metadata
library_name: transformers
license: apache-2.0
base_model: distilgpt2
tags:
- generated_from_trainer
model-index:
- name: distilgpt2-finetuned-wellness
results: []
distilgpt2-finetuned-wellness
This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7698
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.4055 | 0.9927 | 102 | 2.8632 |
| 2.6839 | 1.9951 | 205 | 2.3235 |
| 2.3467 | 2.9976 | 308 | 2.1428 |
| 2.1832 | 4.0 | 411 | 2.0383 |
| 2.0576 | 4.9927 | 513 | 1.9659 |
| 1.9634 | 5.9951 | 616 | 1.9195 |
| 1.8834 | 6.9976 | 719 | 1.8783 |
| 1.8251 | 8.0 | 822 | 1.8546 |
| 1.7861 | 8.9927 | 924 | 1.8331 |
| 1.7299 | 9.9951 | 1027 | 1.8186 |
| 1.6952 | 10.9976 | 1130 | 1.8070 |
| 1.673 | 12.0 | 1233 | 1.7945 |
| 1.6387 | 12.9927 | 1335 | 1.7904 |
| 1.6138 | 13.9951 | 1438 | 1.7845 |
| 1.6028 | 14.9976 | 1541 | 1.7793 |
| 1.5778 | 16.0 | 1644 | 1.7761 |
| 1.5668 | 16.9927 | 1746 | 1.7727 |
| 1.5534 | 17.9951 | 1849 | 1.7719 |
| 1.5557 | 18.9976 | 1952 | 1.7711 |
| 1.5438 | 19.8540 | 2040 | 1.7698 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.0