初始化项目，由ModelHub XC社区提供模型
Model: jekunz/Qwen3-1.7B-sv-SmolTalk Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.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
|
||||
checkpoint-2017/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
58
README.md
Normal file
58
README.md
Normal file
@@ -0,0 +1,58 @@
|
||||
---
|
||||
base_model: Qwen/Qwen3-1.7B
|
||||
library_name: transformers
|
||||
model_name: Qwen3-1.7B-sv-smoltalk
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- trl
|
||||
- sft
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for Qwen3-1.7B-sv-smoltalk
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B).
|
||||
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="None", 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 SFT.
|
||||
|
||||
### Framework versions
|
||||
|
||||
- TRL: 0.25.1
|
||||
- Transformers: 4.57.3
|
||||
- Pytorch: 2.9.1
|
||||
- Datasets: 4.4.1
|
||||
- Tokenizers: 0.22.1
|
||||
|
||||
## Citations
|
||||
|
||||
|
||||
|
||||
Cite TRL as:
|
||||
|
||||
```bibtex
|
||||
@misc{vonwerra2022trl,
|
||||
title = {{TRL: Transformer Reinforcement Learning}},
|
||||
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
||||
year = 2020,
|
||||
journal = {GitHub repository},
|
||||
publisher = {GitHub},
|
||||
howpublished = {\url{https://github.com/huggingface/trl}}
|
||||
}
|
||||
```
|
||||
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
|
||||
}
|
||||
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 %}
|
||||
28
checkpoint-2017/added_tokens.json
Normal file
28
checkpoint-2017/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
|
||||
}
|
||||
89
checkpoint-2017/chat_template.jinja
Normal file
89
checkpoint-2017/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 %}
|
||||
60
checkpoint-2017/config.json
Normal file
60
checkpoint-2017/config.json
Normal file
@@ -0,0 +1,60 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6144,
|
||||
"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_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.57.3",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
12
checkpoint-2017/generation_config.json
Normal file
12
checkpoint-2017/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": "4.57.3"
|
||||
}
|
||||
151388
checkpoint-2017/merges.txt
Normal file
151388
checkpoint-2017/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-2017/model.safetensors
Normal file
3
checkpoint-2017/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a147d613e556d6f1060230aff94696ca8e07c80098a61a5210c6788a59f7577d
|
||||
size 3441185608
|
||||
3
checkpoint-2017/optimizer.pt
Normal file
3
checkpoint-2017/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5457867f62ddc0ac388bef7ff92bd2bf6b58584fd79fae36250dda9a66e77bb2
|
||||
size 6882572207
|
||||
3
checkpoint-2017/rng_state_0.pth
Normal file
3
checkpoint-2017/rng_state_0.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7350b59a307e1d89d4515e24325811dc1aa8deab5b5b4635887adaaf78ea1dc5
|
||||
size 16389
|
||||
3
checkpoint-2017/rng_state_1.pth
Normal file
3
checkpoint-2017/rng_state_1.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:af262eaf45f7c1f39099b694376de497429ab46c1046a1d9afe70a315f1b6d81
|
||||
size 16389
|
||||
3
checkpoint-2017/rng_state_2.pth
Normal file
3
checkpoint-2017/rng_state_2.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:57f833fda5ff0e7e566107275c268625e3eb07e8475116fe109d9c667809d469
|
||||
size 16389
|
||||
3
checkpoint-2017/rng_state_3.pth
Normal file
3
checkpoint-2017/rng_state_3.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2a6e6037388bc56484982620075eea8724b4696f67f60603b9c448e44f41705c
|
||||
size 16389
|
||||
3
checkpoint-2017/rng_state_4.pth
Normal file
3
checkpoint-2017/rng_state_4.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d2bf73391bb68f0fffcb931501656f3679db7d996fe258d8287099b6cb7a23a2
