Finetuning experiments
Collection
Using common-known datasets to finetune several models. Experiments are run in Colab.
•
6 items
•
Updated
finetuned-Qwen1.5-0.5B-eli5-askscience-TextGeneration
This model is a fine-tuned version of Qwen/Qwen1.5-0.5B on the eli5_category dataset. It achieves the following results on the evaluation set:
- Loss: 3.3621
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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.2384 | 1.0 | 1480 | 3.3621 |
| 2.573 | 2.0 | 2960 | 3.4468 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 7