This model is a fine-tuned version of lewtun/gemma-7b-sft-full-openhermes-v0 on the argilla/dpo-mix-7k dataset.
It achieves the following results on the evaluation set:
Loss: 0.4770
Rewards/chosen: 0.8211
Rewards/rejected: -0.2073
Rewards/accuracies: 0.7083
Rewards/margins: 1.0284
Logps/rejected: -827.8626
Logps/chosen: -710.1602
Logits/rejected: 78.7369
Logits/chosen: 85.9201
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: 8
gradient_accumulation_steps: 8
total_train_batch_size: 128
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
