finetuned_byT5large_multi_joint

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: 0.6791
• Chrf++: 56.6354
• Gen Len: 119.9236

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
1.3573	1.9986	2106	0.5833	60.5302	96.9631
0.9244	3.9967	4212	0.5620	61.8526	100.4668
0.8350	5.9948	6318	0.6142	60.1184	113.8245
0.9480	7.9929	8424	0.6885	58.6951	106.4845
1.2080	9.9910	10530	0.6791	56.6354	119.9236

Framework versions

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