🚀 输出模型（outputs/out）
本项目基于 transformers 库，所训练的模型是 Qwen/Qwen2.5 - 7B 在特定数据集上的微调版本。该模型支持多种语言，包括中文、英文、法文、西班牙文等。本项目使用 axolotl 工具进行训练，以下是详细介绍。
查看 axolotl 配置
axolotl 版本：0.4.1
base_model: Qwen/Qwen2.5-7B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
type: sharegpt
conversation: chatml
- path: NewEden/Kalo-Opus-Instruct-22k-Refusal-Murdered
type: sharegpt
conversation: chatml
- path: Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
type: sharegpt
conversation: chatml
- path: NewEden/Gryphe-Sonnet-3.5-35k-Subset
type: sharegpt
conversation: chatml
- path: Nitral-AI/Reasoning-1shot_ShareGPT
type: sharegpt
conversation: chatml
- path: Nitral-AI/GU_Instruct-ShareGPT
type: sharegpt
conversation: chatml
- path: Nitral-AI/Medical_Instruct-ShareGPT
type: sharegpt
conversation: chatml
- path: AquaV/Resistance-Sharegpt
type: sharegpt
conversation: chatml
- path: AquaV/US-Army-Survival-Sharegpt
type: sharegpt
conversation: chatml
- path: Gryphe/Sonnet3.5-SlimOrcaDedupCleaned
type: sharegpt
conversation: chatml
chat_template: chatml
val_set_size: 0.002
output_dir: ./outputs/out
adapter:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true
wandb_project: qwen7B
wandb_entity:
wandb_watch:
wandb_name: qwen7B
wandb_log_model:
gradient_accumulation_steps: 32
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00001
weight_decay: 0.05
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_ratio: 0.1
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 2
debug:
deepspeed:
fsdp:
fsdp_config:
special_tokens:
pad_token: <pad>
🚀 快速开始
此模型是 Qwen/Qwen2.5 - 7B 在特定数据集上的微调版本，在评估集上取得了以下结果：
📚 详细文档
模型描述
更多信息待补充。
预期用途与限制
更多信息待补充。
训练和评估数据
更多信息待补充。
🔧 技术细节
训练超参数
训练过程中使用了以下超参数：
- 学习率：1e - 05
- 训练批次大小：1
- 评估批次大小：1
- 随机种子：42
- 分布式类型：多GPU
- 设备数量：4
- 梯度累积步数：32
- 总训练批次大小：128
- 总评估批次大小：4
- 优化器：Adam，β=(0.9, 0.999)，ε = 1e - 08
- 学习率调度器类型：余弦
- 学习率调度器热身步数：46
- 训练轮数：2
训练结果
| 训练损失 |
轮数 |
步数 |
验证损失 |
| 1.0297 |
0.0043 |
1 |
1.1468 |
| 0.8512 |
0.2515 |
58 |
0.8729 |
| 0.8496 |
0.5030 |
116 |
0.8193 |
| 0.8175 |
0.7546 |
174 |
0.8033 |
| 0.7868 |
1.0041 |
232 |
0.7961 |
| 0.8119 |
1.2555 |
290 |
0.7934 |
| 0.799 |
1.5069 |
348 |
0.7926 |
| 0.7891 |
1.7583 |
406 |
0.7923 |
框架版本
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
📄 许可证
本项目采用 Apache - 2.0 许可证。
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Transformers 支持多种语言