crypto_sustainability_news_FacebookAI_roberta-large-mnli

This model is a fine-tuned version of FacebookAI/roberta-large-mnli on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0004
• Accuracy: 1.0

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: 32
• eval_batch_size: 32
• seed: 42
• 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
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1506	1.0	8	0.9386	0.6167
0.5328	2.0	16	0.1748	0.9833
0.0889	3.0	24	0.0116	1.0
0.0091	4.0	32	0.0030	1.0
0.0092	5.0	40	0.0014	1.0
0.0016	6.0	48	0.0010	1.0
0.0011	7.0	56	0.0008	1.0
0.001	8.0	64	0.0007	1.0
0.0009	9.0	72	0.0006	1.0
0.0008	10.0	80	0.0006	1.0
0.0007	11.0	88	0.0005	1.0
0.0007	12.0	96	0.0005	1.0
0.0006	13.0	104	0.0004	1.0
0.0006	14.0	112	0.0004	1.0
0.0006	15.0	120	0.0004	1.0
0.0006	16.0	128	0.0004	1.0
0.0006	17.0	136	0.0004	1.0
0.0005	18.0	144	0.0004	1.0
0.0005	19.0	152	0.0004	1.0
0.0005	20.0	160	0.0004	1.0

Framework versions

• Transformers 4.47.0.dev0
• Pytorch 2.4.0+cu121
• Datasets 3.0.2
• Tokenizers 0.20.0