metadata
license: cc-by-nc-4.0
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: greek-nllb-5ep-384
results: []
greek-nllb-4ep-384
This model is a fine-tuned version of facebook/nllb-200-distilled-600M on the squad dataset. It achieves the following results on the evaluation set:
- Loss: 1.2837
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2156 | 0.17 | 100 | 1.5542 |
| 1.7147 | 0.34 | 200 | 1.4823 |
| 1.5438 | 0.51 | 300 | 1.4377 |
| 1.5006 | 0.67 | 400 | 1.3997 |
| 1.4573 | 0.84 | 500 | 1.3753 |
| 1.4484 | 1.01 | 600 | 1.3596 |
| 1.3177 | 1.18 | 700 | 1.3491 |
| 1.2981 | 1.35 | 800 | 1.3432 |
| 1.2977 | 1.52 | 900 | 1.3346 |
| 1.2898 | 1.69 | 1000 | 1.3183 |
| 1.2964 | 1.86 | 1100 | 1.3114 |
| 1.2480 | 2.03 | 1200 | 1.3176 |
| 1.1766 | 2.2 | 1300 | 1.3019 |
| 1.1779 | 2.36 | 1400 | 1.3076 |
| 1.1770 | 2.53 | 1500 | 1.2968 |
| 1.1793 | 2.7 | 1600 | 1.2967 |
| 1.1721 | 2.87 | 1700 | 1.2879 |
| 1.1593 | 3.04 | 1800 | 1.2964 |
| 1.0904 | 3.21 | 1900 | 1.2948 |
| 1.1110 | 3.38 | 2000 | 1.2885 |
| 1.0947 | 3.55 | 2100 | 1.2885 |
| 1.0936 | 3.72 | 2200 | 1.2872 |
| 1.0875 | 4.05 | 2300 | 1.2823 |
| 1.0875 | 4.22 | 2400 | 1.2904 |
| 1.0875 | 4.39 | 2500 | 1.2875 |
| 1.0875 | 4.56 | 2600 | 1.2888 |
| 1.0875 | 4.73 | 2700 | 1.2865 |
| 1.0875 | 4.89 | 2800 | 1.2861 |
| 1.0875 | 5.00 | 2900 | 1.2837 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2