This model is a fine-tuned version of Minbyul/biomistral-7b-wo-live_qa-sft on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

Loss: 0.4714
Rewards/chosen: -0.1308
Rewards/rejected: -0.7214
Rewards/accuracies: 0.75
Rewards/margins: 0.5906
Logps/rejected: -487.4595
Logps/chosen: -90.0080
Logits/rejected: -4.0457
Logits/chosen: -5.2055

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: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 2
total_train_batch_size: 64
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: 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
0.1183	0.82	100	0.4731	-0.1249	-0.7085	0.75	0.5837	-486.1749	-89.4136	-4.0476	-5.2050

Framework versions

Transformers 4.39.0.dev0
Pytorch 2.1.2
Datasets 2.14.6
Tokenizers 0.15.2

RichardErkhov/Minbyul_-_biomistral-7b-dpo-full-sft-wo-live_qa-4bits

Original model description:

biomistral-7b-dpo-full-sft-wo-live_qa

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
Minbyul_-_biomistral-7b-dpo-full-sft-wo-live_qa-4bits