|
||||
size 16389
|
||||
3
checkpoint-2017/rng_state_5.pth
Normal file
3
checkpoint-2017/rng_state_5.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:222199bb7faa2ce2cb817e7f870ac7c364fb0f0872e17d8a9280f38596da9a06
|
||||
size 16389
|
||||
3
checkpoint-2017/rng_state_6.pth
Normal file
3
checkpoint-2017/rng_state_6.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ca3accfbfe6616f878cfeda3df23f4418e00b348760c584e397d6c92081cb5c4
|
||||
size 16389
|
||||
3
checkpoint-2017/rng_state_7.pth
Normal file
3
checkpoint-2017/rng_state_7.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a64b41c5668afda0c862d9774a14b1c0a390fe6a57086de71f9fdfb00edb457e
|
||||
size 16389
|
||||
3
checkpoint-2017/scheduler.pt
Normal file
3
checkpoint-2017/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a9d3c43a439fd1e7969124f1fe7099d977b4acb19713ad4f618cba8fed9a2d0f
|
||||
size 1465
|
||||
31
checkpoint-2017/special_tokens_map.json
Normal file
31
checkpoint-2017/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
|
||||
}
|
||||
}
|
||||
BIN
checkpoint-2017/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
checkpoint-2017/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
239
checkpoint-2017/tokenizer_config.json
Normal file
239
checkpoint-2017/tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
||||
{
|
||||
"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,
|
||||
"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
|
||||
}
|
||||
434
checkpoint-2017/trainer_state.json
Normal file
434
checkpoint-2017/trainer_state.json
Normal file
@@ -0,0 +1,434 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 2017,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"entropy": 0.9350311723351479,
|
||||
"epoch": 0.02479082739386427,
|
||||
"grad_norm": 2.921875,
|
||||
"learning_rate": 7.277227722772277e-06,
|
||||
"loss": 1.9223,
|
||||
"mean_token_accuracy": 0.6512195858359336,
|
||||
"num_tokens": 12987057.0,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"entropy": 1.3992473047971725,
|
||||
"epoch": 0.04958165478772854,
|
||||
"grad_norm": 0.5859375,
|
||||
"learning_rate": 1.4702970297029704e-05,
|
||||
"loss": 1.4095,
|
||||
"mean_token_accuracy": 0.6870005157589912,
|
||||
"num_tokens": 25982341.0,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"entropy": 1.2823992617428304,
|
||||
"epoch": 0.07437248218159281,
|
||||
"grad_norm": 0.546875,
|
||||
"learning_rate": 2.212871287128713e-05,
|
||||
"loss": 1.2825,
|
||||
"mean_token_accuracy": 0.7077956217527389,
|
||||
"num_tokens": 38965652.0,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"entropy": 1.2264368762075901,
|
||||
"epoch": 0.09916330957545708,
|
||||
"grad_norm": 0.58203125,
|
||||
"learning_rate": 2.9554455445544555e-05,
|
||||
"loss": 1.2252,
|
||||
"mean_token_accuracy": 0.7175403034687042,
|
||||
"num_tokens": 51955113.0,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"entropy": 1.1745939214527608,
|
||||
"epoch": 0.12395413696932135,
|
||||
"grad_norm": 0.5625,
|
||||
"learning_rate": 2.9950390604994976e-05,
|
||||
"loss": 1.1733,
|
||||
"mean_token_accuracy": 0.7261676301062107,
|
||||
"num_tokens": 64940008.0,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"entropy": 1.1452814097702504,
|
||||
"epoch": 0.14874496436318563,
|
||||
"grad_norm": 0.56640625,
|
||||
"learning_rate": 2.978907368725783e-05,
|
||||
"loss": 1.1429,
|
||||
"mean_token_accuracy": 0.7316162596642971,
|
||||
"num_tokens": 77929904.0,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"entropy": 1.1280623151361941,
|
||||
"epoch": 0.1735357917570499,
|
||||
"grad_norm": 0.58984375,
|
||||
"learning_rate": 2.9517054537806585e-05,
|
||||
"loss": 1.1256,
|
||||
"mean_token_accuracy": 0.7344555719196797,
|
||||
"num_tokens": 90917917.0,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"entropy": 1.106316467821598,
