning_rate": 3.531876680021235e-05,
+      "loss": 0.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.2933333333333334,
+      "grad_norm": 0.00015705930127296597,
+      "learning_rate": 3.5056239958116336e-05,
+      "loss": 0.0,
+      "step": 1310
+    },
+    {
+      "epoch": 1.3032098765432099,
+      "grad_norm": 0.00022515420278068632,
+      "learning_rate": 3.479238336847444e-05,
+      "loss": 0.0,
+      "step": 1320
+    },
+    {
+      "epoch": 1.3130864197530865,
+      "grad_norm": 0.00014641444431617856,
+      "learning_rate": 3.4527231921330464e-05,
+      "loss": 0.0,
+      "step": 1330
+    },
+    {
+      "epoch": 1.322962962962963,
+      "grad_norm": 9.774778300197795e-05,
+      "learning_rate": 3.426082067794863e-05,
+      "loss": 0.0,
+      "step": 1340
+    },
+    {
+      "epoch": 1.3328395061728395,
+      "grad_norm": 0.00012512759712990373,
+      "learning_rate": 3.399318486617734e-05,
+      "loss": 0.0,
+      "step": 1350
+    },
+    {
+      "epoch": 1.342716049382716,
+      "grad_norm": 0.00013536612095776945,
+      "learning_rate": 3.372435987579108e-05,
+      "loss": 0.0,
+      "step": 1360
+    },
+    {
+      "epoch": 1.3525925925925926,
+      "grad_norm": 0.00013231099001131952,
+      "learning_rate": 3.345438125381065e-05,
+      "loss": 0.0,
+      "step": 1370
+    },
+    {
+      "epoch": 1.3624691358024692,
+      "grad_norm": 0.00011779498163377866,
+      "learning_rate": 3.318328469980285e-05,
+      "loss": 0.0,
+      "step": 1380
+    },
+    {
+      "epoch": 1.3723456790123456,
+      "grad_norm": 0.0001909748971229419,
+      "learning_rate": 3.291110606115984e-05,
+      "loss": 0.0,
+      "step": 1390
+    },
+    {
+      "epoch": 1.3822222222222222,
+      "grad_norm": 0.0001980375382117927,
+      "learning_rate": 3.263788132835898e-05,
+      "loss": 0.0,
+      "step": 1400
+    },
+    {
+      "epoch": 1.3920987654320989,
+      "grad_norm": 0.00011503389396239072,
+      "learning_rate": 3.236364663020384e-05,
+      "loss": 0.0,
+      "step": 1410
+    },
+    {
+      "epoch": 1.4019753086419753,
+      "grad_norm": 0.00013515223690774292,
+      "learning_rate": 3.208843822904679e-05,
+      "loss": 0.0,
+      "step": 1420
+    },
+    {
+      "epoch": 1.411851851851852,
+      "grad_norm": 0.00011641118908300996,
+      "learning_rate": 3.1812292515994e-05,
+      "loss": 0.0,
+      "step": 1430
+    },
+    {
+      "epoch": 1.4217283950617283,
+      "grad_norm": 9.361303091282025e-05,
+      "learning_rate": 3.1535246006093414e-05,
+      "loss": 0.0001,
+      "step": 1440
+    },
+    {
+      "epoch": 1.431604938271605,
+      "grad_norm": 0.00013731363287661225,
+      "learning_rate": 3.125733533350633e-05,
+      "loss": 0.0,
+      "step": 1450
+    },
+    {
+      "epoch": 1.4414814814814814,
+      "grad_norm": 0.000537275685928762,
+      "learning_rate": 3.097859724666322e-05,
+      "loss": 0.0026,
+      "step": 1460
+    },
+    {
+      "epoch": 1.451358024691358,
+      "grad_norm": 0.4905455708503723,
+      "learning_rate": 3.069906860340443e-05,
+      "loss": 0.0029,
+      "step": 1470
+    },
+    {
+      "epoch": 1.4612345679012346,
+      "grad_norm": 0.004352442920207977,
+      "learning_rate": 3.041878636610644e-05,
+      "loss": 0.0001,
+      "step": 1480
+    },
+    {
+      "epoch": 1.471111111111111,
+      "grad_norm": 0.0011432188330218196,
+      "learning_rate": 3.0137787596794304e-05,
+      "loss": 0.0,
+      "step": 1490
+    },
+    {
+      "epoch": 1.4809876543209877,
+      "grad_norm": 0.0010975116165354848,
+      "learning_rate": 2.9856109452240877e-05,
+      "loss": 0.0,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4809876543209877,
+      "eval_nlpcc25_task1_dev_accuracy": 0.9998015873015873,
+      "eval_nlpcc25_task1_dev_loss": 0.0016044721705839038,
+      "eval_nlpcc25_task1_dev_runtime": 2528.9364,
+      "eval_nlpcc25_task1_dev_samples_per_second": 1.107,
+      "eval_nlpcc25_task1_dev_steps_per_second": 0.277,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3036,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.610691447990518e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

Qwen2.5-7B-Instruct-lora-2/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc27925817800cee3170b92f598d1cfe9fce4b0491f781c2f4977cfd2644a9a
+size 5752

Qwen2.5-7B-Instruct-lora-2/checkpoint-2000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /data/zhaoguoyu/Experiments/mgtd-sys/detector/ckpt/Qwen2.5-7B-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 0.15.0

Qwen2.5-7B-Instruct-lora-2/checkpoint-2000/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/zhaoguoyu/Experiments/mgtd-sys/detector/ckpt/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

Qwen2.5-7B-Instruct-lora-2/checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b687877fe9030563f9e59d9d42f63279b4329498ff477bf08180340718c56e
+size 80792096

Qwen2.5-7B-Instruct-lora-2/checkpoint-2000/added_tokens.json

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

Qwen2.5-7B-Instruct-lora-2/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d3fbbe54d5fcaac3f48dce4e4e215c54e8a6f303133dae7727fed45dbf732b6
+size 161810282

Qwen2.5-7B-Instruct-lora-2/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
+size 14244

Qwen2.5-7B-Instruct-lora-2/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f42ba79e7d828e6bd9344c98bfd844a063f0f6271f1c6145ceffd59a0728e79
+size 1064

