t5-base-finetuned-ner_docred_30

zblaaa/t5-base-finetuned-ner_docred_30

t5-base-finetuned-ner_docred_30 is a machine learning model from zblaaa. Use it for the machine learning task on the model card, and read the license before you ship it in a product. 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

26% of all-time downloads

All-time downloads

Public

Repo size

8 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin892 MB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: t5
Access: Public
Created: Jul 12, 2023
Updated: Jul 12, 2023
SHA: a3728e1a

Model card

From the Hugging Face model README

t5-base-finetuned-ner_docred_30

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

Loss: 0.1900
Rouge1: 6.698
Rouge2: 5.261
Rougel: 6.6835
Rougelsum: 6.6818
Gen Len: 20.0

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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	125	0.5156	6.5406	4.9855	6.4905	6.494	20.0
No log	2.0	250	0.3949	6.5113	4.9122	6.4534	6.4453	20.0
No log	3.0	375	0.3280	6.5165	4.9088	6.4537	6.451	20.0
0.7311	4.0	500	0.2949	6.424	4.7298	6.3672	6.3627	20.0
0.7311	5.0	625	0.2764	6.6189	5.1219	6.5651	6.5672	20.0
0.7311	6.0	750	0.2633	6.628	5.1335	6.5664	6.5721	20.0
0.7311	7.0	875	0.2547	6.5591	4.9979	6.5075	6.5057	20.0
0.3331	8.0	1000	0.2482	6.6612	5.1918	6.5987	6.6068	20.0
0.3331	9.0	1125	0.2413	6.6093	5.0954	6.5515	6.5553	20.0
0.3331	10.0	1250	0.2357	6.6264	5.1201	6.5681	6.5723	20.0
0.3331	11.0	1375	0.2300	6.6487	5.1525	6.6176	6.6177	20.0
0.2788	12.0	1500	0.2226	6.6858	5.2325	6.6745	6.6762	20.0
0.2788	13.0	1625	0.2166	6.6495	5.1531	6.6378	6.6377	20.0
0.2788	14.0	1750	0.2108	6.6807	5.2212	6.6653	6.6664	20.0
0.2788	15.0	1875	0.2068	6.6811	5.2248	6.6699	6.6697	20.0
0.2435	16.0	2000	0.2030	6.6701	5.2077	6.652	6.6492	20.0
0.2435	17.0	2125	0.1997	6.6845	5.2334	6.6647	6.6624	20.0
0.2435	18.0	2250	0.1978	6.6762	5.2202	6.6571	6.6559	20.0
0.2435	19.0	2375	0.1964	6.684	5.2358	6.6695	6.6683	20.0
0.2188	20.0	2500	0.1957	6.6882	5.2426	6.675	6.6735	20.0
0.2188	21.0	2625	0.1942	6.6882	5.2426	6.675	6.6735	20.0
0.2188	22.0	2750	0.1932	6.6935	5.2513	6.6784	6.6762	20.0
0.2188	23.0	2875	0.1924	6.6935	5.2513	6.6784	6.6762	20.0
0.2052	24.0	3000	0.1918	6.6882	5.2426	6.675	6.6735	20.0
0.2052	25.0	3125	0.1915	6.6935	5.2513	6.6784	6.6762	20.0
0.2052	26.0	3250	0.1908	6.698	5.261	6.6835	6.6818	20.0
0.2052	27.0	3375	0.1905	6.698	5.261	6.6835	6.6818	20.0
0.1977	28.0	3500	0.1901	6.698	5.261	6.6835	6.6818	20.0
0.1977	29.0	3625	0.1900	6.698	5.261	6.6835	6.6818	20.0
0.1977	30.0	3750	0.1900	6.698	5.261	6.6835	6.6818	20.0

Framework versions

Transformers 4.30.0.dev0
Pytorch 2.1.0.dev20230611+cu118
Datasets 2.12.0
Tokenizers 0.13.3

Library: transformers
Type: t5
License: apache-2.0
Created: Jul 12, 2023
Updated: Jul 12, 2023