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	0.3479	0.8675	0.6877	0.6587	0.6359
0.3396	2.0	692	0.3445	0.8799	0.7140	0.6864	0.6986
0.1864	3.0	1038	0.4053	0.8795	0.7170	0.6573	0.6834
0.1864	4.0	1384	0.5250	0.875	0.7251	0.6485	0.6745
0.0923	5.0	1730	0.5543	0.8787	0.7116	0.6867	0.6984
0.0679	6.0	2076	0.6802	0.8694	0.6817	0.6657	0.6721
0.0679	7.0	2422	0.6481	0.8821	0.7263	0.6946	0.7095
0.0492	8.0	2768	0.6654	0.8795	0.7171	0.6606	0.6857
0.0404	9.0	3114	0.6279	0.8720	0.6908	0.6872	0.6887
0.0404	10.0	3460	0.7850	0.8821	0.7289	0.6925	0.7041
0.0313	11.0	3806	0.8283	0.8765	0.7144	0.6832	0.6889
0.0303	12.0	4152	0.8205	0.8769	0.7206	0.6695	0.6787

trhgquan/visobert-human-finetune-seed-24

visobert-human-finetune-seed-24