metadata
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: easyword-model-peft-distilled-1.3B
results: []
easyword-model-peft-distilled-1.3B
This model is a fine-tuned version of facebook/nllb-200-distilled-1.3B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.4596
- Bleu: 2.6322
- Gen Len: 5.8199
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 31 | 4.9810 | 0.0 | 9.4099 |
| No log | 2.0 | 62 | 4.4936 | 0.0 | 8.7516 |
| No log | 3.0 | 93 | 4.0142 | 1.017 | 7.1801 |
| No log | 4.0 | 124 | 3.6795 | 1.7949 | 6.2733 |
| No log | 5.0 | 155 | 3.5729 | 2.5943 | 5.9255 |
| No log | 6.0 | 186 | 3.5270 | 2.6178 | 5.882 |
| No log | 7.0 | 217 | 3.4960 | 2.92 | 5.8075 |
| No log | 8.0 | 248 | 3.4751 | 2.6168 | 5.8447 |
| No log | 9.0 | 279 | 3.4634 | 2.6063 | 5.8385 |
| No log | 10.0 | 310 | 3.4596 | 2.6322 | 5.8199 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3