Model description

More information needed

Intended uses & limitations

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 2e-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: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 40

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.8421	4	1.6083	0.2115
No log	1.8421	8	1.5519	0.3077
7.0606	2.8421	12	1.4896	0.3846
7.0606	3.8421	16	1.4160	0.3846
6.3113	4.8421	20	1.3599	0.3269
6.3113	5.8421	24	1.2338	0.3462
6.3113	6.8421	28	1.1538	0.4808
5.1603	7.8421	32	1.0931	0.5577
5.1603	8.8421	36	1.0510	0.5577
3.5688	9.8421	40	0.9583	0.5577
3.5688	10.8421	44	0.9648	0.5577
3.5688	11.8421	48	0.9486	0.6154
2.9736	12.8421	52	0.9201	0.5962
2.9736	13.8421	56	1.0203	0.5577
2.5257	14.8421	60	0.8558	0.6154
2.5257	15.8421	64	0.9309	0.5769
2.5257	16.8421	68	0.9707	0.5769
2.3819	17.8421	72	0.8505	0.6731
2.3819	18.8421	76	0.9245	0.6538
1.9541	19.8421	80	0.9093	0.6731
1.9541	20.8421	84	0.8463	0.7115
1.9541	21.8421	88	0.9135	0.6731
1.7643	22.8421	92	0.8720	0.7115
1.7643	23.8421	96	0.8631	0.7115
1.5146	24.8421	100	0.8862	0.6923
1.5146	25.8421	104	0.8584	0.75
1.5146	26.8421	108	0.9111	0.6923
1.4609	27.8421	112	0.8703	0.75
1.4609	28.8421	116	0.8478	0.7692
1.463	29.8421	120	0.8645	0.75
1.463	30.8421	124	0.9137	0.6731
1.463	31.8421	128	0.9311	0.6731
1.3699	32.8421	132	0.9070	0.7115
1.3699	33.8421	136	0.8930	0.7115
1.2756	34.8421	140	0.8930	0.7115
1.2756	35.8421	144	0.8935	0.7308
1.2756	36.8421	148	0.8960	0.7308
1.273	37.8421	152	0.8951	0.7308
1.273	38.8421	156	0.8955	0.7308
1.2626	39.8421	160	0.8954	0.7308