metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: bert-base-uncased-finetuned-vi-infovqa
results: []
bert-base-uncased-finetuned-vi-infovqa
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 13.9895
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: 4
- eval_batch_size: 4
- seed: 250500
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.3635 | 1.07 | 500 | 4.5286 |
| 3.8961 | 2.13 | 1000 | 4.4055 |
| 3.3012 | 3.2 | 1500 | 5.0429 |
| 2.5998 | 4.26 | 2000 | 5.4774 |
| 1.8851 | 5.33 | 2500 | 6.4376 |
| 1.3968 | 6.4 | 3000 | 6.8778 |
| 1.1244 | 7.46 | 3500 | 7.1008 |
| 0.8851 | 8.53 | 4000 | 6.8303 |
| 0.7654 | 9.59 | 4500 | 8.6628 |
| 0.6895 | 10.66 | 5000 | 6.0228 |
| 0.5989 | 11.73 | 5500 | 8.8191 |
| 0.6033 | 12.79 | 6000 | 9.7359 |
| 0.6005 | 13.86 | 6500 | 7.6668 |
| 0.522 | 14.93 | 7000 | 8.7185 |
| 0.464 | 15.99 | 7500 | 10.1035 |
| 0.4112 | 17.06 | 8000 | 8.7928 |
| 0.3501 | 18.12 | 8500 | 9.9157 |
| 0.3401 | 19.19 | 9000 | 12.1013 |
| 0.3233 | 20.26 | 9500 | 10.2730 |
| 0.2513 | 21.32 | 10000 | 8.4839 |
| 0.2319 | 22.39 | 10500 | 10.9367 |
| 0.2269 | 23.45 | 11000 | 9.6821 |
| 0.237 | 24.52 | 11500 | 10.2357 |
| 0.1868 | 25.59 | 12000 | 9.8762 |
| 0.1655 | 26.65 | 12500 | 10.7398 |
| 0.1561 | 27.72 | 13000 | 11.8157 |
| 0.1714 | 28.78 | 13500 | 10.8686 |
| 0.1098 | 29.85 | 14000 | 13.1537 |
| 0.1222 | 30.92 | 14500 | 14.5398 |
| 0.1325 | 31.98 | 15000 | 12.6095 |
| 0.1088 | 33.05 | 15500 | 12.0747 |
| 0.0855 | 34.12 | 16000 | 12.4450 |
| 0.0832 | 35.18 | 16500 | 12.9436 |
| 0.0687 | 36.25 | 17000 | 12.5902 |
| 0.0804 | 37.31 | 17500 | 11.9873 |
| 0.0427 | 38.38 | 18000 | 12.6357 |
| 0.0529 | 39.45 | 18500 | 11.5851 |
| 0.0478 | 40.51 | 19000 | 13.1796 |
| 0.0513 | 41.58 | 19500 | 13.8597 |
| 0.0449 | 42.64 | 20000 | 13.6467 |
| 0.0327 | 43.71 | 20500 | 13.0391 |
| 0.0329 | 44.78 | 21000 | 13.1984 |
| 0.0266 | 45.84 | 21500 | 13.9690 |
| 0.0301 | 46.91 | 22000 | 13.9516 |
| 0.0193 | 47.97 | 22500 | 13.9104 |
| 0.0273 | 49.04 | 23000 | 13.9895 |
Framework versions
- Transformers 4.14.1
- Pytorch 1.10.0+cu111
- Datasets 1.16.1
- Tokenizers 0.10.3