初始化项目，由ModelHub XC社区提供模型
Model: testUser/Qwen3-1.7b-Medical-R1-sft Source: Original Platform
This commit is contained in:
ModelHub XC
47
.gitattributes
vendored
Normal file
47
.gitattributes
vendored
Normal file
@@ -0,0 +1,47 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
108
README.md
Normal file
108
README.md
Normal file
@@ -0,0 +1,108 @@
|
||||
---
|
||||
frameworks:
|
||||
- Pytorch
|
||||
license: Apache License 2.0
|
||||
tasks:
|
||||
- text-generation
|
||||
|
||||
#model-type:
|
||||
##如 gpt、phi、llama、chatglm、baichuan 等
|
||||
#- gpt
|
||||
|
||||
#domain:
|
||||
##如 nlp、cv、audio、multi-modal
|
||||
#- nlp
|
||||
|
||||
#language:
|
||||
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
|
||||
#- cn
|
||||
|
||||
#metrics:
|
||||
##如 CIDEr、Blue、ROUGE 等
|
||||
#- CIDEr
|
||||
|
||||
#tags:
|
||||
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
|
||||
#- pretrained
|
||||
|
||||
#tools:
|
||||
##如 vllm、fastchat、llamacpp、AdaSeq 等
|
||||
#- vllm
|
||||
---
|
||||
|
||||
[Github](https://github.com/Zeyi-Lin/Qwen3-Medical-SFT)
|
||||
|
||||
- **基础模型**：[Qwen3-1.7B](https://modelscope.cn/models/Qwen/Qwen3-1.7B/summary)
|
||||
- **微调后模型**：[Qwen3-1.7b-Medical-R1-sft](https://modelscope.cn/models/testUser/Qwen3-1.7b-Medical-R1-sft/summary)
|
||||
- **数据集**：[delicate_medical_r1_data](https://modelscope.cn/datasets/krisfu/delicate_medical_r1_data)
|
||||
- **SwanLab**：[qwen3-sft-medical](https://swanlab.cn/@ZeyiLin/qwen3-sft-medical/runs/agps0dkifth5l1xytcdyk/chart)
|
||||
- **微调方式**：全参数微调、LoRA微调
|
||||
- **推理风格**：R1推理风格
|
||||
- **算力要求**：
|
||||
- **全参数微调**：32GB显存
|
||||
- **LoRA微调**：28GB显存
|
||||
- **图文教程**：[Qwen3大模型微调入门实战（完整代码）](https://zhuanlan.zhihu.com/p/1903848838214705484)
|
||||
|
||||
## 模型下载
|
||||
|
||||
```bash
|
||||
#安装ModelScope
|
||||
pip install modelscope
|
||||
```
|
||||
```python
|
||||
#SDK模型下载
|
||||
from modelscope import snapshot_download
|
||||
model_dir = snapshot_download('testUser/Qwen3-1.7b-Medical-R1-sft')
|
||||
```
|
||||
Git下载
|
||||
```
|
||||
#Git模型下载
|
||||
git clone https://www.modelscope.cn/testUser/Qwen3-1.7b-Medical-R1-sft.git
|
||||
```
|
||||
|
||||
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
|
||||
|
||||
## 模型推理
|
||||
|
||||
```bash
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
def predict(messages, model, tokenizer):
|
||||
if torch.backends.mps.is_available():
|
||||
device = "mps"
|
||||
elif torch.cuda.is_available():
|
||||
device = "cuda"
|
||||
else:
|
||||
device = "cpu"
|
||||
|
||||
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
model_inputs = tokenizer([text], return_tensors="pt").to(device)
|
||||
|
||||
generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=2048)
|
||||
generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)]
|
||||
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
||||
|
||||
return response
|
||||
|
||||
|
||||
# 加载原下载路径的tokenizer和model
|
||||
tokenizer = AutoTokenizer.from_pretrained("./Qwen3-1.7b-Medical-R1-sft", use_fast=False, trust_remote_code=True)
|
||||
model = AutoModelForCausalLM.from_pretrained("./Qwen3-1.7b-Medical-R1-sft", device_map="auto", torch_dtype=torch.bfloat16)
|
||||
|
||||
test_texts = {
|
||||
'instruction': "你是一个医学专家，你需要根据用户的问题，给出带有思考的回答。",
|
||||
'input': "医生，我最近被诊断为糖尿病，听说碳水化合物的选择很重要，我应该选择什么样的碳水化合物呢？"
|
||||
}
|
||||
|
||||
