opus-mt-en-ar-evaluated-en-to-ar-1000instances-un_multi-leaningRate2e-05-batchSize8-11-action-1

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

• Loss: 0.1294
• Bleu: 64.0048
• Meteor: 0.4903
• Gen Len: 21.85

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: 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: 11

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Meteor	Gen Len
0.0489	1.0	100	0.1287	63.7573	0.4877	21.79
0.0447	2.0	200	0.1293	63.8776	0.49	21.875
0.0442	3.0	300	0.1294	64.0048	0.4903	21.85
0.0433	4.0	400	0.1294	64.0048	0.4903	21.85
0.0429	5.0	500	0.1294	64.0048	0.4903	21.85
0.0435	6.0	600	0.1294	64.0048	0.4903	21.85
0.0429	7.0	700	0.1294	64.0048	0.4903	21.85
0.0426	8.0	800	0.1294	64.0048	0.4903	21.85

Framework versions

• Transformers 4.18.0
• Pytorch 1.11.0
• Datasets 2.1.0
• Tokenizers 0.12.1