t5-small-finetuned-welsh-breton-kernewek

This model is a fine-tuned version of Jendersen/t5-small-finetuned-welsh-breton-kernewek on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7294
• Rouge1: 28.5495
• Rouge2: 16.4098
• Rougel: 27.3406
• Rougelsum: 27.424
• Bleu: 0.0206
• Chrf++: 16.7248
• F1: 44.5459
• Gen Len: 18.9918

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bleu	Chrf++	F1	Gen Len
0.8844	1.0	5853	0.7346	28.4424	16.3267	27.2378	27.3239	0.0205	16.6707	44.4736	18.9933
0.8800	2.0	11706	0.7330	28.5017	16.3618	27.2933	27.3794	0.0206	16.6938	44.5045	18.9931
0.8745	3.0	17559	0.7316	28.5504	16.3976	27.3458	27.4307	0.0206	16.7286	44.5385	18.9924
0.8668	4.0	23412	0.7294	28.5378	16.3979	27.3302	27.4156	0.0206	16.72	44.5359	18.9935
0.8632	5.0	29265	0.7294	28.5495	16.4098	27.3406	27.424	0.0206	16.7248	44.5459	18.9918

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2