learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
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
No log	1.0	347	3.4224
0.0766	2.0	694	3.0937
0.0569	3.0	1041	3.4725
0.0569	4.0	1388	3.3484
0.0365	5.0	1735	3.5406
0.0364	6.0	2082	3.3922
0.0364	7.0	2429	3.2977
0.0353	8.0	2776	3.3093
0.0136	9.0	3123	3.5960
0.0136	10.0	3470	3.5143
0.0249	11.0	3817	3.5032
0.0156	12.0	4164	3.5010
0.0154	13.0	4511	3.4902
0.0154	14.0	4858	3.5322
0.0116	15.0	5205	3.4929
0.0066	16.0	5552	3.5660
0.0066	17.0	5899	3.5789
0.0053	18.0	6246	3.5614
0.003	19.0	6593	3.5579
0.003	20.0	6940	3.5902

kylePham/Model

Model