learning_rate: 3e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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_ratio: 0.06
num_epochs: 8

Training Loss	Epoch	Step	Validation Loss
2.9303	0.2463	100	1.4581
1.5302	0.4926	200	1.3927
1.4989	0.7389	300	1.3911
1.4649	0.9852	400	1.3221
1.4015	1.2315	500	1.3565
1.3874	1.4778	600	1.2956
1.3699	1.7241	700	1.2915
1.3664	1.9704	800	1.2818
1.3284	2.2167	900	1.2541
1.3181	2.4631	1000	1.2590
1.3009	2.7094	1100	1.2409
1.3332	2.9557	1200	1.2647
1.2581	3.2020	1300	1.2192
1.2849	3.4483	1400	1.2634
1.2838	3.6946	1500	1.2322
1.2664	3.9409	1600	1.2561
1.2275	4.1872	1700	1.1981
1.2216	4.4335	1800	1.2147
1.2317	4.6798	1900	1.2067
1.2038	4.9261	2000	1.2021
1.2022	5.1724	2100	1.2170
1.2011	5.4187	2200	1.1946
1.1699	5.6650	2300	1.1933
1.1717	5.9113	2400	1.1642
1.1799	6.1576	2500	1.1737
1.1637	6.4039	2600	1.1751
1.1417	6.6502	2700	1.1575
1.1449	6.8966	2800	1.1655
1.1621	7.1429	2900	1.1472
1.1502	7.3892	3000	1.1504
1.1497	7.6355	3100	1.1807
1.1274	7.8818	3200	1.1436

taiypeo/roberta-large-aeslc

roberta-large-aeslc