metadata
license: apache-2.0
base_model: distilgpt2
tags:
- generated_from_trainer
model-index:
- name: StatementOfWork_Generator_Omega2
results: []
StatementOfWork_Generator_Omega2
This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9899
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: 50
- eval_batch_size: 50
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 15 | 1.0194 |
| No log | 2.0 | 30 | 1.0190 |
| No log | 3.0 | 45 | 1.0147 |
| No log | 4.0 | 60 | 1.0102 |
| No log | 5.0 | 75 | 1.0135 |
| No log | 6.0 | 90 | 1.0091 |
| No log | 7.0 | 105 | 1.0055 |
| No log | 8.0 | 120 | 1.0024 |
| No log | 9.0 | 135 | 0.9965 |
| No log | 10.0 | 150 | 0.9984 |
| No log | 11.0 | 165 | 1.0013 |
| No log | 12.0 | 180 | 0.9934 |
| No log | 13.0 | 195 | 0.9952 |
| No log | 14.0 | 210 | 0.9917 |
| No log | 15.0 | 225 | 0.9911 |
| No log | 16.0 | 240 | 0.9900 |
| No log | 17.0 | 255 | 0.9918 |
| No log | 18.0 | 270 | 0.9902 |
| No log | 19.0 | 285 | 0.9900 |
| No log | 20.0 | 300 | 0.9899 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2