bert-leg-al-perplexity

This model is a fine-tuned version of PlanTL-GOB-ES/RoBERTalex on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.2238

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-06
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	63	2.3119
No log	2.0	126	2.1746
No log	3.0	189	2.1621
No log	4.0	252	2.2585
No log	5.0	315	2.2080

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2