Jimmy19991222's picture
Upload folder using huggingface_hub
49a029e verified
metadata
library_name: transformers
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
  - alignment-handbook
  - generated_from_trainer
datasets:
  - princeton-nlp/llama3-ultrafeedback-armorm
model-index:
  - name: llama-3-8b-instruct-gapo-v2-bert_p-beta10-gamma0.3-lr1.0e-6-scale-log
    results: []

llama-3-8b-instruct-gapo-v2-bert_p-beta10-gamma0.3-lr1.0e-6-scale-log

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the princeton-nlp/llama3-ultrafeedback-armorm dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3512
  • Rewards/chosen: -16.2535
  • Rewards/rejected: -21.8386
  • Rewards/accuracies: 0.8394
  • Rewards/margins: 5.5851
  • Logps/rejected: -2.1839
  • Logps/chosen: -1.6254
  • Logits/rejected: -1.4706
  • Logits/chosen: -1.4609

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: 2
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • 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 Rewards/chosen Rewards/rejected Rewards/accuracies Rewards/margins Logps/rejected Logps/chosen Logits/rejected Logits/chosen
1.1724 0.8550 400 1.3512 -16.2535 -21.8386 0.8394 5.5851 -2.1839 -1.6254 -1.4706 -1.4609

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.2.0
  • Datasets 2.21.0
  • Tokenizers 0.19.1