gemma-2-2b_HelpSteer2_sftsd1_rmsd1
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: 0.6583
- Accuracy: 0.6189
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: 1
- 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 | 1.4367 | 0.5140 |
0.9375 | 0.0789 | 100 | 1.0160 | 0.5684 |
0.6408 | 0.1578 | 200 | 0.6840 | 0.5871 |
0.6936 | 0.2366 | 300 | 0.6790 | 0.5852 |
0.6222 | 0.3155 | 400 | 0.6837 | 0.5852 |
0.6689 | 0.3944 | 500 | 0.6691 | 0.6058 |
0.6736 | 0.4733 | 600 | 0.6778 | 0.5843 |
0.7012 | 0.5522 | 700 | 0.6629 | 0.6086 |
0.6788 | 0.6310 | 800 | 0.6692 | 0.6011 |
0.6715 | 0.7099 | 900 | 0.6641 | 0.6208 |
0.6608 | 0.7888 | 1000 | 0.6608 | 0.6152 |
0.6386 | 0.8677 | 1100 | 0.6582 | 0.6114 |
0.6649 | 0.9466 | 1200 | 0.6597 | 0.6227 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 19
Model tree for RylanSchaeffer/gemma-2-2b_HelpSteer2_sftsd1_rmsd1
Base model
RylanSchaeffer/gemma-2-2b_HelpSteer2_sftsd1
Finetuned
this model