Qwen2.5-7B-Instruct-lora-2/checkpoint-2000/special_tokens_map.json

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

Qwen2.5-7B-Instruct-lora-2/checkpoint-2000/tokenizer.json

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

Qwen2.5-7B-Instruct-lora-2/checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

Qwen2.5-7B-Instruct-lora-2/checkpoint-2000/trainer_state.json

@@ -0,0 +1,1470 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9748148148148148,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009876543209876543,
+      "grad_norm": 7.599112033843994,
+      "learning_rate": 1.6447368421052632e-06,
+      "loss": 4.2059,
+      "step": 10
+    },
+    {
+      "epoch": 0.019753086419753086,
+      "grad_norm": 6.403433322906494,
+      "learning_rate": 3.2894736842105265e-06,
+      "loss": 4.1463,
+      "step": 20
+    },
+    {
+      "epoch": 0.02962962962962963,
+      "grad_norm": 9.776185989379883,
+      "learning_rate": 4.9342105263157895e-06,
+      "loss": 4.1087,
+      "step": 30
+    },
+    {
+      "epoch": 0.03950617283950617,
+      "grad_norm": 5.836405277252197,
+      "learning_rate": 6.578947368421053e-06,
+      "loss": 3.7657,
+      "step": 40
+    },
+    {
+      "epoch": 0.04938271604938271,
+      "grad_norm": 4.362349033355713,
+      "learning_rate": 8.223684210526317e-06,
+      "loss": 3.2134,
+      "step": 50
+    },
+    {
+      "epoch": 0.05925925925925926,
+      "grad_norm": 5.1398701667785645,
+      "learning_rate": 9.868421052631579e-06,
+      "loss": 2.6238,
+      "step": 60
+    },
+    {
+      "epoch": 0.0691358024691358,
+      "grad_norm": 8.642521858215332,
+      "learning_rate": 1.1513157894736843e-05,
+      "loss": 1.5929,
+      "step": 70
+    },
+    {
+      "epoch": 0.07901234567901234,
+      "grad_norm": 1.0219271183013916,
+      "learning_rate": 1.3157894736842106e-05,
+      "loss": 0.1491,
+      "step": 80
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.4035845100879669,
+      "learning_rate": 1.4802631578947368e-05,
+      "loss": 0.0206,
+      "step": 90
+    },
+    {
+      "epoch": 0.09876543209876543,
+      "grad_norm": 0.6767832636833191,
+      "learning_rate": 1.6447368421052635e-05,
+      "loss": 0.0073,
+      "step": 100
+    },
+    {
+      "epoch": 0.10864197530864197,
+      "grad_norm": 0.014764077961444855,
+      "learning_rate": 1.8092105263157896e-05,
+      "loss": 0.0011,
+      "step": 110
+    },
+    {
+      "epoch": 0.11851851851851852,
+      "grad_norm": 0.15152056515216827,
+      "learning_rate": 1.9736842105263158e-05,
+      "loss": 0.0005,
+      "step": 120
+    },
+    {
+      "epoch": 0.12839506172839507,
+      "grad_norm": 0.06782546639442444,
+      "learning_rate": 2.1381578947368423e-05,
+      "loss": 0.0014,
+      "step": 130
+    },
+    {
+      "epoch": 0.1382716049382716,
+      "grad_norm": 0.03198217228055,
+      "learning_rate": 2.3026315789473685e-05,
+      "loss": 0.0009,
+      "step": 140
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.02691480703651905,
+      "learning_rate": 2.4671052631578947e-05,
+      "loss": 0.0024,
+      "step": 150
+    },
+    {
+      "epoch": 0.1580246913580247,
+      "grad_norm": 0.0057847509160637856,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 0.0001,
+      "step": 160
+    },
+    {
+      "epoch": 0.16790123456790124,
+      "grad_norm": 0.003663571085780859,
+      "learning_rate": 2.7960526315789477e-05,
+      "loss": 0.0002,
+      "step": 170
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.004447426181286573,
+      "learning_rate": 2.9605263157894735e-05,
+      "loss": 0.0003,
+      "step": 180
+    },
+    {
+      "epoch": 0.18765432098765433,
+      "grad_norm": 0.10373878479003906,
+      "learning_rate": 3.125e-05,
+      "loss": 0.0006,
+      "step": 190
+    },
+    {
+      "epoch": 0.19753086419753085,
+      "grad_norm": 0.002619905164465308,
+      "learning_rate": 3.289473684210527e-05,
+      "loss": 0.0006,
+      "step": 200
+    },
+    {
+      "epoch": 0.2074074074074074,
+      "grad_norm": 0.007042820565402508,
+      "learning_rate": 3.4539473684210524e-05,
+      "loss": 0.0015,
+      "step": 210
+    },
+    {
+      "epoch": 0.21728395061728395,
+      "grad_norm": 0.0016206403961405158,
+      "learning_rate": 3.618421052631579e-05,
+      "loss": 0.0049,
+      "step": 220
+    },
+    {
+      "epoch": 0.2271604938271605,
+      "grad_norm": 0.001877307309769094,
+      "learning_rate": 3.7828947368421054e-05,
+      "loss": 0.0001,
+      "step": 230
+    },
+    {
+      "epoch": 0.23703703703703705,
+      "grad_norm": 0.003795365337282419,
+      "learning_rate": 3.9473684210526316e-05,
+      "loss": 0.0001,
+      "step": 240
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 0.008357529528439045,
+      "learning_rate": 4.111842105263158e-05,
+      "loss": 0.004,
+      "step": 250
+    },
+    {
+      "epoch": 0.25679012345679014,
+      "grad_norm": 0.026294540613889694,
+      "learning_rate": 4.2763157894736847e-05,
+      "loss": 0.0002,
+      "step": 260
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.08903225511312485,
+      "learning_rate": 4.440789473684211e-05,
+      "loss": 0.0005,
+      "step": 270
+    },
+    {
+      "epoch": 0.2765432098765432,
+      "grad_norm": 0.05173858627676964,
+      "learning_rate": 4.605263157894737e-05,
+      "loss": 0.0003,
+      "step": 280
+    },
