23 lines
577 B
JSON
23 lines
577 B
JSON
|
{
|
||
|
|
"base_model": "kmseong/llama2_7b-chat-Safety-FT-lr5e-5",
|
||
|
|
"fine_tuning_type": "Full Parameter",
|
||
|
|
"loss_type": "constrained",
|
||
|
|
"dataset": "GSM8K",
|
||
|
|
"num_train_samples": 7473,
|
||
|
|
"batch_size": 4,
|
||
|
|
"grad_accum": 4,
|
||
|
|
"learning_rate": 5e-05,
|
||
|
|
"weight_decay": 0.01,
|
||
|
|
"warmup_ratio": 0.1,
|
||
|
|
"epochs": 3,
|
||
|
|
"max_length": 1024,
|
||
|
|
"max_grad_norm": 1.0,
|
||
|
|
"lr_scheduler_type": "cosine",
|
||
|
|
"optimizer": "AdamW (torch)",
|
||
|
|
"dtype": "bf16",
|
||
|
|
"csft_beta": 0.1,
|
||
|
|
"csft_bias_factor": 20.0,
|
||
|
|
"csft_first_token_bias_factor": 5.0,
|
||
|
|
"csft_bias_length": 5,
|
||
|
|
"safety_mix_ratio": 0.0
|
||
|
|
}
|