instruction = test_texts['instruction']
|
||||
input_value = test_texts['input']
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": f"{instruction}"},
|
||||
{"role": "user", "content": f"{input_value}"}
|
||||
]
|
||||
|
||||
response = predict(messages, model, tokenizer)
|
||||
print(response)
|
||||
```
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|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
|
||||
}
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6144,
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.51.3",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework":"Pytorch","task":"text-generation"}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.51.3"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ab33d7e7d1a01d4ee6967128ef30b119c2d139c173164e3f86598e200ee9d783
|
||||
size 3441185608
|
||||
3
optimizer.pt
Normal file
3
optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:94cd75fef508b00c7b253be818cdf9dda44b7edf75beb45cdebec6733148eeb4
|
||||
size 6882566374
|
||||
3
rng_state.pth
Normal file
3
rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a969b6f4ac3bfc308a974fa586ee9101753f5a3b5a103f94f3cbaf30697af148
|
||||
size 14244
|
||||
3
scheduler.pt
Normal file
3
scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2e651a1d22271c5cf6d5954508692803faef3fceed63035118a71611e61bffac
|
||||
size 1064
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -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
|
||||
}
|
||||
}
|
||||
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -0,0 +1,240 @@
|
||||
{
|
||||
"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
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"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\\n' }}\n {%- endif %}\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 {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first 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 {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
870
trainer_state.json
Normal file
870
trainer_state.json
Normal file
@@ -0,0 +1,870 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.997229916897507,
|
||||
"eval_steps": 100,
|
||||
"global_step": 1082,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.018467220683287166,
|
||||
"grad_norm": 6.75,
|
||||
"learning_rate": 9.916820702402958e-05,
|
||||
"loss": 1.6631,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.03693444136657433,
|
||||
"grad_norm": 5.15625,
|
||||
"learning_rate": 9.824399260628466e-05,
|
||||
"loss": 1.5735,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.055401662049861494,
|
||||
"grad_norm": 4.46875,
|
||||
"learning_rate": 9.731977818853975e-05,
|
||||
"loss": 1.4646,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.07386888273314866,
|
||||
"grad_norm": 5.0625,
|
||||
"learning_rate": 9.639556377079483e-05,
|
||||
"loss": 1.5077,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.09233610341643583,
|
||||
"grad_norm": 4.75,
|
||||
"learning_rate": 9.547134935304991e-05,
|
||||
"loss": 1.4535,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.11080332409972299,
|
||||
"grad_norm": 4.5,
|
||||
"learning_rate": 9.4547134935305e-05,
|
||||
"loss": 1.4545,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.12927054478301014,
|
||||
"grad_norm": 4.4375,
|
||||
"learning_rate": 9.362292051756008e-05,
