T5tuned

waelChafei/T5tuned

T5tuned is a text classification model from waelChafei. 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

1% of all-time downloads

All-time downloads

583

Public

Parameters

111M

1.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors443 MB · 100%

At a glance

Task: Text Classification
Library: transformers
License: apache-2.0
Model type: bert
Access: Public
Created: Mar 25, 2024
Updated: Apr 15, 2024
SHA: 44f44ba0

Try a prompt

Base models

Model card

From the Hugging Face model README

TTC4900Model

This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5372
Accuracy: 0.8371
F1: 0.7316
Precision: 0.7615
Recall: 0.7112

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: 5e-05
train_batch_size: 32
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
1.4792	0.04	50	1.3375	0.5157	0.1525	0.2666	0.2006
1.2938	0.08	100	1.1358	0.6112	0.2290	0.4100	0.2395
1.1393	0.12	150	1.0186	0.6552	0.4235	0.5382	0.4140
1.0714	0.16	200	0.9367	0.7043	0.4586	0.5566	0.4520
0.9874	0.2	250	0.8549	0.7151	0.4912	0.7129	0.4745
0.8875	0.24	300	0.7741	0.7479	0.5512	0.6722	0.5300
0.8267	0.28	350	0.7463	0.7497	0.5841	0.6718	0.5784
0.798	0.33	400	0.7388	0.7559	0.5798	0.6802	0.5712
0.778	0.37	450	0.7351	0.7668	0.5795	0.7799	0.5318
0.7568	0.41	500	0.7147	0.7792	0.5958	0.7228	0.5931
0.721	0.45	550	0.8179	0.7299	0.5823	0.6824	0.5868
0.7534	0.49	600	0.6631	0.7874	0.6106	0.7809	0.5804
0.7242	0.53	650	0.6918	0.7843	0.5966	0.7648	0.5666
0.7236	0.57	700	0.7457	0.7733	0.5752	0.7704	0.5465
0.702	0.61	750	0.6810	0.7928	0.6059	0.7791	0.5692
0.6681	0.65	800	0.6318	0.8029	0.6441	0.7699	0.6255
0.6463	0.69	850	0.6754	0.7968	0.6387	0.7553	0.6412
0.7443	0.73	900	0.7580	0.7720	0.5804	0.7278	0.5933
0.7273	0.77	950	0.6410	0.8082	0.6364	0.7804	0.6112
0.6329	0.81	1000	0.6294	0.8028	0.6452	0.7305	0.6362
0.6623	0.85	1050	0.6742	0.7797	0.5614	0.8038	0.5437
0.6198	0.89	1100	0.6250	0.8048	0.6306	0.7658	0.6202
0.614	0.93	1150	0.7138	0.7852	0.6231	0.6792	0.6433
0.6423	0.98	1200	0.6581	0.7991	0.6601	0.7570	0.6526
0.6175	1.02	1250	0.6336	0.8107	0.6790	0.7297	0.6737
0.5583	1.06	1300	0.6364	0.8074	0.6505	0.7822	0.6284
0.5371	1.1	1350	0.6051	0.8158	0.6878	0.7743	0.6513
0.5173	1.14	1400	0.6464	0.7972	0.6981	0.7249	0.7007
0.5602	1.18	1450	0.6631	0.7928	0.6419	0.7471	0.6506
0.5187	1.22	1500	0.6140	0.8164	0.6756	0.7739	0.6674
0.6183	1.26	1550	0.6166	0.8170	0.6782	0.7513	0.6611
0.4991	1.3	1600	0.6289	0.8198	0.6920	0.8022	0.6470
0.5449	1.34	1650	0.6011	0.8194	0.6995	0.7613	0.6684
0.5358	1.38	1700	0.6036	0.8110	0.7041	0.7335	0.6973
0.5451	1.42	1750	0.6156	0.8141	0.6392	0.8173	0.6160
0.5421	1.46	1800	0.5723	0.8252	0.7149	0.7704	0.6930
0.5199	1.5	1850	0.6290	0.8129	0.6658	0.7989	0.6102
0.5477	1.54	1900	0.5792	0.8222	0.7008	0.7831	0.6682
0.5117	1.59	1950	0.5652	0.8288	0.7119	0.7801	0.6796
0.5201	1.63	2000	0.5661	0.8276	0.7143	0.7802	0.6871
0.5098	1.67	2050	0.5745	0.8265	0.6906	0.7897	0.6591
0.5226	1.71	2100	0.5768	0.8251	0.6948	0.7516	0.6903
0.5367	1.75	2150	0.5573	0.8318	0.7180	0.7886	0.6879
0.5484	1.79	2200	0.5738	0.8241	0.6990	0.7818	0.6638
0.534	1.83	2250	0.5601	0.8299	0.7167	0.7799	0.6898
0.5423	1.87	2300	0.5571	0.8240	0.7228	0.7592	0.7153
0.5056	1.91	2350	0.5635	0.8267	0.7004	0.8005	0.6642
0.5355	1.95	2400	0.5546	0.8275	0.7167	0.7681	0.7053
0.5387	1.99	2450	0.5417	0.8315	0.7277	0.7656	0.7028
0.4148	2.03	2500	0.6051	0.8310	0.7170	0.7716	0.6878
0.4685	2.07	2550	0.5605	0.8302	0.7139	0.7818	0.6980
0.5007	2.11	2600	0.5530	0.8326	0.7288	0.7650	0.7165
0.4524	2.15	2650	0.5648	0.8302	0.7188	0.7680	0.6941
0.4437	2.2	2700	0.5636	0.8275	0.7287	0.7684	0.7171
0.4326	2.24	2750	0.5542	0.8341	0.7166	0.7889	0.6903
0.4182	2.28	2800	0.5697	0.8272	0.7283	0.7398	0.7227
0.4466	2.32	2850	0.5628	0.8343	0.7257	0.7925	0.6958
0.4118	2.36	2900	0.5717	0.8266	0.7249	0.7334	0.7250
0.3689	2.4	2950	0.5716	0.8342	0.7259	0.7705	0.7105
0.4332	2.44	3000	0.5557	0.8345	0.7316	0.7586	0.7192
0.3926	2.48	3050	0.5635	0.8352	0.7266	0.7762	0.7071
0.4141	2.52	3100	0.5553	0.8354	0.7273	0.7732	0.6983
0.3984	2.56	3150	0.5605	0.8349	0.7343	0.7670	0.7142
0.4267	2.6	3200	0.5478	0.8376	0.7325	0.7828	0.7054
0.4309	2.64	3250	0.5512	0.8339	0.7341	0.7672	0.7155
0.408	2.68	3300	0.5598	0.8351	0.7339	0.7637	0.7134
0.4174	2.72	3350	0.5553	0.8320	0.7374	0.7668	0.7206
0.3979	2.76	3400	0.5559	0.8357	0.7342	0.7713	0.7151
0.4021	2.8	3450	0.5500	0.8356	0.7364	0.7595	0.7259
0.4018	2.85	3500	0.5485	0.8371	0.7356	0.7715	0.7151
0.392	2.89	3550	0.5566	0.8348	0.7368	0.7627	0.7252
0.3695	2.93	3600	0.5548	0.8355	0.7380	0.7614	0.7251
0.3936	2.97	3650	0.5503	0.8353	0.7387	0.7627	0.7256

Framework versions

Transformers 4.38.2
Pytorch 2.1.2
Datasets 2.1.0
Tokenizers 0.15.2

Task: Text Classification
Library: transformers
Type: bert
License: apache-2.0
Created: Mar 25, 2024
Updated: Apr 15, 2024