+    {
+      "epoch": 0.28641975308641976,
+      "grad_norm": 0.036562711000442505,
+      "learning_rate": 4.769736842105263e-05,
+      "loss": 0.0012,
+      "step": 290
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.008022695779800415,
+      "learning_rate": 4.9342105263157894e-05,
+      "loss": 0.0036,
+      "step": 300
+    },
+    {
+      "epoch": 0.30617283950617286,
+      "grad_norm": 0.0021413813810795546,
+      "learning_rate": 4.999940495590975e-05,
+      "loss": 0.0006,
+      "step": 310
+    },
+    {
+      "epoch": 0.3160493827160494,
+      "grad_norm": 0.015379426069557667,
+      "learning_rate": 4.999576867793816e-05,
+      "loss": 0.0092,
+      "step": 320
+    },
+    {
+      "epoch": 0.32592592592592595,
+      "grad_norm": 0.003894766792654991,
+      "learning_rate": 4.9988827182291254e-05,
+      "loss": 0.001,
+      "step": 330
+    },
+    {
+      "epoch": 0.3358024691358025,
+      "grad_norm": 0.0016231742920354009,
+      "learning_rate": 4.997858138685056e-05,
+      "loss": 0.0001,
+      "step": 340
+    },
+    {
+      "epoch": 0.345679012345679,
+      "grad_norm": 0.0015260468935593963,
+      "learning_rate": 4.996503264642876e-05,
+      "loss": 0.0016,
+      "step": 350
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.03330058977007866,
+      "learning_rate": 4.994818275259052e-05,
+      "loss": 0.0013,
+      "step": 360
+    },
+    {
+      "epoch": 0.3654320987654321,
+      "grad_norm": 0.002741268603131175,
+      "learning_rate": 4.992803393341563e-05,
+      "loss": 0.0017,
+      "step": 370
+    },
+    {
+      "epoch": 0.37530864197530867,
+      "grad_norm": 0.004990574903786182,
+      "learning_rate": 4.9904588853204365e-05,
+      "loss": 0.0001,
+      "step": 380
+    },
+    {
+      "epoch": 0.3851851851851852,
+      "grad_norm": 0.013514043763279915,
+      "learning_rate": 4.9877850612125173e-05,
+      "loss": 0.0001,
+      "step": 390
+    },
+    {
+      "epoch": 0.3950617283950617,
+      "grad_norm": 0.0015880317660048604,
+      "learning_rate": 4.984782274580476e-05,
+      "loss": 0.0001,
+      "step": 400
+    },
+    {
+      "epoch": 0.4049382716049383,
+      "grad_norm": 0.002702023135498166,
+      "learning_rate": 4.981450922486053e-05,
+      "loss": 0.0001,
+      "step": 410
+    },
+    {
+      "epoch": 0.4148148148148148,
+      "grad_norm": 0.0020927605219185352,
+      "learning_rate": 4.977791445437559e-05,
+      "loss": 0.0001,
+      "step": 420
+    },
+    {
+      "epoch": 0.4246913580246914,
+      "grad_norm": 0.0007626357255503535,
+      "learning_rate": 4.973804327331625e-05,
+      "loss": 0.0002,
+      "step": 430
+    },
+    {
+      "epoch": 0.4345679012345679,
+      "grad_norm": 0.0026151000056415796,
+      "learning_rate": 4.969490095389213e-05,
+      "loss": 0.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.0007740291184745729,
+      "learning_rate": 4.964849320085905e-05,
+      "loss": 0.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.454320987654321,
+      "grad_norm": 0.0005287025705911219,
+      "learning_rate": 4.9598826150764656e-05,
+      "loss": 0.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.4641975308641975,
+      "grad_norm": 0.0004778858565259725,
+      "learning_rate": 4.9545906371137e-05,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.4740740740740741,
+      "grad_norm": 0.0007034554146230221,
+      "learning_rate": 4.9489740859616094e-05,
+      "loss": 0.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.4839506172839506,
+      "grad_norm": 0.0006262129172682762,
+      "learning_rate": 4.9430337043028604e-05,
+      "loss": 0.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.00045443352428264916,
+      "learning_rate": 4.9367702776405806e-05,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "eval_nlpcc25_task1_dev_accuracy": 0.9995238095238096,
+      "eval_nlpcc25_task1_dev_loss": 0.0022831459064036608,
+      "eval_nlpcc25_task1_dev_runtime": 2528.8573,
+      "eval_nlpcc25_task1_dev_samples_per_second": 1.107,
+      "eval_nlpcc25_task1_dev_steps_per_second": 0.277,
+      "step": 500
+    },
+    {
+      "epoch": 0.5037037037037037,
+      "grad_norm": 0.0003733730991370976,
+      "learning_rate": 4.930184634194488e-05,
+      "loss": 0.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.5135802469135803,
+      "grad_norm": 0.0003028757928404957,
+      "learning_rate": 4.923277644791378e-05,
+      "loss": 0.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.5234567901234568,
+      "grad_norm": 0.00028728952747769654,
+      "learning_rate": 4.9160502227499704e-05,
+      "loss": 0.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.0003644278913270682,
+      "learning_rate": 4.908503323760143e-05,
+      "loss": 0.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.5432098765432098,
+      "grad_norm": 0.0005966073367744684,
+      "learning_rate": 4.900637945756554e-05,
+      "loss": 0.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.5530864197530864,
+      "grad_norm": 0.000367969973012805,
+      "learning_rate": 4.892455128786692e-05,
+      "loss": 0.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.562962962962963,
+      "grad_norm": 0.0002780740906018764,
+      "learning_rate": 4.8839559548733436e-05,
+      "loss": 0.0077,
+      "step": 570
+    },
+    {
+      "epoch": 0.5728395061728395,
+      "grad_norm": 0.00031342540751211345,
