gs-aristoBERTo

This model is a fine-tuned version of Jacobo/aristoBERTo on MAAT corpus. It achieves the following results on the evaluation set:

• Loss: 2.1094

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: 4
• eval_batch_size: 4
• 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: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.1329	1.0	2726	2.7255
2.6399	2.0	5452	2.5283
2.4392	3.0	8178	2.4309
2.2819	4.0	10904	2.2972
2.179	5.0	13630	2.2721
2.0791	6.0	16356	2.2173
2.0095	7.0	19082	2.1580
1.9416	8.0	21808	2.1574
1.8792	9.0	24534	2.0896
1.8555	10.0	27260	2.0767

Framework versions

• Transformers 4.50.0
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1