learning_rate: 1e-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
lr_scheduler_warmup_ratio: 0.1
num_epochs: 35
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6953	1.0	93	0.6749	0.6593
0.682	2.0	186	0.6566	0.7802
0.6648	3.0	279	0.6398	0.6593
0.575	4.0	372	0.5919	0.7363
0.4928	5.0	465	0.5255	0.8022
0.5632	6.0	558	0.6413	0.7033
0.5774	7.0	651	0.6841	0.6484
0.4103	8.0	744	0.5126	0.7802
0.4039	9.0	837	0.5442	0.7692
0.2816	10.0	930	0.5887	0.7582
0.3828	11.0	1023	0.6073	0.7473
0.4426	12.0	1116	0.5738	0.8132
0.4324	13.0	1209	0.6415	0.7473
0.4265	14.0	1302	0.6272	0.7253
0.3727	15.0	1395	0.6898	0.7033
0.0826	16.0	1488	0.6399	0.7692
0.2454	17.0	1581	0.6483	0.8022
0.305	18.0	1674	0.7375	0.7582
0.0908	19.0	1767	0.7478	0.7692
0.4096	20.0	1860	0.6736	0.8132
0.327	21.0	1953	0.6455	0.8462
0.1344	22.0	2046	0.7261	0.8132
0.1325	23.0	2139	0.7110	0.8352
0.2949	24.0	2232	0.8017	0.8022
0.4198	25.0	2325	0.8576	0.7912
0.2725	26.0	2418	0.8864	0.8022
0.2007	27.0	2511	0.9958	0.7692
0.009	28.0	2604	0.9285	0.7912
0.0138	29.0	2697	0.9492	0.8022
0.0122	30.0	2790	0.9575	0.8022
0.0474	31.0	2883	0.9338	0.8022
0.0416	32.0	2976	0.9612	0.8022
0.1355	33.0	3069	0.9378	0.8132
0.0395	34.0	3162	1.0091	0.8022
0.2037	35.0	3255	0.9924	0.8022

NiloofarMomeni/distilhubert-finetuned-grd-balnc

distilhubert-finetuned-grd-balnc