初始化项目，由ModelHub XC社区提供模型
Model: Lsd45/vaccine-cold-chain-agent Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt 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
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz 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
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl 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
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* 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
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
67
README.md
Normal file
67
README.md
Normal file
@@ -0,0 +1,67 @@
|
|||||||
|
---
|
||||||
|
base_model: Qwen/Qwen3-0.6B
|
||||||
|
library_name: transformers
|
||||||
|
model_name: vaccine-cold-chain-agent
|
||||||
|
tags:
|
||||||
|
- generated_from_trainer
|
||||||
|
- grpo
|
||||||
|
- trl
|
||||||
|
licence: license
|
||||||
|
---
|
||||||
|
|
||||||
|
# Model Card for vaccine-cold-chain-agent
|
||||||
|
|
||||||
|
This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B).
|
||||||
|
It has been trained using [TRL](https://github.com/huggingface/trl).
|
||||||
|
|
||||||
|
## Quick start
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import pipeline
|
||||||
|
|
||||||
|
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
||||||
|
generator = pipeline("text-generation", model="Lsd45/vaccine-cold-chain-agent", device="cuda")
|
||||||
|
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
||||||
|
print(output["generated_text"])
|
||||||
|
```
|
||||||
|
|
||||||
|
## Training procedure
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
|
||||||
|
|
||||||
|
### Framework versions
|
||||||
|
|
||||||
|
- TRL: 1.2.0
|
||||||
|
- Transformers: 5.7.0.dev0
|
||||||
|
- Pytorch: 2.6.0+cu124
|
||||||
|
- Datasets: 4.8.4
|
||||||
|
- Tokenizers: 0.22.2
|
||||||
|
|
||||||
|
## Citations
|
||||||
|
|
||||||
|
Cite GRPO as:
|
||||||
|
|
||||||
|
```bibtex
|
||||||
|
@article{shao2024deepseekmath,
|
||||||
|
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
|
||||||
|
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
|
||||||
|
year = 2024,
|
||||||
|
eprint = {arXiv:2402.03300},
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
Cite TRL as:
|
||||||
|
|
||||||
|
```bibtex
|
||||||
|
@software{vonwerra2020trl,
|
||||||
|
title = {{TRL: Transformers Reinforcement Learning}},
|
||||||
|
author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
|
||||||
|
license = {Apache-2.0},
|
||||||
|
url = {https://github.com/huggingface/trl},
|
||||||
|
year = {2020}
|
||||||
|
}
|
||||||
|
```
|
||||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- messages[0].content + '\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||||
|
{%- else %}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||||
|
{%- for message in messages[::-1] %}
|
||||||
|
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||||
|
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||||
|
{%- set ns.multi_step_tool = false %}
|
||||||
|
{%- set ns.last_query_index = index %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if message.content is string %}
|
||||||
|
{%- set content = message.content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set content = '' %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{%- set reasoning_content = '' %}
|
||||||
|
{%- if message.reasoning_content is string %}
|
||||||
|
{%- set reasoning_content = message.reasoning_content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- if '</think>' in content %}
|
||||||
|
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||||
|
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if loop.index0 > ns.last_query_index %}
|
||||||
|
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if message.tool_calls %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if (loop.first and content) or (not loop.first) %}
|
||||||
|
{{- '\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if tool_call.function %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{%- if tool_call.arguments is string %}
|
||||||
|
{{- tool_call.arguments }}
|
||||||
|
{%- else %}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||||
|
{{- '<think>\n\n</think>\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
3
completions/completions_00005.parquet
Normal file
3
completions/completions_00005.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:da53270bc1cbd333b4a843d1ee571424982150f20486a2f86603f09f57f8d5c0
|
||||||
|
size 22675
|
||||||
3
completions/completions_00010.parquet
Normal file
3
completions/completions_00010.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:45d28c1e1e5f5179b74106e219d45a38fae8692d01ccb60390b1be41f9c7787b
