metadata
base_model: meta-llama/Meta-Llama-3.1-8B
tags:
- alignment-handbook
- trl
- dpo
- generated_from_trainer
datasets:
- princeton-nlp/llama3-ultrafeedback-armorm
model-index:
- name: Llama-3.1-8B-Magpie-Align-v0.1-RC1
results: []
This model is a fine-tuned version of Magpie-Align/Llama-3.1-8B-Magpie-Align-SFT-v0.1 on the princeton-nlp/llama3-ultrafeedback-armorm dataset. It achieves the following results on the evaluation set:
- Loss: 0.3290
- Rewards/chosen: -4.8185
- Rewards/rejected: -6.6901
- Rewards/accuracies: 0.8952
- Rewards/margins: 1.8716
- Logps/rejected: -867.8638
- Logps/chosen: -686.8736
- Logits/rejected: -0.5907
- Logits/chosen: -0.5749
Model description
More details will be added soon.
Benchmark
- MT-Bench: 8.375 (1st Turn), 7.650 (Second Turn), 8.013 (Average)
- Alpaca Eval 2 (GPT-4-Turbo-1106): 45.73 (LC), 52.79 (WR)
- Arena Hard: 42.4
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-06
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 16
- total_train_batch_size: 256
- total_eval_batch_size: 32
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.4439 | 0.4275 | 100 | 0.4168 | -4.9964 | -6.3086 | 0.8145 | 1.3123 | -829.7151 | -704.6570 | -0.5150 | -0.5001 |
| 0.343 | 0.8549 | 200 | 0.3298 | -4.9310 | -6.7966 | 0.8952 | 1.8655 | -878.5105 | -698.1248 | -0.5776 | -0.5622 |
Framework versions
- Transformers 4.43.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1