|
--- |
|
license: apache-2.0 |
|
base_model: bert-large-uncased-whole-word-masking |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: pictalk |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# pictalk |
|
|
|
This model is a fine-tuned version of [bert-large-uncased-whole-word-masking](https://huggingface.co/bert-large-uncased-whole-word-masking) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.5286 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 128 |
|
- eval_batch_size: 128 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 50 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 3.2507 | 1.0 | 25 | 2.7433 | |
|
| 2.518 | 2.0 | 50 | 2.2772 | |
|
| 2.323 | 3.0 | 75 | 2.0185 | |
|
| 2.0883 | 4.0 | 100 | 1.9731 | |
|
| 1.8835 | 5.0 | 125 | 1.9086 | |
|
| 1.8641 | 6.0 | 150 | 1.7880 | |
|
| 1.7244 | 7.0 | 175 | 1.7763 | |
|
| 1.7395 | 8.0 | 200 | 1.7191 | |
|
| 1.6834 | 9.0 | 225 | 1.6734 | |
|
| 1.6631 | 10.0 | 250 | 1.6970 | |
|
| 1.5764 | 11.0 | 275 | 1.6939 | |
|
| 1.54 | 12.0 | 300 | 1.6576 | |
|
| 1.5205 | 13.0 | 325 | 1.5530 | |
|
| 1.4832 | 14.0 | 350 | 1.5448 | |
|
| 1.4582 | 15.0 | 375 | 1.6000 | |
|
| 1.418 | 16.0 | 400 | 1.5240 | |
|
| 1.4152 | 17.0 | 425 | 1.5330 | |
|
| 1.3529 | 18.0 | 450 | 1.5850 | |
|
| 1.3886 | 19.0 | 475 | 1.4814 | |
|
| 1.3268 | 20.0 | 500 | 1.6087 | |
|
| 1.2914 | 21.0 | 525 | 1.5714 | |
|
| 1.3431 | 22.0 | 550 | 1.4989 | |
|
| 1.2838 | 23.0 | 575 | 1.5934 | |
|
| 1.2943 | 24.0 | 600 | 1.4751 | |
|
| 1.2704 | 25.0 | 625 | 1.5158 | |
|
| 1.284 | 26.0 | 650 | 1.6148 | |
|
| 1.2148 | 27.0 | 675 | 1.4828 | |
|
| 1.2382 | 28.0 | 700 | 1.4890 | |
|
| 1.1684 | 29.0 | 725 | 1.5531 | |
|
| 1.2053 | 30.0 | 750 | 1.4755 | |
|
| 1.1973 | 31.0 | 775 | 1.4426 | |
|
| 1.2127 | 32.0 | 800 | 1.5464 | |
|
| 1.1802 | 33.0 | 825 | 1.4410 | |
|
| 1.1828 | 34.0 | 850 | 1.5026 | |
|
| 1.1338 | 35.0 | 875 | 1.5691 | |
|
| 1.11 | 36.0 | 900 | 1.5073 | |
|
| 1.1456 | 37.0 | 925 | 1.5055 | |
|
| 1.1253 | 38.0 | 950 | 1.5108 | |
|
| 1.1214 | 39.0 | 975 | 1.4563 | |
|
| 1.1654 | 40.0 | 1000 | 1.5881 | |
|
| 1.0921 | 41.0 | 1025 | 1.4060 | |
|
| 1.1087 | 42.0 | 1050 | 1.4952 | |
|
| 1.0824 | 43.0 | 1075 | 1.5512 | |
|
| 1.1127 | 44.0 | 1100 | 1.5481 | |
|
| 1.0994 | 45.0 | 1125 | 1.5692 | |
|
| 1.0579 | 46.0 | 1150 | 1.4802 | |
|
| 1.1006 | 47.0 | 1175 | 1.5585 | |
|
| 1.0692 | 48.0 | 1200 | 1.4303 | |
|
| 1.1131 | 49.0 | 1225 | 1.5129 | |
|
| 1.0943 | 50.0 | 1250 | 1.5286 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
