metadata
library_name: transformers
license: apache-2.0
base_model: distilgpt2
tags:
- generated_from_trainer
model-index:
- name: distilgpt2-finetuned-python_code_instructions_18k_alpaca
results: []
distilgpt2-finetuned-python_code_instructions_18k_alpaca
This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4143
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7118 | 1.0 | 3862 | 1.5780 |
| 1.5838 | 2.0 | 7724 | 1.4955 |
| 1.4914 | 3.0 | 11586 | 1.4615 |
| 1.4532 | 4.0 | 15448 | 1.4364 |
| 1.4292 | 5.0 | 19310 | 1.4241 |
| 1.4136 | 6.0 | 23172 | 1.4171 |
| 1.3778 | 7.0 | 27034 | 1.4143 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1