metadata

license: mit
tags:
  - generated_from_trainer
base_model: w11wo/indo-gpt2-small
datasets:
  - cahya/alpaca-id-cleaned
model-index:
  - name: my-random-gpt-ft-2
    results: []
language:
  - id

my-random-gpt-ft-2

This model is a fine-tuned version of w11wo/indo-gpt2-small on cahya/alpaca-id-cleaned dataset.

Model description

More information needed

Intended uses & limitations

Prompt format:

Pengguna: <insert user prompt here>

Asisten:

Limitation: This model can't understand the prompt well enough.

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1

Training results

Framework versions

Transformers 4.39.3
Pytorch 2.1.2
Datasets 2.19.0
Tokenizers 0.15.2