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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
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: 30
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8868	1.0	50	0.8761	0.72
0.4771	2.0	100	0.7632	0.76
0.3415	3.0	150	1.0356	0.72
0.2508	4.0	200	0.5432	0.82
0.1699	5.0	250	0.6632	0.81
0.024	6.0	300	0.8745	0.82
0.0353	7.0	350	0.8643	0.79
0.0341	8.0	400	0.5614	0.86
0.0411	9.0	450	0.6230	0.86
0.0345	10.0	500	0.9361	0.76
0.0304	11.0	550	0.6329	0.87
0.0504	12.0	600	1.0623	0.81
0.0526	13.0	650	0.7261	0.83
0.0007	14.0	700	0.8432	0.8
0.0041	15.0	750	0.8342	0.86
0.0002	16.0	800	0.6246	0.89
0.0092	17.0	850	0.5784	0.89
0.0001	18.0	900	0.6059	0.87
0.0001	19.0	950	0.5561	0.86
0.0001	20.0	1000	0.5483	0.85
0.0192	21.0	1050	0.5678	0.87