|
||||||
|
size 22188
|
||||||
3
completions/completions_00015.parquet
Normal file
3
completions/completions_00015.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:490f67901ab064a348db95d634358d858a1e1a4498c47328a2016928ff6d270e
|
||||||
|
size 22193
|
||||||
3
completions/completions_00020.parquet
Normal file
3
completions/completions_00020.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7cc9b4ca220ae53e58b06f2ff0b71a7dc9901f784be19b14fa3a6e33762673c8
|
||||||
|
size 21489
|
||||||
3
completions/completions_00025.parquet
Normal file
3
completions/completions_00025.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:60857e90fc1d6d4b8559715a571ec9a2397fdca0cad3cc44e839fa28633e5489
|
||||||
|
size 21285
|
||||||
3
completions/completions_00030.parquet
Normal file
3
completions/completions_00030.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2b6d06d53a6dcf47da9dc63d368b38d8fb10157b55f6be77f2d35e8d716b86c7
|
||||||
|
size 22002
|
||||||
3
completions/completions_00035.parquet
Normal file
3
completions/completions_00035.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7e42ebc66e91765a7c04e5c42efdea0ac7660b0efc5790b23fb36a74f76cf88e
|
||||||
|
size 22549
|
||||||
3
completions/completions_00040.parquet
Normal file
3
completions/completions_00040.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:fbdf98c0994c72e8102e19857dc0ecc0e2f46115c0740763bc0c554d88a204cf
|
||||||
|
size 22934
|
||||||
3
completions/completions_00045.parquet
Normal file
3
completions/completions_00045.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ebd9421c2089b8fa7d4c8eb47187c3edf0a6bc023e53b8f39fe6e7710e3b1f32
|
||||||
|
size 21131
|
||||||
3
completions/completions_00050.parquet
Normal file
3
completions/completions_00050.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:4f2d379572eec110ad3433ec7c070b982f68282196c82eebe10e406f3fc0a641
|
||||||
|
size 22984
|
||||||
3
completions/completions_00055.parquet
Normal file
3
completions/completions_00055.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5255677f12055e9a5a8efd8dede8bf4d1ac6207a61ef821c0e0c1be599e02d4a
|
||||||
|
size 22165
|
||||||
3
completions/completions_00060.parquet
Normal file
3
completions/completions_00060.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e8e68da10071cead126f690844fc27a6cd3a709741131a6a435958ac6dfd3969
|
||||||
|
size 21311
|
||||||
3
completions/completions_00065.parquet
Normal file
3
completions/completions_00065.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2a399daa41cb35fd8a80f9a34558b87af827733447f5a943c7316c0cd6288977
|
||||||
|
size 22260
|
||||||
3
completions/completions_00070.parquet
Normal file
3
completions/completions_00070.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ab4065600a7ec6a2a7c613cf7f6ce0709aae67ef399838f3785a1fbf5c60abcb
|
||||||
|
size 22967
|
||||||
3
completions/completions_00075.parquet
Normal file
3
completions/completions_00075.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e908be1d218d18acebb914fbe9758b584a8149a137d8ae78934a0c6769a5c976
|
||||||
|
size 23009
|
||||||
3
completions/completions_00080.parquet
Normal file
3
completions/completions_00080.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f91e695399b6d42949d077030366c12d484f1b103d498bef231e63f54ea785ce
|
||||||
|
size 22422
|
||||||
3
completions/completions_00085.parquet
Normal file
3
completions/completions_00085.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:809a1f1288111cc0773d849adf947f7a1c8d9724732fb5a77756eb5b521e8777
|
||||||
|
size 23201
|
||||||
3
completions/completions_00090.parquet
Normal file
3
completions/completions_00090.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c6a0c5041939171731d16e4358152484a6232443fa7501ce4e108f21cdcfef54
|
||||||
|
size 22810
|
||||||
3
completions/completions_00095.parquet
Normal file
3
completions/completions_00095.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a53f30fcd731504d84072432dd9c41898bc7e87e9bf5b7df22d78bc3df246fe3
|
||||||
|
size 23816
|
||||||
3
completions/completions_00100.parquet
Normal file
3
completions/completions_00100.parquet
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:995df8be2a89081fffec5199a69ddd403b1eb5d362e4ac875b858df9310ea2c8
|
||||||
|
size 23645
|
||||||
63
config.json
Normal file
63
config.json
Normal file
@@ -0,0 +1,63 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": null,
|
||||||
|
"dtype": "float32",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 1024,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 3072,
|
||||||
|
"layer_types": [
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 40960,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_parameters": {