|
||||
"epoch": 0.19832661915091415,
|
||||
"grad_norm": 0.5546875,
|
||||
"learning_rate": 2.9136369330613327e-05,
|
||||
"loss": 1.104,
|
||||
"mean_token_accuracy": 0.7381731517612934,
|
||||
"num_tokens": 103911070.0,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"entropy": 1.0862759150564671,
|
||||
"epoch": 0.22311744654477844,
|
||||
"grad_norm": 0.5625,
|
||||
"learning_rate": 2.864986764929012e-05,
|
||||
"loss": 1.0831,
|
||||
"mean_token_accuracy": 0.7422050322592258,
|
||||
"num_tokens": 116908048.0,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"entropy": 1.071421894133091,
|
||||
"epoch": 0.2479082739386427,
|
||||
"grad_norm": 0.578125,
|
||||
"learning_rate": 2.8061191156796658e-05,
|
||||
"loss": 1.0683,
|
||||
"mean_token_accuracy": 0.7446134378015995,
|
||||
"num_tokens": 129891292.0,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"entropy": 1.0597773297131061,
|
||||
"epoch": 0.27269910133250697,
|
||||
"grad_norm": 0.55859375,
|
||||
"learning_rate": 2.737474633611185e-05,
|
||||
"loss": 1.0563,
|
||||
"mean_token_accuracy": 0.7466570647060871,
|
||||
"num_tokens": 142876112.0,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"entropy": 1.0568923234939576,
|
||||
"epoch": 0.29748992872637126,
|
||||
"grad_norm": 0.546875,
|
||||
"learning_rate": 2.6595671505916456e-05,
|
||||
"loss": 1.0532,
|
||||
"mean_token_accuracy": 0.747249816954136,
|
||||
"num_tokens": 155871785.0,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"entropy": 1.051955975741148,
|
||||
"epoch": 0.3222807561202355,
|
||||
"grad_norm": 0.578125,
|
||||
"learning_rate": 2.5729798358187858e-05,
|
||||
"loss": 1.0482,
|
||||
"mean_token_accuracy": 0.7482274283468723,
|
||||
"num_tokens": 168864657.0,
|
||||
"step": 650
|
||||
},
|
||||
{
|
||||
"entropy": 1.0347797067463398,
|
||||
"epoch": 0.3470715835140998,
|
||||
"grad_norm": 0.55859375,
|
||||
"learning_rate": 2.478360830561368e-05,
|
||||
"loss": 1.0308,
|
||||
"mean_token_accuracy": 0.7513435909152031,
|
||||
"num_tokens": 181847527.0,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"entropy": 1.0355973771214486,
|
||||
"epoch": 0.37186241090796407,
|
||||
"grad_norm": 0.53515625,
|
||||
"learning_rate": 2.376418396558165e-05,
|
||||
"loss": 1.0314,
|
||||
"mean_token_accuracy": 0.7509755866229534,
|
||||
"num_tokens": 194832579.0,
|
||||
"step": 750
|
||||
},
|
||||
{
|
||||
"entropy": 1.0291439467668533,
|
||||
"epoch": 0.3966532383018283,
|
||||
"grad_norm": 0.5546875,
|
||||
"learning_rate": 2.2679156143907717e-05,
|
||||
"loss": 1.0251,
|
||||
"mean_token_accuracy": 0.7523766578733921,
|
||||
"num_tokens": 207819397.0,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"entropy": 1.0309783019125462,
|
||||
"epoch": 0.4214440656956926,
|
||||
"grad_norm": 0.515625,
|
||||
"learning_rate": 2.153664671515084e-05,
|
||||
"loss": 1.0268,
|
||||
"mean_token_accuracy": 0.7517271949350834,
|
||||
"num_tokens": 220806448.0,
|
||||
"step": 850
|
||||
},
|
||||
{
|
||||
"entropy": 1.0233621565997602,
|
||||
"epoch": 0.4462348930895569,
|
||||
"grad_norm": 0.51953125,
|
||||
"learning_rate": 2.0345207827078517e-05,
|
||||
"loss": 1.0188,
|
||||
"mean_token_accuracy": 0.7533569988608361,
|
||||
"num_tokens": 233800554.0,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"entropy": 1.0196293856203555,
|
||||
"epoch": 0.4710257204834211,
|
||||
"grad_norm": 0.53125,
|
||||
"learning_rate": 1.9113757884362315e-05,
|
||||
"loss": 1.0156,
|
||||
"mean_token_accuracy": 0.7541334366798401,
|
||||
"num_tokens": 246788996.0,
|
||||
"step": 950
|
||||
},
|
||||
{
|
||||
"entropy": 1.023166581392288,
|
||||
"epoch": 0.4958165478772854,
|
||||
"grad_norm": 0.53125,
|
||||
"learning_rate": 1.7851514790691512e-05,
|
||||
"loss": 1.0183,
|
||||
"mean_token_accuracy": 0.7532591855525971,
