reward-model-v3
This model is a fine-tuned version of ChaiML/reward_models_100_170000000_cp_498032 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5182
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: 3
- eval_batch_size: 3
- seed: 7
- gradient_accumulation_steps: 16
- total_train_batch_size: 48
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 200
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.534 | 1.0 | 417 | 0.5333 |
0.4919 | 2.0 | 834 | 0.5192 |
0.4681 | 3.0 | 1251 | 0.5182 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 3
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for anhnv125/reward-model-v3
Base model
ChaiML/reward_models_100_170000000_cp_498032