llama-3-instruct-8b-dpo-full – AI Model by visity | AlphaNeural AI

You can deploy this model and start earning money today!

visity/
llama-3-instruct-8b-dpo-full

like

0

text-generation

generated_from_trainer

text-generation-inference

endpoints_compatible

Views

No views yet

llama-3-instruct-8b-dpo-full

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3577
Rewards/chosen: -4.0594
Rewards/rejected: -6.1181
Rewards/accuracies: 0.8427
Rewards/margins: 2.0587
Logps/rejected: -715.9326
Logps/chosen: -510.6259
Logits/rejected: -1.3913
Logits/chosen: -1.4030

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: 1e-06
train_batch_size: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 128
total_eval_batch_size: 64
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
0.3548	0.8547	400	0.3577	-4.0594	-6.1181	0.8427	2.0587	-715.9326	-510.6259	-1.3913	-1.4030

Framework versions

Transformers 4.44.2
Pytorch 2.2.2+cu121
Datasets 2.18.0
Tokenizers 0.19.0