glot500-word-dropout-0.1-fr-ca

This model is a fine-tuned version of cis-lmu/glot500-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.8141
• Precision: 0.2514
• Recall: 0.1056
• F1: 0.1487
• Accuracy: 0.3548

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: 16
• eval_batch_size: 16
• 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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
2.2926	1.0	625	1.9717	0.2099	0.0805	0.1164	0.3179
1.9299	2.0	1250	1.8141	0.2514	0.1056	0.1487	0.3548

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.0
• Tokenizers 0.21.0