|
||||
"loss": 1.4397,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.14773776546629733,
|
||||
"grad_norm": 4.625,
|
||||
"learning_rate": 9.269870609981516e-05,
|
||||
"loss": 1.3854,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.16620498614958448,
|
||||
"grad_norm": 4.15625,
|
||||
"learning_rate": 9.177449168207024e-05,
|
||||
"loss": 1.4051,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.18467220683287167,
|
||||
"grad_norm": 4.40625,
|
||||
"learning_rate": 9.085027726432532e-05,
|
||||
"loss": 1.387,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.18467220683287167,
|
||||
"eval_loss": 1.387468934059143,
|
||||
"eval_runtime": 11.6368,
|
||||
"eval_samples_per_second": 20.71,
|
||||
"eval_steps_per_second": 20.71,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20313942751615882,
|
||||
"grad_norm": 4.1875,
|
||||
"learning_rate": 8.99260628465804e-05,
|
||||
"loss": 1.3813,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.22160664819944598,
|
||||
"grad_norm": 5.09375,
|
||||
"learning_rate": 8.90018484288355e-05,
|
||||
"loss": 1.4082,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24007386888273316,
|
||||
"grad_norm": 3.890625,
|
||||
"learning_rate": 8.807763401109058e-05,
|
||||
"loss": 1.3898,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.2585410895660203,
|
||||
"grad_norm": 4.0625,
|
||||
"learning_rate": 8.715341959334566e-05,
|
||||
"loss": 1.3405,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2770083102493075,
|
||||
"grad_norm": 4.28125,
|
||||
"learning_rate": 8.622920517560074e-05,
|
||||
"loss": 1.2887,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.29547553093259465,
|
||||
"grad_norm": 5.46875,
|
||||
"learning_rate": 8.530499075785582e-05,
|
||||
"loss": 1.3473,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3139427516158818,
|
||||
"grad_norm": 3.96875,
|
||||
"learning_rate": 8.43807763401109e-05,
|
||||
"loss": 1.3954,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.33240997229916897,
|
||||
"grad_norm": 4.4375,
|
||||
"learning_rate": 8.3456561922366e-05,
|
||||
"loss": 1.3254,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3508771929824561,
|
||||
"grad_norm": 4.9375,
|
||||
"learning_rate": 8.253234750462108e-05,
|
||||
"loss": 1.3269,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.36934441366574333,
|
||||
"grad_norm": 4.375,
|
||||
"learning_rate": 8.160813308687616e-05,
|
||||
"loss": 1.3035,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.36934441366574333,
|
||||
"eval_loss": 1.3003418445587158,
|
||||
"eval_runtime": 11.4082,
|
||||
"eval_samples_per_second": 21.125,
|
||||
"eval_steps_per_second": 21.125,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3878116343490305,
|
||||
"grad_norm": 4.0,
|
||||
"learning_rate": 8.068391866913125e-05,
|
||||
"loss": 1.2879,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.40627885503231764,
|
||||
"grad_norm": 3.921875,
|
||||
"learning_rate": 7.975970425138633e-05,
|
||||
"loss": 1.2655,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4247460757156048,
|
||||
"grad_norm": 4.25,
|
||||
"learning_rate": 7.883548983364141e-05,
|
||||
"loss": 1.2731,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 0.44321329639889195,
|
||||
"grad_norm": 4.03125,
|
||||
"learning_rate": 7.791127541589649e-05,
|
||||
