mT5_base

This model is a fine-tuned version of google/mt5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1703
• Bleu Score: 51.176
• Precision: 27.4791
• Recall: 27.4791
• Gen Len: 16.8805
• Err: 27.4791

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu Score	Precision	Recall	Gen Len	Err
1.3269	1.0	838	0.2396	48.4521	20.7885	20.7885	16.8339	20.7885
0.2831	2.0	1676	0.1861	50.5118	26.1649	26.1649	16.8781	26.1649
0.2167	3.0	2514	0.1703	51.176	27.4791	27.4791	16.8805	27.4791

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.0