This model is a fine-tuned version of google/gemma-2-9b-it on the jz666/gemma2-ultrafeedback-ppl-split dataset.
It achieves the following results on the evaluation set:
Loss: 4.3984
Rewards/chosen: -5.6187
Rewards/rejected: -6.5674
Rewards/accuracies: 0.5840
Rewards/margins: 0.9487
Logps/rejected: -0.6567
Logps/chosen: -0.5619
Logits/rejected: -5.9764
Logits/chosen: -6.2082
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: 8e-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
