Minbyul's picture
End of training
f69c191 verified
metadata
license: llama2
base_model: epfl-llm/meditron-7b
tags:
  - alignment-handbook
  - trl
  - dpo
  - generated_from_trainer
  - trl
  - dpo
  - alignment-handbook
  - generated_from_trainer
datasets:
  - HuggingFaceH4/ultrafeedback_binarized
model-index:
  - name: meditron-7b-dpo-full-wo-kqa_golden-ep3
    results: []

meditron-7b-dpo-full-wo-kqa_golden-ep3

This model is a fine-tuned version of epfl-llm/meditron-7b on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4459
  • Rewards/chosen: -0.4566
  • Rewards/rejected: -1.4012
  • Rewards/accuracies: 0.8068
  • Rewards/margins: 0.9447
  • Logps/rejected: -1444.6896
  • Logps/chosen: -859.0582
  • Logits/rejected: -0.9203
  • Logits/chosen: -0.8310

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: 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: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1

Training results

Training Loss Epoch Step Logits/chosen Logits/rejected Logps/chosen Logps/rejected Validation Loss Rewards/accuracies Rewards/chosen Rewards/margins Rewards/rejected
0.5643 0.5 100 -0.6995 -0.8645 -818.2397 -1334.0771 0.5890 0.7727 -0.0484 0.2467 -0.2951
0.3959 1.0 200 -0.8310 -0.9203 -859.0582 -1444.6896 0.4459 0.8068 -0.4566 0.9447 -1.4012

Framework versions

  • Transformers 4.39.0.dev0
  • Pytorch 2.1.2
  • Datasets 2.14.6
  • Tokenizers 0.15.2