metadata
license: mit
base_model: openai-community/gpt2
tags:
- generated_from_trainer
model-index:
- name: finetuned-gpt2-decision_making_model
results: []
finetuned-gpt2-decision_making_model
This model is a fine-tuned version of openai-community/gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5029
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 14 | 2.7515 |
| No log | 2.0 | 28 | 2.4849 |
| No log | 3.0 | 42 | 2.4757 |
| No log | 4.0 | 56 | 2.4459 |
| No log | 5.0 | 70 | 2.4741 |
| No log | 6.0 | 84 | 2.4835 |
| No log | 7.0 | 98 | 2.5468 |
| No log | 8.0 | 112 | 2.4869 |
| No log | 9.0 | 126 | 2.4977 |
| No log | 10.0 | 140 | 2.5029 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1