TisaleoRuta

This model is a fine-tuned version of IAMRS23/TisaleoRuta on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000
• Perplexity: 2214.4521

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 8
• 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
• lr_scheduler_warmup_steps: 500
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Perplexity
2.4572	1.0	100	0.5378	2105.8848
0.1479	2.0	200	0.0013	2214.4521
0.0031	3.0	300	0.0003	2214.4521
0.0012	4.0	400	0.0001	2214.4521
0.0006	5.0	500	0.0001	2214.4521
0.0004	6.0	600	0.0000	2214.4521
0.0003	7.0	700	0.0000	2214.4521
0.0002	8.0	800	0.0000	2214.4521
0.0002	9.0	900	0.0000	2214.4521
0.0002	10.0	1000	0.0000	2214.4521

Framework versions

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