learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 64
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: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss
3.5064	0.2140	25	2.4667
1.9406	0.4280	50	2.5449
1.9175	0.6421	75	2.5669
1.8659	0.8561	100	2.7958
1.9603	1.0685	125	2.6281
1.8811	1.2825	150	2.5601
1.8955	1.4965	175	2.5833
1.8982	1.7105	200	2.6373
1.825	1.9246	225	2.6426
1.88	2.1370	250	2.8641
1.851	2.3510	275	2.6415
1.8619	2.5650	300	2.5749
1.8365	2.7790	325	2.6245
1.8783	2.9930	350	2.5929
1.8693	3.2055	375	2.5986
1.8605	3.4195	400	2.6601
1.8759	3.6335	425	2.5904
1.8731	3.8475	450	2.6054
1.8536	4.0599	475	2.6441
1.8509	4.2739	500	2.6678
1.8609	4.4880	525	2.6946
1.8478	4.7020	550	2.6386
1.8492	4.9160	575	2.6799
1.8549	5.1284	600	2.6355
1.88	5.3424	625	2.7021
1.8569	5.5564	650	2.6380
1.862	5.7705	675	2.6349
1.8486	5.9845	700	2.6843
1.8503	6.1969	725	2.6926
1.8503	6.4109	750	2.6962
1.84	6.6249	775	2.6286
1.8466	6.8390	800	2.6278
1.8584	7.0514	825	2.6274
1.8633	7.2654	850	2.6308
1.8744	7.4794	875	2.6365
1.8522	7.6934	900	2.6514
1.8578	7.9074	925	2.6701
1.8661	8.1199	950	2.6817
1.8301	8.3339	975	2.6813
1.8499	8.5479	1000	2.6841
1.8484	8.7619	1025	2.6832
1.8815	8.9759	1050	2.6814
1.8082	9.1883	1075	2.6836
1.8302	9.4024	1100	2.6839
1.8822	9.6164	1125	2.6824
1.8648	9.8304	1150	2.6822

alexandroputra/medsiglip-448-ft-tb-screening

medsiglip-448-ft-tb-screening