初始化项目，由ModelHub XC社区提供模型
Model: jekunz/Qwen3-1.7B-Base-sv-CPT-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
|
||||
57
README.md
Normal file
57
README.md
Normal file
@@ -0,0 +1,57 @@
|
||||
---
|
||||
library_name: transformers
|
||||
model_name: qwen-base-sv10m-cp78125-sv-smoltalk
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- trl
|
||||
- sft
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for qwen-base-sv10m-cp78125-sv-smoltalk
|
||||
|
||||
This model is a fine-tuned version of [None](https://huggingface.co/None).
|
||||
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
|
||||
}
|
||||
85
chat_template.jinja
Normal file
85
chat_template.jinja
Normal file
@@ -0,0 +1,85 @@
|
||||
{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set content = message.content %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in message.content %}
|
||||
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- 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
|
||||
}
|
||||
85
checkpoint-2017/chat_template.jinja
Normal file
85
checkpoint-2017/chat_template.jinja
Normal file
@@ -0,0 +1,85 @@
|
||||
{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set content = message.content %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in message.content %}
|
||||
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- 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": 151643,
|
||||
"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": 32768,
|
||||
"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
|
||||
}
|
||||
8
checkpoint-2017/generation_config.json
Normal file
8
checkpoint-2017/generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"eos_token_id": [
|
||||
151643
|
||||
],
|
||||
"max_new_tokens": 2048,
|
||||
"pad_token_id": 151643,
|
||||
"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 sha256:7d8fe43f929c085ba60aefd636426815fa8d651c4fb3b3e9d16e14eb64974413
|
||||
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 sha256:0c0be3d5558001fabc78f2a461f5dd0b320e9a8a34aaffd630440592702880bb
|
||||
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": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
checkpoint-2017/tokenizer.json
Normal file
3
checkpoint-2017/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
||||
size 11422654
|
||||
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": "<|endoftext|>",
|
||||
"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": 1.3586728751659394,
|
||||
"epoch": 0.02479082739386427,
|
||||
"grad_norm": 2.15625,
|
||||
"learning_rate": 7.277227722772277e-06,
|
||||
"loss": 1.4755,
|
||||
"mean_token_accuracy": 0.6909261329472065,
|
||||
"num_tokens": 12987057.0,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"entropy": 1.2912243032455444,
|
||||
"epoch": 0.04958165478772854,
|
||||
"grad_norm": 0.890625,
|
||||
"learning_rate": 1.4702970297029704e-05,
|
||||
"loss": 1.2929,
|
||||
"mean_token_accuracy": 0.7083150233328342,
|
||||
"num_tokens": 25982341.0,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"entropy": 1.195389568209648,
|
||||
"epoch": 0.07437248218159281,
|
||||
"grad_norm": 0.625,
|
||||
"learning_rate": 2.212871287128713e-05,
|
||||
"loss": 1.1604,
|
||||
"mean_token_accuracy": 0.7253781369328499,
|
||||
"num_tokens": 38965652.0,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"entropy": 1.130024016946554,
|
||||
"epoch": 0.09916330957545708,
|
||||
"grad_norm": 0.671875,
|
||||
"learning_rate": 2.9554455445544555e-05,
|
||||
"loss": 1.1103,
|
||||
"mean_token_accuracy": 0.7349422338604927,
|
||||
"num_tokens": 51955113.0,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"entropy": 1.083964577615261,
|
||||
"epoch": 0.12395413696932135,
|
||||
"grad_norm": 0.6015625,
|
||||
"learning_rate": 2.9950390604994976e-05,
|
||||
"loss": 1.0694,
|
||||
"mean_token_accuracy": 0.7426358266174793,
