metadata
license: apache-2.0
base_model: distilgpt2
tags:
- generated_from_trainer
model-index:
- name: distilgpt2-alpaca-instruction-fine-tuning-qlora
results: []
distilgpt2-alpaca-instruction-fine-tuning-qlora
This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2520
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: 0.0005
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.952 | 0.11 | 1000 | 2.3906 |
| 2.5521 | 0.22 | 2000 | 2.3438 |
| 2.478 | 0.33 | 3000 | 2.3125 |
| 2.4709 | 0.44 | 4000 | 2.2832 |
| 2.4583 | 0.55 | 5000 | 2.2793 |
| 2.4337 | 0.66 | 6000 | 2.2617 |
| 2.416 | 0.77 | 7000 | 2.2656 |
| 2.4111 | 0.88 | 8000 | 2.2559 |
| 2.4054 | 0.99 | 9000 | 2.2520 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1