m2m100_pruned_ta-freeze100-finetuned-mcsw-to-en-smallmcswbitext
This model is a fine-tuned version of Elaine/m2m100_pruned_ta on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7877
- Bleu: 31.7539
- Gen Len: 27.4
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.4228 | 0.8 | 2500 | 1.7877 | 31.7539 | 27.4 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3