translate_model_fixed_v0.1

This model is a fine-tuned version of gshields/translate_model_error_v0.1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.7025
• Bleu: 32.5366
• Gen Len: 17.5094

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
2.8699	1.0	505	2.7094	32.695	17.5337
2.6355	2.0	1010	2.7025	32.5366	17.5094

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.13.3