+      "learning_rate": 4.875141547871519e-05,
+      "loss": 0.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.582716049382716,
+      "grad_norm": 0.000353014562278986,
+      "learning_rate": 4.866013073319841e-05,
+      "loss": 0.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.00029066085699014366,
+      "learning_rate": 4.856571738286426e-05,
+      "loss": 0.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.6024691358024692,
+      "grad_norm": 0.00024000390840228647,
+      "learning_rate": 4.8468187912092744e-05,
+      "loss": 0.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.6123456790123457,
+      "grad_norm": 0.0003632376901805401,
+      "learning_rate": 4.836755521731183e-05,
+      "loss": 0.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.00029751085094176233,
+      "learning_rate": 4.826383260529221e-05,
+      "loss": 0.0002,
+      "step": 630
+    },
+    {
+      "epoch": 0.6320987654320988,
+      "grad_norm": 3.190973997116089,
+      "learning_rate": 4.815703379138765e-05,
+      "loss": 0.0017,
+      "step": 640
+    },
+    {
+      "epoch": 0.6419753086419753,
+      "grad_norm": 0.18289895355701447,
+      "learning_rate": 4.804717289772147e-05,
+      "loss": 0.0043,
+      "step": 650
+    },
+    {
+      "epoch": 0.6518518518518519,
+      "grad_norm": 0.2459922581911087,
+      "learning_rate": 4.7934264451319105e-05,
+      "loss": 0.003,
+      "step": 660
+    },
+    {
+      "epoch": 0.6617283950617284,
+      "grad_norm": 0.004725860431790352,
+      "learning_rate": 4.7818323382187214e-05,
+      "loss": 0.0002,
+      "step": 670
+    },
+    {
+      "epoch": 0.671604938271605,
+      "grad_norm": 0.004160716664046049,
+      "learning_rate": 4.769936502133946e-05,
+      "loss": 0.0002,
+      "step": 680
+    },
+    {
+      "epoch": 0.6814814814814815,
+      "grad_norm": 0.002101948019117117,
+      "learning_rate": 4.7577405098769256e-05,
+      "loss": 0.0001,
+      "step": 690
+    },
+    {
+      "epoch": 0.691358024691358,
+      "grad_norm": 0.0015966896899044514,
+      "learning_rate": 4.74524597413698e-05,
+      "loss": 0.0001,
+      "step": 700
+    },
+    {
+      "epoch": 0.7012345679012346,
+      "grad_norm": 0.0010343171888962388,
+      "learning_rate": 4.732454547080159e-05,
+      "loss": 0.0,
+      "step": 710
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.0007301874575205147,
+      "learning_rate": 4.7193679201307705e-05,
+      "loss": 0.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.7209876543209877,
+      "grad_norm": 0.0008054127101786435,
+      "learning_rate": 4.705987823747731e-05,
+      "loss": 0.0,
+      "step": 730
+    },
+    {
+      "epoch": 0.7308641975308642,
+      "grad_norm": 0.0006862932350486517,
+      "learning_rate": 4.692316027195733e-05,
+      "loss": 0.0001,
+      "step": 740
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.0005865858984179795,
+      "learning_rate": 4.678354338311306e-05,
+      "loss": 0.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.7506172839506173,
+      "grad_norm": 0.0004720942524727434,
+      "learning_rate": 4.6641046032637516e-05,
+      "loss": 0.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.7604938271604939,
+      "grad_norm": 0.0004310516524128616,
+      "learning_rate": 4.6495687063110325e-05,
+      "loss": 0.0,
+      "step": 770
+    },
+    {
+      "epoch": 0.7703703703703704,
+      "grad_norm": 0.00043949694372713566,
+      "learning_rate": 4.634748569550612e-05,
+      "loss": 0.0,
+      "step": 780
+    },
+    {
+      "epoch": 0.7802469135802469,
+      "grad_norm": 0.0004090226429980248,
+      "learning_rate": 4.61964615266529e-05,
+      "loss": 0.0,
+      "step": 790
+    },
+    {
+      "epoch": 0.7901234567901234,
+      "grad_norm": 0.00037527765380218625,
+      "learning_rate": 4.6042634526640755e-05,
+      "loss": 0.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.0162104368209839,
+      "learning_rate": 4.588602503618118e-05,
+      "loss": 0.0021,
+      "step": 810
+    },
+    {
+      "epoch": 0.8098765432098766,
+      "grad_norm": 1.3063777685165405,
+      "learning_rate": 4.572665376391741e-05,
+      "loss": 0.0006,
+      "step": 820
+    },
+    {
+      "epoch": 0.8197530864197531,
+      "grad_norm": 0.9236663579940796,
+      "learning_rate": 4.55645417836861e-05,
+      "loss": 0.0058,
+      "step": 830
+    },
+    {
+      "epoch": 0.8296296296296296,
+      "grad_norm": 0.01748817227780819,
+      "learning_rate": 4.5399710531730685e-05,
+      "loss": 0.0025,
+      "step": 840
+    },
+    {
+      "epoch": 0.8395061728395061,
+      "grad_norm": 0.003460384439677,
+      "learning_rate": 4.5232181803866886e-05,
+      "loss": 0.0005,
+      "step": 850
+    },
+    {
+      "epoch": 0.8493827160493828,
+      "grad_norm": 0.0013236172962933779,
+      "learning_rate": 4.506197775260055e-05,
+      "loss": 0.0001,
+      "step": 860
+    },
+    {
+      "epoch": 0.8592592592592593,
+      "grad_norm": 0.0011838016798719764,
+      "learning_rate": 4.4889120884198495e-05,
+      "loss": 0.0,
+      "step": 870
+    },
+    {
+      "epoch": 0.8691358024691358,
+      "grad_norm": 0.0007675419910810888,
+      "learning_rate": 4.47136340557124e-05,
+      "loss": 0.0,
+      "step": 880
+    },
+    {
+      "epoch": 0.8790123456790123,
+      "grad_norm": 0.0007905301754362881,
+      "learning_rate": 4.453554047195644e-05,
