learning_rate: 8.8e-05
train_batch_size: 32
eval_batch_size: 64
seed: 42
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: cosine
lr_scheduler_warmup_ratio: 0.079905
num_epochs: 50

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Adv Acc
0.783	1.0	72	0.7087	0.8549	0.8549	0.1451
0.7764	2.0	144	3.0179	0.8863	0.8862	0.1451
2.9074	3.0	216	2.7534	0.8941	0.8941	0.1451
3.3278	4.0	288	4.3535	0.8549	0.8546	0.0
3.6887	5.0	360	6.0152	0.9059	0.9055	0.1216
5.4634	6.0	432	6.3364	0.8863	0.8851	0.0118
3.965	7.0	504	3.9418	0.8392	0.8391	0.1294
6.9282	8.0	576	3.6172	0.8667	0.8661	0.0706
3.7356	9.0	648	3.3176	0.8706	0.8694	0.1059
2.9881	10.0	720	2.9793	0.8745	0.8739	0.1608
2.9243	11.0	792	3.2793	0.8314	0.8305	0.1098
2.8977	12.0	864	3.6846	0.8863	0.8862	0.1529
3.2782	13.0	936	4.2865	0.8824	0.8822	0.0
3.2658	14.0	1008	3.6497	0.8627	0.8627	0.0
3.121	15.0	1080	3.6188	0.8627	0.8625	0.0157

bhaswata08/sutra-classifier-adv-epoch50-cosine

sutra-classifier-adv-epoch50-cosine