---
tags:
- generated_from_trainer
model-index:
- name: superlative-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. -->

# superlative-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: 3.9895

## 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 |
|:-------------:|:-----:|:-------:|:---------------:|
| 4.7768        | 0.03  | 76320   | 4.7625          |
| 4.4994        | 1.03  | 152640  | 4.4851          |
| 4.3586        | 0.03  | 228960  | 4.3523          |
| 4.2722        | 1.03  | 305280  | 4.2704          |
| 4.2128        | 2.03  | 381600  | 4.2144          |
| 4.1637        | 0.03  | 457920  | 4.1737          |
| 4.1288        | 1.03  | 534240  | 4.1432          |
| 4.0985        | 0.03  | 610560  | 4.1191          |
| 4.0699        | 1.03  | 686880  | 4.0997          |
| 4.0461        | 2.03  | 763200  | 4.0839          |
| 4.0238        | 0.03  | 839520  | 4.0716          |
| 4.0037        | 1.03  | 915840  | 4.0607          |
| 3.9934        | 0.03  | 992160  | 4.0516          |
| 3.9755        | 1.03  | 1068480 | 4.0440          |
| 3.9605        | 0.03  | 1144800 | 4.0370          |
| 3.9465        | 0.03  | 1221120 | 4.0317          |
| 3.9323        | 1.03  | 1297440 | 4.0269          |
| 3.9218        | 0.03  | 1373760 | 4.0221          |
| 3.9132        | 1.03  | 1450080 | 4.0180          |
| 3.9112        | 0.03  | 1526400 | 4.0147          |
| 3.9084        | 1.03  | 1602720 | 4.0120          |
| 3.9015        | 0.03  | 1679040 | 4.0093          |
| 3.8991        | 1.03  | 1755360 | 4.0071          |
| 3.8977        | 0.03  | 1831680 | 4.0053          |
| 3.8892        | 0.03  | 1908000 | 4.0033          |
| 3.8818        | 0.03  | 1984320 | 4.0013          |
| 3.8748        | 0.03  | 2060640 | 3.9992          |
| 3.8679        | 1.03  | 2136960 | 3.9976          |
| 3.8693        | 2.03  | 2213280 | 3.9966          |
| 3.8634        | 0.03  | 2289600 | 3.9957          |
| 3.8557        | 1.03  | 2365920 | 3.9948          |
| 3.85          | 0.03  | 2442240 | 3.9942          |
| 3.8426        | 1.03  | 2518560 | 3.9934          |
| 3.8418        | 0.03  | 2594880 | 3.9927          |
| 3.835         | 1.03  | 2671200 | 3.9919          |
| 3.8405        | 2.03  | 2747520 | 3.9913          |
| 3.8384        | 0.03  | 2823840 | 3.9907          |
| 3.8387        | 1.03  | 2900160 | 3.9903          |
| 3.8427        | 0.03  | 2976480 | 3.9898          |
| 3.8428        | 1.02  | 3052726 | 3.9895          |


### Framework versions

- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3