metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: MTL-distilbert-base-uncased
results: []
MTL-distilbert-base-uncased
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3718
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: 15
- eval_batch_size: 15
- 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 |
|---|---|---|---|
| 3.1225 | 1.0 | 50 | 2.7381 |
| 2.7945 | 2.0 | 100 | 2.6858 |
| 2.7162 | 3.0 | 150 | 2.5329 |
| 2.6526 | 4.0 | 200 | 2.5430 |
| 2.5863 | 5.0 | 250 | 2.4785 |
| 2.5701 | 6.0 | 300 | 2.4415 |
| 2.5362 | 7.0 | 350 | 2.4678 |
| 2.4961 | 8.0 | 400 | 2.4571 |
| 2.4842 | 9.0 | 450 | 2.3915 |
| 2.4697 | 10.0 | 500 | 2.4644 |
| 2.4407 | 11.0 | 550 | 2.3628 |
| 2.4264 | 12.0 | 600 | 2.4008 |
| 2.4321 | 13.0 | 650 | 2.3672 |
| 2.4169 | 14.0 | 700 | 2.3586 |
| 2.4056 | 15.0 | 750 | 2.3705 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.11.0