KimByeongSu's picture
gpt-neo-2.7B-cs-finetuning-7-60000
127a443 verified
|
raw
history blame
1.43 kB
metadata
license: mit
base_model: EleutherAI/gpt-neo-2.7B
tags:
  - generated_from_trainer
model-index:
  - name: gpt-neo-2.7B-cs-finetuning-7-60000
    results: []

gpt-neo-2.7B-cs-finetuning-7-60000

This model is a fine-tuned version of EleutherAI/gpt-neo-2.7B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.4477

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
2.5787 1.0 765 2.4157
1.8828 2.0 1530 2.3721
1.4804 3.0 2295 2.4477

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.2.1
  • Datasets 2.12.0
  • Tokenizers 0.15.1