opus-mt-en-bkm-10e32

This model is a fine-tuned version of kalese/opus-mt-en-bkm on the arrow dataset. It achieves the following results on the evaluation set:

• Loss: 0.5341
• Bleu: 32.9859
• Gen Len: 59.4587

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: 32
• eval_batch_size: 32
• 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	Gen Len
0.6836	1.0	557	0.5107	34.8746	59.0061
0.6574	2.0	1114	0.5185	34.148	59.4474
0.635	3.0	1671	0.5243	33.7365	59.0982
0.6196	4.0	2228	0.5271	33.4739	59.0476
0.6032	5.0	2785	0.5302	33.1361	59.1885
0.5942	6.0	3342	0.5329	33.2175	59.511
0.5794	7.0	3899	0.5345	32.8581	59.3146
0.5671	8.0	4456	0.5344	33.0341	59.4416
0.5532	9.0	5013	0.5340	32.8106	59.42
0.5494	10.0	5570	0.5341	32.9859	59.4587

Framework versions

• Transformers 4.39.1
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2