learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 4
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: 20

Training Loss	Epoch	Step	Validation Loss
11.0414	1.0	11	10.4768
10.5361	2.0	22	9.6812
10.0148	3.0	33	8.9731
9.3895	4.0	44	8.7481
8.9148	5.0	55	8.3119
8.6222	6.0	66	8.0413
8.3471	7.0	77	7.7988
8.1107	8.0	88	7.6168
7.9351	9.0	99	7.4008
7.5972	10.0	110	7.1992
7.4541	11.0	121	7.0545
7.3436	12.0	132	6.9558
7.2126	13.0	143	6.8006
7.1090	14.0	154	6.6990
7.0149	15.0	165	6.6203
6.9819	16.0	176	6.5532
6.8978	17.0	187	6.4716
6.8420	18.0	198	6.4320
6.7765	19.0	209	6.4127
6.7872	20.0	220	6.4082

ross160/fine_tuned_model

fine_tuned_model