learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 3407
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.06
num_epochs: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.3798	1.0	6	1.3859	0.7176
1.3841	2.0	12	1.3744	0.7155
1.3566	3.0	18	1.4371	0.7130
1.3652	4.0	24	1.3793	0.7193
1.3869	5.0	30	1.4522	0.7055
1.3302	6.0	36	1.4605	0.7042
1.3277	7.0	42	1.4848	0.7005
1.3264	8.0	48	1.3649	0.7277
1.3271	9.0	54	1.3329	0.7348
1.3242	10.0	60	1.4326	0.7109
1.3164	11.0	66	1.3092	0.7252
1.3218	12.0	72	1.4003	0.7114
1.3153	13.0	78	1.2768	0.7323
1.3749	14.0	84	1.3195	0.7256
1.3106	15.0	90	1.3585	0.7067
1.3176	16.0	96	1.3711	0.7264
1.4064	16.7273	100	1.3267	0.7214

Mardiyyah/cellate1.0-tapt_freeze_llrd_ww_mask-LR_2e-05

cellate1.0-tapt_freeze_llrd_ww_mask-LR_2e-05