imdb-spoiler-robertaOrigDatasetLR1

Zritze/imdb-spoiler-robertaOrigDatasetLR1

imdb-spoiler-robertaOrigDatasetLR1 is a text classification model from Zritze. Use it when you need a label for a piece of 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

693

Public

Parameters

125M

20.9 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors499 MB · 99%

At a glance

Task: Text Classification
Library: transformers
License: mit
Model type: roberta
Access: Public
Created: Apr 18, 2024
Updated: Apr 18, 2024
SHA: 56fee120

Try a prompt

Base models

FacebookAI/roberta-base

Model card

From the Hugging Face model README

imdb-spoiler-robertaOrigDatasetLR1

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

Loss: 0.5854
Accuracy: 0.7275
Recall: 0.7025
Precision: 0.7395
F1: 0.7205

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: 1e-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

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Recall	Precision	F1
0.6251	0.12	500	0.5814	0.6987	0.7987	0.6656	0.7261
0.5877	0.25	1000	0.5645	0.709	0.7712	0.6859	0.7261
0.5741	0.38	1500	0.5460	0.7211	0.643	0.7621	0.6975
0.5602	0.5	2000	0.5551	0.7212	0.8033	0.6901	0.7424
0.5571	0.62	2500	0.5527	0.7201	0.8323	0.6798	0.7483
0.5518	0.75	3000	0.5324	0.7304	0.7462	0.7233	0.7346
0.5599	0.88	3500	0.5345	0.7254	0.78	0.7032	0.7396
0.5583	1.0	4000	0.5332	0.729	0.7268	0.7300	0.7284
0.5051	1.12	4500	0.5525	0.7127	0.5915	0.7809	0.6731
0.5321	1.25	5000	0.5414	0.7259	0.7905	0.7000	0.7425
0.5085	1.38	5500	0.5497	0.7265	0.7113	0.7336	0.7223
0.5046	1.5	6000	0.5311	0.729	0.7183	0.7340	0.7261
0.5205	1.62	6500	0.5519	0.7289	0.7177	0.7341	0.7258
0.4905	1.75	7000	0.5636	0.7331	0.7502	0.7254	0.7376
0.5	1.88	7500	0.5355	0.726	0.7083	0.7343	0.7210
0.4922	2.0	8000	0.5460	0.7355	0.7462	0.7305	0.7383
0.4467	2.12	8500	0.5750	0.7238	0.6677	0.7520	0.7074
0.4395	2.25	9000	0.6195	0.7269	0.7252	0.7276	0.7264
0.4504	2.38	9500	0.5891	0.728	0.678	0.7533	0.7137
0.4285	2.5	10000	0.5959	0.7264	0.6833	0.7477	0.7140
0.4389	2.62	10500	0.5954	0.7221	0.6378	0.7672	0.6965
0.4553	2.75	11000	0.5842	0.7262	0.7157	0.7311	0.7233
0.4607	2.88	11500	0.5779	0.7285	0.6945	0.7452	0.7189
0.4373	3.0	12000	0.5854	0.7275	0.7025	0.7395	0.7205

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Task: Text Classification
Library: transformers
Type: roberta
License: mit
Created: Apr 18, 2024
Updated: Apr 18, 2024