初始化项目，由ModelHub XC社区提供模型
Model: terasut/gkd-qwen-2.5-0.5b-base_v5_from1.5b_eff32 Source: Original Platform
This commit is contained in:
ModelHub XC
39
.gitattributes
vendored
Normal file
39
.gitattributes
vendored
Normal file
@@ -0,0 +1,39 @@
|
||||
*.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-1750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
checkpoint-2625/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
checkpoint-875/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
60
README.md
Normal file
60
README.md
Normal file
@@ -0,0 +1,60 @@
|
||||
---
|
||||
library_name: transformers
|
||||
model_name: gkd-qwen-2.5-0.5b-base_v5_from1.5b_eff32
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- gkd
|
||||
- trl
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for gkd-qwen-2.5-0.5b-base_v5_from1.5b_eff32
|
||||
|
||||
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
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/terasut-workspace/ai-patternrecog/runs/tcq3qf7x)
|
||||
|
||||
|
||||
|
||||
This model was trained with GKD, a method introduced in [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://huggingface.co/papers/2306.13649).
|
||||
|
||||
## Citations
|
||||
|
||||
Cite GKD as:
|
||||
|
||||
```bibtex
|
||||
@inproceedings{agarwal2024on-policy,
|
||||
title = {{On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes}},
|
||||
author = {Rishabh Agarwal and Nino Vieillard and Yongchao Zhou and Piotr Stanczyk and Sabela Ramos Garea and Matthieu Geist and Olivier Bachem},
|
||||
year = 2024,
|
||||
booktitle = {The Twelfth International Conference on Learning Representations, {ICLR} 2024, Vienna, Austria, May 7-11, 2024},
|
||||
publisher = {OpenReview.net},
|
||||
url = {https://openreview.net/forum?id=3zKtaqxLhW},
|
||||
}
|
||||
```
|
||||
|
||||
Cite TRL as:
|
||||
|
||||
```bibtex
|
||||
@software{vonwerra2020trl,
|
||||
title = {{TRL: Transformers Reinforcement Learning}},
|
||||
author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
|
||||
license = {Apache-2.0},
|
||||
url = {https://github.com/huggingface/trl},
|
||||
year = {2020}
|
||||
}
|
||||
```
|
||||
56
chat_template.jinja
Normal file
56
chat_template.jinja
Normal file
@@ -0,0 +1,56 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- 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' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- 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" and not message.tool_calls %}
|
||||
{{- '<|im_start|>assistant\n' }}{% generation %}{{- message.content + '<|im_end|>\n' }}{% endgeneration %}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>assistant' }}{% generation %}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}{% endgeneration %}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) 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' }}
|
||||
{%- endif %}
|
||||
56
checkpoint-1750/chat_template.jinja
Normal file
56
checkpoint-1750/chat_template.jinja
Normal file
@@ -0,0 +1,56 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- 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' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- 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" and not message.tool_calls %}
|
||||
{{- '<|im_start|>assistant\n' }}{% generation %}{{- message.content + '<|im_end|>\n' }}{% endgeneration %}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>assistant' }}{% generation %}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}{% endgeneration %}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) 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' }}
|
||||
{%- endif %}
|
||||
58
checkpoint-1750/config.json
Normal file
58
checkpoint-1750/config.json
Normal file
@@ -0,0 +1,58 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 896,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4864,
|
||||
"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"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 24,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 14,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.5.3",
|
||||
"use_cache": false,
|
||||
"use_mrope": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
10
checkpoint-1750/generation_config.json
Normal file
10