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"rope_type": "default"
|
||||||
|
},
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"transformers_version": "5.7.0.dev0",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
|||||||
|
{
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"temperature": 0.6,
|
||||||
|
"top_k": 20,
|
||||||
|
"top_p": 0.95,
|
||||||
|
"transformers_version": "5.7.0.dev0"
|
||||||
|
}
|
||||||
89
last-checkpoint/chat_template.jinja
Normal file
89
last-checkpoint/chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- messages[0].content + '\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||||
|
{%- else %}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||||
|
{%- for message in messages[::-1] %}
|
||||||
|
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||||
|
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||||
|
{%- set ns.multi_step_tool = false %}
|
||||||
|
{%- set ns.last_query_index = index %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if message.content is string %}
|
||||||
|
{%- set content = message.content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set content = '' %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{%- set reasoning_content = '' %}
|
||||||
|
{%- if message.reasoning_content is string %}
|
||||||
|
{%- set reasoning_content = message.reasoning_content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- if '</think>' in content %}
|
||||||
|
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||||
|
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if loop.index0 > ns.last_query_index %}
|
||||||
|
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if message.tool_calls %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if (loop.first and content) or (not loop.first) %}
|
||||||
|
{{- '\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if tool_call.function %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{%- if tool_call.arguments is string %}
|
||||||
|
{{- tool_call.arguments }}
|
||||||
|
{%- else %}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||||
|
{{- '<think>\n\n</think>\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
63
last-checkpoint/config.json
Normal file
63
last-checkpoint/config.json
Normal file
@@ -0,0 +1,63 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": null,
|
||||||
|
"dtype": "float32",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 1024,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 3072,
|
||||||
|
"layer_types": [
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 40960,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_parameters": {
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"rope_type": "default"
|
||||||
|
},
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"transformers_version": "5.7.0.dev0",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
12
last-checkpoint/generation_config.json
Normal file
12
last-checkpoint/generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
|||||||
|
{
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"temperature": 0.6,
|
||||||
|
"top_k": 20,
|
||||||
|
"top_p": 0.95,
|
||||||
|
"transformers_version": "5.7.0.dev0"
|
||||||
|
}
|
||||||
3
last-checkpoint/model.safetensors
Normal file
3
last-checkpoint/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:0f30277af82ed00b800ce3c2f64f297b325ff5ab6efe5ccf4d195a6fb8176f3a
|
||||||
|
size 2384234968
|
||||||
3
last-checkpoint/optimizer.pt
Normal file
3
last-checkpoint/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:028b0694d91145a92bd60e86ef1f3699c317b4ddcbddd7e487ed766f89bb1ecc
|
||||||
|
size 4768664614
|
||||||
3
last-checkpoint/rng_state.pth
Normal file
3
last-checkpoint/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ebabe45dfccda450cd514e1b8ab00d92ab40c4e38299af2f6ec42be9f891dcd1
|
||||||
|
size 14244
|
||||||
3
last-checkpoint/scheduler.pt
Normal file
3
last-checkpoint/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5cb6a97bc3be1000acb4b9749ce6ff7a8db226ac1adc71cd71301dcc8b30bf5f
|
||||||
|
size 1064
|
||||||
3
last-checkpoint/tokenizer.json
Normal file
3
last-checkpoint/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||||
|
size 11422650
|
||||||
75
last-checkpoint/tokenizer_config.json
Normal file
75
last-checkpoint/tokenizer_config.json
Normal file
@@ -0,0 +1,75 @@
|
|||||||
|
{
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"backend": "tokenizers",
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_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|>"
|
||||||
|
],
|
||||||
|
"is_local": false,
|
||||||
|
"local_files_only": false,
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"padding_side": "left",
