|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: existential-there-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. --> |
|
|
|
|
|
# existential-there-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: 3.8852 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2507 | 0.03 | 76320 | 4.2154 | |
|
|
| 4.0435 | 0.03 | 152640 | 4.0466 | |
|
|
| 3.936 | 1.03 | 228960 | 3.9725 | |
|
|
| 3.8613 | 0.03 | 305280 | 3.9314 | |
|
|
| 3.8119 | 1.03 | 381600 | 3.9064 | |
|
|
| 3.7702 | 0.03 | 457920 | 3.8916 | |
|
|
| 3.7381 | 1.03 | 534240 | 3.8794 | |
|
|
| 3.7121 | 0.03 | 610560 | 3.8730 | |
|
|
| 3.6823 | 1.03 | 686880 | 3.8687 | |
|
|
| 3.6624 | 0.03 | 763200 | 3.8663 | |
|
|
| 3.6374 | 1.03 | 839520 | 3.8646 | |
|
|
| 3.6147 | 0.03 | 915840 | 3.8646 | |
|
|
| 3.5968 | 1.03 | 992160 | 3.8638 | |
|
|
| 3.579 | 0.03 | 1068480 | 3.8646 | |
|
|
| 3.5567 | 1.03 | 1144800 | 3.8663 | |
|
|
| 3.5475 | 0.03 | 1221120 | 3.8671 | |
|
|
| 3.5315 | 1.03 | 1297440 | 3.8682 | |
|
|
| 3.5161 | 0.03 | 1373760 | 3.8702 | |
|
|
| 3.5065 | 1.03 | 1450080 | 3.8708 | |
|
|
| 3.4897 | 0.03 | 1526400 | 3.8728 | |
|
|
| 3.4823 | 0.03 | 1602720 | 3.8739 | |
|
|
| 3.4733 | 1.03 | 1679040 | 3.8754 | |
|
|
| 3.4682 | 0.03 | 1755360 | 3.8767 | |
|
|
| 3.4618 | 0.03 | 1831680 | 3.8798 | |
|
|
| 3.4486 | 0.03 | 1908000 | 3.8796 | |
|
|
| 3.4409 | 1.03 | 1984320 | 3.8801 | |
|
|
| 3.4276 | 0.03 | 2060640 | 3.8819 | |
|
|
| 3.4134 | 1.03 | 2136960 | 3.8837 | |
|
|
| 3.4049 | 0.03 | 2213280 | 3.8849 | |
|
|
| 3.3913 | 1.03 | 2289600 | 3.8853 | |
|
|
| 3.3763 | 0.03 | 2365920 | 3.8865 | |
|
|
| 3.372 | 1.03 | 2442240 | 3.8874 | |
|
|
| 3.3612 | 0.03 | 2518560 | 3.8876 | |
|
|
| 3.3494 | 1.03 | 2594880 | 3.8880 | |
|
|
| 3.3423 | 0.03 | 2671200 | 3.8876 | |
|
|
| 3.3315 | 1.03 | 2747520 | 3.8883 | |
|
|
| 3.3276 | 0.03 | 2823840 | 3.8874 | |
|
|
| 3.3207 | 1.03 | 2900160 | 3.8872 | |
|
|
| 3.3176 | 0.03 | 2976480 | 3.8865 | |
|
|
| 3.3159 | 1.02 | 3052726 | 3.8852 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
