ptt5-wikilingua-cstnews

arthurmluz/ptt5-wikilingua-cstnews

ptt5-wikilingua-cstnews is a machine learning model from arthurmluz. 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 mit.

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

Downloads · 30 days

38% of all-time downloads

All-time downloads

Public

Repo size

1.8 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin892 MB · 100%

At a glance

Library: transformers
License: mit
Model type: t5
Access: Public
Created: Oct 22, 2023
Updated: Nov 27, 2024
SHA: d59c757f

Base models

arthurmluz/ptt5-wikilingua-30epochs

Model card

From the Hugging Face model README

ptt5-wikilingua-cstnews

This model is a fine-tuned version of arthurmluz/ptt5-wikilingua-30epochs on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.2336
Rouge1: 0.2757
Rouge2: 0.2182
Rougel: 0.2534
Rougelsum: 0.2727
Gen Len: 19.0

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: 2
eval_batch_size: 2
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	47	1.4403	0.2059	0.1334	0.1769	0.1998	18.6452
No log	2.0	94	1.3259	0.2356	0.1632	0.2052	0.2286	18.871
No log	3.0	141	1.2783	0.244	0.1737	0.215	0.2331	18.871
No log	4.0	188	1.2469	0.2518	0.1866	0.2174	0.2366	18.9355
1.7624	5.0	235	1.2306	0.266	0.1958	0.2321	0.2539	18.9355
1.7624	6.0	282	1.2214	0.2644	0.1991	0.2347	0.2533	18.9355
1.7624	7.0	329	1.2133	0.2603	0.1975	0.2327	0.2505	18.9355
1.7624	8.0	376	1.2076	0.267	0.2058	0.2423	0.2589	18.9355
1.3494	9.0	423	1.2026	0.2698	0.2073	0.2454	0.2643	18.9355
1.3494	10.0	470	1.1997	0.2704	0.2078	0.2457	0.2649	19.0
1.3494	11.0	517	1.2006	0.2762	0.2151	0.2518	0.2736	19.0
1.3494	12.0	564	1.2012	0.2772	0.2163	0.2545	0.2746	19.0
1.1715	13.0	611	1.2017	0.2787	0.2176	0.2555	0.2763	19.0
1.1715	14.0	658	1.2048	0.278	0.2187	0.256	0.2753	19.0
1.1715	15.0	705	1.2063	0.2755	0.2219	0.2579	0.2735	19.0
1.1715	16.0	752	1.2057	0.2768	0.2219	0.2589	0.2748	19.0
1.1715	17.0	799	1.2084	0.2798	0.2244	0.26	0.2783	19.0
1.0497	18.0	846	1.2138	0.2787	0.2258	0.2602	0.2764	19.0
1.0497	19.0	893	1.2177	0.2783	0.2248	0.26	0.2761	19.0
1.0497	20.0	940	1.2166	0.2767	0.2215	0.2583	0.2745	19.0
1.0497	21.0	987	1.2187	0.2738	0.2162	0.2527	0.2715	19.0
0.9439	22.0	1034	1.2196	0.2741	0.2171	0.2531	0.2718	19.0
0.9439	23.0	1081	1.2229	0.2741	0.2171	0.2531	0.2718	19.0
0.9439	24.0	1128	1.2257	0.2757	0.2182	0.2534	0.2727	19.0
0.9439	25.0	1175	1.2292	0.2739	0.2171	0.2525	0.2713	19.0
0.8986	26.0	1222	1.2294	0.2739	0.2171	0.2525	0.2713	19.0
0.8986	27.0	1269	1.2310	0.2767	0.2192	0.2548	0.2741	19.0
0.8986	28.0	1316	1.2325	0.2747	0.218	0.2536	0.2725	19.0
0.8986	29.0	1363	1.2335	0.2739	0.2171	0.2525	0.2713	19.0
0.8805	30.0	1410	1.2336	0.2757	0.2182	0.2534	0.2727	19.0

Framework versions

Transformers 4.34.0
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.14.1

Library: transformers
Type: t5
License: mit
Languages: pt
Created: Oct 22, 2023
Updated: Nov 27, 2024