metadata

license: mit
base_model: gpt2
tags:
  - generated_from_trainer
model-index:
  - name: results
    results: []
language:
  - en
metrics:
  - accuracy

Results

This model is a fine-tuned version of gpt2 on the Kubernetes dataset, which is updated in the same hub!

Model description

This model can be used to generate texts related to Kubernetes. This would be the first model towards interests in IBN.

Intended uses & limitations

It can be used for the text generation.

Training and evaluation data

This model contains only the training data and no evaluation data.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 8
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: TrainOutput(global_step=3, training_loss=3.4602108001708984, metrics={'train_runtime': 83.5107, 'train_samples_per_second': 0.036, 'train_steps_per_second': 0.036, 'total_flos': 1567752192000.0, 'train_loss': 3.4602108001708984, 'epoch': 3.0})

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1