---
license: cc
widget:
  - text: "Movie: Parasite Score:"
    example_title: "Parasite"
  - text: "Movie: Come and See Score:"
    example_title: "Come and See"
  - text: "Movie: Harakiri Score:"
    example_title: "Harakiri"
tags:
- generated_from_trainer
model-index:
- name: ReviewTrainingBot
  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. -->

# ReviewTrainingBot

This model was fine-tuned on GPT-2, using a dataset of ~120,000 reviews on letterboxd.com. The intention is to expand this dataset in the future, as well as upload the dataset to the Datasets collection. This is a work in progress.

## 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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 5
- total_train_batch_size: 20
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5

### Framework versions

- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Tokenizers 0.12.1