gemma-2-9b-it-lora-commonsense
This model is a fine-tuned version of google/gemma-2-9b-it on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8229
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0188 | 0.1503 | 200 | 0.9641 |
| 0.9971 | 0.3007 | 400 | 0.9404 |
| 0.9827 | 0.4510 | 600 | 0.9288 |
| 0.9748 | 0.6013 | 800 | 0.9194 |
| 0.971 | 0.7516 | 1000 | 0.9055 |
| 0.957 | 0.9020 | 1200 | 0.8970 |
| 0.9005 | 1.0523 | 1400 | 0.8874 |
| 0.8876 | 1.2026 | 1600 | 0.8748 |
| 0.8782 | 1.3529 | 1800 | 0.8640 |
| 0.8896 | 1.5033 | 2000 | 0.8489 |
| 0.8814 | 1.6536 | 2200 | 0.8417 |
| 0.8666 | 1.8039 | 2400 | 0.8325 |
| 0.8674 | 1.9542 | 2600 | 0.8307 |
| 0.8116 | 2.1046 | 2800 | 0.8366 |
| 0.8032 | 2.2549 | 3000 | 0.8291 |
| 0.8103 | 2.4052 | 3200 | 0.8265 |
| 0.8165 | 2.5556 | 3400 | 0.8245 |
| 0.8085 | 2.7059 | 3600 | 0.8242 |
| 0.8121 | 2.8562 | 3800 | 0.8229 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1