This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-qlora on the HuggingFaceH4/ultrafeedback_binarized dataset.
It achieves the following results on the evaluation set:
Loss: 0.6656
Rewards/chosen: 0.0388
Rewards/rejected: -0.0264
Rewards/accuracies: 0.6900
Rewards/margins: 0.0652
Logps/rejected: -237.8513
Logps/chosen: -255.6933
Logits/rejected: -2.8702
Logits/chosen: -2.8928
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-06
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 1024
total_train_batch_size: 4096
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
