learning_rate: 1.5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss	F1
0.6611	1.0	21	0.5689	0.8067
0.5268	2.0	42	0.4698	0.8598
0.4322	3.0	63	0.5205	0.8485
0.3564	4.0	84	0.6989	0.7356
0.322	5.0	105	0.6610	0.7872
0.1975	6.0	126	1.0724	0.6824
0.2025	7.0	147	0.8713	0.8283
0.1605	8.0	168	0.9925	0.84
0.0834	9.0	189	1.2466	0.8235
0.0851	10.0	210	1.4596	0.8269
0.0742	11.0	231	1.4772	0.8269
0.0261	12.0	252	1.4519	0.8431
0.1153	13.0	273	1.4875	0.84
0.0016	14.0	294	1.4731	0.84
0.0036	15.0	315	1.5420	0.8431
0.0012	16.0	336	1.5392	0.8367
0.0092	17.0	357	1.4960	0.8515
0.0012	18.0	378	1.5128	0.8515
0.0007	19.0	399	1.5327	0.8515
0.0012	20.0	420	1.5213	0.8515

npark95/finetuned_ClinicalLongformer

finetuned_ClinicalLongformer