metadata

license: mit
base_model: facebook/m2m100_1.2B
tags:
  - translation
  - generated_from_trainer
datasets:
  - wmt16
metrics:
  - bleu
model-index:
  - name: m2m100_1.2B
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: wmt16
          type: wmt16
          config: ru-en
          split: validation
          args: ru-en
        metrics:
          - name: Bleu
            type: bleu
            value: 33.3632

m2m100_1.2B

This model is a fine-tuned version of facebook/m2m100_1.2B on the wmt16 dataset. It achieves the following results on the evaluation set:

Loss: 0.8189
Bleu: 33.3632
Gen Len: 36.176

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: 4
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 10
total_train_batch_size: 40
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.7163	1.0	47790	0.8189	33.3632	36.176

Framework versions

Transformers 4.34.0
Pytorch 2.0.1
Datasets 2.14.5
Tokenizers 0.14.1