README.md

metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - dataset
metrics:
  - bleu
model-index:
  - name: m2m100_418M-test
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: dataset
          type: dataset
          config: uptycs
          split: train
          args: uptycs
        metrics:
          - name: Bleu
            type: bleu
            value: 29.9962

m2m100_418M-test

This model is a fine-tuned version of facebook/m2m100_418M on the dataset dataset. It achieves the following results on the evaluation set:

• Loss: 0.9953
• Bleu: 29.9962
• Gen Len: 41.6441

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: 0.0001
• 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
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.3804	1.0	1267	0.9953	29.9962	41.6441

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.1+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2