This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the updated and the original datasets. It achieves the following results on the evaluation set:

Loss: 0.6749
Rewards/chosen: -0.0411
Rewards/rejected: -0.0904
Rewards/accuracies: 0.6100
Rewards/margins: 0.0493
Logps/rejected: -266.5563
Logps/chosen: -288.1525
Logits/rejected: -2.6646
Logits/chosen: -2.7444

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: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 16
total_train_batch_size: 128
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.6794	0.65	100	0.6749	-0.0411	-0.0904	0.6100	0.0493	-266.5563	-288.1525	-2.6646	-2.7444

Framework versions

PEFT 0.7.1
Transformers 4.36.2
Pytorch 2.1.2+cu121
Datasets 2.14.6
Tokenizers 0.15.2

YYYYYYibo/vanilla_doff_dpo_iter_1

vanilla_doff_dpo_iter_1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

YYYYYYibo/
vanilla_doff_dpo_iter_1