metadata
library_name: transformers
license: mit
base_model: facebook/m2m100_418M
tags:
- generated_from_trainer
model-index:
- name: results
results: []
results
This model is a fine-tuned version of facebook/m2m100_418M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6583
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: 5e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 63 | 4.2641 |
| No log | 2.0 | 126 | 3.7198 |
| No log | 3.0 | 189 | 3.3903 |
| No log | 4.0 | 252 | 3.1066 |
| No log | 5.0 | 315 | 2.8501 |
| No log | 6.0 | 378 | 2.6187 |
| No log | 7.0 | 441 | 2.4137 |
| 3.4823 | 8.0 | 504 | 2.2344 |
| 3.4823 | 9.0 | 567 | 2.0787 |
| 3.4823 | 10.0 | 630 | 1.9493 |
| 3.4823 | 11.0 | 693 | 1.8437 |
| 3.4823 | 12.0 | 756 | 1.7626 |
| 3.4823 | 13.0 | 819 | 1.7043 |
| 3.4823 | 14.0 | 882 | 1.6700 |
| 3.4823 | 15.0 | 945 | 1.6583 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1