+      "loss": 0.0,
+      "step": 890
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.0005061720148660243,
+      "learning_rate": 4.435486368243888e-05,
+      "loss": 0.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.8987654320987655,
+      "grad_norm": 0.0005205022753216326,
+      "learning_rate": 4.417162757824808e-05,
+      "loss": 0.0,
+      "step": 910
+    },
+    {
+      "epoch": 0.908641975308642,
+      "grad_norm": 0.0004827196535188705,
+      "learning_rate": 4.398585638889335e-05,
+      "loss": 0.0,
+      "step": 920
+    },
+    {
+      "epoch": 0.9185185185185185,
+      "grad_norm": 0.000379192759282887,
+      "learning_rate": 4.379757467910113e-05,
+      "loss": 0.0,
+      "step": 930
+    },
+    {
+      "epoch": 0.928395061728395,
+      "grad_norm": 0.00045221165055409074,
+      "learning_rate": 4.3606807345566616e-05,
+      "loss": 0.0,
+      "step": 940
+    },
+    {
+      "epoch": 0.9382716049382716,
+      "grad_norm": 0.0005233365809544921,
+      "learning_rate": 4.341357961366181e-05,
+      "loss": 0.0,
+      "step": 950
+    },
+    {
+      "epoch": 0.9481481481481482,
+      "grad_norm": 0.0002833159815054387,
+      "learning_rate": 4.3217917034099823e-05,
+      "loss": 0.0,
+      "step": 960
+    },
+    {
+      "epoch": 0.9580246913580247,
+      "grad_norm": 0.00043191161239519715,
+      "learning_rate": 4.301984547955635e-05,
+      "loss": 0.0,
+      "step": 970
+    },
+    {
+      "epoch": 0.9679012345679012,
+      "grad_norm": 0.0004523663374129683,
+      "learning_rate": 4.281939114124843e-05,
+      "loss": 0.0,
+      "step": 980
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.00025242462288588285,
+      "learning_rate": 4.261658052547124e-05,
+      "loss": 0.0,
+      "step": 990
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.0006344653083942831,
+      "learning_rate": 4.241144045009304e-05,
+      "loss": 0.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "eval_nlpcc25_task1_dev_accuracy": 0.9996031746031745,
+      "eval_nlpcc25_task1_dev_loss": 0.002990948036313057,
+      "eval_nlpcc25_task1_dev_runtime": 2528.4874,
+      "eval_nlpcc25_task1_dev_samples_per_second": 1.107,
+      "eval_nlpcc25_task1_dev_steps_per_second": 0.277,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9975308641975309,
+      "grad_norm": 0.0005013208137825131,
+      "learning_rate": 4.22039980410091e-05,
+      "loss": 0.0,
+      "step": 1010
+    },
+    {
+      "epoch": 1.0069135802469136,
+      "grad_norm": 0.0003089129750151187,
+      "learning_rate": 4.199428072855476e-05,
+      "loss": 0.0,
+      "step": 1020
+    },
+    {
+      "epoch": 1.0167901234567902,
+      "grad_norm": 0.00048567031626589596,
+      "learning_rate": 4.1782316243878314e-05,
+      "loss": 0.0,
+      "step": 1030
+    },
+    {
+      "epoch": 1.0266666666666666,
+      "grad_norm": 0.0002530143829062581,
+      "learning_rate": 4.1568132615274094e-05,
+      "loss": 0.0,
+      "step": 1040
+    },
+    {
+      "epoch": 1.0365432098765432,
+      "grad_norm": 0.00028351074433885515,
+      "learning_rate": 4.1351758164476225e-05,
+      "loss": 0.0001,
+      "step": 1050
+    },
+    {
+      "epoch": 1.0464197530864197,
+      "grad_norm": 0.0005833515897393227,
+      "learning_rate": 4.113322150291365e-05,
+      "loss": 0.0,
+      "step": 1060
+    },
+    {
+      "epoch": 1.0562962962962963,
+      "grad_norm": 0.0011448035947978497,
+      "learning_rate": 4.091255152792678e-05,
+      "loss": 0.0028,
+      "step": 1070
+    },
+    {
+      "epoch": 1.066172839506173,
+      "grad_norm": 0.025126419961452484,
+      "learning_rate": 4.0689777418946394e-05,
+      "loss": 0.0002,
+      "step": 1080
+    },
+    {
+      "epoch": 1.0760493827160493,
+      "grad_norm": 0.0005254483548924327,
+      "learning_rate": 4.0464928633635196e-05,
+      "loss": 0.0006,
+      "step": 1090
+    },
+    {
+      "epoch": 1.085925925925926,
+      "grad_norm": 0.0009111575200222433,
+      "learning_rate": 4.023803490399258e-05,
+      "loss": 0.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0958024691358024,
+      "grad_norm": 0.000739308656193316,
+      "learning_rate": 4.000912623242318e-05,
+      "loss": 0.0,
+      "step": 1110
+    },
+    {
+      "epoch": 1.105679012345679,
+      "grad_norm": 0.0005893895868211985,
+      "learning_rate": 3.977823288776955e-05,
+      "loss": 0.0,
+      "step": 1120
+    },
+    {
+      "epoch": 1.1155555555555556,
+      "grad_norm": 0.00036915784585289657,
+      "learning_rate": 3.954538540130978e-05,
+      "loss": 0.0,
+      "step": 1130
+    },
+    {
+      "epoch": 1.125432098765432,
+      "grad_norm": 0.0005508523900061846,
+      "learning_rate": 3.9310614562720214e-05,
+      "loss": 0.0,
+      "step": 1140
+    },
+    {
+      "epoch": 1.1353086419753087,
+      "grad_norm": 0.0009192466968670487,
+      "learning_rate": 3.9073951416004143e-05,
+      "loss": 0.0002,
+      "step": 1150
+    },
+    {
+      "epoch": 1.145185185185185,
+      "grad_norm": 0.0004524670075625181,
+      "learning_rate": 3.8835427255386856e-05,
+      "loss": 0.0,
+      "step": 1160
+    },
+    {
+      "epoch": 1.1550617283950617,
+      "grad_norm": 0.000336712779244408,
+      "learning_rate": 3.859507362117748e-05,
+      "loss": 0.0,
+      "step": 1170
+    },
+    {
+      "epoch": 1.1649382716049383,
+      "grad_norm": 0.00038848226540721953,
