m2m100-lg-to-en-v2

This model is a fine-tuned version of facebook/m2m100_418M on the None dataset. It achieves the following results on the evaluation set:

• Loss: 11.5952

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: 1e-08
• 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: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
12.3804	1.0	119	12.6272
12.389	2.0	238	12.5538
12.3486	3.0	357	12.4810
12.3239	4.0	476	12.4177
12.2828	5.0	595	12.1366
12.0986	6.0	714	12.0700
12.0733	7.0	833	12.0214
12.0746	8.0	952	11.9687
12.0377	9.0	1071	11.9397
12.0163	10.0	1190	11.9031
11.95	11.0	1309	11.8120
11.9303	12.0	1428	11.7297
11.8673	13.0	1547	11.6198
11.8117	14.0	1666	11.5958
11.7915	15.0	1785	11.5952

Framework versions

• Transformers 4.41.1
• Pytorch 2.1.2
• Datasets 2.19.1
• Tokenizers 0.19.1