deed-summarization_version_11

Hasanur525/deed-summarization_version_11

deed-summarization_version_11 is a machine learning model from Hasanur525. 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.

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

Downloads · 30 days

17% of all-time downloads

All-time downloads

Public

Parameters

582M

2.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors2.3 GB · 99%

At a glance

Library: transformers
Model type: mt5
Access: Public
Created: Feb 20, 2024
Updated: Feb 20, 2024
SHA: bbc5acab

Base models

Hasanur525/deed-summarization_version_10

Model card

From the Hugging Face model README

deed-summarization_version_11

This model is a fine-tuned version of Hasanur525/deed-summarization_version_10 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2748
Rouge1: 0.7615
Rouge2: 0.3638
Rougel: 0.7644
Rougelsum: 0.7534
Gen Len: 98.2164

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: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 5000
num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.1025	1.0	265	0.4128	0.3423	0.1522	0.3482	0.3493	98.4272
0.7311	2.0	530	0.4113	0.3324	0.1504	0.3405	0.3389	98.465
0.1826	3.0	795	0.4086	0.3511	0.1619	0.36	0.3585	98.328
0.6314	4.0	1060	0.4053	0.3198	0.1474	0.3222	0.3179	98.4565
0.4551	5.0	1325	0.4025	0.363	0.1659	0.3732	0.3694	98.3507
1.1978	6.0	1590	0.3960	0.3611	0.1386	0.3589	0.3577	98.3043
1.078	7.0	1855	0.3902	0.3158	0.1445	0.3112	0.3074	98.3809
0.2222	8.0	2120	0.3846	0.4959	0.2242	0.494	0.4793	98.2212
0.811	9.0	2385	0.3811	0.4641	0.2215	0.464	0.4499	98.2457
0.4816	10.0	2650	0.3713	0.436	0.217	0.439	0.4368	98.1881
0.2396	11.0	2915	0.3650	0.556	0.2677	0.5563	0.5475	98.2571
0.1897	12.0	3180	0.3601	0.6718	0.4061	0.6712	0.6631	98.1597
0.6071	13.0	3445	0.3498	0.5639	0.294	0.5623	0.5554	98.1096
0.3386	14.0	3710	0.3416	0.4915	0.2933	0.5002	0.4954	98.069
0.2921	15.0	3975	0.3342	0.4391	0.2676	0.4381	0.4342	97.7353
1.4814	16.0	4240	0.3261	0.5389	0.2966	0.5542	0.5466	98.0945
0.1891	17.0	4505	0.3167	0.4885	0.2725	0.5044	0.4923	98.2146
0.4877	18.0	4770	0.3090	0.6391	0.3774	0.6378	0.6224	98.2098
0.6804	19.0	5035	0.3016	0.766	0.4274	0.7649	0.7553	97.8828
0.1395	20.0	5300	0.2930	0.7208	0.3954	0.7478	0.7245	98.0955
0.4395	21.0	5565	0.2866	0.7457	0.406	0.7629	0.7453	97.9509
0.2215	22.0	5830	0.2820	0.6278	0.3099	0.6447	0.6288	98.0255
0.6845	23.0	6095	0.2775	0.7815	0.3541	0.7789	0.7629	98.1692
0.3637	24.0	6360	0.2753	0.819	0.3989	0.8195	0.8062	98.328
0.4836	25.0	6625	0.2748	0.7615	0.3638	0.7644	0.7534	98.2164

Framework versions

Transformers 4.37.2
Pytorch 2.1.0.dev20230811+cu121
Datasets 2.17.0
Tokenizers 0.15.2

Library: transformers
Type: mt5
Created: Feb 20, 2024
Updated: Feb 20, 2024