Hugging Face's logo

mnoukhov
/
pythia410m-rm-tldr6.9b

Text Classification
Transformers
Safetensors
gpt_neox
trl
reward-trainer
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
pythia410m-rm-tldr6.9b / README.md
mnoukhov's picture
mnoukhov
Model save
3d6f891 verified
preview code
|
raw
history blame contribute delete
1.72 kB
metadata
license: apache-2.0
base_model: mnoukhov/pythia410m-sft-tldr
tags:
  - trl
  - reward-trainer
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: pythia410m-rm-tldr6.9b
    results: []

pythia410m-rm-tldr6.9b

This model is a fine-tuned version of mnoukhov/pythia410m-sft-tldr on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5162
  • Accuracy: 0.7418

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-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.5507 0.2006 291 0.5506 0.7176
0.4921 0.4011 582 0.5163 0.7394
0.4727 0.6017 873 0.5194 0.7368
0.439 0.8022 1164 0.5162 0.7418

Framework versions

  • Transformers 4.41.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1