translation_slo_eng_opus-mt-sla-en_loha

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

• Loss: 2.6782
• Bleu: 34.6439
• Gen Len: 12.7435

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
• training_steps: 400
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
2.8661	0.01	50	2.7221	34.6147	12.741
2.8564	0.02	100	2.7133	34.6112	12.7457
3.028	0.03	150	2.7043	34.6086	12.7529
2.8351	0.04	200	2.6960	34.612	12.7535
2.8428	0.05	250	2.6886	34.6251	12.7459
2.9846	0.06	300	2.6830	34.6364	12.7426
2.8809	0.07	350	2.6796	34.6433	12.7407
2.9782	0.08	400	2.6782	34.6439	12.7435

Framework versions

• PEFT 0.10.1.dev0
• Transformers 4.40.1
• Pytorch 2.1.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1