learning_rate: 2e-05
train_batch_size: 128
eval_batch_size: 128
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: linear
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.3781	200	0.0910	0.9681	0.9632
No log	0.7561	400	0.0904	0.9679	0.9632
No log	1.1342	600	0.0808	0.9716	0.9671
No log	1.5123	800	0.0869	0.9692	0.9645
No log	1.8904	1000	0.0975	0.9719	0.9674
0.0876	2.2684	1200	0.0921	0.9687	0.9640
0.0876	2.6465	1400	0.0921	0.9671	0.9623
0.0876	3.0246	1600	0.1035	0.9705	0.9659
0.0876	3.4026	1800	0.1080	0.9695	0.9650
0.0876	3.7807	2000	0.0977	0.9712	0.9669
0.0439	4.1588	2200	0.1101	0.9722	0.9675
0.0439	4.5369	2400	0.1157	0.9718	0.9673
0.0439	4.9149	2600	0.1297	0.9708	0.9661
0.0439	5.2930	2800	0.1404	0.9713	0.9667
0.0439	5.6711	3000	0.1254	0.9713	0.9666
0.023	6.0491	3200	0.1609	0.9705	0.9660
0.023	6.4272	3400	0.1506	0.9712	0.9665
0.023	6.8053	3600	0.1502	0.9698	0.9652
0.023	7.1834	3800	0.1726	0.9708	0.9661
0.023	7.5614	4000	0.1773	0.9709	0.9661
0.023	7.9395	4200	0.1671	0.9707	0.9661
0.011	8.3176	4400	0.2037	0.9710	0.9662
0.011	8.6957	4600	0.1927	0.9713	0.9667
0.011	9.0737	4800	0.1991	0.9714	0.9667
0.011	9.4518	5000	0.2080	0.9715	0.9668
0.011	9.8299	5200	0.2061	0.9704	0.9657

RonTon05/PhoBert_content_90K

PhoBert_content_90K