KimByeongSu's picture
Upload tokenizer
e1ff793 verified
metadata
license: mit
tags:
  - generated_from_trainer
base_model: EleutherAI/gpt-neo-2.7B
model-index:
  - name: gpt-neo-2.7B-cs-finetuning-7
    results: []

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

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: 1.6803

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
2.4775 1.0 1329 2.3779
1.8846 2.0 2658 2.3283
1.4746 3.0 3993 1.6803

Framework versions

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