初始化项目，由ModelHub XC社区提供模型
Model: ali-elganzory/Baguettotron-longsft_16k-DPO-Tulu3-decontaminated Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
69
README.md
Normal file
69
README.md
Normal file
@@ -0,0 +1,69 @@
|
||||
---
|
||||
base_model: ali-elganzory/Baguettotron-longsft_16k-SFT-Tulu3-decontaminated
|
||||
library_name: transformers
|
||||
model_name: Baguettotron-longsft_16k-DPO-Tulu3-decontaminated
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- trl
|
||||
- dpo
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for Baguettotron-longsft_16k-DPO-Tulu3-decontaminated
|
||||
|
||||
This model is a fine-tuned version of [ali-elganzory/Baguettotron-longsft_16k-SFT-Tulu3-decontaminated](https://huggingface.co/ali-elganzory/Baguettotron-longsft_16k-SFT-Tulu3-decontaminated).
|
||||
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 DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
|
||||
|
||||
### Framework versions
|
||||
|
||||
- TRL: 0.27.1
|
||||
- Transformers: 4.57.6
|
||||
- Pytorch: 2.6.0+cu126
|
||||
- Datasets: 4.8.4
|
||||
- Tokenizers: 0.22.2
|
||||
|
||||
## Citations
|
||||
|
||||
Cite DPO as:
|
||||
|
||||
```bibtex
|
||||
@inproceedings{rafailov2023direct,
|
||||
title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
|
||||
author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
|
||||
year = 2023,
|
||||
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
|
||||
url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
|
||||
editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
|
||||
}
|
||||
```
|
||||
|
||||
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}}
|
||||
}
|
||||
```
|
||||
9
all_results.json
Normal file
9
all_results.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 4.194636241930751,
|
||||
"train_runtime": 7092.6143,
|
||||
"train_samples": 272585,
|
||||
"train_samples_per_second": 38.432,
|
||||
"train_steps_per_second": 0.3
|
||||
}
|
||||
25
chat_template.jinja
Normal file
25
chat_template.jinja
Normal file
@@ -0,0 +1,25 @@
|
||||
|
||||
{%- for message in messages -%}
|
||||
{%- if message["role"] == "system" -%}
|
||||
{{- "<|system|>
|
||||
" + message["content"] + "
|
||||
" -}}
|
||||
{%- elif message["role"] == "user" -%}
|
||||
{{- "<|user|>
|
||||
" + message["content"] + "
|
||||
" -}}
|
||||
{%- elif message["role"] == "assistant" -%}
|
||||
{%- if not loop.last -%}
|
||||
{{- "<|assistant|>
|
||||
" + message["content"] + eos_token + "
|
||||
" -}}
|
||||
{%- else -%}
|
||||
{{- "<|assistant|>
|
||||
" + message["content"] + eos_token -}}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
{%- if loop.last and add_generation_prompt -%}
|
||||
{{- "<|assistant|>
|
||||
" -}}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
34
config.json
Normal file
34
config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 65492,
|
||||
"head_dim": 64,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 576,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 1536,
|
||||
"max_position_embeddings": 16384,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 9,
|
||||
"num_hidden_layers": 80,
|
||||
"num_key_value_heads": 3,
|
||||
"pad_token_id": 3,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 4.0,
|
||||
"original_max_position_embeddings": 4096,
|
||||
"rope_type": "yarn"
|
||||
},
|
||||
"rope_theta": 10000,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": false,
|
||||
"vocab_size": 65600
|
||||
}
|
||||
52
config.yaml
Normal file
52
config.yaml
Normal file
@@ -0,0 +1,52 @@
|
||||
model_name_or_path: ali-elganzory/Baguettotron-longsft_16k-SFT-Tulu3-decontaminated
|
||||
dtype: bfloat16
|
||||
attn_implementation: flash_attention_2
|
||||
trust_remote_code: true
|
||||
chat_template: "\n{%- for message in messages -%}\n\t{%- if message[\"role\"] == \"\
|
||||
system\" -%}\n\t\t{{- \"<|system|>\n\" + message[\"content\"] + \"\n\" -}}\n\t{%-\
|
||||
\ elif message[\"role\"] == \"user\" -%}\n\t\t{{- \"<|user|>\n\" + message[\"content\"\
|
||||
] + \"\n\" -}}\n\t{%- elif message[\"role\"] == \"assistant\" -%}\n\t\t{%- if not\
|
||||
\ loop.last -%}\n\t\t\t{{- \"<|assistant|>\n\" + message[\"content\"] + eos_token\
|
||||
\ + \"\n\" -}}\n\t\t{%- else -%}\n\t\t\t{{- \"<|assistant|>\n\" + message[\"content\"\
|
||||
] + eos_token -}}\n\t\t{%- endif -%}\n\t{%- endif -%}\n\t{%- if loop.last and add_generation_prompt\
|
||||
