roberta-ivrmenu-entity

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

• Loss: nan
• Precision: 0.8282
• Recall: 0.8911
• F1: 0.8585
• Accuracy: 0.9345

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: 0.0001
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• 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	Precision	Recall	F1	Accuracy
No log	1.0	2	nan	0.9036	0.4950	0.6397	0.6503
No log	2.0	4	nan	0.5952	0.5776	0.5863	0.7387
No log	3.0	6	nan	0.7124	0.7030	0.7076	0.8232
No log	4.0	8	nan	0.6879	0.7492	0.7172	0.8402
No log	5.0	10	nan	0.7333	0.7987	0.7646	0.8880
No log	6.0	12	nan	0.7462	0.8152	0.7792	0.9044
No log	7.0	14	nan	0.7761	0.8350	0.8045	0.9142
No log	8.0	16	nan	0.8145	0.8548	0.8341	0.9247
No log	9.0	18	nan	0.8185	0.8779	0.8471	0.9306
No log	10.0	20	nan	0.8282	0.8911	0.8585	0.9345

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu117
• Datasets 2.12.0
• Tokenizers 0.12.1