---
license: apache-2.0
base_model: distilbert/distilgpt2
tags:
- generated_from_trainer
model-index:
- name: distilgpt2-spock
  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. -->

# distilgpt2-spock

This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the dataset of all lines of dialogue spoken by the character Spock in the original Star Trek series: [https://huggingface.co/datasets/omgbobbyg/spock].


It achieves the following results on the evaluation set:
- Loss: 3.8278

## Model description

This model was fine-tuned based on the dataset of all lines spoken by the character Spock as a causal language model.

## 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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 4.3742        | 1.0   | 869  | 3.9095          |
| 3.7966        | 2.0   | 1738 | 3.8367          |
| 3.6567        | 3.0   | 2607 | 3.8278          |


### Framework versions

- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1