bert-multilingual-finetuned-xtreme-tamil-ner

This model is a fine-tuned version of bert-base-multilingual-uncased on the xtreme dataset. It achieves the following results on the evaluation set:

• Loss: 0.2338
• Precision: 0.7463
• Recall: 0.8197
• F1: 0.7813
• Accuracy: 0.9236

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: 2e-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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.3899	1.0	469	0.2517	0.6893	0.7893	0.7360	0.9143
0.2093	2.0	938	0.2338	0.7463	0.8197	0.7813	0.9236

Framework versions

• Transformers 4.22.1
• Pytorch 1.12.1+cu113
• Datasets 2.4.0
• Tokenizers 0.12.1