t5-small-finetuned-TEC-to-eng-two

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

• Loss: 1.0135
• Bleu: 47.4124
• Gen Len: 15.0625

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: 0.001
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	2	1.6435	29.1493	15.5208
No log	2.0	4	1.3090	33.8289	14.8542
No log	3.0	6	1.1451	39.7632	14.8542
No log	4.0	8	1.0720	42.4127	15.1458
No log	5.0	10	1.0381	46.3985	15.0625
No log	6.0	12	1.0210	46.9342	15.0625
No log	7.0	14	1.0135	47.4124	15.0625

Framework versions

• Transformers 4.27.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2