This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the data/rlced_conifer dataset.
It achieves the following results on the evaluation set:
Loss: 0.1691
Rewards/chosen: -2.9092
Rewards/rejected: -8.6906
Rewards/accuracies: 0.9240
Rewards/margins: 5.7814
Logps/rejected: -1311.8641
Logps/chosen: -712.8596
Logits/rejected: 0.8491
Logits/chosen: -0.7188
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: 16
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 512
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