"loss": 1.2768,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4616805170821791,
|
||||
"grad_norm": 4.4375,
|
||||
"learning_rate": 7.698706099815157e-05,
|
||||
"loss": 1.2938,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.4801477377654663,
|
||||
"grad_norm": 4.28125,
|
||||
"learning_rate": 7.606284658040665e-05,
|
||||
"loss": 1.2415,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4986149584487535,
|
||||
"grad_norm": 3.609375,
|
||||
"learning_rate": 7.513863216266173e-05,
|
||||
"loss": 1.2689,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 0.5170821791320406,
|
||||
"grad_norm": 4.59375,
|
||||
"learning_rate": 7.421441774491682e-05,
|
||||
"loss": 1.2088,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5355493998153278,
|
||||
"grad_norm": 4.375,
|
||||
"learning_rate": 7.32902033271719e-05,
|
||||
"loss": 1.242,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 0.554016620498615,
|
||||
"grad_norm": 4.4375,
|
||||
"learning_rate": 7.236598890942699e-05,
|
||||
"loss": 1.2242,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.554016620498615,
|
||||
"eval_loss": 1.2419342994689941,
|
||||
"eval_runtime": 11.7953,
|
||||
"eval_samples_per_second": 20.432,
|
||||
"eval_steps_per_second": 20.432,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.5724838411819021,
|
||||
"grad_norm": 4.0625,
|
||||
"learning_rate": 7.144177449168207e-05,
|
||||
"loss": 1.2356,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 0.5909510618651893,
|
||||
"grad_norm": 3.59375,
|
||||
"learning_rate": 7.051756007393715e-05,
|
||||
"loss": 1.249,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.6094182825484764,
|
||||
"grad_norm": 3.625,
|
||||
"learning_rate": 6.959334565619225e-05,
|
||||
"loss": 1.2189,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"epoch": 0.6278855032317636,
|
||||
"grad_norm": 4.15625,
|
||||
"learning_rate": 6.866913123844733e-05,
|
||||
"loss": 1.2613,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.6463527239150508,
|
||||
"grad_norm": 3.890625,
|
||||
"learning_rate": 6.774491682070241e-05,
|
||||
"loss": 1.2315,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 0.6648199445983379,
|
||||
"grad_norm": 4.5625,
|
||||
"learning_rate": 6.68207024029575e-05,
|
||||
"loss": 1.2211,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.6832871652816251,
|
||||
"grad_norm": 3.78125,
|
||||
"learning_rate": 6.589648798521258e-05,
|
||||
"loss": 1.1796,
|
||||
"step": 370
|
||||
},
|
||||
{
|
||||
"epoch": 0.7017543859649122,
|
||||
"grad_norm": 3.84375,
|
||||
"learning_rate": 6.497227356746766e-05,
|
||||
"loss": 1.2086,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.7202216066481995,
|
||||
"grad_norm": 4.125,
|
||||
"learning_rate": 6.404805914972274e-05,
|
||||
"loss": 1.2105,
|
||||
"step": 390
|
||||
},
|
||||
{
|
||||
"epoch": 0.7386888273314867,
|
||||
"grad_norm": 3.734375,
|
||||
"learning_rate": 6.312384473197782e-05,
|
||||
"loss": 1.1587,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.7386888273314867,
|
||||
"eval_loss": 1.1842167377471924,
|
||||
"eval_runtime": 11.4783,
|
||||
"eval_samples_per_second": 20.996,
|
||||
"eval_steps_per_second": 20.996,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.7571560480147738,
|
||||
"grad_norm": 4.03125,
|
||||
"learning_rate": 6.21996303142329e-05,
|
||||
"loss": 1.1543,
|
||||
