m2m100_418M-finetuned-tq-to-ar

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.4806
• Bleu: 3.5687
• Gen Len: 37.0213

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-06
• 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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
2.0921	0.71	500	2.4668	3.4363	37.5629
2.2662	1.42	1000	2.4560	3.4209	37.3412
2.2529	2.13	1500	2.4655	3.3428	36.7942
2.2298	2.84	2000	2.4653	3.1674	38.6119
2.2172	3.56	2500	2.4806	3.5687	37.0213

Framework versions

• Transformers 4.32.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3