roberta-base_bedtype

This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3227
• Accuracy: 0.7667

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 27
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.5213	1.67	10	1.5302	0.3
1.0298	3.33	20	1.3052	0.4667
0.8736	5.0	30	1.3569	0.5
0.5861	6.67	40	1.1600	0.5333
0.3691	8.33	50	1.0009	0.6
0.1836	10.0	60	1.3470	0.5667
0.1459	11.67	70	0.8977	0.7667
0.0572	13.33	80	1.2357	0.6667
0.0331	15.0	90	1.0230	0.7667
0.0108	16.67	100	1.1812	0.7333
0.0077	18.33	110	1.1969	0.7333
0.0053	20.0	120	1.0829	0.7667
0.0043	21.67	130	1.0876	0.7333
0.0037	23.33	140	1.2074	0.7667
0.003	25.0	150	1.2255	0.7667
0.0028	26.67	160	1.2475	0.7667
0.0026	28.33	170	1.2703	0.7667
0.0024	30.0	180	1.2863	0.7667
0.0023	31.67	190	1.2981	0.7667
0.0022	33.33	200	1.3081	0.7667
0.0022	35.0	210	1.3149	0.7667
0.0021	36.67	220	1.3192	0.7667
0.0021	38.33	230	1.3217	0.7667
0.0021	40.0	240	1.3227	0.7667

Framework versions

• Transformers 4.39.1
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2