m2m100_418M-finetuned-tq-to-ar-1-2

This model is a fine-tuned version of ad019el/m2m100_418M-finetuned-tq-to-ar-only-clean-data on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.3123
• Bleu: 3.2398
• Gen Len: 39.2562

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: 5e-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
2.3145	0.68	500	2.2961	3.5196	39.7015
2.2469	1.36	1000	2.2789	3.1373	42.5945
2.1915	2.05	1500	2.3092	3.3981	41.4192
2.1358	2.73	2000	2.3077	3.2268	41.8321
2.0879	3.41	2500	2.3123	3.2398	39.2562

Framework versions

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