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: 0.5140
Rewards/chosen: -1.9817
Rewards/rejected: -2.6516
Rewards/accuracies: 0.7131
Rewards/margins: 0.6699
Logps/rejected: -449.2577
Logps/chosen: -386.9050
Logits/rejected: -17.7330
Logits/chosen: -17.7324
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-07
train_batch_size: 2
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 32
total_train_batch_size: 256
total_eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
