learning_rate: 5e-05
train_batch_size: 256
eval_batch_size: 256
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
lr_scheduler_warmup_ratio: 0.05
num_epochs: 3

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.791	0.1214	50	1.7097	0.4492
1.4512	0.2427	100	1.4715	0.4492
1.4028	0.3641	150	1.4398	0.4541
1.4328	0.4854	200	1.3781	0.5
1.3371	0.6068	250	1.3501	0.5225
1.2848	0.7282	300	1.3389	0.5117
1.3063	0.8495	350	1.3197	0.5381
1.3037	0.9709	400	1.3000	0.5332
1.2577	1.0922	450	1.2872	0.5547
1.2852	1.2136	500	1.2735	0.5684
1.2491	1.3350	550	1.2703	0.5635
1.2681	1.4563	600	1.2725	0.5527
1.2511	1.5777	650	1.2616	0.5605
1.2518	1.6990	700	1.2645	0.5586
1.2332	1.8204	750	1.2517	0.5732
1.1977	1.9417	800	1.2498	0.5674
1.273	2.0631	850	1.2543	0.5605
1.2316	2.1845	900	1.2510	0.5703
1.2316	2.3058	950	1.2559	0.5635
1.2187	2.4272	1000	1.2477	0.5732
1.2367	2.5485	1050	1.2473	0.5713
1.2246	2.6699	1100	1.2446	0.5732
1.2313	2.7913	1150	1.2481	0.5703
1.1941	2.9126	1200	1.2474	0.5703

minato-ryan/cv-age-multi-3epoch

cv-age-multi-3epoch