OSainz/mdt-ie-ner-baseline

tmp

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

• Loss: 0.6486
• Precision: 0.6540
• Recall: 0.6944
• F1: 0.6736

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
No log	1.0	38	0.7892	0.5800	0.6787	0.6255
No log	2.0	76	0.5906	0.7267	0.7540	0.7401
No log	3.0	114	0.5466	0.7219	0.7771	0.7485
No log	4.0	152	0.5249	0.7266	0.7623	0.7440
No log	5.0	190	0.5261	0.7228	0.7674	0.7445

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2