---
library_name: transformers
tags:
- medical
license: apache-2.0
datasets:
- SylvanL/Traditional-Chinese-Medicine-Dataset-SFT
language:
- zh
base_model:
- SylvanL/ChatTCM-7B-Pretrain
---



在2张V800-80G上, 

基于SylvanL/ChatTCM-7B-Pretrain, 

使用SylvanL/Traditional-Chinese-Medicine-Dataset-SFT进行了1个epoch的有监督微调(Supervised Fine-tuning).

```
epoch 1: 
    "epoch": 0.9999178959467966,
    "num_input_tokens_seen": 1649269888,
    "total_flos": 3298213988794368.0,
    "train_loss": 1.0691444667014194,
    "train_runtime": 587389.2072,
    "train_samples_per_second": 3.483,
    "train_steps_per_second": 0.016

```

```
llamafactory-cli train \
    --stage sft \
    --do_train True \
    --model_name_or_path {model_name_or_path} \
    --preprocessing_num_workers 16 \
    --finetuning_type full \
    --template default \
    --flash_attn auto \
    --dataset_dir {dataset_dir} \
    --dataset SFT_medicalKnowledge_source1_548404,SFT_medicalKnowledge_source2_99334,SFT_medicalKnowledge_source3_556540,SFT_nlpDiseaseDiagnosed_61486,SFT_nlpSyndromeDiagnosed_48665,SFT_structGeneral_310860,SFT_structPrescription_92896,SFT_external_traditionalTrans_7304,SFT_external_shuffledCOIGCQIA_44694,_SFT_external_shuffledCOIG_275985 \
    --cutoff_len 1024 \
    --learning_rate 5e-05 \
    --num_train_epochs 1.0 \
    --max_samples 1000000 \
    --per_device_train_batch_size 28 \
    --gradient_accumulation_steps 4 \
    --lr_scheduler_type cosine \
    --max_grad_norm 1.0 \
    --logging_steps 1 \
    --save_steps 1000 \
    --warmup_steps 0 \
    --optim adamw_torch \
    --packing False \
    --report_to none \
    --output_dir {output_dir} \
    --bf16 True \
    --plot_loss True \
    --ddp_timeout 180000000 \
    --include_num_input_tokens_seen True \
    --deepspeed cache/ds_z3_offload_config.json

```