---
tags:
- generated_from_trainer
model-index:
- name: superlative-quantifier-lstm-3
  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-3

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: 3.9893

## 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: 3
- 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 |
|:-------------:|:-----:|:-------:|:---------------:|
| 4.7985        | 0.03  | 76320   | 4.7866          |
| 4.5144        | 1.03  | 152640  | 4.5020          |
| 4.3706        | 0.03  | 228960  | 4.3653          |
| 4.2853        | 1.03  | 305280  | 4.2807          |
| 4.2215        | 2.03  | 381600  | 4.2234          |
| 4.1723        | 0.03  | 457920  | 4.1822          |
| 4.1396        | 1.03  | 534240  | 4.1511          |
| 4.1084        | 0.03  | 610560  | 4.1267          |
| 4.0794        | 1.03  | 686880  | 4.1064          |
| 4.0535        | 0.03  | 763200  | 4.0905          |
| 4.0315        | 1.03  | 839520  | 4.0768          |
| 4.0098        | 0.03  | 915840  | 4.0656          |
| 4.0005        | 1.03  | 992160  | 4.0558          |
| 3.9838        | 2.03  | 1068480 | 4.0484          |
| 3.9698        | 0.03  | 1144800 | 4.0409          |
| 3.9498        | 1.03  | 1221120 | 4.0346          |
| 3.9379        | 2.03  | 1297440 | 4.0304          |
| 3.9296        | 0.03  | 1373760 | 4.0261          |
| 3.9193        | 1.03  | 1450080 | 4.0215          |
| 3.9159        | 0.03  | 1526400 | 4.0179          |
| 3.9123        | 1.03  | 1602720 | 4.0143          |
| 3.9072        | 0.03  | 1679040 | 4.0113          |
| 3.906         | 1.03  | 1755360 | 4.0091          |
| 3.9027        | 0.03  | 1831680 | 4.0067          |
| 3.8946        | 1.03  | 1908000 | 4.0048          |
| 3.8892        | 0.03  | 1984320 | 4.0029          |
| 3.8824        | 0.03  | 2060640 | 4.0012          |
| 3.8758        | 0.03  | 2136960 | 3.9999          |
| 3.8751        | 0.03  | 2213280 | 3.9983          |
| 3.869         | 0.03  | 2289600 | 3.9967          |
| 3.8615        | 1.03  | 2365920 | 3.9956          |
| 3.8512        | 2.03  | 2442240 | 3.9942          |
| 3.8463        | 0.03  | 2518560 | 3.9931          |
| 3.8445        | 1.03  | 2594880 | 3.9924          |
| 3.8404        | 2.03  | 2671200 | 3.9919          |
| 3.8438        | 0.03  | 2747520 | 3.9912          |
| 3.845         | 0.03  | 2823840 | 3.9907          |
| 3.8445        | 0.03  | 2900160 | 3.9900          |
| 3.8503        | 0.03  | 2976480 | 3.9897          |
| 3.8497        | 1.02  | 3052726 | 3.9893          |


### Framework versions

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