This model is a fine-tuned version of lewtun/gemma-7b-sft-full-deita-10k-v0 on the argilla/dpo-mix-7k dataset.
It achieves the following results on the evaluation set:
Loss: 1.2743
Rewards/chosen: -1.9500
Rewards/rejected: -5.9664
Rewards/accuracies: 0.75
Rewards/margins: 4.0164
Logps/rejected: -466.4656
Logps/chosen: -458.2794
Logits/rejected: 100.2494
Logits/chosen: 106.4162
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
