gpt1B_reward_test

thorirhrafn/gpt1B_reward_test

gpt1B_reward_test is a machine learning model from thorirhrafn. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.

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

Downloads · 30 days

38% of all-time downloads

All-time downloads

Public

Repo size

51.5 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors50.3 MB · 98%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Apr 19, 2024
Updated: Apr 20, 2024
SHA: e4a8444b

Base models

AI-Sweden-Models/gpt-sw3-1.3b

Model card

From the Hugging Face model README

gpt1B_reward_test

This model is a fine-tuned version of AI-Sweden-Models/gpt-sw3-1.3b on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6367
Accuracy: 0.6504

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: 3e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6878	0.04	200	0.6850	0.5791
0.6724	0.08	400	0.6740	0.6024
0.6611	0.13	600	0.6703	0.6081
0.6435	0.17	800	0.6773	0.6036
0.6787	0.21	1000	0.6544	0.6189
0.7166	0.25	1200	0.6697	0.6223
0.614	0.3	1400	0.6590	0.6250
0.6279	0.34	1600	0.6422	0.6343
0.6185	0.38	1800	0.6427	0.6389
0.5539	0.42	2000	0.6459	0.6390
0.5988	0.47	2200	0.6485	0.6379
0.6096	0.51	2400	0.6570	0.6439
0.5898	0.55	2600	0.6381	0.6441
0.6366	0.59	2800	0.6479	0.6389
0.6457	0.64	3000	0.6397	0.6490
0.6171	0.68	3200	0.6476	0.6467
0.5262	0.72	3400	0.6506	0.6458
0.5723	0.76	3600	0.6467	0.6471
0.6194	0.81	3800	0.6393	0.6480
0.5946	0.85	4000	0.6375	0.6490
0.5868	0.89	4200	0.6366	0.6503
0.5905	0.93	4400	0.6367	0.6505
0.5651	0.97	4600	0.6367	0.6504

Framework versions

PEFT 0.8.2
Transformers 4.38.1
Pytorch 2.2.0+cu118
Datasets 2.17.1
Tokenizers 0.15.2

Library: peft
License: apache-2.0
Created: Apr 19, 2024
Updated: Apr 20, 2024