molgpt_selfies_100mzinc_384width

victornica/molgpt_selfies_100mzinc_384width

molgpt_selfies_100mzinc_384width is a text generation model from victornica. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.

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

Downloads · 30 days

2% of all-time downloads

All-time downloads

996

Public

Repo size

686 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin57.1 MB · 100%

At a glance

Task: Text Generation
Library: transformers
License: mit
Model type: gpt2
Access: Public
Created: Sep 9, 2023
Updated: Sep 10, 2023
SHA: 01c0cf91

Try a prompt

Base models

Model card

From the Hugging Face model README

molgpt_selfies_100mzinc_384width

This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.5005

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: 0.0005
train_batch_size: 192
eval_batch_size: 192
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 5000
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.578	0.1	50000	0.5535
0.5564	0.2	100000	0.5450
0.5487	0.3	150000	0.5389
0.5429	0.4	200000	0.5336
0.5369	0.5	250000	0.5275
0.5306	0.6	300000	0.5213
0.5236	0.7	350000	0.5146
0.5163	0.8	400000	0.5079
0.5095	0.9	450000	0.5022
0.5055	1.0	500000	0.5005

Framework versions

Transformers 4.33.1
Pytorch 2.0.1
Datasets 2.14.5
Tokenizers 0.13.3

Task: Text Generation
Library: transformers
Type: gpt2
License: mit
Created: Sep 9, 2023
Updated: Sep 10, 2023