|
||||
"num_tokens": 64940008.0,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"entropy": 1.0586608110368252,
|
||||
"epoch": 0.14874496436318563,
|
||||
"grad_norm": 0.5859375,
|
||||
"learning_rate": 2.978907368725783e-05,
|
||||
"loss": 1.0479,
|
||||
"mean_token_accuracy": 0.7466910901665688,
|
||||
"num_tokens": 77929904.0,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"entropy": 1.0466859459877014,
|
||||
"epoch": 0.1735357917570499,
|
||||
"grad_norm": 0.6171875,
|
||||
"learning_rate": 2.9517054537806585e-05,
|
||||
"loss": 1.0374,
|
||||
"mean_token_accuracy": 0.7483436167240143,
|
||||
"num_tokens": 90917917.0,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"entropy": 1.0320545549690723,
|
||||
"epoch": 0.19832661915091415,
|
||||
"grad_norm": 0.6015625,
|
||||
"learning_rate": 2.9136369330613327e-05,
|
||||
"loss": 1.0239,
|
||||
"mean_token_accuracy": 0.7508709374070167,
|
||||
"num_tokens": 103911070.0,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"entropy": 1.0159100976586342,
|
||||
"epoch": 0.22311744654477844,
|
||||
"grad_norm": 0.5859375,
|
||||
"learning_rate": 2.864986764929012e-05,
|
||||
"loss": 1.008,
|
||||
"mean_token_accuracy": 0.754148696064949,
|
||||
"num_tokens": 116908048.0,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"entropy": 1.0052815113961697,
|
||||
"epoch": 0.2479082739386427,
|
||||
"grad_norm": 0.6015625,
|
||||
"learning_rate": 2.8061191156796658e-05,
|
||||
"loss": 0.9979,
|
||||
"mean_token_accuracy": 0.7558307178318501,
|
||||
"num_tokens": 129891292.0,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"entropy": 0.9971283619105816,
|
||||
"epoch": 0.27269910133250697,
|
||||
"grad_norm": 0.57421875,
|
||||
"learning_rate": 2.737474633611185e-05,
|
||||
"loss": 0.9897,
|
||||
"mean_token_accuracy": 0.7573503164947033,
|
||||
"num_tokens": 142876112.0,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"entropy": 0.9957551054656506,
|
||||
"epoch": 0.29748992872637126,
|
||||
"grad_norm": 0.57421875,
|
||||
"learning_rate": 2.6595671505916456e-05,
|
||||
"loss": 0.9886,
|
||||
"mean_token_accuracy": 0.7574590389430523,
|
||||
"num_tokens": 155871785.0,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"entropy": 0.9934693467617035,
|
||||
"epoch": 0.3222807561202355,
|
||||
"grad_norm": 0.5859375,
|
||||
"learning_rate": 2.5729798358187858e-05,
|
||||
"loss": 0.9863,
|
||||
"mean_token_accuracy": 0.7580893678963184,
|
||||
"num_tokens": 168864657.0,
|
||||
"step": 650
|
||||
},
|
||||
{
|
||||
"entropy": 0.9791013410687447,
|
||||
"epoch": 0.3470715835140998,
|
||||
"grad_norm": 0.58203125,
|
||||
"learning_rate": 2.478360830561368e-05,
|
||||
"loss": 0.9721,
|
||||
"mean_token_accuracy": 0.7607471886277198,
|
||||
"num_tokens": 181847527.0,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"entropy": 0.9810490027070046,
|
||||
"epoch": 0.37186241090796407,
|
||||
"grad_norm": 0.546875,
|
||||
"learning_rate": 2.376418396558165e-05,
|
||||
"loss": 0.974,
|
||||
"mean_token_accuracy": 0.7601690106093884,
|
||||
"num_tokens": 194832579.0,
|
||||
"step": 750
|
||||
},
|
||||
{
|
||||
"entropy": 0.9764066061377525,
|
||||
"epoch": 0.3966532383018283,
|
||||
"grad_norm": 0.60546875,
|
||||
"learning_rate": 2.2679156143907717e-05,
|
||||
"loss": 0.9697,
|
||||
"mean_token_accuracy": 0.7612905742228031,
|
||||
"num_tokens": 207819397.0,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"entropy": 0.9791778637468815,
|
||||
"epoch": 0.4214440656956926,
|
||||
"grad_norm": 0.53515625,
|
||||
"learning_rate": 2.153664671515084e-05,
|
||||
"loss": 0.9723,
|
||||
"mean_token_accuracy": 0.7604146462678909,
|
||||
"num_tokens": 220806448.0,
|
||||
"step": 850
|
||||
},
|
||||
{
|
||||
"entropy": 0.9723606041073799,
|
||||
"epoch": 0.4462348930895569,
|
||||
"grad_norm": 0.5234375,
|
||||
"learning_rate": 2.0345207827078517e-05,