|
||||||
|
"response_schema": {
|
||||||
|
"properties": {
|
||||||
|
"content": {
|
||||||
|
"type": "string"
|
||||||
|
},
|
||||||
|
"reasoning_content": {
|
||||||
|
"type": "string"
|
||||||
|
},
|
||||||
|
"role": {
|
||||||
|
"const": "assistant"
|
||||||
|
},
|
||||||
|
"tool_calls": {
|
||||||
|
"items": {
|
||||||
|
"properties": {
|
||||||
|
"function": {
|
||||||
|
"properties": {
|
||||||
|
"arguments": {
|
||||||
|
"additionalProperties": {},
|
||||||
|
"type": "object"
|
||||||
|
},
|
||||||
|
"name": {
|
||||||
|
"type": "string"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"type": "object"
|
||||||
|
},
|
||||||
|
"type": {
|
||||||
|
"const": "function"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"type": "object",
|
||||||
|
"x-parser": "json",
|
||||||
|
"x-parser-args": {
|
||||||
|
"transform": "{type: 'function', function: @}"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"type": "array",
|
||||||
|
"x-regex-iterator": "<tool_call>\\s*(.+?)\\s*</tool_call>"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"type": "object",
|
||||||
|
"x-regex": "^(?:<think>\\n?(?:(?P<reasoning_content>.*?\\S.*?)\\n?|[\\s]*)</think>\\s*)?(?P<content>.*?)(?:\\n(?=<tool_call>))?(?=(?:<tool_call>|<\\|im_end\\|>|$))(?P<tool_calls>(?:<tool_call>.+?</tool_call>\\s*)+)?\\s*(?:<\\|im_end\\|>|$)"
|
||||||
|
},
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"truncation_side": "left",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
614
last-checkpoint/trainer_state.json
Normal file
614
last-checkpoint/trainer_state.json
Normal file
@@ -0,0 +1,614 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 0.4,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 100,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 188.4,
|
||||||
|
"completions/max_terminated_length": 188.4,
|
||||||
|
"completions/mean_length": 121.775,
|
||||||
|
"completions/mean_terminated_length": 121.775,
|
||||||
|
"completions/min_length": 78.2,
|
||||||
|
"completions/min_terminated_length": 78.2,
|
||||||
|
"entropy": 0.24368538679555057,
|
||||||
|
"epoch": 0.02,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 5.132767200469971,
|
||||||
|
"learning_rate": 9.84e-07,
|
||||||
|
"loss": 0.021476665139198305,
|
||||||
|
"num_tokens": 29677.0,
|
||||||
|
"reward": 0.5543750047683715,
|
||||||
|
"reward_std": 0.14613429307937623,
|
||||||
|
"rewards/reward_func/mean": 0.5543750047683715,
|
||||||
|
"rewards/reward_func/std": 0.14613429754972457,
|
||||||
|
"step": 5,
|
||||||
|
"step_time": 14.864119119599128,
|
||||||
|
"tools/call_frequency": 3.875,
|
||||||
|
"tools/failure_frequency": 0.8958312749862671
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 168.6,
|
||||||
|
"completions/max_terminated_length": 168.6,
|
||||||
|
"completions/mean_length": 130.725,
|
||||||
|
"completions/mean_terminated_length": 130.725,
|
||||||
|
"completions/min_length": 104.0,
|
||||||
|
"completions/min_terminated_length": 104.0,
|
||||||
|
"entropy": 0.24438673248514534,
|
||||||
|
"epoch": 0.04,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 3.591146469116211,
|
||||||
|
"learning_rate": 9.64e-07,
|
||||||
|
"loss": 0.029430291056632994,
|
||||||
|
"num_tokens": 59716.0,
|
||||||
|
"reward": 0.5546875,
|
||||||
|
"reward_std": 0.14634020775556564,
|
||||||
|
"rewards/reward_func/mean": 0.5546875,
|
||||||
|
"rewards/reward_func/std": 0.14634020924568175,
|
||||||
|
"step": 10,
|
||||||
|
"step_time": 14.065522156999942,
|
||||||
|
"tools/call_frequency": 4.025,
|
||||||
|
"tools/failure_frequency": 0.9068181872367859
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.025,
|
||||||
|
"completions/max_length": 163.4,
|
||||||
|
"completions/max_terminated_length": 163.4,
|
||||||
|
"completions/mean_length": 128.0,
|
||||||
|
"completions/mean_terminated_length": 128.1500015258789,
|
||||||
|
"completions/min_length": 105.8,
|
||||||
|
"completions/min_terminated_length": 105.8,
|
||||||
|
"entropy": 0.2112921039108187,
|
||||||
|
"epoch": 0.06,
|
||||||
|
"frac_reward_zero_std": 0.4,
|
||||||
|
"grad_norm": 4.043612480163574,
|
||||||
|
"learning_rate": 9.439999999999999e-07,
|
||||||
|
"loss": 0.010420092940330505,
|
||||||
|
"num_tokens": 89639.0,
|
||||||
|
"reward": 0.5423749923706055,
|
||||||
|
"reward_std": 0.1744689464569092,
|
||||||
|
"rewards/reward_func/mean": 0.5423749923706055,
|
||||||
|
"rewards/reward_func/std": 0.17446894943714142,
|
||||||
|
"step": 15,
|
||||||
|
"step_time": 11.504540603999704,
|
||||||
|
"tools/call_frequency": 3.95,
|
||||||
|
"tools/failure_frequency": 0.8987920165061951
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.025,
|
||||||
|
"completions/max_length": 209.8,
|
||||||
