metadata
license: apache-2.0
tags:
- generated_from_trainer
base_model: distilbert/distilgpt2
model-index:
- name: healthinsurance_textgen
results: []
healthinsurance_textgen
This model is a fine-tuned version of distilbert/distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6360
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: 8
- eval_batch_size: 8
- 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 | 10 | 2.5799 |
| No log | 2.0 | 20 | 2.3829 |
| No log | 3.0 | 30 | 2.2232 |
| No log | 4.0 | 40 | 2.1162 |
| No log | 5.0 | 50 | 2.0297 |
| No log | 6.0 | 60 | 1.9680 |
| No log | 7.0 | 70 | 1.9128 |
| No log | 8.0 | 80 | 1.8481 |
| No log | 9.0 | 90 | 1.8161 |
| No log | 10.0 | 100 | 1.7868 |
| No log | 11.0 | 110 | 1.7447 |
| No log | 12.0 | 120 | 1.7269 |
| No log | 13.0 | 130 | 1.7026 |
| No log | 14.0 | 140 | 1.6866 |
| No log | 15.0 | 150 | 1.6742 |
| No log | 16.0 | 160 | 1.6633 |
| No log | 17.0 | 170 | 1.6499 |
| No log | 18.0 | 180 | 1.6432 |
| No log | 19.0 | 190 | 1.6379 |
| No log | 20.0 | 200 | 1.6360 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cpu
- Datasets 2.18.0
- Tokenizers 0.15.2