ar2enCkptfromgendata_03

This model is a fine-tuned version of Shularp/ar2enCkptfromgendata_02 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8021
• Bleu: 54.7767

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
0.1882	1.0	38	0.8021	54.7767
0.2384	2.0	76	0.8021	54.7767
0.2024	3.0	114	0.8021	54.7767
0.1823	4.0	152	0.8021	54.7767
0.2082	5.0	190	0.8021	54.7767
0.2366	6.0	228	0.8021	54.7767
0.2485	7.0	266	0.8021	54.7767
0.199	8.0	304	0.8021	54.7767
0.2307	9.0	342	0.8021	54.7767
0.2629	10.0	380	0.8021	54.7767

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3