|
"completions/max_terminated_length": 178.0,
|
||||||
|
"completions/mean_length": 138.075,
|
||||||
|
"completions/mean_terminated_length": 132.8,
|
||||||
|
"completions/min_length": 105.4,
|
||||||
|
"completions/min_terminated_length": 105.4,
|
||||||
|
"entropy": 0.22869818531908095,
|
||||||
|
"epoch": 0.08,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 3.174783229827881,
|
||||||
|
"learning_rate": 9.24e-07,
|
||||||
|
"loss": 0.030705225467681885,
|
||||||
|
"num_tokens": 119967.0,
|
||||||
|
"reward": 0.5546875,
|
||||||
|
"reward_std": 0.15467961132526398,
|
||||||
|
"rewards/reward_func/mean": 0.5546875,
|
||||||
|
"rewards/reward_func/std": 0.15467961132526398,
|
||||||
|
"step": 20,
|
||||||
|
"step_time": 15.2172645851997,
|
||||||
|
"tools/call_frequency": 4.225,
|
||||||
|
"tools/failure_frequency": 0.9109591126441956
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 179.2,
|
||||||
|
"completions/max_terminated_length": 179.2,
|
||||||
|
"completions/mean_length": 133.6,
|
||||||
|
"completions/mean_terminated_length": 133.6,
|
||||||
|
"completions/min_length": 108.6,
|
||||||
|
"completions/min_terminated_length": 108.6,
|
||||||
|
"entropy": 0.23596344091929494,
|
||||||
|
"epoch": 0.1,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 2.9762465953826904,
|
||||||
|
"learning_rate": 9.039999999999999e-07,
|
||||||
|
"loss": 0.03595758378505707,
|
||||||
|
"num_tokens": 150118.0,
|
||||||
|
"reward": 0.5421875,
|
||||||
|
"reward_std": 0.1739386200904846,
|
||||||
|
"rewards/reward_func/mean": 0.5421875,
|
||||||
|
"rewards/reward_func/std": 0.1739386200904846,
|
||||||
|
"step": 25,
|
||||||
|
"step_time": 11.905974677799714,
|
||||||
|
"tools/call_frequency": 4.05,
|
||||||
|
"tools/failure_frequency": 0.9073529362678527
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 174.6,
|
||||||
|
"completions/max_terminated_length": 174.6,
|
||||||
|
"completions/mean_length": 131.3,
|
||||||
|
"completions/mean_terminated_length": 131.3,
|
||||||
|
"completions/min_length": 106.4,
|
||||||
|
"completions/min_terminated_length": 106.4,
|
||||||
|
"entropy": 0.24171450519934295,
|
||||||
|
"epoch": 0.12,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 2.964181900024414,
|
||||||
|
"learning_rate": 8.839999999999999e-07,
|
||||||
|
"loss": 0.03578909039497376,
|
||||||
|
"num_tokens": 180183.0,
|
||||||
|
"reward": 0.5546875,
|
||||||
|
"reward_std": 0.15467961132526398,
|
||||||
|
"rewards/reward_func/mean": 0.5546875,
|
||||||
|
"rewards/reward_func/std": 0.15467961132526398,
|
||||||
|
"step": 30,
|
||||||
|
"step_time": 11.773073928199846,
|
||||||
|
"tools/call_frequency": 4.025,
|
||||||
|
"tools/failure_frequency": 0.9068181872367859
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 164.0,
|
||||||
|
"completions/max_terminated_length": 164.0,
|
||||||
|
"completions/mean_length": 133.5,
|
||||||
|
"completions/mean_terminated_length": 133.5,
|
||||||
|
"completions/min_length": 106.4,
|
||||||
|
"completions/min_terminated_length": 106.4,
|
||||||
|
"entropy": 0.25739177097566424,
|
||||||
|
"epoch": 0.14,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 3.43412184715271,
|
||||||
|
"learning_rate": 8.639999999999999e-07,
|
||||||
|
"loss": 0.037665295600891116,
|
||||||
|
"num_tokens": 210329.0,
|
||||||
|
"reward": 0.5546875,
|
||||||
|
"reward_std": 0.15467961132526398,
|
||||||
|
"rewards/reward_func/mean": 0.5546875,
|
||||||
|
"rewards/reward_func/std": 0.15467961132526398,
|
||||||
|
"step": 35,
|
||||||
|
"step_time": 11.653867780799919,
|
||||||
|
"tools/call_frequency": 4.1,
|
||||||
|
"tools/failure_frequency": 0.9084893107414246
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 163.0,
|
||||||
|
"completions/max_terminated_length": 163.0,
|
||||||
|
"completions/mean_length": 130.35,
|
||||||
|
"completions/mean_terminated_length": 130.35,
|
||||||
|
"completions/min_length": 105.2,
|
||||||
|
"completions/min_terminated_length": 105.2,
|
||||||
|
"entropy": 0.24240239977370948,
|
||||||
|
"epoch": 0.16,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 1.9415134191513062,
|
||||||
|
"learning_rate": 8.439999999999999e-07,
|
||||||
|
"loss": 0.038230502605438234,
|
||||||
|
"num_tokens": 240351.0,
|
||||||
|
"reward": 0.5546875,
|
||||||
|
"reward_std": 0.15467961132526398,
|
||||||
|
"rewards/reward_func/mean": 0.5546875,
|
||||||
|
"rewards/reward_func/std": 0.15467961132526398,
|
||||||
|
"step": 40,
|
||||||
|
"step_time": 11.493494538199593,
|
||||||
|
"tools/call_frequency": 4.1,
|
||||||
|
"tools/failure_frequency": 0.9085227489471436
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 189.2,
|
||||||
|
"completions/max_terminated_length": 189.2,
