|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: superlative-quantifier-lstm-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. --> |
|
|
|
# superlative-quantifier-lstm-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: 3.9853 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.7763 | 0.03 | 76320 | 4.7620 | |
|
| 4.4989 | 1.03 | 152640 | 4.4853 | |
|
| 4.3556 | 0.03 | 228960 | 4.3511 | |
|
| 4.2721 | 1.03 | 305280 | 4.2690 | |
|
| 4.2111 | 0.03 | 381600 | 4.2130 | |
|
| 4.1619 | 1.03 | 457920 | 4.1721 | |
|
| 4.1268 | 0.03 | 534240 | 4.1413 | |
|
| 4.0969 | 1.03 | 610560 | 4.1164 | |
|
| 4.0684 | 0.03 | 686880 | 4.0977 | |
|
| 4.0424 | 1.03 | 763200 | 4.0819 | |
|
| 4.0213 | 0.03 | 839520 | 4.0687 | |
|
| 4.0022 | 1.03 | 915840 | 4.0577 | |
|
| 3.9921 | 2.03 | 992160 | 4.0491 | |
|
| 3.9758 | 0.03 | 1068480 | 4.0414 | |
|
| 3.9621 | 1.03 | 1144800 | 4.0342 | |
|
| 3.9449 | 2.03 | 1221120 | 4.0284 | |
|
| 3.931 | 0.03 | 1297440 | 4.0237 | |
|
| 3.9215 | 1.03 | 1373760 | 4.0190 | |
|
| 3.9109 | 0.03 | 1450080 | 4.0155 | |
|
| 3.9095 | 0.03 | 1526400 | 4.0124 | |
|
| 3.9049 | 1.03 | 1602720 | 4.0085 | |
|
| 3.9 | 0.03 | 1679040 | 4.0056 | |
|
| 3.8962 | 1.03 | 1755360 | 4.0035 | |
|
| 3.8938 | 2.03 | 1831680 | 4.0011 | |
|
| 3.8866 | 0.03 | 1908000 | 3.9991 | |
|
| 3.8816 | 0.03 | 1984320 | 3.9976 | |
|
| 3.8738 | 0.03 | 2060640 | 3.9959 | |
|
| 3.8678 | 1.03 | 2136960 | 3.9945 | |
|
| 3.8677 | 0.03 | 2213280 | 3.9936 | |
|
| 3.8607 | 1.03 | 2289600 | 3.9922 | |
|
| 3.8561 | 2.03 | 2365920 | 3.9911 | |
|
| 3.8476 | 0.03 | 2442240 | 3.9901 | |
|
| 3.841 | 1.03 | 2518560 | 3.9895 | |
|
| 3.8375 | 2.03 | 2594880 | 3.9884 | |
|
| 3.834 | 0.03 | 2671200 | 3.9873 | |
|
| 3.837 | 0.03 | 2747520 | 3.9869 | |
|
| 3.839 | 1.03 | 2823840 | 3.9863 | |
|
| 3.8355 | 0.03 | 2900160 | 3.9858 | |
|
| 3.8396 | 1.03 | 2976480 | 3.9855 | |
|
| 3.8402 | 2.02 | 3052726 | 3.9853 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
