Llama-3.1-8B-Instruct-SAA-100
This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the bct_non_cot_dpo_100 dataset. It achieves the following results on the evaluation set:
- Loss: 1.6738
- Rewards/chosen: -0.1622
- Rewards/rejected: -0.2212
- Rewards/accuracies: 0.8000
- Rewards/margins: 0.0590
- Logps/rejected: -2.2122
- Logps/chosen: -1.6219
- Logits/rejected: -0.5028
- Logits/chosen: -0.3970
- Sft Loss: 0.2269
- Odds Ratio Loss: 14.4681
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: 5e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Sft Loss | Odds Ratio Loss |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.3868 | 8.8889 | 50 | 1.6738 | -0.1622 | -0.2212 | 0.8000 | 0.0590 | -2.2122 | -1.6219 | -0.5028 | -0.3970 | 0.2269 | 14.4681 |
Framework versions
- PEFT 0.12.0
- Transformers 4.45.2
- Pytorch 2.3.0
- Datasets 2.19.0
- Tokenizers 0.20.0
- Downloads last month
- 9
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for chchen/Llama-3.1-8B-Instruct-SAA-100
Base model
meta-llama/Llama-3.1-8B
Finetuned
meta-llama/Llama-3.1-8B-Instruct