\ -%}\n\t\t{{- \"<|assistant|>\n\" -}}\n\t{%- endif -%}\n{%- endfor -%}\n"
|
||||
additional_special_tokens:
|
||||
- <|system|>
|
||||
- <|user|>
|
||||
- <|assistant|>
|
||||
dataset_mixture:
|
||||
datasets:
|
||||
- id: ali-elganzory/llama-3.1-tulu-3-8b-preference-mixture-decontaminated
|
||||
config: default
|
||||
split: train
|
||||
columns:
|
||||
- chosen
|
||||
- rejected
|
||||
dataset_num_proc: 32
|
||||
remove_unused_columns: true
|
||||
eval_strategy: 'no'
|
||||
output_dir: /e/project1/reformo/ali/alignment-handbook/results/mv_exp/dpo/ali-elganzory-Baguettotron-longsft_16k-SFT-Tulu3-decontaminated_tulu-3-8b-preference-mixture-decontaminated_GH200
|
||||
overwrite_output_dir: false
|
||||
save_strategy: steps
|
||||
save_steps: 200
|
||||
save_total_limit: 2
|
||||
log_level: info
|
||||
report_to:
|
||||
- wandb
|
||||
logging_steps: 10
|
||||
logging_strategy: steps
|
||||
seed: 42
|
||||
bf16: true
|
||||
gradient_checkpointing: true
|
||||
gradient_checkpointing_kwargs:
|
||||
use_reentrant: false
|
||||
learning_rate: 5.0e-07
|
||||
lr_scheduler_type: linear
|
||||
max_length: 2048
|
||||
beta: 5
|
||||
warmup_ratio: 0.1
|
||||
per_device_train_batch_size: 32
|
||||
gradient_accumulation_steps: 1
|
||||
num_train_epochs: 1
|
||||
hub_model_id: ali-elganzory/Baguettotron-longsft_16k-DPO-Tulu3-decontaminated
|
||||
hub_strategy: every_save
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": [
|
||||
65492
|
||||
],
|
||||
"pad_token_id": 3,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0a43fa80231204106dc98ba7b76468aebd12d1575355fa08d275377d60837fe4
|
||||
size 642069144
|
||||
80
special_tokens_map.json
Normal file
80
special_tokens_map.json
Normal file
@@ -0,0 +1,80 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<think>",
|
||||
"</think>",
|
||||
"source_1",
|
||||
"source_2",
|
||||
"source_3",
|
||||
"source_4",
|
||||
"source_5",
|
||||
"source_6",
|
||||
"source_7",
|
||||
"source_8",
|
||||
"source_9",
|
||||
"source_10",
|
||||
"<ref",
|
||||
"</ref>",
|
||||
"→",
|
||||
"↺",
|
||||
"※",
|
||||
"?maybe?",
|
||||
"●",
|
||||
"◐",
|
||||
"○",
|
||||
"⚠",
|
||||
"☐",
|
||||
"☑",
|
||||
"✓",
|
||||
"⟨H≈0.1⟩",
|
||||
"⟨H≈0.2⟩",
|
||||
"⟨H≈0.3⟩",
|
||||
"⟨H≈0.4⟩",
|
||||
"⟨H≈0.5⟩",
|
||||
"⟨H≈0.6⟩",
|
||||
"⟨H≈0.7⟩",
|
||||
"⟨H≈0.8⟩",
|
||||
"⟨H≈0.9⟩",
|
||||
"⟨H≈1.0⟩",
|
||||
"⟨H≈1.1⟩",
|
||||
"⟨H≈1.2⟩",
|
||||
"⟨H≈1.3⟩",
|
||||
"⟨H≈1.4⟩",
|
||||
"⟨H≈1.5⟩",
|
||||
"⟨H≈1.6⟩",
|
||||
"⟨H≈1.7⟩",
|
||||
"⟨H≈1.8⟩",
|
||||
"<|system|>",
|
||||
"<|user|>",
|
||||
"<|assistant|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "[PAD]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "[UNK]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
327074
tokenizer.json
Normal file
327074
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
480
tokenizer_config.json
Normal file
480
tokenizer_config.json
Normal file
@@ -0,0 +1,480 @@
|
||||
{
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "[UNK]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "[PAD]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65491": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65492": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65493": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65494": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65495": {
|
||||
"content": "source_1",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65496": {
|
||||
"content": "source_2",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65497": {
|
||||
"content": "source_3",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65498": {
|
||||
"content": "source_4",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65499": {
|
||||
"content": "source_5",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65500": {
|
||||
"content": "source_6",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65501": {
|
||||
"content": "source_7",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65502": {
|
||||
"content": "source_8",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65503": {
|
||||
"content": "source_9",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65504": {
|
||||
"content": "source_10",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65505": {
|
||||
"content": "<ref",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65506": {
|
||||
"content": "</ref>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65507": {
|
||||
