learning_rate: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
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: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	110	2.8199	0.2104	0.1085
No log	2.0	220	2.5135	0.2588	0.1064
No log	3.0	330	2.4995	0.2588	0.1064
No log	4.0	440	2.4478	0.2588	0.1064
2.8208	5.0	550	2.4481	0.2588	0.1064
2.8208	6.0	660	2.4810	0.2588	0.1064
2.8208	7.0	770	2.4651	0.2588	0.1064
2.8208	8.0	880	2.4627	0.2588	0.1064
2.8208	9.0	990	2.4602	0.2588	0.1064
2.4034	10.0	1100	2.4659	0.2588	0.1064

FaishalbhiteX/indobert-QA-multiple-choice-fine-tune

indobert-QA-multiple-choice-fine-tune