|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: superlative-quantifier-transformer-3 |
|
|
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-3 |
|
|
|
|
|
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: 3.8809 |
|
|
|
|
|
## 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: 3 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2274 | 0.03 | 76320 | 4.2122 | |
|
|
| 4.0217 | 1.03 | 152640 | 4.0429 | |
|
|
| 3.9138 | 0.03 | 228960 | 3.9681 | |
|
|
| 3.847 | 1.03 | 305280 | 3.9266 | |
|
|
| 3.7968 | 0.03 | 381600 | 3.9022 | |
|
|
| 3.7555 | 1.03 | 457920 | 3.8854 | |
|
|
| 3.7231 | 0.03 | 534240 | 3.8756 | |
|
|
| 3.696 | 1.03 | 610560 | 3.8691 | |
|
|
| 3.6687 | 0.03 | 686880 | 3.8645 | |
|
|
| 3.642 | 1.03 | 763200 | 3.8634 | |
|
|
| 3.6205 | 0.03 | 839520 | 3.8609 | |
|
|
| 3.5972 | 1.03 | 915840 | 3.8607 | |
|
|
| 3.5832 | 0.03 | 992160 | 3.8597 | |
|
|
| 3.564 | 0.03 | 1068480 | 3.8614 | |
|
|
| 3.5446 | 1.03 | 1144800 | 3.8617 | |
|
|
| 3.5275 | 0.03 | 1221120 | 3.8629 | |
|
|
| 3.5116 | 1.03 | 1297440 | 3.8646 | |
|
|
| 3.4951 | 0.03 | 1373760 | 3.8642 | |
|
|
| 3.4826 | 1.03 | 1450080 | 3.8669 | |
|
|
| 3.4759 | 0.03 | 1526400 | 3.8677 | |
|
|
| 3.466 | 1.03 | 1602720 | 3.8688 | |
|
|
| 3.456 | 0.03 | 1679040 | 3.8713 | |
|
|
| 3.4498 | 0.03 | 1755360 | 3.8724 | |
|
|
| 3.4418 | 1.03 | 1831680 | 3.8738 | |
|
|
| 3.4263 | 0.03 | 1908000 | 3.8743 | |
|
|
| 3.4157 | 0.03 | 1984320 | 3.8782 | |
|
|
| 3.4027 | 1.03 | 2060640 | 3.8770 | |
|
|
| 3.3903 | 0.03 | 2136960 | 3.8805 | |
|
|
| 3.3845 | 0.03 | 2213280 | 3.8793 | |
|
|
| 3.3713 | 0.03 | 2289600 | 3.8804 | |
|
|
| 3.3606 | 1.03 | 2365920 | 3.8811 | |
|
|
| 3.3478 | 0.03 | 2442240 | 3.8819 | |
|
|
| 3.3346 | 0.03 | 2518560 | 3.8828 | |
|
|
| 3.3264 | 1.03 | 2594880 | 3.8833 | |
|
|
| 3.3163 | 0.03 | 2671200 | 3.8837 | |
|
|
| 3.3109 | 0.03 | 2747520 | 3.8838 | |
|
|
| 3.3066 | 1.03 | 2823840 | 3.8829 | |
|
|
| 3.3018 | 0.03 | 2900160 | 3.8825 | |
|
|
| 3.2973 | 1.03 | 2976480 | 3.8817 | |
|
|
| 3.2935 | 0.02 | 3052726 | 3.8809 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
