metadata
license: apache-2.0
base_model: distilgpt2
tags:
- generated_from_trainer
model-index:
- name: nlpmodel
results: []
nlpmodel
This model is a fine-tuned version of distilgpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: nan
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: 0.0006
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.9619 | 0.0 | 100 | 3.1582 |
| 3.5241 | 0.01 | 200 | 3.0684 |
| 3.4974 | 0.01 | 300 | 3.0059 |
| 3.4257 | 0.02 | 400 | 2.9492 |
| 3.3314 | 0.02 | 500 | 2.9199 |
| 3.2822 | 0.03 | 600 | 2.9082 |
| 3.2201 | 0.03 | 700 | 2.8789 |
| 3.1969 | 0.04 | 800 | 2.8594 |
| 3.2104 | 0.04 | 900 | 2.8379 |
| 3.1859 | 0.05 | 1000 | 2.8262 |
| 3.1731 | 0.05 | 1100 | nan |
| 0.0 | 0.06 | 1200 | nan |
| 0.0 | 0.06 | 1300 | nan |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0