|
||||||
|
"completions/mean_length": 144.325,
|
||||||
|
"completions/mean_terminated_length": 144.325,
|
||||||
|
"completions/min_length": 103.4,
|
||||||
|
"completions/min_terminated_length": 103.4,
|
||||||
|
"entropy": 0.2922910688444972,
|
||||||
|
"epoch": 0.18,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 2.625551223754883,
|
||||||
|
"learning_rate": 8.24e-07,
|
||||||
|
"loss": 0.029571545124053956,
|
||||||
|
"num_tokens": 270934.0,
|
||||||
|
"reward": 0.5421875,
|
||||||
|
"reward_std": 0.1739386200904846,
|
||||||
|
"rewards/reward_func/mean": 0.5421875,
|
||||||
|
"rewards/reward_func/std": 0.1739386200904846,
|
||||||
|
"step": 45,
|
||||||
|
"step_time": 13.904022978000103,
|
||||||
|
"tools/call_frequency": 4.3,
|
||||||
|
"tools/failure_frequency": 0.9124376058578492
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 173.4,
|
||||||
|
"completions/max_terminated_length": 173.4,
|
||||||
|
"completions/mean_length": 136.9,
|
||||||
|
"completions/mean_terminated_length": 136.9,
|
||||||
|
"completions/min_length": 102.0,
|
||||||
|
"completions/min_terminated_length": 102.0,
|
||||||
|
"entropy": 0.30844923059921714,
|
||||||
|
"epoch": 0.2,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 2.4793224334716797,
|
||||||
|
"learning_rate": 8.04e-07,
|
||||||
|
"loss": 0.05630779266357422,
|
||||||
|
"num_tokens": 301212.0,
|
||||||
|
"reward": 0.5546875,
|
||||||
|
"reward_std": 0.15467961132526398,
|
||||||
|
"rewards/reward_func/mean": 0.5546875,
|
||||||
|
"rewards/reward_func/std": 0.15467961132526398,
|
||||||
|
"step": 50,
|
||||||
|
"step_time": 12.183540330400138,
|
||||||
|
"tools/call_frequency": 4.075,
|
||||||
|
"tools/failure_frequency": 0.9079211235046387
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 169.2,
|
||||||
|
"completions/max_terminated_length": 169.2,
|
||||||
|
"completions/mean_length": 133.675,
|
||||||
|
"completions/mean_terminated_length": 133.675,
|
||||||
|
"completions/min_length": 104.0,
|
||||||
|
"completions/min_terminated_length": 104.0,
|
||||||
|
"entropy": 0.2755190956639126,
|
||||||
|
"epoch": 0.22,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 2.5465078353881836,
|
||||||
|
"learning_rate": 7.84e-07,
|
||||||
|
"loss": 0.044404512643814086,
|
||||||
|
"num_tokens": 331366.0,
|
||||||
|
"reward": 0.5546875,
|
||||||
|
"reward_std": 0.15467961132526398,
|
||||||
|
"rewards/reward_func/mean": 0.5546875,
|
||||||
|
"rewards/reward_func/std": 0.15467961132526398,
|
||||||
|
"step": 55,
|
||||||
|
"step_time": 12.093883183000253,
|
||||||
|
"tools/call_frequency": 4.05,
|
||||||
|
"tools/failure_frequency": 0.9073863744735717
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 169.4,
|
||||||
|
"completions/max_terminated_length": 169.4,
|
||||||
|
"completions/mean_length": 131.625,
|
||||||
|
"completions/mean_terminated_length": 131.625,
|
||||||
|
"completions/min_length": 99.6,
|
||||||
|
"completions/min_terminated_length": 99.6,
|
||||||
|
"entropy": 0.27003198163583875,
|
||||||
|
"epoch": 0.24,
|
||||||
|
"frac_reward_zero_std": 0.4,
|
||||||
|
"grad_norm": 2.265756845474243,
|
||||||
|
"learning_rate": 7.64e-07,
|
||||||
|
"loss": 0.023787906765937804,
|
||||||
|
"num_tokens": 361436.0,
|
||||||
|
"reward": 0.5421875,
|
||||||
|
"reward_std": 0.1739386200904846,
|
||||||
|
"rewards/reward_func/mean": 0.5421875,
|
||||||
|
"rewards/reward_func/std": 0.1739386200904846,
|
||||||
|
"step": 60,
|
||||||
|
"step_time": 11.345259791600256,
|
||||||
|
"tools/call_frequency": 3.975,
|
||||||
|
"tools/failure_frequency": 0.9049531102180481
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 161.0,
|
||||||
|
"completions/max_terminated_length": 161.0,
|
||||||
|
"completions/mean_length": 134.475,
|
||||||
|
"completions/mean_terminated_length": 134.475,
|
||||||
|
"completions/min_length": 102.2,
|
||||||
|
"completions/min_terminated_length": 102.2,
|
||||||
|
"entropy": 0.31135775299044327,
|
||||||
|
"epoch": 0.26,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 2.0467045307159424,
|
||||||
|
"learning_rate": 7.44e-07,
|
||||||
|
"loss": 0.03975436091423035,
|
||||||
|
"num_tokens": 391623.0,
|
||||||
|
"reward": 0.5421875,
|
||||||
|
"reward_std": 0.1739386200904846,
|
||||||
|
"rewards/reward_func/mean": 0.5421875,
|
||||||
|
"rewards/reward_func/std": 0.1739386200904846,
|
||||||
|
"step": 65,
|
||||||
|
"step_time": 11.19052229420031,
|
||||||
|
"tools/call_frequency": 3.9,
|
||||||
|
"tools/failure_frequency": 0.9035714268684387
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 187.2,
|
||||||
|
"completions/max_terminated_length": 187.2,
|
||||||
|
"completions/mean_length": 138.75,
|
||||||
|
"completions/mean_terminated_length": 138.75,
