learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 5

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.5635	0.4193	200	0.4160	0.8932	0.8911
0.2762	0.8386	400	0.2421	0.9387	0.9371
0.1315	1.2579	600	0.3010	0.9390	0.9376
0.0801	1.6771	800	0.2305	0.9552	0.9547
0.0736	2.0964	1000	0.2306	0.9577	0.9573
0.0288	2.5157	1200	0.2389	0.9545	0.9532
0.0159	2.9350	1400	0.1933	0.9661	0.9656
0.0069	3.3543	1600	0.1857	0.9652	0.9648
0.0062	3.7736	1800	0.1807	0.9677	0.9674
0.0061	4.1929	2000	0.1841	0.9674	0.9671
0.0011	4.6122	2200	0.1834	0.9681	0.9677

Petri99/MBERT-Clinc

MBERT-Clinc