metadata
license: mit
base_model: facebook/mbart-large-50
tags:
- generated_from_trainer
model-index:
- name: pattern_model
results: []
pattern_model
This model is a fine-tuned version of facebook/mbart-large-50 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.9395
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: 1.5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.5011 | 0.1613 | 5 | 7.5987 |
| 6.3012 | 0.3226 | 10 | 5.8828 |
| 5.6098 | 0.4839 | 15 | 5.5494 |
| 5.3656 | 0.6452 | 20 | 5.3440 |
| 5.0999 | 0.8065 | 25 | 5.2776 |
| 4.9572 | 0.9677 | 30 | 5.1436 |
| 4.7974 | 1.1290 | 35 | 5.0645 |
| 4.9493 | 1.2903 | 40 | 4.9931 |
| 4.903 | 1.4516 | 45 | 4.9546 |
| 4.6146 | 1.6129 | 50 | 4.9395 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1