This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the yangzhao02/ListUltraFeedback dataset. It achieves the following results on the evaluation set:

Loss: -0.9897
Logps: -558.8966
Logits: -2.5945
Rank Correct Batch: 38.7188
Rank Pair Batch: 56.0
Rank Accuracy Batch: 0.6914
Ndcg: 0.9888

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: 1
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 16
total_train_batch_size: 128
total_eval_batch_size: 16
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	Logps	Logits	Rank Correct Batch	Rank Pair Batch	Rank Accuracy Batch	Ndcg
-0.9877	0.2672	125	-0.9873	-430.1288	-2.2773	37.3125	56.0	0.6663	0.9860
-0.9901	0.5344	250	-0.9890	-503.5457	-2.4979	37.9844	56.0	0.6783	0.9877
-0.9901	0.8016	375	-0.9896	-551.1685	-2.5548	38.5312	56.0	0.6881	0.9887

Framework versions

Transformers 4.45.1
Pytorch 2.6.0+cu118
Datasets 2.19.1
Tokenizers 0.20.3

yangzhao02/llama3-8b-neural_ndcg-beta0.05-tau2.0

llama3-8b-neural_ndcg-beta0.05-tau2.0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

yangzhao02/
llama3-8b-neural_ndcg-beta0.05-tau2.0