|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: existential-there-quantifier-lstm-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-lstm-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: 3.9934 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.8273 | 0.03 | 76320 | 4.7836 | |
|
|
| 4.5391 | 1.03 | 152640 | 4.5012 | |
|
|
| 4.3969 | 0.03 | 228960 | 4.3667 | |
|
|
| 4.3045 | 1.03 | 305280 | 4.2836 | |
|
|
| 4.2419 | 0.03 | 381600 | 4.2262 | |
|
|
| 4.192 | 1.03 | 457920 | 4.1851 | |
|
|
| 4.1562 | 0.03 | 534240 | 4.1534 | |
|
|
| 4.1266 | 1.03 | 610560 | 4.1292 | |
|
|
| 4.0984 | 0.03 | 686880 | 4.1090 | |
|
|
| 4.0793 | 1.03 | 763200 | 4.0937 | |
|
|
| 4.0568 | 0.03 | 839520 | 4.0802 | |
|
|
| 4.0358 | 1.03 | 915840 | 4.0689 | |
|
|
| 4.0206 | 0.03 | 992160 | 4.0594 | |
|
|
| 4.0044 | 1.03 | 1068480 | 4.0509 | |
|
|
| 3.9856 | 0.03 | 1144800 | 4.0442 | |
|
|
| 3.9794 | 0.03 | 1221120 | 4.0388 | |
|
|
| 3.9662 | 1.03 | 1297440 | 4.0339 | |
|
|
| 3.9543 | 0.03 | 1373760 | 4.0289 | |
|
|
| 3.947 | 0.03 | 1450080 | 4.0247 | |
|
|
| 3.9364 | 1.03 | 1526400 | 4.0203 | |
|
|
| 3.9341 | 0.03 | 1602720 | 4.0168 | |
|
|
| 3.9302 | 1.03 | 1679040 | 4.0148 | |
|
|
| 3.9262 | 0.03 | 1755360 | 4.0128 | |
|
|
| 3.9228 | 1.03 | 1831680 | 4.0098 | |
|
|
| 3.9153 | 0.03 | 1908000 | 4.0084 | |
|
|
| 3.9142 | 1.03 | 1984320 | 4.0067 | |
|
|
| 3.9089 | 0.03 | 2060640 | 4.0050 | |
|
|
| 3.9009 | 1.03 | 2136960 | 4.0033 | |
|
|
| 3.8964 | 0.03 | 2213280 | 4.0018 | |
|
|
| 3.8902 | 1.03 | 2289600 | 4.0003 | |
|
|
| 3.8809 | 0.03 | 2365920 | 3.9990 | |
|
|
| 3.8823 | 1.03 | 2442240 | 3.9980 | |
|
|
| 3.8772 | 0.03 | 2518560 | 3.9973 | |
|
|
| 3.8719 | 0.03 | 2594880 | 3.9966 | |
|
|
| 3.8723 | 1.03 | 2671200 | 3.9958 | |
|
|
| 3.8664 | 0.03 | 2747520 | 3.9952 | |
|
|
| 3.8675 | 1.03 | 2823840 | 3.9947 | |
|
|
| 3.8662 | 0.03 | 2900160 | 3.9940 | |
|
|
| 3.8698 | 1.03 | 2976480 | 3.9936 | |
|
|
| 3.871 | 0.02 | 3052726 | 3.9934 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