+      "learning_rate": 3.8352922295598476e-05,
+      "loss": 0.0,
+      "step": 1180
+    },
+    {
+      "epoch": 1.1748148148148148,
+      "grad_norm": 0.0007016750751063228,
+      "learning_rate": 3.810900529858295e-05,
+      "loss": 0.0,
+      "step": 1190
+    },
+    {
+      "epoch": 1.1846913580246914,
+      "grad_norm": 0.00020055304048582911,
+      "learning_rate": 3.786335488354068e-05,
+      "loss": 0.0,
+      "step": 1200
+    },
+    {
+      "epoch": 1.194567901234568,
+      "grad_norm": 0.0006126250373199582,
+      "learning_rate": 3.7616003533093204e-05,
+      "loss": 0.0,
+      "step": 1210
+    },
+    {
+      "epoch": 1.2044444444444444,
+      "grad_norm": 0.00017670773377176374,
+      "learning_rate": 3.736698395477857e-05,
+      "loss": 0.0,
+      "step": 1220
+    },
+    {
+      "epoch": 1.214320987654321,
+      "grad_norm": 0.0001492701849201694,
+      "learning_rate": 3.7116329076726455e-05,
+      "loss": 0.0,
+      "step": 1230
+    },
+    {
+      "epoch": 1.2241975308641975,
+      "grad_norm": 0.0001376178115606308,
+      "learning_rate": 3.6864072043303945e-05,
+      "loss": 0.0,
+      "step": 1240
+    },
+    {
+      "epoch": 1.234074074074074,
+      "grad_norm": 0.0001676941174082458,
+      "learning_rate": 3.661024621073291e-05,
+      "loss": 0.0071,
+      "step": 1250
+    },
+    {
+      "epoch": 1.2439506172839505,
+      "grad_norm": 0.00019377398712094873,
+      "learning_rate": 3.635488514267923e-05,
+      "loss": 0.0,
+      "step": 1260
+    },
+    {
+      "epoch": 1.2538271604938271,
+      "grad_norm": 0.0001418793690390885,
+      "learning_rate": 3.609802260581464e-05,
+      "loss": 0.0,
+      "step": 1270
+    },
+    {
+      "epoch": 1.2637037037037038,
+      "grad_norm": 0.00016002310439944267,
+      "learning_rate": 3.583969256535172e-05,
+      "loss": 0.0,
+      "step": 1280
+    },
+    {
+      "epoch": 1.2735802469135802,
+      "grad_norm": 0.00014259129238780588,
+      "learning_rate": 3.5579929180552676e-05,
+      "loss": 0.0,
+      "step": 1290
+    },
+    {
+      "epoch": 1.2834567901234568,
+      "grad_norm": 0.000264517730101943,
+      "learning_rate": 3.531876680021235e-05,
+      "loss": 0.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.2933333333333334,
+      "grad_norm": 0.00015705930127296597,
+      "learning_rate": 3.5056239958116336e-05,
+      "loss": 0.0,
+      "step": 1310
+    },
+    {
+      "epoch": 1.3032098765432099,
+      "grad_norm": 0.00022515420278068632,
+      "learning_rate": 3.479238336847444e-05,
+      "loss": 0.0,
+      "step": 1320
+    },
+    {
+      "epoch": 1.3130864197530865,
+      "grad_norm": 0.00014641444431617856,
+      "learning_rate": 3.4527231921330464e-05,
+      "loss": 0.0,
+      "step": 1330
+    },
+    {
+      "epoch": 1.322962962962963,
+      "grad_norm": 9.774778300197795e-05,
+      "learning_rate": 3.426082067794863e-05,
+      "loss": 0.0,
+      "step": 1340
+    },
+    {
+      "epoch": 1.3328395061728395,
+      "grad_norm": 0.00012512759712990373,
+      "learning_rate": 3.399318486617734e-05,
+      "loss": 0.0,
+      "step": 1350
+    },
+    {
+      "epoch": 1.342716049382716,
+      "grad_norm": 0.00013536612095776945,
+      "learning_rate": 3.372435987579108e-05,
+      "loss": 0.0,
+      "step": 1360
+    },
+    {
+      "epoch": 1.3525925925925926,
+      "grad_norm": 0.00013231099001131952,
+      "learning_rate": 3.345438125381065e-05,
+      "loss": 0.0,
+      "step": 1370
+    },
+    {
+      "epoch": 1.3624691358024692,
+      "grad_norm": 0.00011779498163377866,
+      "learning_rate": 3.318328469980285e-05,
+      "loss": 0.0,
+      "step": 1380
+    },
+    {
+      "epoch": 1.3723456790123456,
+      "grad_norm": 0.0001909748971229419,
+      "learning_rate": 3.291110606115984e-05,
+      "loss": 0.0,
+      "step": 1390
+    },
+    {
+      "epoch": 1.3822222222222222,
+      "grad_norm": 0.0001980375382117927,
+      "learning_rate": 3.263788132835898e-05,
+      "loss": 0.0,
+      "step": 1400
+    },
+    {
+      "epoch": 1.3920987654320989,
+      "grad_norm": 0.00011503389396239072,
+      "learning_rate": 3.236364663020384e-05,
+      "loss": 0.0,
+      "step": 1410
+    },
+    {
+      "epoch": 1.4019753086419753,
+      "grad_norm": 0.00013515223690774292,
+      "learning_rate": 3.208843822904679e-05,
+      "loss": 0.0,
+      "step": 1420
+    },
+    {
+      "epoch": 1.411851851851852,
+      "grad_norm": 0.00011641118908300996,
+      "learning_rate": 3.1812292515994e-05,
+      "loss": 0.0,
+      "step": 1430
+    },
+    {
+      "epoch": 1.4217283950617283,
+      "grad_norm": 9.361303091282025e-05,
+      "learning_rate": 3.1535246006093414e-05,
+      "loss": 0.0001,
+      "step": 1440
+    },
+    {
+      "epoch": 1.431604938271605,
+      "grad_norm": 0.00013731363287661225,
+      "learning_rate": 3.125733533350633e-05,
+      "loss": 0.0,
+      "step": 1450
+    },
+    {
+      "epoch": 1.4414814814814814,
+      "grad_norm": 0.000537275685928762,
+      "learning_rate": 3.097859724666322e-05,
+      "loss": 0.0026,
+      "step": 1460
+    },
+    {
+      "epoch": 1.451358024691358,
+      "grad_norm": 0.4905455708503723,
+      "learning_rate": 3.069906860340443e-05,
+      "loss": 0.0029,
+      "step": 1470
+    },
+    {
+      "epoch": 1.4612345679012346,
+      "grad_norm": 0.004352442920207977,
