imdb-spoiler-distilbertOrigDatasetSampledOnly

Zritze/imdb-spoiler-distilbertOrigDatasetSampledOnly

imdb-spoiler-distilbertOrigDatasetSampledOnly 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 apache-2.0.

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

Downloads · 30 days

2% of all-time downloads

All-time downloads

283

Public

Parameters

125M

9.9 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: apache-2.0
Model type: roberta
Access: Public
Created: Apr 17, 2024
Updated: Apr 17, 2024
SHA: d4ab781c

Try a prompt

Base models

Model card

From the Hugging Face model README

imdb-spoiler-distilbertOrigDatasetSampledOnly

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

Loss: 1.1065
Accuracy: 0.6849
Recall: 0.6615
Precision: 0.6939
F1: 0.6773

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

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Recall	Precision	F1
0.5154	0.12	500	0.6116	0.6853	0.8147	0.6471	0.7213
0.4616	0.25	1000	0.6352	0.6946	0.7063	0.6902	0.6981
0.4422	0.38	1500	0.7289	0.69	0.7265	0.6771	0.7009
0.4228	0.5	2000	0.7194	0.6957	0.6575	0.7120	0.6836
0.4464	0.62	2500	0.6603	0.6926	0.6757	0.6994	0.6873
0.4142	0.75	3000	0.6885	0.6813	0.726	0.6664	0.6949
0.4273	0.88	3500	0.6638	0.69	0.7328	0.6750	0.7027
0.5912	1.0	4000	0.5640	0.7025	0.7113	0.6990	0.7051
0.4345	1.12	4500	0.7228	0.6949	0.6435	0.7172	0.6784
0.4336	1.25	5000	0.6732	0.6911	0.5915	0.7387	0.6569
0.4289	1.38	5500	0.6717	0.694	0.662	0.7073	0.6839
0.4219	1.5	6000	0.6760	0.6834	0.688	0.6817	0.6848
0.4175	1.62	6500	0.7393	0.6897	0.6757	0.6952	0.6853
0.4171	1.75	7000	0.7033	0.6797	0.597	0.7154	0.6509
0.4345	1.88	7500	0.6748	0.6874	0.6505	0.7023	0.6754
0.4063	2.0	8000	0.7267	0.6913	0.6098	0.7285	0.6639
0.3102	2.12	8500	1.0369	0.684	0.6308	0.7059	0.6662
0.3338	2.25	9000	1.0451	0.6846	0.6773	0.6874	0.6823
0.3257	2.38	9500	1.0364	0.682	0.6322	0.7021	0.6654
0.3235	2.5	10000	1.0224	0.6823	0.6315	0.7028	0.6653
0.3171	2.62	10500	1.1165	0.6859	0.6368	0.7061	0.6696
0.3266	2.75	11000	1.1109	0.6834	0.6315	0.7046	0.6661
0.2914	2.88	11500	1.1022	0.6829	0.6488	0.6963	0.6717
0.3041	3.0	12000	1.1065	0.6849	0.6615	0.6939	0.6773

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: apache-2.0
Created: Apr 17, 2024
Updated: Apr 17, 2024