|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: superlative-quantifier-transformer-2 |
|
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. --> |
|
|
|
# superlative-quantifier-transformer-2 |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.8856 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 2 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- training_steps: 3052726 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.2306 | 0.03 | 76320 | 4.2201 | |
|
| 4.0253 | 1.03 | 152640 | 4.0477 | |
|
| 3.9163 | 0.03 | 228960 | 3.9724 | |
|
| 3.8489 | 0.03 | 305280 | 3.9299 | |
|
| 3.7989 | 1.03 | 381600 | 3.9039 | |
|
| 3.7564 | 0.03 | 457920 | 3.8884 | |
|
| 3.7234 | 1.03 | 534240 | 3.8788 | |
|
| 3.6968 | 0.03 | 610560 | 3.8713 | |
|
| 3.6681 | 1.03 | 686880 | 3.8674 | |
|
| 3.6431 | 0.03 | 763200 | 3.8649 | |
|
| 3.6175 | 1.03 | 839520 | 3.8633 | |
|
| 3.598 | 0.03 | 915840 | 3.8642 | |
|
| 3.583 | 0.03 | 992160 | 3.8640 | |
|
| 3.5621 | 1.03 | 1068480 | 3.8648 | |
|
| 3.547 | 0.03 | 1144800 | 3.8659 | |
|
| 3.5256 | 1.03 | 1221120 | 3.8667 | |
|
| 3.5086 | 0.03 | 1297440 | 3.8688 | |
|
| 3.495 | 1.03 | 1373760 | 3.8700 | |
|
| 3.4808 | 0.03 | 1450080 | 3.8722 | |
|
| 3.4732 | 1.03 | 1526400 | 3.8723 | |
|
| 3.4675 | 0.03 | 1602720 | 3.8748 | |
|
| 3.4571 | 0.03 | 1679040 | 3.8764 | |
|
| 3.4518 | 0.03 | 1755360 | 3.8770 | |
|
| 3.443 | 1.03 | 1831680 | 3.8785 | |
|
| 3.4294 | 0.03 | 1908000 | 3.8809 | |
|
| 3.4177 | 1.03 | 1984320 | 3.8815 | |
|
| 3.4052 | 0.03 | 2060640 | 3.8838 | |
|
| 3.3927 | 1.03 | 2136960 | 3.8837 | |
|
| 3.3877 | 0.03 | 2213280 | 3.8853 | |
|
| 3.3741 | 1.03 | 2289600 | 3.8868 | |
|
| 3.3619 | 0.03 | 2365920 | 3.8880 | |
|
| 3.3485 | 1.03 | 2442240 | 3.8876 | |
|
| 3.3367 | 0.03 | 2518560 | 3.8876 | |
|
| 3.3265 | 1.03 | 2594880 | 3.8885 | |
|
| 3.3158 | 0.03 | 2671200 | 3.8887 | |
|
| 3.3131 | 1.03 | 2747520 | 3.8890 | |
|
| 3.3081 | 0.03 | 2823840 | 3.8884 | |
|
| 3.3024 | 1.03 | 2900160 | 3.8880 | |
|
| 3.2987 | 0.03 | 2976480 | 3.8873 | |
|
| 3.2952 | 0.02 | 3052726 | 3.8856 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
