gemma-2-2b_HelpSteer2_sftsd1_rmsd0
This model is a fine-tuned version of RylanSchaeffer/gemma-2-2b_HelpSteer2_sftsd1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6665
- Accuracy: 0.6161
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 1250
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 0 | 0 | 1.9984 | 0.5478 |
1.2599 | 0.0789 | 100 | 0.9695 | 0.5318 |
0.6956 | 0.1578 | 200 | 0.7229 | 0.5702 |
0.668 | 0.2366 | 300 | 0.6930 | 0.5852 |
0.6827 | 0.3155 | 400 | 0.6730 | 0.6030 |
0.7002 | 0.3944 | 500 | 0.6649 | 0.6236 |
0.6566 | 0.4733 | 600 | 0.6824 | 0.6142 |
0.6776 | 0.5522 | 700 | 0.6710 | 0.5927 |
0.7018 | 0.6310 | 800 | 0.6702 | 0.5974 |
0.6937 | 0.7099 | 900 | 0.6667 | 0.6058 |
0.6456 | 0.7888 | 1000 | 0.6679 | 0.6067 |
0.6617 | 0.8677 | 1100 | 0.6628 | 0.6021 |
0.6543 | 0.9466 | 1200 | 0.6698 | 0.6086 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 22
Model tree for RylanSchaeffer/gemma-2-2b_HelpSteer2_sftsd1_rmsd0
Base model
RylanSchaeffer/gemma-2-2b_HelpSteer2_sftsd1
Finetuned
this model