lab2_adam

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-fr on the kde4 dataset. It achieves the following results on the evaluation set:

• Loss: 1.3674
• Bleu: 43.9529

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: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 0.1
• training_steps: 100

Training results

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 3.6.0
• Tokenizers 0.22.2