|
||||
"num_tokens": 259781274.0,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"entropy": 1.0117680232226849,
|
||||
"epoch": 0.5206073752711496,
|
||||
"grad_norm": 0.52734375,
|
||||
"learning_rate": 1.6567926949014805e-05,
|
||||
"loss": 1.0079,
|
||||
"mean_token_accuracy": 0.755366503894329,
|
||||
"num_tokens": 272766654.0,
|
||||
"step": 1050
|
||||
},
|
||||
{
|
||||
"entropy": 1.0149836498498916,
|
||||
"epoch": 0.5453982026650139,
|
||||
"grad_norm": 0.53125,
|
||||
"learning_rate": 1.5272602536401258e-05,
|
||||
"loss": 1.0105,
|
||||
"mean_token_accuracy": 0.7547966828942299,
|
||||
"num_tokens": 285761894.0,
|
||||
"step": 1100
|
||||
},
|
||||
{
|
||||
"entropy": 1.0172268342971802,
|
||||
"epoch": 0.5701890300588782,
|
||||
"grad_norm": 0.515625,
|
||||
"learning_rate": 1.3975237582927023e-05,
|
||||
"loss": 1.0126,
|
||||
"mean_token_accuracy": 0.7544859103858471,
|
||||
"num_tokens": 298753069.0,
|
||||
"step": 1150
|
||||
},
|
||||
{
|
||||
"entropy": 1.0113342855870724,
|
||||
"epoch": 0.5949798574527425,
|
||||
"grad_norm": 0.515625,
|
||||
"learning_rate": 1.2685543392946551e-05,
|
||||
"loss": 1.0072,
|
||||
"mean_token_accuracy": 0.7554229401051998,
|
||||
"num_tokens": 311750957.0,
|
||||
"step": 1200
|
||||
},
|
||||
{
|
||||
"entropy": 1.0141666044294835,
|
||||
"epoch": 0.6197706848466068,
|
||||
"grad_norm": 0.546875,
|
||||
"learning_rate": 1.1413173852029593e-05,
|
||||
"loss": 1.0096,
|
||||
"mean_token_accuracy": 0.7549486918747426,
|
||||
"num_tokens": 324739809.0,
|
||||
"step": 1250
|
||||
},
|
||||
{
|
||||
"entropy": 1.011275120228529,
|
||||
"epoch": 0.644561512240471,
|
||||
"grad_norm": 0.51171875,
|
||||
"learning_rate": 1.0167653163701218e-05,
|
||||
"loss": 1.0066,
|
||||
"mean_token_accuracy": 0.755563808530569,
|
||||
"num_tokens": 337733441.0,
|
||||
"step": 1300
|
||||
},
|
||||
{
|
||||
"entropy": 1.0095749548077584,
|
||||
"epoch": 0.6693523396343353,
|
||||
"grad_norm": 0.52734375,
|
||||
"learning_rate": 8.958304556904608e-06,
|
||||
"loss": 1.0051,
|
||||
"mean_token_accuracy": 0.7557943074405193,
|
||||
"num_tokens": 350729616.0,
|
||||
"step": 1350
|
||||
},
|
||||
{
|
||||
"entropy": 1.0063166113197803,
|
||||
"epoch": 0.6941431670281996,
|
||||
"grad_norm": 0.52734375,
|
||||
"learning_rate": 7.794180497840417e-06,
|
||||
"loss": 1.0018,
|
||||
"mean_token_accuracy": 0.7565754729509354,
|
||||
"num_tokens": 363726550.0,
|
||||
"step": 1400
|
||||
},
|
||||
{
|
||||
"entropy": 1.0057007387280463,
|
||||
"epoch": 0.7189339944220638,
|
||||
"grad_norm": 0.52734375,
|
||||
"learning_rate": 6.683994928575307e-06,
|
||||
"loss": 1.001,
|
||||
"mean_token_accuracy": 0.75655224904418,
|
||||
"num_tokens": 376715458.0,
|
||||
"step": 1450
|
||||
},
|
||||
{
|
||||
"entropy": 1.010465783327818,
|
||||
"epoch": 0.7437248218159281,
|
||||
"grad_norm": 0.515625,
|
||||
"learning_rate": 5.636058039641382e-06,
|
||||
"loss": 1.0057,
|
||||
"mean_token_accuracy": 0.7555474500358105,
|
||||
"num_tokens": 389703743.0,
|
||||
"step": 1500
|
||||
},
|
||||
{
|
||||
"entropy": 1.0062365026772022,
|
||||
"epoch": 0.7685156492097924,
|
||||
"grad_norm": 0.5078125,
|
||||
"learning_rate": 4.6582140648800434e-06,
|
||||
"loss": 1.0012,
|
||||
"mean_token_accuracy": 0.7565624009072781,
|
||||
"num_tokens": 402693509.0,
|
||||
"step": 1550
|
||||
},
|
||||
{
|
||||
"entropy": 1.0175788636505603,
|
||||
"epoch": 0.7933064766036566,
|
||||
"grad_norm": 0.5078125,
|
||||
"learning_rate": 3.7577825641611918e-06,
|
||||
"loss": 1.0135,
|
||||
"mean_token_accuracy": 0.754096201211214,
|
||||
"num_tokens": 415676636.0,
|
||||
"step": 1600
|
||||
},
|
||||
{
|
||||
"entropy": 1.0108901219069957,
|
||||
"epoch": 0.8180973039975209,
|
||||
"grad_norm": 0.51171875,
|
||||
"learning_rate": 2.941503633500518e-06,
|
||||
