fine-tuned-NLI-mnli_original-with-roberta-large

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

• Loss: 0.3381
• Accuracy: 0.9053
• F1: 0.9056

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.3302	0.4997	1533	0.2972	0.8940	0.8934
0.3139	0.9993	3066	0.2751	0.9027	0.9030
0.242	1.4990	4599	0.2866	0.9030	0.9030
0.2627	1.9987	6132	0.2921	0.9065	0.9066
0.1818	2.4984	7665	0.3049	0.9035	0.9038
0.1932	2.9980	9198	0.3153	0.9039	0.9038
0.1457	3.4977	10731	0.3381	0.9053	0.9056

Framework versions

• Transformers 4.42.3
• Pytorch 1.13.1+cu117
• Datasets 2.2.0
• Tokenizers 0.19.1