translate_mod

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2082
• Bleu: 18.6765
• Gen Len: 16.663

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.2509	1.0	4434	0.2305	15.2399	16.7113
0.239	2.0	8868	0.2172	17.8217	16.6523
0.2288	3.0	13302	0.2118	18.4048	16.6511
0.2273	4.0	17736	0.2090	18.2961	16.6802
0.2225	5.0	22170	0.2082	18.6765	16.663

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1