checkpoint-1750/generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"do_sample": false,
|
||||
"eos_token_id": [
|
||||
151645
|
||||
],
|
||||
"max_new_tokens": 2048,
|
||||
"pad_token_id": 151643,
|
||||
"transformers_version": "5.5.3",
|
||||
"use_cache": false
|
||||
}
|
||||
3
checkpoint-1750/model.safetensors
Normal file
3
checkpoint-1750/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:408294005c9b105e91cc612417aa08e1a6ea22f32437ba8ba9bd43c828a33c49
|
||||
size 988097824
|
||||
3
checkpoint-1750/optimizer.pt
Normal file
3
checkpoint-1750/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:acacf31674c6e809b2dda67ed66a796f016426232045ee0ec4436a30a765aba0
|
||||
size 1976378699
|
||||
3
checkpoint-1750/rng_state.pth
Normal file
3
checkpoint-1750/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8a759efdc3644a7047be4e1cf0e339eb0c35a93c8f494a96325adfe2e6bd10e7
|
||||
size 14645
|
||||
3
checkpoint-1750/scheduler.pt
Normal file
3
checkpoint-1750/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fc53ebd3c8ca395477da766ae7fa14a1cd87577954defcd87cfec2f1d6fd424a
|
||||
size 1465
|
||||
3
checkpoint-1750/tokenizer.json
Normal file
3
checkpoint-1750/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
||||
size 11421892
|
||||
30
checkpoint-1750/tokenizer_config.json
Normal file
30
checkpoint-1750/tokenizer_config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"is_local": true,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "left",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1259
checkpoint-1750/trainer_state.json
Normal file
1259
checkpoint-1750/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-1750/training_args.bin
Normal file
3
checkpoint-1750/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e8a2ef5b8d79835ff6ba94d10403139a3a9af53e51adfe2987ac1e7ff4f8e1ec
|
||||
size 6289
|
||||
56
checkpoint-2625/chat_template.jinja
Normal file
56
checkpoint-2625/chat_template.jinja
Normal file
@@ -0,0 +1,56 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- 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' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- 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" and not message.tool_calls %}
|
||||
{{- '<|im_start|>assistant\n' }}{% generation %}{{- message.content + '<|im_end|>\n' }}{% endgeneration %}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>assistant' }}{% generation %}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}{% endgeneration %}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) 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' }}
|
||||
{%- endif %}
|
||||
58
checkpoint-2625/config.json
Normal file
58
checkpoint-2625/config.json
Normal file
@@ -0,0 +1,58 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 896,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4864,
|
||||
"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"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 24,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 14,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.5.3",
|
||||
"use_cache": false,
|
||||
"use_mrope": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
10
checkpoint-2625/generation_config.json
Normal file
10
checkpoint-2625/generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"do_sample": false,
|
||||
"eos_token_id": [
|
||||
151645
|
||||
],
|
||||
"max_new_tokens": 2048,
|
||||
"pad_token_id": 151643,
|
||||
"transformers_version": "5.5.3",
|
||||
"use_cache": false
|
||||
}
|
||||
3
checkpoint-2625/model.safetensors
Normal file
3
checkpoint-2625/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:10cbf78c24b74c3578136d377abf51eeb08995479f597d62e92ca7c6298a5d05
|
||||
size 988097824
|
||||
3
checkpoint-2625/optimizer.pt
Normal file
3
checkpoint-2625/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:efe47928026abf0fda933a387e0c21813634b64b568a52b39247f08d5a1646fa
|
||||
size 1976378699
|
||||
3
checkpoint-2625/rng_state.pth
Normal file
3
checkpoint-2625/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1bb7e3e0894f95e6b09893239ea7465e0b0f84960c938750037c83d683a7c132
|
||||
size 14645
|
||||
3
checkpoint-2625/scheduler.pt
Normal file
3
checkpoint-2625/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a90cf32bcaa40d2760ac49ca5a2167553d01347c3172274302ea44fcf542f183
