metadata
tags:
- generated_from_trainer
model-index:
- name: Bert-MLM
results: []
Bert-MLM
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 7.7544
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-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.02 | 50 | 9.3840 |
| 9.3687 | 0.03 | 100 | 8.6014 |
| 9.3687 | 0.05 | 150 | 8.2440 |
| 8.0254 | 0.06 | 200 | 8.0843 |
| 8.0254 | 0.08 | 250 | 8.0234 |
| 7.8649 | 0.09 | 300 | 7.9828 |
| 7.8649 | 0.11 | 350 | 7.9550 |
| 7.732 | 0.12 | 400 | 7.9101 |
| 7.732 | 0.14 | 450 | 7.8946 |
| 7.6192 | 0.15 | 500 | 7.8525 |
| 7.6192 | 0.17 | 550 | 7.8461 |
| 7.6378 | 0.18 | 600 | 7.8285 |
| 7.6378 | 0.2 | 650 | 7.8182 |
| 7.6338 | 0.22 | 700 | 7.7917 |
| 7.6338 | 0.23 | 750 | nan |
| 7.5994 | 0.25 | 800 | 7.7837 |
| 7.5994 | 0.26 | 850 | 7.7596 |
| 7.5323 | 0.28 | 900 | 7.7634 |
| 7.5323 | 0.29 | 950 | 7.7750 |
| 7.5914 | 0.31 | 1000 | 7.7544 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.0
- Tokenizers 0.15.0