---
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: star-trek-tng-script-generator
  results: []
datasets:
- progs2002/star-trek-tng-scripts
language:
- en
pipeline_tag: text-generation
widget:
- text: "PICARD: Make it so!\nRIKER: Captain! That ship is hailing us."
---

<!-- 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. -->
# data cleaning and training code 
https://github.com/progs2002/StarTrekTNG-ScriptGenerator

# star-trek-tng-script-generator

This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.8459

## 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: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 3.1502        | 0.13  | 500   | 3.0233          |
| 3.0538        | 0.26  | 1000  | 2.9728          |
| 2.9951        | 0.38  | 1500  | 2.9437          |
| 2.9891        | 0.51  | 2000  | 2.9125          |
| 2.9289        | 0.64  | 2500  | 2.9159          |
| 2.9091        | 0.77  | 3000  | 2.9008          |
| 2.8916        | 0.89  | 3500  | 2.8752          |
| 2.8122        | 1.02  | 4000  | 2.8881          |
| 2.5224        | 1.15  | 4500  | 2.8896          |
| 2.5284        | 1.28  | 5000  | 2.8667          |
| 2.5191        | 1.4   | 5500  | 2.8599          |
| 2.5119        | 1.53  | 6000  | 2.8488          |
| 2.4808        | 1.66  | 6500  | 2.8296          |
| 2.4601        | 1.79  | 7000  | 2.8081          |
| 2.4331        | 1.91  | 7500  | 2.7993          |
| 2.3716        | 2.04  | 8000  | 2.8518          |
| 2.1528        | 2.17  | 8500  | 2.8634          |
| 2.1276        | 2.3   | 9000  | 2.8617          |
| 2.1329        | 2.43  | 9500  | 2.8489          |
| 2.1135        | 2.55  | 10000 | 2.8446          |
| 2.1259        | 2.68  | 10500 | 2.8461          |
| 2.1142        | 2.81  | 11000 | 2.8472          |
| 2.1071        | 2.94  | 11500 | 2.8459          |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0