|
||||||
|
"completions/min_length": 109.8,
|
||||||
|
"completions/min_terminated_length": 109.8,
|
||||||
|
"entropy": 0.30972914764424786,
|
||||||
|
"epoch": 0.28,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 1.9595667123794556,
|
||||||
|
"learning_rate": 7.24e-07,
|
||||||
|
"loss": 0.04363401532173157,
|
||||||
|
"num_tokens": 421981.0,
|
||||||
|
"reward": 0.5546875,
|
||||||
|
"reward_std": 0.15467961132526398,
|
||||||
|
"rewards/reward_func/mean": 0.5546875,
|
||||||
|
"rewards/reward_func/std": 0.15467961132526398,
|
||||||
|
"step": 70,
|
||||||
|
"step_time": 12.639552449400071,
|
||||||
|
"tools/call_frequency": 4.0,
|
||||||
|
"tools/failure_frequency": 0.90625
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 229.0,
|
||||||
|
"completions/max_terminated_length": 229.0,
|
||||||
|
"completions/mean_length": 151.35,
|
||||||
|
"completions/mean_terminated_length": 151.35,
|
||||||
|
"completions/min_length": 108.4,
|
||||||
|
"completions/min_terminated_length": 108.4,
|
||||||
|
"entropy": 0.3386134950676933,
|
||||||
|
"epoch": 0.3,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 2.162438154220581,
|
||||||
|
"learning_rate": 7.04e-07,
|
||||||
|
"loss": 0.10028836727142335,
|
||||||
|
"num_tokens": 452843.0,
|
||||||
|
"reward": 0.5421875,
|
||||||
|
"reward_std": 0.1739386200904846,
|
||||||
|
"rewards/reward_func/mean": 0.5421875,
|
||||||
|
"rewards/reward_func/std": 0.1739386200904846,
|
||||||
|
"step": 75,
|
||||||
|
"step_time": 15.725879665600042,
|
||||||
|
"tools/call_frequency": 3.975,
|
||||||
|
"tools/failure_frequency": 0.9052759885787964
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 177.8,
|
||||||
|
"completions/max_terminated_length": 177.8,
|
||||||
|
"completions/mean_length": 142.1,
|
||||||
|
"completions/mean_terminated_length": 142.1,
|
||||||
|
"completions/min_length": 108.2,
|
||||||
|
"completions/min_terminated_length": 108.2,
|
||||||
|
"entropy": 0.3440137348137796,
|
||||||
|
"epoch": 0.32,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 1.5661996603012085,
|
||||||
|
"learning_rate": 6.84e-07,
|
||||||
|
"loss": 0.04704100489616394,
|
||||||
|
"num_tokens": 483332.0,
|
||||||
|
"reward": 0.5546875,
|
||||||
|
"reward_std": 0.15467961132526398,
|
||||||
|
"rewards/reward_func/mean": 0.5546875,
|
||||||
|
"rewards/reward_func/std": 0.15467961132526398,
|
||||||
|
"step": 80,
|
||||||
|
"step_time": 12.160148031599965,
|
||||||
|
"tools/call_frequency": 4.025,
|
||||||
|
"tools/failure_frequency": 0.9068181872367859
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.025,
|
||||||
|
"completions/max_length": 201.8,
|
||||||
|
"completions/max_terminated_length": 201.8,
|
||||||
|
"completions/mean_length": 153.2,
|
||||||
|
"completions/mean_terminated_length": 152.66428833007814,
|
||||||
|
"completions/min_length": 112.0,
|
||||||
|
"completions/min_terminated_length": 112.0,
|
||||||
|
"entropy": 0.4032384747406468,
|
||||||
|
"epoch": 0.34,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 4.639192581176758,
|
||||||
|
"learning_rate": 6.64e-07,
|
||||||
|
"loss": 0.01302967369556427,
|
||||||
|
"num_tokens": 514266.0,
|
||||||
|
"reward": 0.5546875,
|
||||||
|
"reward_std": 0.15467961132526398,
|
||||||
|
"rewards/reward_func/mean": 0.5546875,
|
||||||
|
"rewards/reward_func/std": 0.15467961132526398,
|
||||||
|
"step": 85,
|
||||||
|
"step_time": 14.85692119880041,
|
||||||
|
"tools/call_frequency": 4.275,
|
||||||
|
"tools/failure_frequency": 0.9116071462631226
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 217.0,
|
||||||
|
"completions/max_terminated_length": 217.0,
|
||||||
|
"completions/mean_length": 155.25,
|
||||||
|
"completions/mean_terminated_length": 155.25,
|
||||||
|
"completions/min_length": 107.2,
|
||||||
|
"completions/min_terminated_length": 107.2,
|
||||||
|
"entropy": 0.3891718311235309,
|
||||||
|
"epoch": 0.36,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 2.346120834350586,
|
||||||
|
"learning_rate": 6.44e-07,
|
||||||
|
"loss": 0.07838824391365051,
|
||||||
|
"num_tokens": 545274.0,
|
||||||
|
"reward": 0.5546875,
|
||||||
|
"reward_std": 0.15467961132526398,
|
||||||
|
"rewards/reward_func/mean": 0.5546875,
|
||||||
|
"rewards/reward_func/std": 0.15467961132526398,
|
||||||
|
"step": 90,
|
||||||
|
"step_time": 14.502108011600649,
|
||||||
|
"tools/call_frequency": 4.05,
|
||||||
|
"tools/failure_frequency": 0.9073529362678527
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.025,
|
||||||
|
"completions/max_length": 277.2,
|
||||||
|
"completions/max_terminated_length": 277.2,
|
||||||
|
"completions/mean_length": 173.75,
|
||||||
|
"completions/mean_terminated_length": 174.2357147216797,
