My Finetuned Translation Model

--- library_name: transformers license: apache-2.0 base_model: google-t5/t5-small tags: - generated_from_trainer metrics: - bleu model-index: - name: my-finetuned-translation-model results: [] --- # my-finetuned-translation-model This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.6627 - Bleu: 4.8059 - Gen Len: 22.8668 ## 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: 0.0003 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:| | 3.01 | 1.0 | 10954 | 2.7994 | 4.2711 | 22.706 | | 2.9102 | 2.0 | 21908 | 2.7311 | 4.6527 | 23.5669 | | 2.8405 | 3.0 | 32862 | 2.6933 | 4.7386 | 22.7339 | | 2.8149 | 4.0 | 43816 | 2.6704 | 4.754 | 22.8787 | | 2.7975 | 5.0 | 54770 | 2.6627 | 4.8059 | 22.8668 | ### Framework versions - Transformers 4.57.1 - Pytorch 2.3.1 - Datasets 4.8.4 - Tokenizers 0.22.2