t5-small-finetuned-TEC-to-eng-one

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

• Loss: 1.2059
• Bleu: 42.2748
• Gen Len: 13.766

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	1.7347	29.1089	12.5745
No log	2.0	4	1.4924	33.7353	13.1489
No log	3.0	6	1.3949	34.2666	13.7447
No log	4.0	8	1.3358	37.4856	13.6383
No log	5.0	10	1.2643	39.6756	13.766
No log	6.0	12	1.2218	41.268	13.7234
No log	7.0	14	1.2059	42.2748	13.766

Framework versions

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