|
||||
size 1465
|
||||
3
checkpoint-2625/tokenizer.json
Normal file
3
checkpoint-2625/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
||||
size 11421892
|
||||
30
checkpoint-2625/tokenizer_config.json
Normal file
30
checkpoint-2625/tokenizer_config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"is_local": true,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "left",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1868
checkpoint-2625/trainer_state.json
Normal file
1868
checkpoint-2625/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-2625/training_args.bin
Normal file
3
checkpoint-2625/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e8a2ef5b8d79835ff6ba94d10403139a3a9af53e51adfe2987ac1e7ff4f8e1ec
|
||||
size 6289
|
||||
56
checkpoint-875/chat_template.jinja
Normal file
56
checkpoint-875/chat_template.jinja
Normal file
@@ -0,0 +1,56 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- 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' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- 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" and not message.tool_calls %}
|
||||
{{- '<|im_start|>assistant\n' }}{% generation %}{{- message.content + '<|im_end|>\n' }}{% endgeneration %}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>assistant' }}{% generation %}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}{% endgeneration %}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) 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' }}
|
||||
{%- endif %}
|
||||
58
checkpoint-875/config.json
Normal file
58
checkpoint-875/config.json
Normal file
@@ -0,0 +1,58 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 896,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4864,
|
||||
"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"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 24,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 14,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.5.3",
|
||||
"use_cache": false,
|
||||
"use_mrope": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
10
checkpoint-875/generation_config.json
Normal file
10
checkpoint-875/generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"do_sample": false,
|
||||
"eos_token_id": [
|
||||
151645
|
||||
],
|
||||
"max_new_tokens": 2048,
|
||||
"pad_token_id": 151643,
|
||||
"transformers_version": "5.5.3",
|
||||
"use_cache": false
|
||||
}
|
||||
3
checkpoint-875/model.safetensors
Normal file
3
checkpoint-875/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9233c5c85ca8499a6c3666385fe2fa4e906eb311454b8df8528ea867d093ab5d
|
||||
size 988097824
|
||||
3
checkpoint-875/optimizer.pt
Normal file
3
checkpoint-875/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fa2de7f228893361233d2483c32e1ea56e9fca3f0a4a38c90d35aba8f6833ac5
|
||||
size 1976378699
|
||||
3
checkpoint-875/rng_state.pth
Normal file
3
checkpoint-875/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2ce952e06ca433c9f1a93c4fbb2e94e7dc9c5160b247b0f2a5c3358ba3092fb3
|
||||
size 14645
|
||||
3
checkpoint-875/scheduler.pt
Normal file
3
checkpoint-875/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:977dc1268f934bf99945ed0df8810e94a86fb8f53f0a4e7c78e4ae26e606231a
|
||||
size 1465
|
||||
3
checkpoint-875/tokenizer.json
Normal file
3
checkpoint-875/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
||||
size 11421892
|
||||
30
checkpoint-875/tokenizer_config.json
Normal file
30
checkpoint-875/tokenizer_config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"is_local": true,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "left",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
643
checkpoint-875/trainer_state.json
Normal file
643
checkpoint-875/trainer_state.json
Normal file
@@ -0,0 +1,643 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 875,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.011428571428571429,
|
||||
"grad_norm": 3.078125,
|
||||
"learning_rate": 1.9931428571428572e-05,
|
||||
"loss": 7.941626739501953,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.022857142857142857,
|
||||
"grad_norm": 2.9375,
|
||||
"learning_rate": 1.9855238095238097e-05,
|
||||
"loss": 8.19613037109375,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.03428571428571429,
