llama3_cpo_best_entropy
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the yakazimir/llama3-ultrafeedback-armorm dataset. It achieves the following results on the evaluation set:
- Loss: 1.7538
- Rewards/chosen: -25.5611
- Rewards/rejected: -33.0936
- Rewards/accuracies: 0.8434
- Rewards/margins: 7.5325
- Logps/rejected: -3.3094
- Logps/chosen: -2.5561
- Logits/rejected: -1.1508
- Logits/chosen: -1.2004
- Semantic Entropy: 0.3675
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: 9e-07
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- total_eval_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: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Semantic Entropy |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.7533 | 0.8743 | 400 | 1.7650 | -25.4120 | -32.9268 | 0.8434 | 7.5148 | -3.2927 | -2.5412 | -1.1664 | -1.2180 | 0.3711 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1
- Downloads last month
- 2
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 yakazimir/llama3_cpo_best_entropy
Base model
meta-llama/Meta-Llama-3-8B-Instruct