metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: GPT-2-Base
results: []
GPT-2-Base
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4397
- Accuracy: 0.5
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 44 | 1.8580 | 0.2598 |
| No log | 2.0 | 88 | 1.7766 | 0.2745 |
| No log | 3.0 | 132 | 1.6079 | 0.4069 |
| No log | 4.0 | 176 | 1.4671 | 0.5098 |
| No log | 5.0 | 220 | 1.5152 | 0.4804 |
| No log | 6.0 | 264 | 1.4397 | 0.5 |
| No log | 7.0 | 308 | 1.4590 | 0.5098 |
| No log | 8.0 | 352 | 1.5410 | 0.5049 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0+cu124
- Datasets 2.21.0
- Tokenizers 0.19.1