Llama-3.1-8B-Instruct-SAA
This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the bct_non_cot_dpo_1000 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2005
- Rewards/chosen: -0.0159
- Rewards/rejected: -0.0611
- Rewards/accuracies: 0.8300
- Rewards/margins: 0.0452
- Logps/rejected: -0.6110
- Logps/chosen: -0.1590
- Logits/rejected: -0.4566
- Logits/chosen: -0.3865
- Sft Loss: 0.0178
- Odds Ratio Loss: 1.8274
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: 3.0
Training results
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
- 7
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for chchen/Llama-3.1-8B-Instruct-SAA
Base model
meta-llama/Llama-3.1-8B Finetuned
meta-llama/Llama-3.1-8B-Instruct