|
||||
"loss": 0.9652,
|
||||
"mean_token_accuracy": 0.7619108897447586,
|
||||
"num_tokens": 233800554.0,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"entropy": 0.9694940079748631,
|
||||
"epoch": 0.4710257204834211,
|
||||
"grad_norm": 0.57421875,
|
||||
"learning_rate": 1.9113757884362315e-05,
|
||||
"loss": 0.9632,
|
||||
"mean_token_accuracy": 0.7623741792142391,
|
||||
"num_tokens": 246788996.0,
|
||||
"step": 950
|
||||
},
|
||||
{
|
||||
"entropy": 0.9737490539252758,
|
||||
"epoch": 0.4958165478772854,
|
||||
"grad_norm": 0.52734375,
|
||||
"learning_rate": 1.7851514790691512e-05,
|
||||
"loss": 0.9664,
|
||||
"mean_token_accuracy": 0.7615893495082855,
|
||||
"num_tokens": 259781274.0,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"entropy": 0.9637996312975884,
|
||||
"epoch": 0.5206073752711496,
|
||||
"grad_norm": 0.54296875,
|
||||
"learning_rate": 1.6567926949014805e-05,
|
||||
"loss": 0.9574,
|
||||
"mean_token_accuracy": 0.763445483893156,
|
||||
"num_tokens": 272766654.0,
|
||||
"step": 1050
|
||||
},
|
||||
{
|
||||
"entropy": 0.9670505975186825,
|
||||
"epoch": 0.5453982026650139,
|
||||
"grad_norm": 0.5546875,
|
||||
"learning_rate": 1.5272602536401258e-05,
|
||||
"loss": 0.9603,
|
||||
"mean_token_accuracy": 0.7628799936175347,
|
||||
"num_tokens": 285761894.0,
|
||||
"step": 1100
|
||||
},
|
||||
{
|
||||
"entropy": 0.9692679969966411,
|
||||
"epoch": 0.5701890300588782,
|
||||
"grad_norm": 0.53515625,
|
||||
"learning_rate": 1.3975237582927023e-05,
|
||||
"loss": 0.9625,
|
||||
"mean_token_accuracy": 0.7623443056643009,
|
||||
"num_tokens": 298753069.0,
|
||||
"step": 1150
|
||||
},
|
||||
{
|
||||
"entropy": 0.9643890456855297,
|
||||
"epoch": 0.5949798574527425,
|
||||
"grad_norm": 0.5234375,
|
||||
"learning_rate": 1.2685543392946551e-05,
|
||||
"loss": 0.9578,
|
||||
"mean_token_accuracy": 0.7632720285654068,
|
||||
"num_tokens": 311750957.0,
|
||||
"step": 1200
|
||||
},
|
||||
{
|
||||
"entropy": 0.967204072624445,
|
||||
"epoch": 0.6197706848466068,
|
||||
"grad_norm": 0.55859375,
|
||||
"learning_rate": 1.1413173852029593e-05,
|
||||
"loss": 0.9602,
|
||||
"mean_token_accuracy": 0.7628644931316376,
|
||||
"num_tokens": 324739809.0,
|
||||
"step": 1250
|
||||
},
|
||||
{
|
||||
"entropy": 0.9641332650184631,
|
||||
"epoch": 0.644561512240471,
|
||||
"grad_norm": 0.53515625,
|
||||
"learning_rate": 1.0167653163701218e-05,
|
||||
"loss": 0.9577,
|
||||
"mean_token_accuracy": 0.7634398965537548,
|
||||
"num_tokens": 337733441.0,
|
||||
"step": 1300
|
||||
},
|
||||
{
|
||||
"entropy": 0.9630196557939052,
|
||||
"epoch": 0.6693523396343353,
|
||||
"grad_norm": 0.55078125,
|
||||
"learning_rate": 8.958304556904608e-06,
|
||||
"loss": 0.9561,
|
||||
"mean_token_accuracy": 0.7635413825511932,
|
||||
"num_tokens": 350729616.0,
|
||||
"step": 1350
|
||||
},
|
||||
{
|
||||
"entropy": 0.9601120933890342,
|
||||
"epoch": 0.6941431670281996,
|
||||
"grad_norm": 0.58203125,
|
||||
"learning_rate": 7.794180497840417e-06,
|
||||
"loss": 0.9534,
|
||||
"mean_token_accuracy": 0.7642950342595577,
|
||||
"num_tokens": 363726550.0,
|
||||
"step": 1400
|
||||
},
|
||||
{
|
||||
"entropy": 0.959176854044199,
|
||||
"epoch": 0.7189339944220638,
|
||||
"grad_norm": 0.53515625,
|
||||
"learning_rate": 6.683994928575307e-06,
|
||||
"loss": 0.9527,
|
||||
"mean_token_accuracy": 0.7643388402462006,
|
||||
"num_tokens": 376715458.0,
|
||||
"step": 1450
|
||||
},
|
||||
{
|
||||
"entropy": 0.9641504181921482,
|
||||
"epoch": 0.7437248218159281,
|
||||
"grad_norm": 0.54296875,
|
||||
"learning_rate": 5.636058039641382e-06,
|
||||
"loss": 0.9572,
|
||||
"mean_token_accuracy": 0.7632291333377361,
|
||||
"num_tokens": 389703743.0,
|
||||
"step": 1500
|
||||
},
|
||||
{
|
||||
"entropy": 0.9603779044747353,
|
||||
"epoch": 0.7685156492097924,
|
||||
"grad_norm": 0.5234375,
