learning_rate: 2e-05
train_batch_size: 6
eval_batch_size: 6
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 192
total_eval_batch_size: 24
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 7
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	16	0.5511	0.6921	0.8180	0.6921	1.0
No log	2.0	32	0.4566	0.7793	0.8439	0.8264	0.8622
No log	3.0	48	0.4230	0.8093	0.8611	0.868	0.8543
No log	4.0	64	0.3796	0.8610	0.9061	0.8512	0.9685
No log	5.0	80	0.3521	0.8583	0.9019	0.8659	0.9409
No log	6.0	96	0.3509	0.8556	0.8990	0.8708	0.9291
No log	7.0	112	0.3489	0.8556	0.9020	0.8502	0.9606

sng1789/results

results