learning_rate: 4e-05
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: 2
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
3.8028	0.0833	25	1.5191	0.3944	0.2893	0.4598	0.3944
2.2046	0.1667	50	0.7147	0.75	0.7423	0.7685	0.75
1.2172	0.25	75	0.6074	0.7989	0.7727	0.8508	0.7989
0.9054	0.3333	100	0.3817	0.8656	0.8637	0.8907	0.8656
0.873	0.4167	125	0.3460	0.8678	0.8665	0.8810	0.8678
0.7074	0.5	150	0.2918	0.8889	0.8848	0.9159	0.8889
1.0552	0.5833	175	0.2550	0.89	0.8868	0.9130	0.89
0.5167	0.6667	200	0.2660	0.9044	0.9043	0.9071	0.9044
0.3174	0.75	225	0.2641	0.8956	0.8882	0.9235	0.8956
0.3369	0.8333	250	0.1745	0.9489	0.9490	0.9520	0.9489
0.2966	0.9167	275	0.1484	0.9567	0.9568	0.9589	0.9567
0.5544	1.0	300	0.2000	0.9433	0.9429	0.9508	0.9433

ccaug/results

results