learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.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	Accuracy
0.0074	1.0	938	0.2802	0.9617
0.0045	2.0	1876	0.2970	0.959
0.001	3.0	2814	0.2984	0.9613
0.003	4.0	3752	0.2829	0.9603
0.0041	5.0	4690	0.3201	0.952
0.0013	6.0	5628	0.3253	0.9557
0.0063	7.0	6566	0.2916	0.962
0.0025	8.0	7504	0.3235	0.9607
0.0033	9.0	8442	0.3227	0.9593
0.0	10.0	9380	0.3215	0.961
0.0002	11.0	10318	0.3210	0.96
0.0004	12.0	11256	0.3281	0.9603
0.001	13.0	12194	0.3344	0.9597
0.0	14.0	13132	0.3248	0.961
0.001	15.0	14070	0.3249	0.9583
0.0001	16.0	15008	0.3157	0.9623
0.0	17.0	15946	0.3286	0.961
0.0	18.0	16884	0.3379	0.9607
0.0	19.0	17822	0.3364	0.9613
0.0	20.0	18760	0.3357	0.961

chiwa42/distilbert-base-uncased-finetuned-adl_hw1

distilbert-base-uncased-finetuned-adl_hw1