| { | |
| "model_name_or_path": "/aifs4su/hansirui_1st/models/Qwen1.5-0.5B", | |
| "max_length": 512, | |
| "trust_remote_code": true, | |
| "train_datasets": [ | |
| [ | |
| "inverse-json", | |
| { | |
| "proportion": 1.0, | |
| "path": "/home/hansirui_1st/jiayi/resist/imdb_data/train/pos/5000/train.json" | |
| } | |
| ] | |
| ], | |
| "eval_datasets": null, | |
| "epochs": 1, | |
| "per_device_train_batch_size": 1, | |
| "per_device_eval_batch_size": 4, | |
| "gradient_accumulation_steps": 8, | |
| "gradient_checkpointing": true, | |
| "lr": 1e-05, | |
| "lr_scheduler_type": "constant", | |
| "lr_warmup_ratio": 0.0, | |
| "weight_decay": 0.0, | |
| "seed": 42, | |
| "fp16": false, | |
| "bf16": true, | |
| "tf32": true, | |
| "eval_strategy": "epoch", | |
| "eval_interval": 1000000, | |
| "need_eval": false, | |
| "eval_split_ratio": null, | |
| "output_dir": "/aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-5000", | |
| "log_type": "wandb", | |
| "log_dir": "/aifs4su/hansirui_1st/jiayi/setting3-imdb/Qwen1.5-0.5B/Qwen1.5-0.5B-s3-Q1-5000", | |
| "log_project": "Inverse_Alignment_IMDb", | |
| "log_run_name": "imdb-Qwen1.5-0.5B-s3-Q1-5000", | |
| "save_16bit": true, | |
| "save_interval": 1000000, | |
| "local_rank": 0, | |
| "zero_stage": 3, | |
| "offload": "none", | |
| "deepspeed": false, | |
| "deepspeed_config": null, | |
| "deepscale": false, | |
| "deepscale_config": null, | |
| "global_rank": 0, | |
| "device": { | |
| "type": "torch.device", | |
| "repr": "device(type='cuda', index=0)" | |
| }, | |
| "num_update_steps_per_epoch": 79, | |
| "total_training_steps": 79 | |
| } |