fietje-2-chat / README.md
BramVanroy's picture
Model save
394b5d5 verified
|
raw
history blame
2.13 kB
metadata
license: mit
base_model: BramVanroy/fietje-2b-sft
tags:
  - trl
  - dpo
  - generated_from_trainer
model-index:
  - name: fietje-2b-dpo-lr2.0e-6-beta0.2-gradaccum2-v6
    results: []

fietje-2b-dpo-lr2.0e-6-beta0.2-gradaccum2-v6

This model is a fine-tuned version of BramVanroy/fietje-2b-sft on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2842
  • Rewards/chosen: -1.1549
  • Rewards/rejected: -3.6363
  • Rewards/accuracies: 0.8867
  • Rewards/margins: 2.4815
  • Logps/rejected: -657.6813
  • Logps/chosen: -451.3364
  • Logits/rejected: -1.2868
  • Logits/chosen: -1.3528

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: 2e-06
  • train_batch_size: 8
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-07
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1.0

Training results

Training Loss Epoch Step Validation Loss Rewards/chosen Rewards/rejected Rewards/accuracies Rewards/margins Logps/rejected Logps/chosen Logits/rejected Logits/chosen
0.2515 1.0 1166 0.2842 -1.1549 -3.6363 0.8867 2.4815 -657.6813 -451.3364 -1.2868 -1.3528

Framework versions

  • Transformers 4.39.1
  • Pytorch 2.1.2+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2