metadata

library_name: transformers
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
  - alignment-handbook
  - trl
  - simpo
  - generated_from_trainer
  - trl
  - simpo
  - generated_from_trainer
datasets:
  - yakazimir/llama3-ultrafeedback-armorm
model-index:
  - name: llama3_orpo_best_entropy
    results: []

llama3_orpo_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: 2.5561
Rewards/chosen: -12.9600
Rewards/rejected: -17.5108
Rewards/accuracies: 0.8072
Rewards/margins: 4.5509
Logps/rejected: -1.7511
Logps/chosen: -1.2960
Logits/rejected: -1.3511
Logits/chosen: -1.3851
Semantic Entropy: 0.7683

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-06
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
2.3262	0.8743	400	2.5608	-12.8797	-17.3972	0.8072	4.5175	-1.7397	-1.2880	-1.3473	-1.3813	0.7719

Framework versions

Transformers 4.44.2
Pytorch 2.2.2+cu121
Datasets 2.18.0
Tokenizers 0.19.1