This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-gemma-sft-v0.1 on the argilla/dpo-mix-7k dataset. It achieves the following results on the evaluation set:

Loss: 0.2953
Rewards/chosen: 1.5010
Rewards/rejected: -0.1766
Rewards/accuracies: 0.6875
Rewards/margins: 1.6776
Logps/rejected: -365.6023
Logps/chosen: -333.6483
Logits/rejected: 108.5893
Logits/chosen: 113.8158

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
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.1946	1.8957	100	0.2942	1.5244	-0.1579	0.6458	1.6823	-365.2298	-333.1805	108.6414	113.8343

Framework versions

Transformers 4.40.1
Pytorch 2.1.2+cu121
Datasets 2.19.0
Tokenizers 0.19.1

chrlu/zephyr-7b-gemma-kto-2

zephyr-7b-gemma-kto-2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

chrlu/
zephyr-7b-gemma-kto-2