metadata
license: mit
base_model: gpt2-medium
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: N-TSZ
results: []
language:
- en
N-TSZ
This model is a fine-tuned version of gpt2-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.0972
- Accuracy: 0.0
Model description
Also Sprach Zarathustra!
Intended uses & limitations
The main intended use & limitation is to give a birth of a dancing star!
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 256
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3356 | 2.0870 | 120 | 3.4775 | 0.0000 |
| 0.1808 | 4.1739 | 240 | 4.0972 | 0.0 |
Framework versions
- Transformers 4.43.1
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1