Model description

More information needed

Intended uses & limitations

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
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
lr_scheduler_warmup_ratio: 0.1
num_epochs: 30

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.5802	1.0	48	1.6596	0.5445
0.9821	2.0	96	0.6121	0.8012
0.767	3.0	144	0.5143	0.8323
0.6452	4.0	192	0.4496	0.8516
0.4403	5.0	240	0.5212	0.8472
0.4859	6.0	288	0.4766	0.8828
0.4177	7.0	336	0.4704	0.8516
0.3815	8.0	384	0.4597	0.8694
0.4111	9.0	432	0.4289	0.8828
0.3375	10.0	480	0.4603	0.8709
0.3267	11.0	528	0.5173	0.8739
0.2948	12.0	576	0.4379	0.8932
0.2322	13.0	624	0.4454	0.9036
0.2612	14.0	672	0.5133	0.8739
0.2259	15.0	720	0.4377	0.8947
0.2534	16.0	768	0.5072	0.8724
0.1852	17.0	816	0.4951	0.8843
0.1976	18.0	864	0.5063	0.8902
0.2377	19.0	912	0.4767	0.8843
0.189	20.0	960	0.4763	0.8917
0.1744	21.0	1008	0.5027	0.8813
0.1546	22.0	1056	0.5021	0.8961
0.1451	23.0	1104	0.4772	0.9006
0.1681	24.0	1152	0.4767	0.8976
0.1539	25.0	1200	0.5087	0.8902
0.1054	26.0	1248	0.5186	0.8902
0.1111	27.0	1296	0.5066	0.9006
0.1057	28.0	1344	0.5019	0.8947
0.1498	29.0	1392	0.5147	0.9006
0.1255	29.3789	1410	0.5148	0.8991