gemma2b_quotes_v4
This model is a fine-tuned version of google/gemma-2b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5350
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 50
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.4383 | 0.0100 | 5 | 2.8428 |
1.8807 | 0.0199 | 10 | 2.6970 |
2.389 | 0.0299 | 15 | 2.7069 |
2.2562 | 0.0399 | 20 | 2.6762 |
2.0517 | 0.0499 | 25 | 2.6469 |
1.9751 | 0.0598 | 30 | 2.6153 |
2.2206 | 0.0698 | 35 | 2.6186 |
2.2526 | 0.0798 | 40 | 2.5952 |
1.9522 | 0.0897 | 45 | 2.5328 |
1.8209 | 0.0997 | 50 | 2.5350 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 3
Model tree for dwb2023/gemma2b_quotes_v4
Base model
google/gemma-2b