---
tags:
- generated_from_trainer
model-index:
- name: superlative-quantifier-transformer-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-transformer-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: 3.8837

## 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 |
|:-------------:|:-----:|:-------:|:---------------:|
| 4.2249        | 0.03  | 76320   | 4.2087          |
| 4.0213        | 1.03  | 152640  | 4.0412          |
| 3.9129        | 0.03  | 228960  | 3.9686          |
| 3.8461        | 1.03  | 305280  | 3.9269          |
| 3.7962        | 0.03  | 381600  | 3.9027          |
| 3.7546        | 1.03  | 457920  | 3.8871          |
| 3.7204        | 0.03  | 534240  | 3.8776          |
| 3.6945        | 1.03  | 610560  | 3.8700          |
| 3.6672        | 0.03  | 686880  | 3.8669          |
| 3.6407        | 1.03  | 763200  | 3.8640          |
| 3.6177        | 0.03  | 839520  | 3.8625          |
| 3.5958        | 1.03  | 915840  | 3.8626          |
| 3.5814        | 0.03  | 992160  | 3.8629          |
| 3.5614        | 0.03  | 1068480 | 3.8633          |
| 3.5415        | 1.03  | 1144800 | 3.8646          |
| 3.5217        | 0.03  | 1221120 | 3.8653          |
| 3.5054        | 1.03  | 1297440 | 3.8664          |
| 3.4924        | 0.03  | 1373760 | 3.8680          |
| 3.4793        | 1.03  | 1450080 | 3.8683          |
| 3.471         | 0.03  | 1526400 | 3.8702          |
| 3.4648        | 0.03  | 1602720 | 3.8718          |
| 3.4555        | 1.03  | 1679040 | 3.8740          |
| 3.4495        | 0.03  | 1755360 | 3.8754          |
| 3.4407        | 1.03  | 1831680 | 3.8771          |
| 3.4286        | 0.03  | 1908000 | 3.8777          |
| 3.416         | 0.03  | 1984320 | 3.8798          |
| 3.4039        | 0.03  | 2060640 | 3.8813          |
| 3.3906        | 0.03  | 2136960 | 3.8828          |
| 3.3851        | 0.03  | 2213280 | 3.8833          |
| 3.3725        | 1.03  | 2289600 | 3.8836          |
| 3.3602        | 0.03  | 2365920 | 3.8841          |
| 3.346         | 0.03  | 2442240 | 3.8842          |
| 3.3344        | 0.03  | 2518560 | 3.8863          |
| 3.3257        | 1.03  | 2594880 | 3.8859          |
| 3.3147        | 0.03  | 2671200 | 3.8859          |
| 3.3089        | 1.03  | 2747520 | 3.8863          |
| 3.3062        | 0.03  | 2823840 | 3.8858          |
| 3.3           | 1.03  | 2900160 | 3.8854          |
| 3.2978        | 0.03  | 2976480 | 3.8848          |
| 3.294         | 0.02  | 3052726 | 3.8837          |


### Framework versions

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