---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: bnc_spoken_cbt_log_rarity-mixed-seed
  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. -->

# bnc_spoken_cbt_log_rarity-mixed-seed

This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 4.1428

## 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: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 6.3612        | 0.29  | 500   | 5.3449          |
| 5.057         | 0.59  | 1000  | 4.9241          |
| 4.719         | 0.88  | 1500  | 4.7007          |
| 4.4572        | 1.17  | 2000  | 4.5642          |
| 4.313         | 1.46  | 2500  | 4.4451          |
| 4.2078        | 1.76  | 3000  | 4.3450          |
| 4.0893        | 2.05  | 3500  | 4.2776          |
| 3.9066        | 2.34  | 4000  | 4.2323          |
| 3.8811        | 2.63  | 4500  | 4.1744          |
| 3.8449        | 2.93  | 5000  | 4.1258          |
| 3.6444        | 3.22  | 5500  | 4.1177          |
| 3.599         | 3.51  | 6000  | 4.0930          |
| 3.5865        | 3.81  | 6500  | 4.0622          |
| 3.4817        | 4.1   | 7000  | 4.0622          |
| 3.3285        | 4.39  | 7500  | 4.0593          |
| 3.3233        | 4.68  | 8000  | 4.0477          |
| 3.3173        | 4.98  | 8500  | 4.0366          |
| 3.1582        | 5.27  | 9000  | 4.0495          |
| 3.1499        | 5.56  | 9500  | 4.0489          |
| 3.1452        | 5.85  | 10000 | 4.0490          |


### Framework versions

- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3