+      "learning_rate": 3.041878636610644e-05,
+      "loss": 0.0001,
+      "step": 1480
+    },
+    {
+      "epoch": 1.471111111111111,
+      "grad_norm": 0.0011432188330218196,
+      "learning_rate": 3.0137787596794304e-05,
+      "loss": 0.0,
+      "step": 1490
+    },
+    {
+      "epoch": 1.4809876543209877,
+      "grad_norm": 0.0010975116165354848,
+      "learning_rate": 2.9856109452240877e-05,
+      "loss": 0.0,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4809876543209877,
+      "eval_nlpcc25_task1_dev_accuracy": 0.9998015873015873,
+      "eval_nlpcc25_task1_dev_loss": 0.0016044721705839038,
+      "eval_nlpcc25_task1_dev_runtime": 2528.9364,
+      "eval_nlpcc25_task1_dev_samples_per_second": 1.107,
+      "eval_nlpcc25_task1_dev_steps_per_second": 0.277,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4908641975308643,
+      "grad_norm": 0.0008672023541294038,
+      "learning_rate": 2.957378917905353e-05,
+      "loss": 0.0,
+      "step": 1510
+    },
+    {
+      "epoch": 1.5007407407407407,
+      "grad_norm": 0.000826246221549809,
+      "learning_rate": 2.929086410874902e-05,
+      "loss": 0.0,
+      "step": 1520
+    },
+    {
+      "epoch": 1.5106172839506171,
+      "grad_norm": 0.0006294779013842344,
+      "learning_rate": 2.900737165281707e-05,
+      "loss": 0.0,
+      "step": 1530
+    },
+    {
+      "epoch": 1.520493827160494,
+      "grad_norm": 0.0006735110655426979,
+      "learning_rate": 2.8723349297773444e-05,
+      "loss": 0.0,
+      "step": 1540
+    },
+    {
+      "epoch": 1.5303703703703704,
+      "grad_norm": 0.000603811233304441,
+      "learning_rate": 2.8438834600203006e-05,
+      "loss": 0.0,
+      "step": 1550
+    },
+    {
+      "epoch": 1.5402469135802468,
+      "grad_norm": 0.001000316347926855,
+      "learning_rate": 2.8153865181793636e-05,
+      "loss": 0.0021,
+      "step": 1560
+    },
+    {
+      "epoch": 1.5501234567901234,
+      "grad_norm": 0.0026612593792378902,
+      "learning_rate": 2.7868478724361423e-05,
+      "loss": 0.0001,
+      "step": 1570
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.0036472557112574577,
+      "learning_rate": 2.758271296486802e-05,
+      "loss": 0.0001,
+      "step": 1580
+    },
+    {
+      "epoch": 1.5698765432098765,
+      "grad_norm": 0.0031513418070971966,
+      "learning_rate": 2.7296605690430544e-05,
+      "loss": 0.0001,
+      "step": 1590
+    },
+    {
+      "epoch": 1.579753086419753,
+      "grad_norm": 0.0007969654980115592,
+      "learning_rate": 2.7010194733325057e-05,
+      "loss": 0.0,
+      "step": 1600
+    },
+    {
+      "epoch": 1.5896296296296297,
+      "grad_norm": 0.0007987377466633916,
+      "learning_rate": 2.672351796598388e-05,
+      "loss": 0.0,
+      "step": 1610
+    },
+    {
+      "epoch": 1.5995061728395061,
+      "grad_norm": 0.0005811803857795894,
+      "learning_rate": 2.6436613295987738e-05,
+      "loss": 0.0,
+      "step": 1620
+    },
+    {
+      "epoch": 1.6093827160493828,
+      "grad_norm": 0.0005651491228491068,
+      "learning_rate": 2.6149518661053142e-05,
+      "loss": 0.0,
+      "step": 1630
+    },
+    {
+      "epoch": 1.6192592592592594,
+      "grad_norm": 0.0007077642367221415,
+      "learning_rate": 2.5862272024015883e-05,
+      "loss": 0.0,
+      "step": 1640
+    },
+    {
+      "epoch": 1.6291358024691358,
+      "grad_norm": 0.0007271085632964969,
+      "learning_rate": 2.557491136781116e-05,
+      "loss": 0.0,
+      "step": 1650
+    },
+    {
+      "epoch": 1.6390123456790122,
+      "grad_norm": 0.00046728411689400673,
+      "learning_rate": 2.5287474690451057e-05,
+      "loss": 0.0,
+      "step": 1660
+    },
+    {
+      "epoch": 1.6488888888888888,
+      "grad_norm": 0.0003735675709322095,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 1670
+    },
+    {
+      "epoch": 1.6587654320987655,
+      "grad_norm": 0.00039456685772165656,
+      "learning_rate": 2.471252530954895e-05,
+      "loss": 0.0,
+      "step": 1680
+    },
+    {
+      "epoch": 1.668641975308642,
+      "grad_norm": 0.0005533050280064344,
+      "learning_rate": 2.4425088632188842e-05,
+      "loss": 0.0,
+      "step": 1690
+    },
+    {
+      "epoch": 1.6785185185185185,
+      "grad_norm": 0.0002727876999415457,
+      "learning_rate": 2.4137727975984127e-05,
+      "loss": 0.0,
+      "step": 1700
+    },
+    {
+      "epoch": 1.6883950617283952,
+      "grad_norm": 0.16899436712265015,
+      "learning_rate": 2.385048133894687e-05,
+      "loss": 0.0042,
+      "step": 1710
+    },
+    {
+      "epoch": 1.6982716049382716,
+      "grad_norm": 0.00025011974503286183,
+      "learning_rate": 2.3563386704012268e-05,
+      "loss": 0.0,
+      "step": 1720
+    },
+    {
+      "epoch": 1.7081481481481482,
+      "grad_norm": 0.00042458626558072865,
+      "learning_rate": 2.3276482034016122e-05,
+      "loss": 0.0,
+      "step": 1730
+    },
+    {
+      "epoch": 1.7180246913580248,
+      "grad_norm": 0.0003143450303468853,
+      "learning_rate": 2.2989805266674952e-05,
+      "loss": 0.0007,
+      "step": 1740
+    },
+    {
+      "epoch": 1.7279012345679012,
+      "grad_norm": 0.002475626999512315,
+      "learning_rate": 2.2703394309569462e-05,
+      "loss": 0.0,
+      "step": 1750
+    },
+    {
+      "epoch": 1.7377777777777776,
+      "grad_norm": 0.0013496195897459984,
+      "learning_rate": 2.241728703513199e-05,
+      "loss": 0.0005,
