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
3.0558	1.0	43	3.0721	0.0519
2.9535	2.0	86	2.9192	0.1068
2.7928	3.0	129	2.6951	0.2315
2.5368	4.0	172	2.4673	0.3457
2.3928	5.0	215	2.2777	0.4303
2.1938	6.0	258	2.1163	0.4896
2.0454	7.0	301	1.9760	0.5208
1.9604	8.0	344	1.8527	0.5593
1.8495	9.0	387	1.7479	0.5890
1.6308	10.0	430	1.6564	0.6231
1.6896	11.0	473	1.5779	0.6424
1.6121	12.0	516	1.5088	0.6632
1.5673	13.0	559	1.4500	0.6751
1.4859	14.0	602	1.3988	0.6869
1.4813	15.0	645	1.3561	0.6958
1.4414	16.0	688	1.3177	0.7062
1.4252	17.0	731	1.2833	0.7136
1.3811	18.0	774	1.2549	0.7226
1.3464	19.0	817	1.2304	0.7240
1.2451	20.0	860	1.2093	0.7270
1.2871	21.0	903	1.1904	0.7315
1.2546	22.0	946	1.1746	0.7315
1.2464	23.0	989	1.1611	0.7329
1.3012	24.0	1032	1.1499	0.7374
1.2477	25.0	1075	1.1409	0.7404
1.2761	26.0	1118	1.1337	0.7404
1.2687	27.0	1161	1.1289	0.7404
1.2304	28.0	1204	1.1258	0.7433
1.2628	29.0	1247	1.1244	0.7433
1.2639	29.3077	1260	1.1243	0.7433