|
||||
"grad_norm": 3.5625,
|
||||
"learning_rate": 1.977904761904762e-05,
|
||||
"loss": 7.826921081542968,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.045714285714285714,
|
||||
"grad_norm": 3.15625,
|
||||
"learning_rate": 1.9702857142857144e-05,
|
||||
"loss": 7.580943298339844,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.05714285714285714,
|
||||
"grad_norm": 2.515625,
|
||||
"learning_rate": 1.9626666666666666e-05,
|
||||
"loss": 7.483664703369141,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.06857142857142857,
|
||||
"grad_norm": 3.859375,
|
||||
"learning_rate": 1.955047619047619e-05,
|
||||
"loss": 7.480722808837891,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.08,
|
||||
"grad_norm": 3.46875,
|
||||
"learning_rate": 1.9474285714285717e-05,
|
||||
"loss": 7.279670715332031,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.09142857142857143,
|
||||
"grad_norm": 2.5625,
|
||||
"learning_rate": 1.9398095238095242e-05,
|
||||
"loss": 7.584724426269531,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.10285714285714286,
|
||||
"grad_norm": 2.515625,
|
||||
"learning_rate": 1.9321904761904764e-05,
|
||||
"loss": 7.565158081054688,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.11428571428571428,
|
||||
"grad_norm": 3.5625,
|
||||
"learning_rate": 1.924571428571429e-05,
|
||||
"loss": 7.366996002197266,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.12571428571428572,
|
||||
"grad_norm": 3.109375,
|
||||
"learning_rate": 1.916952380952381e-05,
|
||||
"loss": 7.434650421142578,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.13714285714285715,
|
||||
"grad_norm": 3.328125,
|
||||
"learning_rate": 1.9093333333333336e-05,
|
||||
"loss": 6.9210762023925785,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.14857142857142858,
|
||||
"grad_norm": 3.015625,
|
||||
"learning_rate": 1.9017142857142858e-05,
|
||||
"loss": 7.027304840087891,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.16,
|
||||
"grad_norm": 3.09375,
|
||||
"learning_rate": 1.8940952380952383e-05,
|
||||
"loss": 7.241950225830078,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.17142857142857143,
|
||||
"grad_norm": 3.0,
|
||||
"learning_rate": 1.8864761904761905e-05,
|
||||
"loss": 7.158929443359375,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.18285714285714286,
|
||||
"grad_norm": 2.890625,
|
||||
"learning_rate": 1.878857142857143e-05,
|
||||
"loss": 6.856580352783203,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.19428571428571428,
|
||||
"grad_norm": 4.09375,
|
||||
"learning_rate": 1.871238095238095e-05,
|
||||
"loss": 6.740969848632813,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.2057142857142857,
|
||||
"grad_norm": 3.40625,
|
||||
"learning_rate": 1.8636190476190477e-05,
|
||||
"loss": 7.115393829345703,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.21714285714285714,
|
||||
"grad_norm": 2.9375,
|
||||
"learning_rate": 1.8560000000000002e-05,
|
||||
"loss": 7.437998199462891,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.22857142857142856,
|
||||
"grad_norm": 2.96875,
|
||||
"learning_rate": 1.8483809523809527e-05,
|
||||
"loss": 6.879551696777344,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.24,
|
||||
"grad_norm": 2.890625,
|
||||
"learning_rate": 1.840761904761905e-05,
|
||||
"loss": 6.8273162841796875,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.25142857142857145,
|
||||
"grad_norm": 3.0,
|
||||
"learning_rate": 1.8331428571428574e-05,
|
||||
"loss": 6.558704376220703,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.26285714285714284,
|
||||
"grad_norm": 4.40625,
|
||||
"learning_rate": 1.8255238095238096e-05,
|
||||
"loss": 7.156157684326172,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 0.2742857142857143,
|
||||
"grad_norm": 2.671875,
|
||||
"learning_rate": 1.817904761904762e-05,
|
||||
"loss": 6.985882568359375,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.2857142857142857,
|
||||
"grad_norm": 2.46875,
|
||||
"learning_rate": 1.8102857142857143e-05,
|
||||
"loss": 7.106211090087891,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.29714285714285715,
|
||||
"grad_norm": 2.984375,
|
||||
"learning_rate": 1.8026666666666668e-05,
|
||||
