results

This model is a fine-tuned version of google/mt5-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5622
• Loc: {'precision': 0.9222857142857143, 'recall': 0.9449648711943794, 'f1': 0.9334875650665124, 'number': 854}
• Org: {'precision': 0.8973561430793157, 'recall': 0.8876923076923077, 'f1': 0.8924980665119876, 'number': 650}
• Per: {'precision': 0.9014373716632443, 'recall': 0.9440860215053763, 'f1': 0.9222689075630252, 'number': 465}
• Overall Precision: 0.9092
• Overall Recall: 0.9259
• Overall F1: 0.9175
• Overall Accuracy: 0.9582

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Loc	Org	Per	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.1729	10.0	5000	0.4248	{'precision': 0.9111361079865017, 'recall': 0.9484777517564403, 'f1': 0.9294320137693631, 'number': 854}	{'precision': 0.9027113237639554, 'recall': 0.8707692307692307, 'f1': 0.8864526233359435, 'number': 650}	{'precision': 0.9010309278350516, 'recall': 0.9397849462365592, 'f1': 0.92, 'number': 465}	0.9060	0.9208	0.9134	0.9584
0.0068	20.0	10000	0.5622	{'precision': 0.9222857142857143, 'recall': 0.9449648711943794, 'f1': 0.9334875650665124, 'number': 854}	{'precision': 0.8973561430793157, 'recall': 0.8876923076923077, 'f1': 0.8924980665119876, 'number': 650}	{'precision': 0.9014373716632443, 'recall': 0.9440860215053763, 'f1': 0.9222689075630252, 'number': 465}	0.9092	0.9259	0.9175	0.9582

Framework versions

• Transformers 4.39.3
• Pytorch 1.11.0a0+17540c5
• Datasets 2.20.0
• Tokenizers 0.15.2