"step": 410
|
||||
},
|
||||
{
|
||||
"epoch": 0.775623268698061,
|
||||
"grad_norm": 3.609375,
|
||||
"learning_rate": 6.127541589648798e-05,
|
||||
"loss": 1.162,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.7940904893813481,
|
||||
"grad_norm": 3.484375,
|
||||
"learning_rate": 6.035120147874307e-05,
|
||||
"loss": 1.1555,
|
||||
"step": 430
|
||||
},
|
||||
{
|
||||
"epoch": 0.8125577100646353,
|
||||
"grad_norm": 3.9375,
|
||||
"learning_rate": 5.942698706099815e-05,
|
||||
"loss": 1.179,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 0.8310249307479224,
|
||||
"grad_norm": 3.796875,
|
||||
"learning_rate": 5.8502772643253234e-05,
|
||||
"loss": 1.1859,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 0.8494921514312096,
|
||||
"grad_norm": 3.921875,
|
||||
"learning_rate": 5.7578558225508315e-05,
|
||||
"loss": 1.1635,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 0.8679593721144968,
|
||||
"grad_norm": 3.484375,
|
||||
"learning_rate": 5.66543438077634e-05,
|
||||
"loss": 1.1564,
|
||||
"step": 470
|
||||
},
|
||||
{
|
||||
"epoch": 0.8864265927977839,
|
||||
"grad_norm": 4.09375,
|
||||
"learning_rate": 5.573012939001848e-05,
|
||||
"loss": 1.141,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 0.9048938134810711,
|
||||
"grad_norm": 3.8125,
|
||||
"learning_rate": 5.4805914972273573e-05,
|
||||
"loss": 1.1482,
|
||||
"step": 490
|
||||
},
|
||||
{
|
||||
"epoch": 0.9233610341643582,
|
||||
"grad_norm": 4.1875,
|
||||
"learning_rate": 5.3881700554528655e-05,
|
||||
"loss": 1.2034,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.9233610341643582,
|
||||
"eval_loss": 1.1427098512649536,
|
||||
"eval_runtime": 11.82,
|
||||
"eval_samples_per_second": 20.389,
|
||||
"eval_steps_per_second": 20.389,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.9418282548476454,
|
||||
"grad_norm": 4.125,
|
||||
"learning_rate": 5.295748613678374e-05,
|
||||
"loss": 1.1486,
|
||||
"step": 510
|
||||
},
|
||||
{
|
||||
"epoch": 0.9602954755309326,
|
||||
"grad_norm": 3.671875,
|
||||
"learning_rate": 5.2033271719038825e-05,
|
||||
"loss": 1.1217,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 0.9787626962142197,
|
||||
"grad_norm": 3.6875,
|
||||
"learning_rate": 5.1109057301293906e-05,
|
||||
"loss": 1.1794,
|
||||
"step": 530
|
||||
},
|
||||
{
|
||||
"epoch": 0.997229916897507,
|
||||
"grad_norm": 3.703125,
|
||||
"learning_rate": 5.018484288354899e-05,
|
||||
"loss": 1.1588,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 1.0147737765466298,
|
||||
"grad_norm": 3.546875,
|
||||
"learning_rate": 4.926062846580407e-05,
|
||||
"loss": 0.7576,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"epoch": 1.0332409972299168,
|
||||
"grad_norm": 4.34375,
|
||||
"learning_rate": 4.833641404805915e-05,
|
||||
"loss": 0.6725,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 1.051708217913204,
|
||||
"grad_norm": 4.3125,
|
||||
"learning_rate": 4.741219963031424e-05,
|
||||
"loss": 0.6242,
|
||||
"step": 570
|
||||
},
|
||||
{
|
||||
"epoch": 1.0701754385964912,
|
||||
"grad_norm": 3.796875,
|
||||
"learning_rate": 4.648798521256932e-05,
|
||||
"loss": 0.6287,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 1.0886426592797784,
|
||||
"grad_norm": 3.96875,
|
||||
"learning_rate": 4.55637707948244e-05,
|
||||
"loss": 0.6502,
|
||||
"step": 590
|
||||
},
|