"loss": 7.014789581298828,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.30857142857142855,
|
||||
"grad_norm": 2.5,
|
||||
"learning_rate": 1.7950476190476193e-05,
|
||||
"loss": 6.632127380371093,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 0.32,
|
||||
"grad_norm": 2.84375,
|
||||
"learning_rate": 1.7874285714285715e-05,
|
||||
"loss": 6.882701110839844,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.3314285714285714,
|
||||
"grad_norm": 3.78125,
|
||||
"learning_rate": 1.779809523809524e-05,
|
||||
"loss": 6.729277801513672,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 0.34285714285714286,
|
||||
"grad_norm": 3.578125,
|
||||
"learning_rate": 1.7721904761904762e-05,
|
||||
"loss": 6.794551849365234,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.35428571428571426,
|
||||
"grad_norm": 2.828125,
|
||||
"learning_rate": 1.7645714285714287e-05,
|
||||
"loss": 6.83813247680664,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 0.3657142857142857,
|
||||
"grad_norm": 2.875,
|
||||
"learning_rate": 1.7569523809523812e-05,
|
||||
"loss": 6.796338653564453,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.37714285714285717,
|
||||
"grad_norm": 2.90625,
|
||||
"learning_rate": 1.7493333333333334e-05,
|
||||
"loss": 6.7025390625,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"epoch": 0.38857142857142857,
|
||||
"grad_norm": 2.953125,
|
||||
"learning_rate": 1.741714285714286e-05,
|
||||
"loss": 6.541476440429688,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.4,
|
||||
"grad_norm": 2.59375,
|
||||
"learning_rate": 1.734095238095238e-05,
|
||||
"loss": 6.812630462646484,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 0.4114285714285714,
|
||||
"grad_norm": 3.609375,
|
||||
"learning_rate": 1.7264761904761906e-05,
|
||||
"loss": 6.889384460449219,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.4228571428571429,
|
||||
"grad_norm": 4.03125,
|
||||
"learning_rate": 1.718857142857143e-05,
|
||||
"loss": 7.129203796386719,
|
||||
"step": 370
|
||||
},
|
||||
{
|
||||
"epoch": 0.4342857142857143,
|
||||
"grad_norm": 2.40625,
|
||||
"learning_rate": 1.7112380952380953e-05,
|
||||
"loss": 6.382967376708985,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.44571428571428573,
|
||||
"grad_norm": 3.515625,
|
||||
"learning_rate": 1.703619047619048e-05,
|
||||
"loss": 6.663212585449219,
|
||||
"step": 390
|
||||
},
|
||||
{
|
||||
"epoch": 0.45714285714285713,
|
||||
"grad_norm": 2.90625,
|
||||
"learning_rate": 1.696e-05,
|
||||
"loss": 6.636187744140625,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.4685714285714286,
|
||||
"grad_norm": 3.1875,
|
||||
"learning_rate": 1.6883809523809525e-05,
|
||||
"loss": 6.64324722290039,
|
||||
"step": 410
|
||||
},
|
||||
{
|
||||
"epoch": 0.48,
|
||||
"grad_norm": 2.828125,
|
||||
"learning_rate": 1.6807619047619047e-05,
|
||||
"loss": 6.663475036621094,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.49142857142857144,
|
||||
"grad_norm": 3.328125,
|
||||
"learning_rate": 1.6731428571428572e-05,
|
||||
"loss": 6.452519226074219,
|
||||
"step": 430
|
||||
},
|
||||
{
|
||||
"epoch": 0.5028571428571429,
|
||||
"grad_norm": 2.421875,
|
||||
"learning_rate": 1.6655238095238098e-05,
|
||||
"loss": 6.683634948730469,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 0.5142857142857142,
|
||||
"grad_norm": 3.046875,
|
||||
"learning_rate": 1.6579047619047623e-05,
|
||||
"loss": 6.780387878417969,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 0.5257142857142857,
|
||||
"grad_norm": 2.53125,
|
||||
"learning_rate": 1.6502857142857145e-05,
|
||||
"loss": 7.1892578125,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 0.5371428571428571,
|
||||
"grad_norm": 2.71875,
|
||||
"learning_rate": 1.642666666666667e-05,
|
||||
"loss": 6.890229034423828,
|
||||
"step": 470
|
||||
},
|
||||
{
|
||||
"epoch": 0.5485714285714286,
|
||||
"grad_norm": 3.140625,
|
||||
"learning_rate": 1.635047619047619e-05,
|
||||
"loss": 6.747575378417968,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 0.56,
|
||||
"grad_norm": 3.3125,
|
||||
"learning_rate": 1.6274285714285717e-05,
|
||||
"loss": 6.98467788696289,
|
||||
"step": 490
|
||||
},
|
||||
{
|
||||
"epoch": 0.5714285714285714,
|
||||
"grad_norm": 2.890625,
|
||||
"learning_rate": 1.619809523809524e-05,
