metadata

license: cc-by-nc-4.0
base_model: nadsoft/Faseeh-v0.1-beta
tags:
  - generated_from_trainer
model-index:
  - name: darija-to-english-2
    results: []

darija-to-english-2

This model is a fine-tuned version of nadsoft/Faseeh-v0.1-beta on the None dataset. It achieves the following results on the evaluation set:

eval_loss: 0.6560
eval_bleu: 71.4028
eval_gen_len: 32.4743
eval_runtime: 2284.4559
eval_samples_per_second: 8.271
eval_steps_per_second: 1.034
epoch: 4.0
step: 37792

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: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Framework versions

Transformers 4.37.2
Pytorch 2.2.0+cu121
Datasets 2.17.0
Tokenizers 0.15.1