learning_rate: 4e-05
train_batch_size: 1
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
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_steps: 10
num_epochs: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.5426	1.0	42	0.6406
0.5337	2.0	84	0.6315
0.525	3.0	126	0.6253
0.5173	4.0	168	0.6234
0.5043	5.0	210	0.6203
0.5003	6.0	252	0.6247
0.4904	7.0	294	0.6182
0.4884	8.0	336	0.6152
0.4791	9.0	378	0.6164
0.4755	10.0	420	0.6107
0.4733	11.0	462	0.6122
0.4677	12.0	504	0.6062
0.4712	13.0	546	0.5999
0.4654	14.0	588	0.6035
0.4587	15.0	630	0.6017
0.4595	16.0	672	0.6025
0.4528	17.0	714	0.6077
0.4549	18.0	756	0.6019
0.4538	19.0	798	0.6014
0.4553	20.0	840	0.5982

kavinda123321/mahinda_check1

mahinda_check1