|
||||
"loss": 6.455801391601563,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.5828571428571429,
|
||||
"grad_norm": 2.578125,
|
||||
"learning_rate": 1.6121904761904764e-05,
|
||||
"loss": 6.525889587402344,
|
||||
"step": 510
|
||||
},
|
||||
{
|
||||
"epoch": 0.5942857142857143,
|
||||
"grad_norm": 3.375,
|
||||
"learning_rate": 1.6045714285714286e-05,
|
||||
"loss": 6.479692840576172,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 0.6057142857142858,
|
||||
"grad_norm": 2.875,
|
||||
"learning_rate": 1.596952380952381e-05,
|
||||
"loss": 6.6360313415527346,
|
||||
"step": 530
|
||||
},
|
||||
{
|
||||
"epoch": 0.6171428571428571,
|
||||
"grad_norm": 2.703125,
|
||||
"learning_rate": 1.5893333333333333e-05,
|
||||
"loss": 6.547400665283203,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 0.6285714285714286,
|
||||
"grad_norm": 2.9375,
|
||||
"learning_rate": 1.5817142857142858e-05,
|
||||
"loss": 6.748792266845703,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"epoch": 0.64,
|
||||
"grad_norm": 3.28125,
|
||||
"learning_rate": 1.5740952380952383e-05,
|
||||
"loss": 6.727365112304687,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 0.6514285714285715,
|
||||
"grad_norm": 2.984375,
|
||||
"learning_rate": 1.5664761904761908e-05,
|
||||
"loss": 6.611011505126953,
|
||||
"step": 570
|
||||
},
|
||||
{
|
||||
"epoch": 0.6628571428571428,
|
||||
"grad_norm": 2.984375,
|
||||
"learning_rate": 1.558857142857143e-05,
|
||||
"loss": 6.471088409423828,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 0.6742857142857143,
|
||||
"grad_norm": 2.84375,
|
||||
"learning_rate": 1.5512380952380955e-05,
|
||||
"loss": 6.472038269042969,
|
||||
"step": 590
|
||||
},
|
||||
{
|
||||
"epoch": 0.6857142857142857,
|
||||
"grad_norm": 3.15625,
|
||||
"learning_rate": 1.5436190476190477e-05,
|
||||
"loss": 6.747550201416016,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 0.6971428571428572,
|
||||
"grad_norm": 2.75,
|
||||
"learning_rate": 1.5360000000000002e-05,
|
||||
"loss": 6.638180541992187,
|
||||
"step": 610
|
||||
},
|
||||
{
|
||||
"epoch": 0.7085714285714285,
|
||||
"grad_norm": 3.078125,
|
||||
"learning_rate": 1.5283809523809524e-05,
|
||||
"loss": 6.535469818115234,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 0.72,
|
||||
"grad_norm": 3.109375,
|
||||
"learning_rate": 1.5207619047619049e-05,
|
||||
"loss": 6.981074523925781,
|
||||
"step": 630
|
||||
},
|
||||
{
|
||||
"epoch": 0.7314285714285714,
|
||||
"grad_norm": 2.78125,
|
||||
"learning_rate": 1.5131428571428572e-05,
|
||||
"loss": 6.307097625732422,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 0.7428571428571429,
|
||||
"grad_norm": 2.8125,
|
||||
"learning_rate": 1.5055238095238096e-05,
|
||||
"loss": 6.617960357666016,
|
||||
"step": 650
|
||||
},
|
||||
{
|
||||
"epoch": 0.7542857142857143,
|
||||
"grad_norm": 2.9375,
|
||||
"learning_rate": 1.497904761904762e-05,
|
||||
"loss": 6.845116424560547,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 0.7657142857142857,
|
||||
"grad_norm": 2.140625,
|
||||
"learning_rate": 1.4902857142857143e-05,
|
||||
"loss": 6.583855438232422,
|
||||
"step": 670
|
||||
},
|
||||
{
|
||||
"epoch": 0.7771428571428571,
|
||||
"grad_norm": 2.703125,
|
||||
"learning_rate": 1.4826666666666666e-05,
|
||||
"loss": 6.485343933105469,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 0.7885714285714286,
|
||||
"grad_norm": 2.96875,
|
||||
"learning_rate": 1.475047619047619e-05,
|
||||
"loss": 6.277442169189453,
|
||||
"step": 690
|
||||
},
|
||||
{
|
||||
"epoch": 0.8,
|
||||
"grad_norm": 3.078125,
|
||||
"learning_rate": 1.4674285714285717e-05,
|
||||
"loss": 6.420030212402343,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 0.8114285714285714,
|
||||
"grad_norm": 2.625,
|
||||
"learning_rate": 1.459809523809524e-05,
|
||||
"loss": 6.779734802246094,
|
||||
"step": 710
|
||||
},
|
||||
{
|
||||
"epoch": 0.8228571428571428,
|
||||
"grad_norm": 3.28125,
|
||||
"learning_rate": 1.4521904761904764e-05,
|
||||
"loss": 6.647151947021484,
|
||||
"step": 720
|
||||
},
|
||||
{
|
||||
"epoch": 0.8342857142857143,
|
||||
"grad_norm": 2.5625,
|
||||
"learning_rate": 1.4445714285714287e-05,
|
||||
"loss": 6.453370666503906,
|
||||
"step": 730
|
||||
},
|
||||
{
|
||||