||||
{
|
||||
"epoch": 1.1071098799630656,
|
||||
"grad_norm": 4.59375,
|
||||
"learning_rate": 4.463955637707948e-05,
|
||||
"loss": 0.6231,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 1.1071098799630656,
|
||||
"eval_loss": 1.1928539276123047,
|
||||
"eval_runtime": 11.4582,
|
||||
"eval_samples_per_second": 21.033,
|
||||
"eval_steps_per_second": 21.033,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 1.1255771006463526,
|
||||
"grad_norm": 4.125,
|
||||
"learning_rate": 4.3715341959334564e-05,
|
||||
"loss": 0.6225,
|
||||
"step": 610
|
||||
},
|
||||
{
|
||||
"epoch": 1.1440443213296398,
|
||||
"grad_norm": 3.8125,
|
||||
"learning_rate": 4.2791127541589646e-05,
|
||||
"loss": 0.6459,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 1.162511542012927,
|
||||
"grad_norm": 3.96875,
|
||||
"learning_rate": 4.1866913123844734e-05,
|
||||
"loss": 0.6273,
|
||||
"step": 630
|
||||
},
|
||||
{
|
||||
"epoch": 1.1809787626962143,
|
||||
"grad_norm": 3.90625,
|
||||
"learning_rate": 4.094269870609982e-05,
|
||||
"loss": 0.6267,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 1.1994459833795015,
|
||||
"grad_norm": 4.28125,
|
||||
"learning_rate": 4.0018484288354904e-05,
|
||||
"loss": 0.6355,
|
||||
"step": 650
|
||||
},
|
||||
{
|
||||
"epoch": 1.2179132040627885,
|
||||
"grad_norm": 3.9375,
|
||||
"learning_rate": 3.9094269870609985e-05,
|
||||
"loss": 0.6419,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 1.2363804247460757,
|
||||
"grad_norm": 4.0,
|
||||
"learning_rate": 3.817005545286507e-05,
|
||||
"loss": 0.6489,
|
||||
"step": 670
|
||||
},
|
||||
{
|
||||
"epoch": 1.254847645429363,
|
||||
"grad_norm": 4.03125,
|
||||
"learning_rate": 3.724584103512015e-05,
|
||||
"loss": 0.646,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 1.27331486611265,
|
||||
"grad_norm": 4.28125,
|
||||
"learning_rate": 3.632162661737523e-05,
|
||||
"loss": 0.6222,
|
||||
"step": 690
|
||||
},
|
||||
{
|
||||
"epoch": 1.291782086795937,
|
||||
"grad_norm": 4.09375,
|
||||
"learning_rate": 3.539741219963031e-05,
|
||||
"loss": 0.6345,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 1.291782086795937,
|
||||
"eval_loss": 1.1857507228851318,
|
||||
"eval_runtime": 11.3876,
|
||||
"eval_samples_per_second": 21.163,
|
||||
"eval_steps_per_second": 21.163,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 1.3102493074792243,
|
||||
"grad_norm": 3.515625,
|
||||
"learning_rate": 3.44731977818854e-05,
|
||||
"loss": 0.6477,
|
||||
"step": 710
|
||||
},
|
||||
{
|
||||
"epoch": 1.3287165281625115,
|
||||
"grad_norm": 3.421875,
|
||||
"learning_rate": 3.354898336414049e-05,
|
||||
"loss": 0.6302,
|
||||
"step": 720
|
||||
},
|
||||
{
|
||||
"epoch": 1.3471837488457987,
|
||||
"grad_norm": 4.125,
|
||||
"learning_rate": 3.262476894639557e-05,
|
||||
"loss": 0.6105,
|
||||
"step": 730
|
||||
},
|
||||
{
|
||||
"epoch": 1.365650969529086,
|
||||
"grad_norm": 4.15625,
|
||||
"learning_rate": 3.170055452865065e-05,
|
||||
"loss": 0.6205,
|
||||
"step": 740
|
||||
},
|
||||
{
|
||||
"epoch": 1.384118190212373,
|
||||
"grad_norm": 4.28125,
|
||||
"learning_rate": 3.077634011090573e-05,
|
||||
"loss": 0.6321,
|
||||
"step": 750
|
||||
},
|
||||
{
|
||||
"epoch": 1.4025854108956601,
|
||||
"grad_norm": 3.71875,
|
||||
"learning_rate": 2.9852125693160817e-05,
|
||||
"loss": 0.6389,
|
||||
