learning_rate: 0.0001
train_batch_size: 64
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: linear
lr_scheduler_warmup_steps: 500
num_epochs: 50

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	346	0.4154	0.8469	0.6829	0.4805	0.5007
0.4975	2.0	692	0.3971	0.8570	0.7001	0.5340	0.5654
0.3757	3.0	1038	0.3957	0.8578	0.7168	0.5314	0.5697
0.3757	4.0	1384	0.3873	0.8589	0.7161	0.5491	0.5808
0.3705	5.0	1730	0.3856	0.8615	0.7292	0.5519	0.5873
0.3637	6.0	2076	0.3895	0.8589	0.7281	0.5473	0.5791
0.3637	7.0	2422	0.3795	0.8600	0.6997	0.5457	0.5873
0.3632	8.0	2768	0.3770	0.8634	0.7267	0.5554	0.5965
0.3553	9.0	3114	0.3735	0.8619	0.6968	0.5733	0.6118
0.3553	10.0	3460	0.3881	0.8597	0.7124	0.5667	0.5903
0.3615	11.0	3806	0.3749	0.8619	0.7098	0.5583	0.5991
0.3515	12.0	4152	0.3762	0.8630	0.7066	0.5915	0.6183
0.3515	13.0	4498	0.3745	0.8630	0.7202	0.5603	0.5977
0.3544	14.0	4844	0.3718	0.8582	0.6881	0.5500	0.5889
0.3483	15.0	5190	0.3721	0.8623	0.7124	0.5596	0.6002
0.352	16.0	5536	0.3737	0.8612	0.7282	0.5420	0.5850
0.352	17.0	5882	0.3713	0.8597	0.6833	0.5839	0.6137

trhgquan/visobert-human-tl-seg-seed-1337

visobert-human-tl-seg-seed-1337