gemma-2-2b_HelpSteer2_sftsd2_rmsd0
This model is a fine-tuned version of RylanSchaeffer/gemma-2-2b_HelpSteer2_sftsd2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6664
- Accuracy: 0.6152
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 | 2.0032 | 0.5459 |
1.2597 | 0.0789 | 100 | 0.9730 | 0.5431 |
0.7002 | 0.1578 | 200 | 0.7272 | 0.5768 |
0.6699 | 0.2366 | 300 | 0.6839 | 0.5805 |
0.6751 | 0.3155 | 400 | 0.6737 | 0.5955 |
0.6976 | 0.3944 | 500 | 0.6684 | 0.6152 |
0.6511 | 0.4733 | 600 | 0.6743 | 0.6170 |
0.681 | 0.5522 | 700 | 0.6724 | 0.5899 |
0.6993 | 0.6310 | 800 | 0.6705 | 0.5946 |
0.6933 | 0.7099 | 900 | 0.6695 | 0.6039 |
0.6491 | 0.7888 | 1000 | 0.6711 | 0.5993 |
0.6594 | 0.8677 | 1100 | 0.6692 | 0.6030 |
0.6493 | 0.9466 | 1200 | 0.6807 | 0.6030 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 24
Model tree for RylanSchaeffer/gemma-2-2b_HelpSteer2_sftsd2_rmsd0
Base model
RylanSchaeffer/gemma-2-2b_HelpSteer2_sftsd2
Finetuned
this model