|
--- |
|
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: 3.8657 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.2241 | 0.03 | 76320 | 4.1976 | |
|
| 4.0185 | 1.03 | 152640 | 4.0288 | |
|
| 3.9098 | 0.03 | 228960 | 3.9549 | |
|
| 3.8424 | 1.03 | 305280 | 3.9139 | |
|
| 3.7897 | 0.03 | 381600 | 3.8885 | |
|
| 3.7495 | 1.03 | 457920 | 3.8726 | |
|
| 3.7173 | 0.03 | 534240 | 3.8620 | |
|
| 3.6848 | 1.03 | 610560 | 3.8554 | |
|
| 3.656 | 0.03 | 686880 | 3.8512 | |
|
| 3.6306 | 1.03 | 763200 | 3.8476 | |
|
| 3.6077 | 0.03 | 839520 | 3.8454 | |
|
| 3.5894 | 1.03 | 915840 | 3.8462 | |
|
| 3.5702 | 0.03 | 992160 | 3.8450 | |
|
| 3.5528 | 1.03 | 1068480 | 3.8456 | |
|
| 3.537 | 0.03 | 1144800 | 3.8472 | |
|
| 3.5234 | 1.03 | 1221120 | 3.8479 | |
|
| 3.5086 | 0.03 | 1297440 | 3.8489 | |
|
| 3.4939 | 1.03 | 1373760 | 3.8503 | |
|
| 3.481 | 0.03 | 1450080 | 3.8515 | |
|
| 3.4736 | 1.03 | 1526400 | 3.8532 | |
|
| 3.4635 | 0.03 | 1602720 | 3.8531 | |
|
| 3.4539 | 0.03 | 1679040 | 3.8541 | |
|
| 3.4447 | 1.03 | 1755360 | 3.8572 | |
|
| 3.4313 | 0.03 | 1831680 | 3.8587 | |
|
| 3.4182 | 0.03 | 1908000 | 3.8596 | |
|
| 3.4054 | 1.03 | 1984320 | 3.8609 | |
|
| 3.3944 | 0.03 | 2060640 | 3.8624 | |
|
| 3.3856 | 1.03 | 2136960 | 3.8638 | |
|
| 3.3773 | 0.03 | 2213280 | 3.8645 | |
|
| 3.3645 | 1.03 | 2289600 | 3.8652 | |
|
| 3.3559 | 0.03 | 2365920 | 3.8659 | |
|
| 3.3475 | 1.03 | 2442240 | 3.8671 | |
|
| 3.3376 | 0.03 | 2518560 | 3.8674 | |
|
| 3.3262 | 1.03 | 2594880 | 3.8677 | |
|
| 3.316 | 0.03 | 2671200 | 3.8670 | |
|
| 3.3108 | 0.03 | 2747520 | 3.8680 | |
|
| 3.3042 | 1.03 | 2823840 | 3.8675 | |
|
| 3.2997 | 0.03 | 2900160 | 3.8669 | |
|
| 3.2947 | 1.03 | 2976480 | 3.8666 | |
|
| 3.2859 | 0.02 | 3052726 | 3.8657 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
