|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: existential-there-quantifier-transformer-1 |
|
|
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-1 |
|
|
|
|
|
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: 3.8839 |
|
|
|
|
|
## 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: 1 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2616 | 0.03 | 76320 | 4.2240 | |
|
|
| 4.0508 | 1.03 | 152640 | 4.0508 | |
|
|
| 3.9401 | 0.03 | 228960 | 3.9758 | |
|
|
| 3.865 | 1.03 | 305280 | 3.9339 | |
|
|
| 3.8135 | 0.03 | 381600 | 3.9073 | |
|
|
| 3.7714 | 1.03 | 457920 | 3.8895 | |
|
|
| 3.7388 | 0.03 | 534240 | 3.8792 | |
|
|
| 3.7131 | 1.03 | 610560 | 3.8728 | |
|
|
| 3.684 | 0.03 | 686880 | 3.8681 | |
|
|
| 3.6636 | 1.03 | 763200 | 3.8646 | |
|
|
| 3.6394 | 0.03 | 839520 | 3.8636 | |
|
|
| 3.617 | 1.03 | 915840 | 3.8631 | |
|
|
| 3.5998 | 0.03 | 992160 | 3.8632 | |
|
|
| 3.5818 | 1.03 | 1068480 | 3.8621 | |
|
|
| 3.5593 | 0.03 | 1144800 | 3.8644 | |
|
|
| 3.5503 | 1.03 | 1221120 | 3.8656 | |
|
|
| 3.5342 | 0.03 | 1297440 | 3.8669 | |
|
|
| 3.5177 | 0.03 | 1373760 | 3.8686 | |
|
|
| 3.5074 | 1.03 | 1450080 | 3.8695 | |
|
|
| 3.4918 | 0.03 | 1526400 | 3.8712 | |
|
|
| 3.4844 | 1.03 | 1602720 | 3.8720 | |
|
|
| 3.4726 | 0.03 | 1679040 | 3.8740 | |
|
|
| 3.4666 | 0.03 | 1755360 | 3.8755 | |
|
|
| 3.4589 | 0.03 | 1831680 | 3.8769 | |
|
|
| 3.4472 | 1.03 | 1908000 | 3.8772 | |
|
|
| 3.4392 | 0.03 | 1984320 | 3.8804 | |
|
|
| 3.4254 | 1.03 | 2060640 | 3.8811 | |
|
|
| 3.4139 | 0.03 | 2136960 | 3.8819 | |
|
|
| 3.4048 | 1.03 | 2213280 | 3.8826 | |
|
|
| 3.39 | 0.03 | 2289600 | 3.8845 | |
|
|
| 3.3736 | 0.03 | 2365920 | 3.8846 | |
|
|
| 3.3731 | 0.03 | 2442240 | 3.8849 | |
|
|
| 3.3589 | 1.03 | 2518560 | 3.8856 | |
|
|
| 3.3472 | 0.03 | 2594880 | 3.8856 | |
|
|
| 3.3408 | 1.03 | 2671200 | 3.8866 | |
|
|
| 3.3287 | 0.03 | 2747520 | 3.8863 | |
|
|
| 3.3257 | 0.03 | 2823840 | 3.8861 | |
|
|
| 3.318 | 0.03 | 2900160 | 3.8854 | |
|
|
| 3.3149 | 1.03 | 2976480 | 3.8846 | |
|
|
| 3.3129 | 0.02 | 3052726 | 3.8839 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
