|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: superlative-quantifier-transformer-4 |
|
|
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-4 |
|
|
|
|
|
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: 3.8820 |
|
|
|
|
|
## 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: 4 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2348 | 0.03 | 76320 | 4.2210 | |
|
|
| 4.0286 | 1.03 | 152640 | 4.0483 | |
|
|
| 3.9187 | 0.03 | 228960 | 3.9727 | |
|
|
| 3.8523 | 1.03 | 305280 | 3.9304 | |
|
|
| 3.8009 | 0.03 | 381600 | 3.9063 | |
|
|
| 3.7572 | 1.03 | 457920 | 3.8901 | |
|
|
| 3.7252 | 0.03 | 534240 | 3.8802 | |
|
|
| 3.699 | 1.03 | 610560 | 3.8724 | |
|
|
| 3.6697 | 0.03 | 686880 | 3.8685 | |
|
|
| 3.6434 | 1.03 | 763200 | 3.8662 | |
|
|
| 3.6209 | 0.03 | 839520 | 3.8650 | |
|
|
| 3.5995 | 1.03 | 915840 | 3.8636 | |
|
|
| 3.5856 | 0.03 | 992160 | 3.8644 | |
|
|
| 3.5649 | 1.03 | 1068480 | 3.8665 | |
|
|
| 3.5473 | 0.03 | 1144800 | 3.8657 | |
|
|
| 3.5272 | 1.03 | 1221120 | 3.8663 | |
|
|
| 3.5108 | 0.03 | 1297440 | 3.8679 | |
|
|
| 3.4989 | 1.03 | 1373760 | 3.8709 | |
|
|
| 3.4833 | 0.03 | 1450080 | 3.8700 | |
|
|
| 3.4754 | 0.03 | 1526400 | 3.8715 | |
|
|
| 3.4681 | 0.03 | 1602720 | 3.8735 | |
|
|
| 3.4584 | 0.03 | 1679040 | 3.8749 | |
|
|
| 3.4535 | 1.03 | 1755360 | 3.8758 | |
|
|
| 3.4454 | 0.03 | 1831680 | 3.8766 | |
|
|
| 3.4314 | 1.03 | 1908000 | 3.8790 | |
|
|
| 3.4185 | 0.03 | 1984320 | 3.8803 | |
|
|
| 3.4063 | 1.03 | 2060640 | 3.8815 | |
|
|
| 3.3941 | 0.03 | 2136960 | 3.8821 | |
|
|
| 3.3885 | 1.03 | 2213280 | 3.8828 | |
|
|
| 3.376 | 0.03 | 2289600 | 3.8842 | |
|
|
| 3.3645 | 1.03 | 2365920 | 3.8849 | |
|
|
| 3.3497 | 0.03 | 2442240 | 3.8856 | |
|
|
| 3.3365 | 1.03 | 2518560 | 3.8861 | |
|
|
| 3.3274 | 0.03 | 2594880 | 3.8878 | |
|
|
| 3.3183 | 0.03 | 2671200 | 3.8866 | |
|
|
| 3.3131 | 1.03 | 2747520 | 3.8866 | |
|
|
| 3.3081 | 0.03 | 2823840 | 3.8856 | |
|
|
| 3.3014 | 1.03 | 2900160 | 3.8849 | |
|
|
| 3.2993 | 0.03 | 2976480 | 3.8835 | |
|
|
| 3.2969 | 1.02 | 3052726 | 3.8820 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
