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: 0.4897
Rewards/chosen: -2.0476
Rewards/rejected: -3.4508
Rewards/accuracies: 0.7083
Rewards/margins: 1.4032
Logps/rejected: -520.5655
Logps/chosen: -494.3556
Logits/rejected: 93.1721
Logits/chosen: 99.2168

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: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.193	1.9	100	0.4773	-2.0019	-3.4640	0.7292	1.4620	-520.8292	-493.4434	93.2355	99.2919

Framework versions

Transformers 4.39.0.dev0
Pytorch 2.1.2+cu121
Datasets 2.14.6
Tokenizers 0.15.1

lewtun/gemma-7b-dpo-full-mix1-beta-0.05-epoch-2

gemma-7b-dpo-full-mix1-beta-0.05-epoch-2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

lewtun/
gemma-7b-dpo-full-mix1-beta-0.05-epoch-2