Translation-model-for-GPT-v1

This model is a fine-tuned version of Dhahlan2000/my_awesome_opus_books_model on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.5985
• Bleu: 4.5091
• Gen Len: 9.4756

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
2.9262	1.0	4571	2.6640	3.6877	9.5525
2.8337	2.0	9142	2.5985	4.5091	9.4756

Framework versions

• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1