metadata
base_model: jerteh/gpt2-orao
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: SRGPTSENTPOS4
results: []
SRGPTSENTPOS4
This model is a fine-tuned version of jerteh/gpt2-orao on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1738
- F1: 0.2769
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 32
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.114 | 1.0 | 2703 | 0.0967 | 0.0 |
| 0.0938 | 2.0 | 5406 | 0.1364 | 0.0 |
| 0.1035 | 3.0 | 8109 | 0.1487 | 0.1111 |
| 0.0906 | 4.0 | 10812 | 0.1429 | 0.2558 |
| 0.0575 | 5.0 | 13515 | 0.2198 | 0.2388 |
| 0.0369 | 6.0 | 16218 | 0.1617 | 0.2817 |
| 0.034 | 7.0 | 18921 | 0.1834 | 0.1935 |
| 0.0126 | 8.0 | 21624 | 0.1738 | 0.2769 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.2.0.dev20230928
- Datasets 2.14.2
- Tokenizers 0.13.3