|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: existential-there-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. --> |
|
|
|
|
|
# existential-there-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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2526 | 0.03 | 76320 | 4.2151 | |
|
|
| 4.0455 | 1.03 | 152640 | 4.0461 | |
|
|
| 3.9381 | 0.03 | 228960 | 3.9721 | |
|
|
| 3.8628 | 1.03 | 305280 | 3.9311 | |
|
|
| 3.8124 | 0.03 | 381600 | 3.9065 | |
|
|
| 3.7715 | 1.03 | 457920 | 3.8904 | |
|
|
| 3.7381 | 0.03 | 534240 | 3.8783 | |
|
|
| 3.7124 | 1.03 | 610560 | 3.8721 | |
|
|
| 3.683 | 0.03 | 686880 | 3.8683 | |
|
|
| 3.6615 | 1.03 | 763200 | 3.8654 | |
|
|
| 3.6385 | 0.03 | 839520 | 3.8646 | |
|
|
| 3.616 | 1.03 | 915840 | 3.8642 | |
|
|
| 3.5965 | 0.03 | 992160 | 3.8636 | |
|
|
| 3.578 | 1.03 | 1068480 | 3.8644 | |
|
|
| 3.5575 | 0.03 | 1144800 | 3.8644 | |
|
|
| 3.5489 | 1.03 | 1221120 | 3.8660 | |
|
|
| 3.5313 | 0.03 | 1297440 | 3.8666 | |
|
|
| 3.5161 | 0.03 | 1373760 | 3.8675 | |
|
|
| 3.5035 | 1.03 | 1450080 | 3.8687 | |
|
|
| 3.4905 | 0.03 | 1526400 | 3.8709 | |
|
|
| 3.4821 | 0.03 | 1602720 | 3.8735 | |
|
|
| 3.472 | 1.03 | 1679040 | 3.8752 | |
|
|
| 3.4657 | 0.03 | 1755360 | 3.8762 | |
|
|
| 3.4571 | 0.03 | 1831680 | 3.8779 | |
|
|
| 3.4455 | 1.03 | 1908000 | 3.8795 | |
|
|
| 3.4391 | 0.03 | 1984320 | 3.8816 | |
|
|
| 3.4253 | 1.03 | 2060640 | 3.8817 | |
|
|
| 3.4134 | 0.03 | 2136960 | 3.8836 | |
|
|
| 3.4028 | 1.03 | 2213280 | 3.8853 | |
|
|
| 3.3929 | 0.03 | 2289600 | 3.8861 | |
|
|
| 3.3786 | 1.03 | 2365920 | 3.8866 | |
|
|
| 3.3717 | 0.03 | 2442240 | 3.8879 | |
|
|
| 3.3586 | 1.03 | 2518560 | 3.8886 | |
|
|
| 3.3484 | 0.03 | 2594880 | 3.8890 | |
|
|
| 3.34 | 1.03 | 2671200 | 3.8896 | |
|
|
| 3.3287 | 0.03 | 2747520 | 3.8888 | |
|
|
| 3.3257 | 1.03 | 2823840 | 3.8884 | |
|
|
| 3.3182 | 0.03 | 2900160 | 3.8875 | |
|
|
| 3.315 | 1.03 | 2976480 | 3.8866 | |
|
|
| 3.3135 | 0.02 | 3052726 | 3.8856 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
