mt5-large-gecid-e8-b8

jeremyvictor/mt5-large-gecid-e8-b8

mt5-large-gecid-e8-b8 is a machine learning model from jeremyvictor. 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

18% of all-time downloads

All-time downloads

Public

Repo size

29.5 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin4.9 GB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: mt5
Access: Public
Created: May 5, 2023
Updated: May 5, 2023
SHA: ae5943cb

Model card

From the Hugging Face model README

mt5-large-gecid-e8-b8

This model is a fine-tuned version of google/mt5-large on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3000
Rouge1: 64.4729
Rouge2: 57.8072
Rougel: 64.3868
Rougelsum: 64.3569
Gen Len: 18.7495

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: 0.001
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adafactor
lr_scheduler_type: linear
num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.8319	0.57	500	0.4310	61.7619	53.4157	61.6684	61.6628	18.7567
0.4258	1.13	1000	0.3541	62.8056	55.1747	62.7392	62.7231	18.7601
0.2777	1.7	1500	0.3231	63.4739	56.1433	63.366	63.3544	18.7546
0.2023	2.26	2000	0.3068	64.1314	57.5343	64.0453	64.024	18.7546
0.1432	2.83	2500	0.3000	64.4729	57.8072	64.3868	64.3569	18.7495
0.0976	3.39	3000	0.3257	64.7215	58.3266	64.6223	64.5957	18.7601
0.0811	3.96	3500	0.3112	64.7518	58.4888	64.6487	64.6454	18.7648
0.0472	4.52	4000	0.3389	64.9658	58.822	64.8741	64.8621	18.7592
0.0413	5.09	4500	0.3557	64.9468	58.8286	64.8609	64.8501	18.7592
0.0248	5.66	5000	0.3452	65.2004	59.2566	65.0876	65.0889	18.7605
0.0195	6.22	5500	0.3719	65.1043	59.083	65.0369	65.026	18.7541
0.013	6.79	6000	0.3947	65.3124	59.486	65.2434	65.2324	18.7571
0.0084	7.35	6500	0.4056	65.4053	59.6589	65.3249	65.3115	18.7580
0.0055	7.92	7000	0.4216	65.3303	59.5344	65.2475	65.2284	18.7567

Framework versions

Transformers 4.28.1
Pytorch 1.11.0a0+b6df043
Datasets 2.12.0
Tokenizers 0.13.2

Library: transformers
Type: mt5
License: apache-2.0
Created: May 5, 2023
Updated: May 5, 2023