Views
No views yet
| Parameter | Value |
|---|---|
| Lora_r | 32 |
| Lora_dropout | 0.1 |
| Bnb_4bit_quant_type | “nf4” |
| num_train_epoch | 3 |
| per_device_train_batch_size | 4 |
| per_device_eval_batch_size | 4 |
| gradient_checkpointing | True |
| learning_rate | 4e-4 |
| optim | “paged_adamw_8bit” |
| lora_alpha | 64 |
| bnb_4bit_compute_dtype | “bfloat16” |
| bf16 | True |
| gradient_accumulation_steps | 64 |
| weight_decay | 0.001 |