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	0.4130	0.8469	0.6862	0.4920	0.5122
0.4942	2.0	692	0.3936	0.8600	0.6983	0.5471	0.5774
0.3679	3.0	1038	0.3943	0.8567	0.7126	0.5332	0.5614
0.3679	4.0	1384	0.3840	0.8615	0.7183	0.5512	0.5856
0.3626	5.0	1730	0.3807	0.8619	0.7251	0.5589	0.5904
0.3528	6.0	2076	0.3865	0.8615	0.7231	0.5649	0.5907
0.3528	7.0	2422	0.3771	0.8612	0.6992	0.5556	0.5941
0.3514	8.0	2768	0.3783	0.8638	0.7151	0.5621	0.5979
0.3459	9.0	3114	0.3725	0.8612	0.6871	0.5571	0.5883
0.3459	10.0	3460	0.3813	0.8593	0.7119	0.5569	0.5774
0.3518	11.0	3806	0.3702	0.8619	0.7050	0.5695	0.6067
0.3421	12.0	4152	0.3750	0.8612	0.7007	0.5812	0.6038
0.3421	13.0	4498	0.3710	0.8656	0.7239	0.5672	0.6065
0.3429	14.0	4844	0.3696	0.8623	0.6972	0.5650	0.6023
0.3358	15.0	5190	0.3656	0.8653	0.7161	0.5734	0.6100
0.3405	16.0	5536	0.3701	0.8656	0.7391	0.5571	0.5974
0.3405	17.0	5882	0.3661	0.8619	0.6937	0.5829	0.6095
0.3289	18.0	6228	0.3699	0.8623	0.7096	0.5685	0.5927
0.3289	19.0	6574	0.3649	0.8638	0.7022	0.5765	0.6068
0.3289	20.0	6920	0.3634	0.8645	0.7139	0.5714	0.6023

trhgquan/visobert-human-tl-seed-6969

visobert-human-tl-seed-6969