KimByeongSu's picture
gpt-neo-125m-cs-finetuning-filtered
7cfa7b1 verified
metadata
license: mit
base_model: EleutherAI/gpt-neo-125m
tags:
  - generated_from_trainer
model-index:
  - name: gpt-neo-125m-cs-finetuning-filtered
    results: []

gpt-neo-125m-cs-finetuning-filtered

This model is a fine-tuned version of EleutherAI/gpt-neo-125m on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 3.1868

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-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

Training Loss Epoch Step Validation Loss
3.4022 1.0 950 3.2552
3.137 2.0 1900 3.1998
3.04 3.0 2850 3.1868

Framework versions

  • Transformers 4.36.2
  • Pytorch 1.13.1+cu117
  • Datasets 2.14.6
  • Tokenizers 0.15.0