distilbert-sentiment-yelp-sft

wsklee/distilbert-sentiment-yelp-sft

distilbert-sentiment-yelp-sft is a text classification model from wsklee. 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

10% of all-time downloads

All-time downloads

Public

Parameters

67M

2.7 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors268 MB · 100%

At a glance

Task: Text Classification
Library: transformers
License: apache-2.0
Model type: distilbert
Access: Public
Created: Nov 15, 2024
Updated: Nov 15, 2024
SHA: c4228b95

Try a prompt

Base models

distilbert/distilbert-base-uncased

Model card

From the Hugging Face model README

distilbert-sentiment-yelp-sft

This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1282
Accuracy: 0.9513

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: 0.0003
train_batch_size: 128
eval_batch_size: 256
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3111	0.0457	200	0.1634	0.9365
0.175	0.0914	400	0.1635	0.9385
0.165	0.1371	600	0.2023	0.9212
0.1792	0.1829	800	0.1602	0.9397
0.1832	0.2286	1000	0.1893	0.9272
0.1811	0.2743	1200	0.1942	0.9276
0.1756	0.32	1400	0.1769	0.9307
0.176	0.3657	1600	0.1631	0.9387
0.1759	0.4114	1800	0.1936	0.922
0.173	0.4571	2000	0.1807	0.933
0.1687	0.5029	2200	0.1615	0.9337
0.1663	0.5486	2400	0.1647	0.9362
0.1675	0.5943	2600	0.1620	0.9369
0.1656	0.64	2800	0.1704	0.9323
0.1667	0.6857	3000	0.1662	0.9412
0.1658	0.7314	3200	0.1513	0.9448
0.1624	0.7771	3400	0.1523	0.9422
0.159	0.8229	3600	0.1445	0.9443
0.1549	0.8686	3800	0.1408	0.9466
0.1541	0.9143	4000	0.1447	0.9449
0.1604	0.96	4200	0.1414	0.9475
0.151	1.0057	4400	0.1629	0.9334
0.1342	1.0514	4600	0.1482	0.9441
0.134	1.0971	4800	0.1383	0.9467
0.1316	1.1429	5000	0.1397	0.9472
0.1313	1.1886	5200	0.1414	0.9475
0.1263	1.2343	5400	0.1426	0.9478
0.1206	1.28	5600	0.1401	0.9482
0.1189	1.3257	5800	0.1430	0.9473
0.1166	1.3714	6000	0.1368	0.9511
0.1205	1.4171	6200	0.1331	0.9499
0.1187	1.4629	6400	0.1327	0.9501
0.1185	1.5086	6600	0.1353	0.9501
0.1172	1.5543	6800	0.1383	0.949
0.1146	1.6	7000	0.1325	0.9511
0.1114	1.6457	7200	0.1340	0.9513
0.1152	1.6914	7400	0.1325	0.9508
0.1151	1.7371	7600	0.1290	0.9512
0.1117	1.7829	7800	0.1298	0.9512
0.1144	1.8286	8000	0.1297	0.9513
0.1083	1.8743	8200	0.1295	0.9519
0.1132	1.92	8400	0.1278	0.9512
0.1126	1.9657	8600	0.1282	0.9513

Framework versions

Transformers 4.46.2
Pytorch 2.5.1
Datasets 3.1.0
Tokenizers 0.20.3

Task: Text Classification
Library: transformers
Type: distilbert
License: apache-2.0
Created: Nov 15, 2024
Updated: Nov 15, 2024