|
||||||
|
"completions/min_length": 115.4,
|
||||||
|
"completions/min_terminated_length": 115.4,
|
||||||
|
"entropy": 0.3660696781706065,
|
||||||
|
"epoch": 0.38,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 2.0744283199310303,
|
||||||
|
"learning_rate": 6.24e-07,
|
||||||
|
"loss": 0.04411016702651978,
|
||||||
|
"num_tokens": 577035.0,
|
||||||
|
"reward": 0.5546875,
|
||||||
|
"reward_std": 0.15467961132526398,
|
||||||
|
"rewards/reward_func/mean": 0.5546875,
|
||||||
|
"rewards/reward_func/std": 0.15467961132526398,
|
||||||
|
"step": 95,
|
||||||
|
"step_time": 17.604619891600485,
|
||||||
|
"tools/call_frequency": 5.275,
|
||||||
|
"tools/failure_frequency": 0.927957046031952
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.025,
|
||||||
|
"completions/max_length": 262.6,
|
||||||
|
"completions/max_terminated_length": 249.4,
|
||||||
|
"completions/mean_length": 185.4,
|
||||||
|
"completions/mean_terminated_length": 181.58214416503907,
|
||||||
|
"completions/min_length": 113.4,
|
||||||
|
"completions/min_terminated_length": 113.4,
|
||||||
|
"entropy": 0.3639457892393693,
|
||||||
|
"epoch": 0.4,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 2.8498334884643555,
|
||||||
|
"learning_rate": 6.04e-07,
|
||||||
|
"loss": 0.06711583137512207,
|
||||||
|
"num_tokens": 609256.0,
|
||||||
|
"reward": 0.5546875,
|
||||||
|
"reward_std": 0.15467961132526398,
|
||||||
|
"rewards/reward_func/mean": 0.5546875,
|
||||||
|
"rewards/reward_func/std": 0.15467961132526398,
|
||||||
|
"step": 100,
|
||||||
|
"step_time": 18.920671705199673,
|
||||||
|
"tools/call_frequency": 5.6,
|
||||||
|
"tools/failure_frequency": 0.9292140007019043
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 5,
|
||||||
|
"max_steps": 250,
|
||||||
|
"num_input_tokens_seen": 609256,
|
||||||
|
"num_train_epochs": 1,
|
||||||
|
"save_steps": 50,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": true,
|
||||||
|
"should_training_stop": false
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 0.0,
|
||||||
|
"train_batch_size": 1,
|
||||||
|
"trial_name": null,
|
||||||
|
"trial_params": null
|
||||||
|
}
|
||||||
3
last-checkpoint/training_args.bin
Normal file
3
last-checkpoint/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:4aaf152b694340e3bc8b29995f1f6f4c396fa634812fba33a3a58e1ff8700c9f
|
||||||
|
size 6840
|
||||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:0f30277af82ed00b800ce3c2f64f297b325ff5ab6efe5ccf4d195a6fb8176f3a
|
||||||
|
size 2384234968
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||||
|
size 11422650
|
||||||
75
tokenizer_config.json
Normal file
75
tokenizer_config.json
Normal file
@@ -0,0 +1,75 @@
|
|||||||
|
{
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"backend": "tokenizers",
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_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|>"
|
||||||
|
],
|
||||||
|
"is_local": false,
|
||||||
|
"local_files_only": false,
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"padding_side": "left",
|
||||||
|
"response_schema": {
|
||||||
|
"properties": {
|
||||||
|
"content": {
|
||||||
|
"type": "string"
|
||||||
|
},
|
||||||
|
"reasoning_content": {
|
||||||
|
"type": "string"
|
||||||
|
},
|
||||||
|
"role": {
|
||||||
|
"const": "assistant"
|
||||||
|
},
|
||||||
|
"tool_calls": {
|
||||||
|
"items": {
|
||||||
|
"properties": {
|
||||||
|
"function": {
|
||||||
|
"properties": {
|
||||||
|
"arguments": {
|
||||||
|
"additionalProperties": {},
|
||||||
|
"type": "object"
|
||||||
|
},
|
||||||
|
"name": {
|
||||||
|
"type": "string"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"type": "object"
|
||||||
|
},
|
||||||
|
"type": {
|
||||||
|
"const": "function"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"type": "object",
|
||||||
|
"x-parser": "json",
|
||||||
|
"x-parser-args": {
|
||||||
|
"transform": "{type: 'function', function: @}"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"type": "array",
|
||||||
|
"x-regex-iterator": "<tool_call>\\s*(.+?)\\s*</tool_call>"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"type": "object",
|
||||||
|
"x-regex": "^(?:<think>\\n?(?:(?P<reasoning_content>.*?\\S.*?)\\n?|[\\s]*)</think>\\s*)?(?P<content>.*?)(?:\\n(?=<tool_call>))?(?=(?:<tool_call>|<\\|im_end\\|>|$))(?P<tool_calls>(?:<tool_call>.+?</tool_call>\\s*)+)?\\s*(?:<\\|im_end\\|>|$)"
|
||||||
|
},
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"truncation_side": "left",
|
||||||
|
"unk_token": 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 sha256:4aaf152b694340e3bc8b29995f1f6f4c396fa634812fba33a3a58e1ff8700c9f
|
||||||
|
size 6840
|
||||||
Reference in New Issue
Block a user