"loss": 1.0067,
|
||||
"mean_token_accuracy": 0.7554244147241116,
|
||||
"num_tokens": 428672727.0,
|
||||
"step": 1650
|
||||
},
|
||||
{
|
||||
"entropy": 1.005025475025177,
|
||||
"epoch": 0.8428881313913852,
|
||||
"grad_norm": 0.51171875,
|
||||
"learning_rate": 2.215487452699424e-06,
|
||||
"loss": 0.9997,
|
||||
"mean_token_accuracy": 0.7569046394526958,
|
||||
"num_tokens": 441658704.0,
|
||||
"step": 1700
|
||||
},
|
||||
{
|
||||
"entropy": 1.0120447267591954,
|
||||
"epoch": 0.8676789587852495,
|
||||
"grad_norm": 0.5234375,
|
||||
"learning_rate": 1.5851685481640143e-06,
|
||||
"loss": 1.0064,
|
||||
"mean_token_accuracy": 0.7556189036369324,
|
||||
"num_tokens": 454644190.0,
|
||||
"step": 1750
|
||||
},
|
||||
{
|
||||
"entropy": 1.0109828931093217,
|
||||
"epoch": 0.8924697861791138,
|
||||
"grad_norm": 0.51953125,
|
||||
"learning_rate": 1.0552651132645602e-06,
|
||||
"loss": 1.0065,
|
||||
"mean_token_accuracy": 0.7554912100732326,
|
||||
"num_tokens": 467637106.0,
|
||||
"step": 1800
|
||||
},
|
||||
{
|
||||
"entropy": 1.013734626173973,
|
||||
"epoch": 0.917260613572978,
|
||||
"grad_norm": 0.51953125,
|
||||
"learning_rate": 6.297436907390885e-07,
|
||||
"loss": 1.0082,
|
||||
"mean_token_accuracy": 0.7551266106963158,
|
||||
"num_tokens": 480637699.0,
|
||||
"step": 1850
|
||||
},
|
||||
{
|
||||
"entropy": 1.0092887429893016,
|
||||
"epoch": 0.9420514409668422,
|
||||
"grad_norm": 0.52734375,
|
||||
"learning_rate": 3.117894815076755e-07,
|
||||
"loss": 1.0051,
|
||||
"mean_token_accuracy": 0.7559835283458233,
|
||||
"num_tokens": 493631966.0,
|
||||
"step": 1900
|
||||
},
|
||||
{
|
||||
"entropy": 1.0152117817103863,
|
||||
"epoch": 0.9668422683607065,
|
||||
"grad_norm": 0.51171875,
|
||||
"learning_rate": 1.0378250214803986e-07,
|
||||
"loss": 1.0102,
|
||||
"mean_token_accuracy": 0.7547811089456081,
|
||||
"num_tokens": 506610108.0,
|
||||
"step": 1950
|
||||
},
|
||||
{
|
||||
"entropy": 1.0181812508404255,
|
||||
"epoch": 0.9916330957545708,
|
||||
"grad_norm": 0.51953125,
|
||||
"learning_rate": 7.2797695034398924e-09,
|
||||
"loss": 1.0127,
|
||||
"mean_token_accuracy": 0.7541768151521683,
|
||||
"num_tokens": 519598174.0,
|
||||
"step": 2000
|
||||
}
|
||||
],
|
||||
"logging_steps": 50,
|
||||
"max_steps": 2017,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 1,
|
||||
"save_steps": 50000,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 4.431062590428283e+18,
|
||||
"train_batch_size": 2,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-2017/training_args.bin
Normal file
3
checkpoint-2017/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:41ebcc94f7c0cc0c05a2f416a13cc7c3e079bd5071068dcbc4c3ed935a060260
|
||||
size 6289
|
||||
1
checkpoint-2017/vocab.json
Normal file
1
checkpoint-2017/vocab.json
Normal file
File diff suppressed because one or more lines are too long
60
config.json
Normal file
60
config.json
Normal file
@@ -0,0 +1,60 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6144,
|
||||
"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_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.57.3",
|
||||
"use_cache": true,
|
||||
"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": "4.57.3"
|
||||
}
|
||||
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:a147d613e556d6f1060230aff94696ca8e07c80098a61a5210c6788a59f7577d
|
||||
size 3441185608
|
||||
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
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
||||
{
|
||||
"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,
|
||||
"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
|
||||
}
|
||||
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 sha256:41ebcc94f7c0cc0c05a2f416a13cc7c3e079bd5071068dcbc4c3ed935a060260
|
||||
size 6289
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user