Hugging Face's logo

Tim-05369
/
results

Text Generation
Transformers
Safetensors
llama
trl
orpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
results / README.md
Tim-05369's picture
Tim-05369
Tim-05369/orpo_train_using_space_demo
06d376e verified
preview code
|
raw
history blame
1.46 kB
metadata
license: apache-2.0
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
tags:
  - trl
  - orpo
  - generated_from_trainer
model-index:
  - name: results
    results: []

results

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.4477
  • Rewards/chosen: -0.1131
  • Rewards/rejected: -0.0946
  • Rewards/accuracies: 0.6667
  • Rewards/margins: -0.0185
  • Logps/rejected: -1.8929
  • Logps/chosen: -2.2621
  • Logits/rejected: -2.5533
  • Logits/chosen: -2.5157
  • Nll Loss: 2.3980
  • Log Odds Ratio: -0.9931
  • Log Odds Chosen: -0.3878

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-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Framework versions

  • Transformers 4.43.3
  • Pytorch 2.4.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1