zephyr-7b-dpo-lora – AI Model by yihang7 | AlphaNeural AI

You can deploy this model and start earning money today!

yihang7/
zephyr-7b-dpo-lora

like

0

text-generation

generated_from_trainer

mistralai/Mistral-7B-v0.1

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

zephyr-7b-dpo-lora

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2082
Rewards/chosen: 1.3857
Rewards/rejected: -0.9066
Rewards/accuracies: 0.9414
Rewards/margins: 2.2923
Logps/rejected: -388.5903
Logps/chosen: -238.5479
Logits/rejected: -2.7219
Logits/chosen: -2.6178

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: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 32
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
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
0.2019	1.0	1470	0.2082	1.3857	-0.9066	0.9414	2.2923	-388.5903	-238.5479	-2.7219	-2.6178

Framework versions

Transformers 4.35.0
Pytorch 2.1.1+cu121
Datasets 2.14.6
Tokenizers 0.14.1