learning_rate: 0.0006058454513356471
train_batch_size: 16
eval_batch_size: 32
seed: 1
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.01
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.2427	1.2550	315	0.8253	0.0007
0.8106	2.5100	630	0.7777	0.0021
0.7663	3.7649	945	0.7449	0.0017
0.7263	5.0199	1260	0.6997	0.0027
0.689	6.2749	1575	0.6683	0.0018
0.6524	7.5299	1890	0.6396	0.0008
0.6158	8.7849	2205	0.6139	0.0021
0.5807	10.0398	2520	0.5981	0.0010
0.5437	11.2948	2835	0.5848	0.0030
0.5109	12.5498	3150	0.5841	0.0026
0.4781	13.8048	3465	0.5799	0.0028
0.4453	15.0598	3780	0.5867	0.0034
0.4169	16.3147	4095	0.5915	0.0034
0.3972	17.5697	4410	0.5968	0.0034
0.3847	18.8247	4725	0.5973	0.0033

RoboSG/js-fake-bach-epochs20

js-fake-bach-epochs20