|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: existential-there-quantifier-transformer-0 |
|
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-0 |
|
|
|
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: 3.8606 |
|
|
|
## 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: 0 |
|
- 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.226 | 0.03 | 76320 | 4.1970 | |
|
| 4.0196 | 1.03 | 152640 | 4.0272 | |
|
| 3.9103 | 0.03 | 228960 | 3.9532 | |
|
| 3.842 | 1.03 | 305280 | 3.9117 | |
|
| 3.7902 | 0.03 | 381600 | 3.8860 | |
|
| 3.7496 | 1.03 | 457920 | 3.8709 | |
|
| 3.7142 | 0.03 | 534240 | 3.8605 | |
|
| 3.6843 | 1.03 | 610560 | 3.8533 | |
|
| 3.6562 | 0.03 | 686880 | 3.8494 | |
|
| 3.6294 | 1.03 | 763200 | 3.8464 | |
|
| 3.6054 | 0.03 | 839520 | 3.8448 | |
|
| 3.5872 | 1.03 | 915840 | 3.8442 | |
|
| 3.5719 | 0.03 | 992160 | 3.8433 | |
|
| 3.5494 | 1.03 | 1068480 | 3.8438 | |
|
| 3.5361 | 0.03 | 1144800 | 3.8453 | |
|
| 3.5229 | 1.03 | 1221120 | 3.8448 | |
|
| 3.5091 | 0.03 | 1297440 | 3.8469 | |
|
| 3.4962 | 0.03 | 1373760 | 3.8474 | |
|
| 3.4817 | 0.03 | 1450080 | 3.8502 | |
|
| 3.4739 | 1.03 | 1526400 | 3.8508 | |
|
| 3.4641 | 0.03 | 1602720 | 3.8521 | |
|
| 3.455 | 1.03 | 1679040 | 3.8532 | |
|
| 3.4471 | 0.03 | 1755360 | 3.8544 | |
|
| 3.4338 | 1.03 | 1831680 | 3.8554 | |
|
| 3.4207 | 0.03 | 1908000 | 3.8572 | |
|
| 3.4107 | 1.03 | 1984320 | 3.8577 | |
|
| 3.3968 | 0.03 | 2060640 | 3.8601 | |
|
| 3.3889 | 0.03 | 2136960 | 3.8605 | |
|
| 3.3808 | 1.03 | 2213280 | 3.8612 | |
|
| 3.364 | 0.03 | 2289600 | 3.8615 | |
|
| 3.3563 | 1.03 | 2365920 | 3.8631 | |
|
| 3.3506 | 0.03 | 2442240 | 3.8637 | |
|
| 3.3402 | 1.03 | 2518560 | 3.8635 | |
|
| 3.328 | 0.03 | 2594880 | 3.8644 | |
|
| 3.3179 | 0.03 | 2671200 | 3.8645 | |
|
| 3.3121 | 1.03 | 2747520 | 3.8638 | |
|
| 3.3051 | 0.03 | 2823840 | 3.8637 | |
|
| 3.3015 | 1.03 | 2900160 | 3.8633 | |
|
| 3.2959 | 0.03 | 2976480 | 3.8622 | |
|
| 3.2885 | 0.02 | 3052726 | 3.8606 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