|
||||
"learning_rate": 4.6582140648800434e-06,
|
||||
"loss": 0.9531,
|
||||
"mean_token_accuracy": 0.7641150717437267,
|
||||
"num_tokens": 402693509.0,
|
||||
"step": 1550
|
||||
},
|
||||
{
|
||||
"entropy": 0.9703494548797608,
|
||||
"epoch": 0.7933064766036566,
|
||||
"grad_norm": 0.515625,
|
||||
"learning_rate": 3.7577825641611918e-06,
|
||||
"loss": 0.9645,
|
||||
"mean_token_accuracy": 0.7619730933010578,
|
||||
"num_tokens": 415676636.0,
|
||||
"step": 1600
|
||||
},
|
||||
{
|
||||
"entropy": 0.9646534560620785,
|
||||
"epoch": 0.8180973039975209,
|
||||
"grad_norm": 0.53515625,
|
||||
"learning_rate": 2.941503633500518e-06,
|
||||
"loss": 0.9582,
|
||||
"mean_token_accuracy": 0.7631721512973308,
|
||||
"num_tokens": 428672727.0,
|
||||
"step": 1650
|
||||
},
|
||||
{
|
||||
"entropy": 0.9584815502166748,
|
||||
"epoch": 0.8428881313913852,
|
||||
"grad_norm": 0.54296875,
|
||||
"learning_rate": 2.215487452699424e-06,
|
||||
"loss": 0.9516,
|
||||
"mean_token_accuracy": 0.7645354972779751,
|
||||
"num_tokens": 441658704.0,
|
||||
"step": 1700
|
||||
},
|
||||
{
|
||||
"entropy": 0.9654586097598076,
|
||||
"epoch": 0.8676789587852495,
|
||||
"grad_norm": 0.53515625,
|
||||
"learning_rate": 1.5851685481640143e-06,
|
||||
"loss": 0.9581,
|
||||
"mean_token_accuracy": 0.7633582444489002,
|
||||
"num_tokens": 454644190.0,
|
||||
"step": 1750
|
||||
},
|
||||
{
|
||||
"entropy": 0.9650468651950359,
|
||||
"epoch": 0.8924697861791138,
|
||||
"grad_norm": 0.5390625,
|
||||
"learning_rate": 1.0552651132645602e-06,
|
||||
"loss": 0.9583,
|
||||
"mean_token_accuracy": 0.7630480709671974,
|
||||
"num_tokens": 467637106.0,
|
||||
"step": 1800
|
||||
},
|
||||
{
|
||||
"entropy": 0.9669888707995414,
|
||||
"epoch": 0.917260613572978,
|
||||
"grad_norm": 0.53515625,
|
||||
"learning_rate": 6.297436907390885e-07,
|
||||
"loss": 0.9595,
|
||||
"mean_token_accuracy": 0.7629272870719432,
|
||||
"num_tokens": 480637699.0,
|
||||
"step": 1850
|
||||
},
|
||||
{
|
||||
"entropy": 0.9635004520416259,
|
||||
"epoch": 0.9420514409668422,
|
||||
"grad_norm": 0.53515625,
|
||||
"learning_rate": 3.117894815076755e-07,
|
||||
"loss": 0.9571,
|
||||
"mean_token_accuracy": 0.7636180396378041,
|
||||
"num_tokens": 493631966.0,
|
||||
"step": 1900
|
||||
},
|
||||
{
|
||||
"entropy": 0.9683159920573234,
|
||||
"epoch": 0.9668422683607065,
|
||||
"grad_norm": 0.52734375,
|
||||
"learning_rate": 1.0378250214803986e-07,
|
||||
"loss": 0.9612,
|
||||
"mean_token_accuracy": 0.7624971939623356,
|
||||
"num_tokens": 506610108.0,
|
||||
"step": 1950
|
||||
},
|
||||
{
|
||||
"entropy": 0.9708416217565536,
|
||||
"epoch": 0.9916330957545708,
|
||||
"grad_norm": 0.53515625,
|
||||
"learning_rate": 7.2797695034398924e-09,
|
||||
"loss": 0.9639,
|
||||
"mean_token_accuracy": 0.7619807639718056,
|
||||
"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 sha256:566b1dbabcab0bc14a60e5d2e8e1a32977bbfc133d78ebb046bd1473eea1e81c
|
||||
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": 151643,
|
||||
"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": 32768,
|
||||
"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
|
||||
}
|
||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"eos_token_id": [
|
||||
151643
|
||||
],
|
||||
"max_new_tokens": 2048,
|
||||
"pad_token_id": 151643,
|
||||
"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 sha256:7d8fe43f929c085ba60aefd636426815fa8d651c4fb3b3e9d16e14eb64974413
|
||||
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": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
||||
size 11422654
|
||||
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": "<|endoftext|>",
|
||||
"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 sha256:566b1dbabcab0bc14a60e5d2e8e1a32977bbfc133d78ebb046bd1473eea1e81c
|
||||
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