metadata

license: apache-2.0
base_model: DevAibest/opus-mt-en-fr-finetuned-en-to-fr
tags:
  - generated_from_trainer
datasets:
  - opus_books
metrics:
  - bleu
model-index:
  - name: opus-mt-finetuned-en-to-fr
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: opus_books
          type: opus_books
          config: en-fr
          split: train
          args: en-fr
        metrics:
          - name: Bleu
            type: bleu
            value: 26.9265

opus-mt-finetuned-en-to-fr

This model is a fine-tuned version of DevAibest/opus-mt-en-fr-finetuned-en-to-fr on the opus_books dataset. It achieves the following results on the evaluation set:

Loss: 1.6538
Bleu: 26.9265
Gen Len: 34.161

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	398	1.6540	26.2729	34.3078
1.764	2.0	796	1.6364	26.484	34.4081
1.6142	3.0	1194	1.6313	26.533	34.273
1.5079	4.0	1592	1.6291	26.6765	34.1672
1.5079	5.0	1990	1.6323	26.8527	34.0352
1.4218	6.0	2388	1.6314	26.8336	34.1142
1.3423	7.0	2786	1.6316	26.8037	34.2929
1.2812	8.0	3184	1.6361	26.9189	34.2471
1.2421	9.0	3582	1.6369	26.9398	34.2674
1.2421	10.0	3980	1.6413	26.9029	34.2462
1.1991	11.0	4378	1.6445	26.9221	34.1811
1.1562	12.0	4776	1.6495	26.8817	34.249
1.1392	13.0	5174	1.6517	26.8928	34.1777
1.1194	14.0	5572	1.6531	26.8547	34.2342
1.1194	15.0	5970	1.6538	26.9265	34.161

Framework versions

Transformers 4.33.0
Pytorch 2.0.0
Datasets 2.1.0
Tokenizers 0.13.3