zephyr-7b-align-scan-0.0-0.3-polynomial-1

This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6417
  • Rewards/chosen: 0.2397
  • Rewards/rejected: 0.0477
  • Rewards/accuracies: 0.3353
  • Rewards/margins: 0.1920
  • Logps/rejected: -80.9526
  • Logps/chosen: -73.6081
  • Logits/rejected: -2.5236
  • Logits/chosen: -2.5399

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: 1.760046153641933e-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: polynomial
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1

Training results

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
18
Safetensors
Model size
7.24B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for taicheng/zephyr-7b-align-scan-0.0-0.3-polynomial-1

Finetuned
(311)
this model

Dataset used to train taicheng/zephyr-7b-align-scan-0.0-0.3-polynomial-1