nmt_T5_tr_en_only_random

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

• Loss: 3.3747
• Bleu: 1.2398
• Gen Len: 17.2055

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
3.1088	1.0	25000	3.4158	1.2151	17.0938
2.9552	2.0	50000	3.3891	1.1851	17.1034
2.9321	3.0	75000	3.3747	1.2398	17.2055

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu118
• Datasets 2.4.0
• Tokenizers 0.19.1