"content": "→",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65508": {
|
||||
"content": "↺",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65509": {
|
||||
"content": "※",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65510": {
|
||||
"content": "?maybe?",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65511": {
|
||||
"content": "●",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65512": {
|
||||
"content": "◐",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65513": {
|
||||
"content": "○",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65514": {
|
||||
"content": "⚠",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65515": {
|
||||
"content": "☐",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65516": {
|
||||
"content": "☑",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65517": {
|
||||
"content": "✓",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65518": {
|
||||
"content": "⟨H≈0.1⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65519": {
|
||||
"content": "⟨H≈0.2⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65520": {
|
||||
"content": "⟨H≈0.3⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65521": {
|
||||
"content": "⟨H≈0.4⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65522": {
|
||||
"content": "⟨H≈0.5⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65523": {
|
||||
"content": "⟨H≈0.6⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65524": {
|
||||
"content": "⟨H≈0.7⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65525": {
|
||||
"content": "⟨H≈0.8⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65526": {
|
||||
"content": "⟨H≈0.9⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65527": {
|
||||
"content": "⟨H≈1.0⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65528": {
|
||||
"content": "⟨H≈1.1⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65529": {
|
||||
"content": "⟨H≈1.2⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65530": {
|
||||
"content": "⟨H≈1.3⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65531": {
|
||||
"content": "⟨H≈1.4⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65532": {
|
||||
"content": "⟨H≈1.5⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65533": {
|
||||
"content": "⟨H≈1.6⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65534": {
|
||||
"content": "⟨H≈1.7⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65535": {
|
||||
"content": "⟨H≈1.8⟩",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65536": {
|
||||
"content": "<|system|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65537": {
|
||||
"content": "<|user|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"65538": {
|
||||
"content": "<|assistant|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<think>",
|
||||
"</think>",
|
||||
"source_1",
|
||||
"source_2",
|
||||
"source_3",
|
||||
"source_4",
|
||||
"source_5",
|
||||
"source_6",
|
||||
"source_7",
|
||||
"source_8",
|
||||
"source_9",
|
||||
"source_10",
|
||||
"<ref",
|
||||
"</ref>",
|
||||
"→",
|
||||
"↺",
|
||||
"※",
|
||||
"?maybe?",
|
||||
"●",
|
||||
"◐",
|
||||
"○",
|
||||
"⚠",
|
||||
"☐",
|
||||
"☑",
|
||||
"✓",
|
||||
"⟨H≈0.1⟩",
|
||||
"⟨H≈0.2⟩",
|
||||
"⟨H≈0.3⟩",
|
||||
"⟨H≈0.4⟩",
|
||||
"⟨H≈0.5⟩",
|
||||
"⟨H≈0.6⟩",
|
||||
"⟨H≈0.7⟩",
|
||||
"⟨H≈0.8⟩",
|
||||
"⟨H≈0.9⟩",
|
||||
"⟨H≈1.0⟩",
|
||||
"⟨H≈1.1⟩",
|
||||
"⟨H≈1.2⟩",
|
||||
"⟨H≈1.3⟩",
|
||||
"⟨H≈1.4⟩",
|
||||
"⟨H≈1.5⟩",
|
||||
"⟨H≈1.6⟩",
|
||||
"⟨H≈1.7⟩",
|
||||
"⟨H≈1.8⟩",
|
||||
"<|system|>",
|
||||
"<|user|>",
|
||||
"<|assistant|>"
|
||||
],
|
||||
"bos_token": "<|begin_of_text|>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|im_end|>",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "[PAD]",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "PreTrainedTokenizerFast",
|
||||
"unk_token": "[UNK]"
|
||||
}
|
||||
9
train_results.json
Normal file
9
train_results.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 4.194636241930751,
|
||||
"train_runtime": 7092.6143,
|
||||
"train_samples": 272585,
|
||||
"train_samples_per_second": 38.432,
|
||||
"train_steps_per_second": 0.3
|
||||
}
|
||||
3238
trainer_state.json
Normal file
3238
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
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 sha256:86ca4f9e55a98bf18fc4bba2372de2b80238b032cc87e6f64cae84895ec377ba
|
||||
size 8888
|
||||
Reference in New Issue
Block a user