"step": 760
|
||||
},
|
||||
{
|
||||
"epoch": 1.4210526315789473,
|
||||
"grad_norm": 4.375,
|
||||
"learning_rate": 2.8927911275415898e-05,
|
||||
"loss": 0.6595,
|
||||
"step": 770
|
||||
},
|
||||
{
|
||||
"epoch": 1.4395198522622346,
|
||||
"grad_norm": 4.25,
|
||||
"learning_rate": 2.800369685767098e-05,
|
||||
"loss": 0.6204,
|
||||
"step": 780
|
||||
},
|
||||
{
|
||||
"epoch": 1.4579870729455218,
|
||||
"grad_norm": 3.921875,
|
||||
"learning_rate": 2.707948243992606e-05,
|
||||
"loss": 0.5896,
|
||||
"step": 790
|
||||
},
|
||||
{
|
||||
"epoch": 1.4764542936288088,
|
||||
"grad_norm": 3.875,
|
||||
"learning_rate": 2.6155268022181146e-05,
|
||||
"loss": 0.6114,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 1.4764542936288088,
|
||||
"eval_loss": 1.1792447566986084,
|
||||
"eval_runtime": 11.8232,
|
||||
"eval_samples_per_second": 20.384,
|
||||
"eval_steps_per_second": 20.384,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 1.494921514312096,
|
||||
"grad_norm": 4.09375,
|
||||
"learning_rate": 2.5231053604436227e-05,
|
||||
"loss": 0.6368,
|
||||
"step": 810
|
||||
},
|
||||
{
|
||||
"epoch": 1.5133887349953832,
|
||||
"grad_norm": 4.53125,
|
||||
"learning_rate": 2.4306839186691312e-05,
|
||||
"loss": 0.6206,
|
||||
"step": 820
|
||||
},
|
||||
{
|
||||
"epoch": 1.5318559556786704,
|
||||
"grad_norm": 3.90625,
|
||||
"learning_rate": 2.3382624768946397e-05,
|
||||
"loss": 0.6158,
|
||||
"step": 830
|
||||
},
|
||||
{
|
||||
"epoch": 1.5503231763619576,
|
||||
"grad_norm": 3.890625,
|
||||
"learning_rate": 2.2458410351201482e-05,
|
||||
"loss": 0.6154,
|
||||
"step": 840
|
||||
},
|
||||
{
|
||||
"epoch": 1.5687903970452446,
|
||||
"grad_norm": 4.1875,
|
||||
"learning_rate": 2.1534195933456563e-05,
|
||||
"loss": 0.6319,
|
||||
"step": 850
|
||||
},
|
||||
{
|
||||
"epoch": 1.587257617728532,
|
||||
"grad_norm": 3.6875,
|
||||
"learning_rate": 2.0609981515711645e-05,
|
||||
"loss": 0.6223,
|
||||
"step": 860
|
||||
},
|
||||
{
|
||||
"epoch": 1.605724838411819,
|
||||
"grad_norm": 3.46875,
|
||||
"learning_rate": 1.968576709796673e-05,
|
||||
"loss": 0.5849,
|
||||
"step": 870
|
||||
},
|
||||
{
|
||||
"epoch": 1.6241920590951062,
|
||||
"grad_norm": 4.25,
|
||||
"learning_rate": 1.876155268022181e-05,
|
||||
"loss": 0.6047,
|
||||
"step": 880
|
||||
},
|
||||
{
|
||||
"epoch": 1.6426592797783934,
|
||||
"grad_norm": 4.03125,
|
||||
"learning_rate": 1.7837338262476896e-05,
|
||||
"loss": 0.6238,
|
||||
"step": 890
|
||||
},
|
||||
{
|
||||
"epoch": 1.6611265004616804,
|
||||
"grad_norm": 4.15625,
|
||||
"learning_rate": 1.6913123844731977e-05,
|
||||
"loss": 0.6116,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 1.6611265004616804,
|
||||
"eval_loss": 1.1671314239501953,
|
||||
"eval_runtime": 11.8194,
|
||||
"eval_samples_per_second": 20.39,
|
||||
"eval_steps_per_second": 20.39,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 1.6795937211449676,
|
||||
"grad_norm": 3.9375,
|
||||
"learning_rate": 1.5988909426987062e-05,
|
||||
"loss": 0.616,
|
||||
"step": 910
|
||||
},
|
||||
{
|
||||
"epoch": 1.6980609418282548,
|
||||
"grad_norm": 4.0,
|
||||
"learning_rate": 1.5064695009242144e-05,
|
||||
"loss": 0.6052,
|
||||
"step": 920
|
||||
},
|
||||
{
|
||||
"epoch": 1.716528162511542,
|
||||
"grad_norm": 4.25,
|
||||
"learning_rate": 1.4140480591497229e-05,
