finetuned_byT5large_multi

This model is a fine-tuned version of google/byt5-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7354
• Chrf++: 55.9688
• Gen Len: 132.9647

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: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• 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: 13

Training results

Training Loss	Epoch	Step	Validation Loss	Chrf++	Gen Len
1.4718	1.9986	2106	0.5570	60.5937	107.8111
0.9825	3.9967	4212	0.6283	60.2458	112.5978
0.9172	5.9948	6318	0.6607	59.3436	116.7028
0.8266	7.9929	8424	0.7354	55.9688	132.9647

Framework versions

• Transformers 5.5.0
• Pytorch 2.11.0+cu130
• Datasets 4.3.0
• Tokenizers 0.22.2