learning_rate: 0.0002
train_batch_size: 6
eval_batch_size: 6
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 12
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	0.5	100	0.3263	0.9016	0.8977	0.9059	0.9016
No log	1.0	200	0.1914	0.9484	0.9442	0.9432	0.9484
No log	1.5	300	0.0657	0.9891	0.9853	0.9820	0.9891
No log	2.0	400	0.0342	0.9906	0.9868	0.9833	0.9906
0.6054	2.5	500	0.0265	0.9938	0.9928	0.9939	0.9938
0.6054	3.0	600	0.0256	0.9938	0.9928	0.9939	0.9938

Anranhhh/results_lora

results_lora