+      "step": 1760
+    },
+    {
+      "epoch": 1.7476543209876543,
+      "grad_norm": 0.00017028844740707427,
+      "learning_rate": 2.2131521275638572e-05,
+      "loss": 0.0,
+      "step": 1770
+    },
+    {
+      "epoch": 1.757530864197531,
+      "grad_norm": 0.00014113387442193925,
+      "learning_rate": 2.184613481820637e-05,
+      "loss": 0.0,
+      "step": 1780
+    },
+    {
+      "epoch": 1.7674074074074073,
+      "grad_norm": 0.00028848147485405207,
+      "learning_rate": 2.1561165399797e-05,
+      "loss": 0.0,
+      "step": 1790
+    },
+    {
+      "epoch": 1.777283950617284,
+      "grad_norm": 0.00021244629169814289,
+      "learning_rate": 2.1276650702226562e-05,
+      "loss": 0.0,
+      "step": 1800
+    },
+    {
+      "epoch": 1.7871604938271606,
+      "grad_norm": 0.00019675836665555835,
+      "learning_rate": 2.099262834718293e-05,
+      "loss": 0.0,
+      "step": 1810
+    },
+    {
+      "epoch": 1.797037037037037,
+      "grad_norm": 0.0004635763179976493,
+      "learning_rate": 2.0709135891250985e-05,
+      "loss": 0.0,
+      "step": 1820
+    },
+    {
+      "epoch": 1.8069135802469136,
+      "grad_norm": 0.00012990082905162126,
+      "learning_rate": 2.0426210820946476e-05,
+      "loss": 0.0,
+      "step": 1830
+    },
+    {
+      "epoch": 1.8167901234567903,
+      "grad_norm": 0.00016129855066537857,
+      "learning_rate": 2.0143890547759132e-05,
+      "loss": 0.0,
+      "step": 1840
+    },
+    {
+      "epoch": 1.8266666666666667,
+      "grad_norm": 0.00018279206415172666,
+      "learning_rate": 1.9862212403205698e-05,
+      "loss": 0.0,
+      "step": 1850
+    },
+    {
+      "epoch": 1.836543209876543,
+      "grad_norm": 0.00023649405920878053,
+      "learning_rate": 1.958121363389356e-05,
+      "loss": 0.0,
+      "step": 1860
+    },
+    {
+      "epoch": 1.8464197530864197,
+      "grad_norm": 0.0002646524226292968,
+      "learning_rate": 1.9300931396595583e-05,
+      "loss": 0.0,
+      "step": 1870
+    },
+    {
+      "epoch": 1.8562962962962963,
+      "grad_norm": 0.0005494295619428158,
+      "learning_rate": 1.9021402753336784e-05,
+      "loss": 0.0096,
+      "step": 1880
+    },
+    {
+      "epoch": 1.8661728395061727,
+      "grad_norm": 0.0009147037053480744,
+      "learning_rate": 1.8742664666493676e-05,
+      "loss": 0.0,
+      "step": 1890
+    },
+    {
+      "epoch": 1.8760493827160494,
+      "grad_norm": 0.001351756858639419,
+      "learning_rate": 1.846475399390659e-05,
+      "loss": 0.0,
+      "step": 1900
+    },
+    {
+      "epoch": 1.885925925925926,
+      "grad_norm": 0.0009297579526901245,
+      "learning_rate": 1.8187707484006005e-05,
+      "loss": 0.0,
+      "step": 1910
+    },
+    {
+      "epoch": 1.8958024691358024,
+      "grad_norm": 0.001504297717474401,
+      "learning_rate": 1.7911561770953213e-05,
+      "loss": 0.0,
+      "step": 1920
+    },
+    {
+      "epoch": 1.905679012345679,
+      "grad_norm": 0.0016418690793216228,
+      "learning_rate": 1.763635336979616e-05,
+      "loss": 0.0,
+      "step": 1930
+    },
+    {
+      "epoch": 1.9155555555555557,
+      "grad_norm": 0.0011701845796778798,
+      "learning_rate": 1.7362118671641023e-05,
+      "loss": 0.0002,
+      "step": 1940
+    },
+    {
+      "epoch": 1.925432098765432,
+      "grad_norm": 0.0010625842260196805,
+      "learning_rate": 1.7088893938840178e-05,
+      "loss": 0.0,
+      "step": 1950
+    },
+    {
+      "epoch": 1.9353086419753085,
+      "grad_norm": 0.0015219110064208508,
+      "learning_rate": 1.6816715300197156e-05,
+      "loss": 0.0,
+      "step": 1960
+    },
+    {
+      "epoch": 1.9451851851851854,
+      "grad_norm": 0.0005342438234947622,
+      "learning_rate": 1.654561874618936e-05,
+      "loss": 0.0,
+      "step": 1970
+    },
+    {
+      "epoch": 1.9550617283950618,
+      "grad_norm": 0.0008706999942660332,
+      "learning_rate": 1.6275640124208928e-05,
+      "loss": 0.0,
+      "step": 1980
+    },
+    {
+      "epoch": 1.9649382716049382,
+      "grad_norm": 0.00037755907396785915,
+      "learning_rate": 1.6006815133822662e-05,
+      "loss": 0.0,
+      "step": 1990
+    },
+    {
+      "epoch": 1.9748148148148148,
+      "grad_norm": 0.0005140100256539881,
+      "learning_rate": 1.5739179322051382e-05,
+      "loss": 0.0,
+      "step": 2000
+    },
+    {
+      "epoch": 1.9748148148148148,
+      "eval_nlpcc25_task1_dev_accuracy": 0.9997619047619046,
+      "eval_nlpcc25_task1_dev_loss": 0.0013579174410551786,
+      "eval_nlpcc25_task1_dev_runtime": 2528.9656,
+      "eval_nlpcc25_task1_dev_samples_per_second": 1.107,
+      "eval_nlpcc25_task1_dev_steps_per_second": 0.277,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3036,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1490710644069171e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

Qwen2.5-7B-Instruct-lora-2/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc27925817800cee3170b92f598d1cfe9fce4b0491f781c2f4977cfd2644a9a
+size 5752

Qwen2.5-7B-Instruct-lora-2/checkpoint-2500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /data/zhaoguoyu/Experiments/mgtd-sys/detector/ckpt/Qwen2.5-7B-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 0.15.0

Qwen2.5-7B-Instruct-lora-2/checkpoint-2500/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/zhaoguoyu/Experiments/mgtd-sys/detector/ckpt/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}