metadata
license: apache-2.0
base_model: distilgpt2
tags:
- generated_from_trainer
model-index:
- name: S1_InstructionGenerator
results: []
S1_InstructionGenerator
This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0900
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 173 | 0.1076 |
| No log | 2.0 | 346 | 0.0987 |
| 0.1211 | 3.0 | 519 | 0.0946 |
| 0.1211 | 4.0 | 692 | 0.0916 |
| 0.1211 | 5.0 | 865 | 0.0905 |
| 0.1044 | 6.0 | 1038 | 0.0900 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2