metadata
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