learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 16
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: linear
lr_scheduler_warmup_steps: 50
num_epochs: 15

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Accuracy	F1	Precision	Recall
1.255	1.0	501	1.2030	0.0054	0.4875	0.4123	0.4276	0.4875
1.1924	2.0	1002	1.1502	0.0054	0.5065	0.4473	0.4296	0.5065
1.1519	3.0	1503	1.1191	0.0054	0.5224	0.4801	0.5272	0.5224
1.1277	4.0	2004	1.0978	0.0054	0.5474	0.5198	0.5485	0.5474
1.1069	5.0	2505	1.0835	0.0054	0.5504	0.5209	0.5528	0.5504
1.0909	6.0	3006	1.0699	0.0054	0.5633	0.5406	0.5616	0.5633
1.0801	7.0	3507	1.0595	0.0054	0.5693	0.5516	0.5610	0.5693
1.0689	8.0	4008	1.0531	0.0054	0.5653	0.5466	0.5565	0.5653
1.0661	9.0	4509	1.0472	0.0054	0.5673	0.5495	0.5584	0.5673
1.0605	10.0	5010	1.0427	0.0054	0.5613	0.5438	0.5507	0.5613
1.0548	11.0	5511	1.0391	0.0054	0.5683	0.5531	0.5543	0.5683
1.0497	12.0	6012	1.0368	0.0054	0.5703	0.5542	0.5574	0.5703
1.0467	13.0	6513	1.0354	0.0054	0.5683	0.5525	0.5550	0.5683
1.0459	14.0	7014	1.0343	0.0054	0.5673	0.5518	0.5537	0.5673
1.0425	15.0	7515	1.0338	0.0054	0.5673	0.5515	0.5539	0.5673

hafidev/bert-base-uncased-cefr-text-classification-beta-v1

bert-base-uncased-cefr-text-classification-beta-v1