|
||||
"loss": 0.6142,
|
||||
"step": 930
|
||||
},
|
||||
{
|
||||
"epoch": 1.7349953831948293,
|
||||
"grad_norm": 3.78125,
|
||||
"learning_rate": 1.3216266173752312e-05,
|
||||
"loss": 0.6027,
|
||||
"step": 940
|
||||
},
|
||||
{
|
||||
"epoch": 1.7534626038781163,
|
||||
"grad_norm": 4.40625,
|
||||
"learning_rate": 1.2292051756007395e-05,
|
||||
"loss": 0.6218,
|
||||
"step": 950
|
||||
},
|
||||
{
|
||||
"epoch": 1.7719298245614035,
|
||||
"grad_norm": 3.71875,
|
||||
"learning_rate": 1.1367837338262476e-05,
|
||||
"loss": 0.6089,
|
||||
"step": 960
|
||||
},
|
||||
{
|
||||
"epoch": 1.7903970452446907,
|
||||
"grad_norm": 4.09375,
|
||||
"learning_rate": 1.0443622920517561e-05,
|
||||
"loss": 0.6063,
|
||||
"step": 970
|
||||
},
|
||||
{
|
||||
"epoch": 1.8088642659279779,
|
||||
"grad_norm": 3.640625,
|
||||
"learning_rate": 9.519408502772643e-06,
|
||||
"loss": 0.6226,
|
||||
"step": 980
|
||||
},
|
||||
{
|
||||
"epoch": 1.827331486611265,
|
||||
"grad_norm": 4.1875,
|
||||
"learning_rate": 8.595194085027728e-06,
|
||||
"loss": 0.5896,
|
||||
"step": 990
|
||||
},
|
||||
{
|
||||
"epoch": 1.845798707294552,
|
||||
"grad_norm": 4.0625,
|
||||
"learning_rate": 7.67097966728281e-06,
|
||||
"loss": 0.6116,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"epoch": 1.845798707294552,
|
||||
"eval_loss": 1.1601166725158691,
|
||||
"eval_runtime": 11.43,
|
||||
"eval_samples_per_second": 21.085,
|
||||
"eval_steps_per_second": 21.085,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"epoch": 1.8642659279778393,
|
||||
"grad_norm": 4.0625,
|
||||
"learning_rate": 6.746765249537892e-06,
|
||||
"loss": 0.5911,
|
||||
"step": 1010
|
||||
},
|
||||
{
|
||||
"epoch": 1.8827331486611265,
|
||||
"grad_norm": 3.96875,
|
||||
"learning_rate": 5.822550831792976e-06,
|
||||
"loss": 0.6343,
|
||||
"step": 1020
|
||||
},
|
||||
{
|
||||
"epoch": 1.9012003693444137,
|
||||
"grad_norm": 4.15625,
|
||||
"learning_rate": 4.898336414048059e-06,
|
||||
"loss": 0.6378,
|
||||
"step": 1030
|
||||
},
|
||||
{
|
||||
"epoch": 1.919667590027701,
|
||||
"grad_norm": 3.90625,
|
||||
"learning_rate": 3.9741219963031425e-06,
|
||||
"loss": 0.629,
|
||||
"step": 1040
|
||||
},
|
||||
{
|
||||
"epoch": 1.938134810710988,
|
||||
"grad_norm": 4.125,
|
||||
"learning_rate": 3.0499075785582256e-06,
|
||||
"loss": 0.5951,
|
||||
"step": 1050
|
||||
},
|
||||
{
|
||||
"epoch": 1.9566020313942751,
|
||||
"grad_norm": 3.765625,
|
||||
"learning_rate": 2.1256931608133088e-06,
|
||||
"loss": 0.6105,
|
||||
"step": 1060
|
||||
},
|
||||
{
|
||||
"epoch": 1.9750692520775623,
|
||||
"grad_norm": 3.828125,
|
||||
"learning_rate": 1.201478743068392e-06,
|
||||
"loss": 0.6253,
|
||||
"step": 1070
|
||||
},
|
||||
{
|
||||
"epoch": 1.9935364727608493,
|
||||
"grad_norm": 3.734375,
|
||||
"learning_rate": 2.7726432532347505e-07,
|
||||
"loss": 0.6319,
|
||||
"step": 1080
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 1082,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 2000,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 2.9384102298648576e+16,
|
||||
"train_batch_size": 1,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f37022c4aac2a56e9a36a22d073b570b30147b0d8152b0176fb4b112ca1a2abc
|
||||
size 5368
|
||||
151645
vocab.json
Normal file
151645
vocab.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user