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: 8
total_train_batch_size: 256
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	1.0	2	1.5027	0.4091
No log	2.0	4	1.3949	0.4545
No log	3.0	6	1.2983	0.4659
No log	4.0	8	1.2602	0.4773
No log	5.0	10	1.2465	0.5568
8.9015	6.0	12	1.2463	0.6136
8.9015	7.0	14	1.2369	0.6136
8.9015	8.0	16	1.2061	0.6136
8.9015	9.0	18	1.1656	0.6477
8.9015	10.0	20	1.1330	0.6705
8.9015	11.0	22	1.1127	0.6818
7.6818	12.0	24	1.0981	0.6818
7.6818	13.0	26	1.0913	0.7045
7.6818	14.0	28	1.0857	0.6932
7.6818	15.0	30	1.0804	0.6932
7.6818	16.0	32	1.0732	0.6932
7.6818	17.0	34	1.0684	0.6932
7.0174	18.0	36	1.0644	0.6932
7.0174	19.0	38	1.0629	0.6932
7.0174	20.0	40	1.0626	0.6932