"epoch": 0.8457142857142858,
|
||||
"grad_norm": 2.5625,
|
||||
"learning_rate": 1.436952380952381e-05,
|
||||
"loss": 6.6205802917480465,
|
||||
"step": 740
|
||||
},
|
||||
{
|
||||
"epoch": 0.8571428571428571,
|
||||
"grad_norm": 2.265625,
|
||||
"learning_rate": 1.4293333333333334e-05,
|
||||
"loss": 6.353859329223633,
|
||||
"step": 750
|
||||
},
|
||||
{
|
||||
"epoch": 0.8685714285714285,
|
||||
"grad_norm": 3.015625,
|
||||
"learning_rate": 1.4217142857142858e-05,
|
||||
"loss": 6.357454299926758,
|
||||
"step": 760
|
||||
},
|
||||
{
|
||||
"epoch": 0.88,
|
||||
"grad_norm": 3.03125,
|
||||
"learning_rate": 1.4140952380952381e-05,
|
||||
"loss": 6.682913208007813,
|
||||
"step": 770
|
||||
},
|
||||
{
|
||||
"epoch": 0.8914285714285715,
|
||||
"grad_norm": 2.625,
|
||||
"learning_rate": 1.4064761904761905e-05,
|
||||
"loss": 6.127779769897461,
|
||||
"step": 780
|
||||
},
|
||||
{
|
||||
"epoch": 0.9028571428571428,
|
||||
"grad_norm": 4.375,
|
||||
"learning_rate": 1.398857142857143e-05,
|
||||
"loss": 6.364295578002929,
|
||||
"step": 790
|
||||
},
|
||||
{
|
||||
"epoch": 0.9142857142857143,
|
||||
"grad_norm": 2.8125,
|
||||
"learning_rate": 1.3912380952380953e-05,
|
||||
"loss": 6.2481742858886715,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 0.9257142857142857,
|
||||
"grad_norm": 2.875,
|
||||
"learning_rate": 1.3836190476190477e-05,
|
||||
"loss": 6.126508712768555,
|
||||
"step": 810
|
||||
},
|
||||
{
|
||||
"epoch": 0.9371428571428572,
|
||||
"grad_norm": 3.0,
|
||||
"learning_rate": 1.376e-05,
|
||||
"loss": 6.082854080200195,
|
||||
"step": 820
|
||||
},
|
||||
{
|
||||
"epoch": 0.9485714285714286,
|
||||
"grad_norm": 3.09375,
|
||||
"learning_rate": 1.3683809523809526e-05,
|
||||
"loss": 6.128392028808594,
|
||||
"step": 830
|
||||
},
|
||||
{
|
||||
"epoch": 0.96,
|
||||
"grad_norm": 3.40625,
|
||||
"learning_rate": 1.3607619047619049e-05,
|
||||
"loss": 6.288749313354492,
|
||||
"step": 840
|
||||
},
|
||||
{
|
||||
"epoch": 0.9714285714285714,
|
||||
"grad_norm": 2.78125,
|
||||
"learning_rate": 1.3531428571428573e-05,
|
||||
"loss": 6.770208740234375,
|
||||
"step": 850
|
||||
},
|
||||
{
|
||||
"epoch": 0.9828571428571429,
|
||||
"grad_norm": 2.96875,
|
||||
"learning_rate": 1.3455238095238096e-05,
|
||||
"loss": 6.299668502807617,
|
||||
"step": 860
|
||||
},
|
||||
{
|
||||
"epoch": 0.9942857142857143,
|
||||
"grad_norm": 2.765625,
|
||||
"learning_rate": 1.3379047619047621e-05,
|
||||
"loss": 6.4255424499511715,
|
||||
"step": 870
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 2625,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 3,
|
||||
"save_steps": 500,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 4.697082881099981e+16,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-875/training_args.bin
Normal file
3
checkpoint-875/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e8a2ef5b8d79835ff6ba94d10403139a3a9af53e51adfe2987ac1e7ff4f8e1ec
|
||||
size 6289
|
||||
58
config.json
Normal file
58
config.json
Normal file
@@ -0,0 +1,58 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 896,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4864,
|
||||
"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"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 24,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 14,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.5.3",
|
||||
"use_cache": false,
|
||||
"use_mrope": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"do_sample": false,
|
||||
"eos_token_id": [
|
||||
151645
|
||||
],
|
||||
"max_new_tokens": 2048,
|
||||
"pad_token_id": 151643,
|
||||
"transformers_version": "5.5.3",
|
||||
"use_cache": false
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:10cbf78c24b74c3578136d377abf51eeb08995479f597d62e92ca7c6298a5d05
|
||||
size 988097824
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
||||
size 11421892
|
||||
30
tokenizer_config.json
Normal file
30
tokenizer_config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"is_local": true,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "left",
|
||||
"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:e2c5a96fca09ac848cb9a7b8f3e374248bbdb8129e9aec130a23e0eeaaa5fff8
|
||||
size 6353
|
||||
Reference in New Issue
Block a user