reward-gpt

bradmin/reward-gpt

reward-gpt is a text classification model from bradmin. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

5% of all-time downloads

All-time downloads

342

Public

Parameters

1.3B

237 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pt73.8 GB · 58%

At a glance

Task: Text Classification
Library: transformers
License: apache-2.0
Model type: gpt_neox
Access: Public
Created: Oct 28, 2023
Updated: Nov 3, 2023
SHA: abb6ce9a

Try a prompt

Base models

EleutherAI/polyglot-ko-1.3b

Model card

From the Hugging Face model README

reward-gpt

This model is a fine-tuned version of EleutherAI/polyglot-ko-1.3b on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0084
Accuracy: 0.0

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: 9e-06
train_batch_size: 4
eval_batch_size: 4
seed: 2023
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
lr_scheduler_type: cosine
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.1952	0.13	100	0.0789
0.0753	0.25	200	0.0183
0.0789	0.38	300	0.0273
0.1131	0.5	400	0.0146
0.0998	0.63	500	0.0134
0.0686	0.75	600	0.0079
0.069	0.88	700	0.0084

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

Task: Text Classification
Library: transformers
Type: gpt_neox
License: apache-2.0
Created: Oct 28, 2023
Updated: Nov 3, 2023