PhoBert_Lexical_Dataset59KCoDuoi

gechim/PhoBert_Lexical_Dataset59KCoDuoi

PhoBert_Lexical_Dataset59KCoDuoi is a machine learning model from gechim. 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

29% of all-time downloads

All-time downloads

Public

Parameters

135M

538 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors538 MB · 100%

At a glance

Library: transformers
Model type: roberta
Access: Public
Created: Jun 23, 2024
Updated: Jun 23, 2024
SHA: 82a40250

Base models

vinai/phobert-base-v2

Model card

From the Hugging Face model README

PhoBert_Lexical_Dataset59KCoDuoi

This model is a fine-tuned version of vinai/phobert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2741
Accuracy: 0.9600
F1: 0.9602

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: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.2558	200	0.1794	0.9396	0.9400
No log	0.5115	400	0.1533	0.9475	0.9479
No log	0.7673	600	0.1522	0.9496	0.9499
0.1767	1.0230	800	0.1494	0.9542	0.9545
0.1767	1.2788	1000	0.1485	0.9519	0.9520
0.1767	1.5345	1200	0.1608	0.9524	0.9523
0.1767	1.7903	1400	0.1223	0.9580	0.9582
0.1176	2.0460	1600	0.1462	0.9600	0.9603
0.1176	2.3018	1800	0.1363	0.9588	0.9591
0.1176	2.5575	2000	0.1441	0.9574	0.9577
0.1176	2.8133	2200	0.1369	0.9566	0.9568
0.0972	3.0691	2400	0.1530	0.9547	0.9550
0.0972	3.3248	2600	0.1278	0.9607	0.9608
0.0972	3.5806	2800	0.1334	0.9604	0.9606
0.0972	3.8363	3000	0.1280	0.9608	0.9609
0.0821	4.0921	3200	0.1379	0.9603	0.9604
0.0821	4.3478	3400	0.1466	0.9587	0.9589
0.0821	4.6036	3600	0.1379	0.9604	0.9606
0.0821	4.8593	3800	0.1347	0.9606	0.9607
0.0687	5.1151	4000	0.1492	0.9614	0.9614
0.0687	5.3708	4200	0.1611	0.9606	0.9606
0.0687	5.6266	4400	0.1407	0.9594	0.9596
0.0687	5.8824	4600	0.1446	0.9590	0.9591
0.0584	6.1381	4800	0.1659	0.9575	0.9578
0.0584	6.3939	5000	0.1666	0.9602	0.9602
0.0584	6.6496	5200	0.1683	0.9586	0.9588
0.0584	6.9054	5400	0.1668	0.9609	0.9611
0.0477	7.1611	5600	0.1844	0.9580	0.9582
0.0477	7.4169	5800	0.1695	0.9626	0.9627
0.0477	7.6726	6000	0.1767	0.9596	0.9597
0.0477	7.9284	6200	0.1960	0.9594	0.9596
0.0397	8.1841	6400	0.1932	0.9599	0.9600
0.0397	8.4399	6600	0.1990	0.9593	0.9594
0.0397	8.6957	6800	0.1999	0.9602	0.9603
0.0397	8.9514	7000	0.1803	0.9577	0.9580
0.0349	9.2072	7200	0.2082	0.9574	0.9575
0.0349	9.4629	7400	0.2075	0.9597	0.9598
0.0349	9.7187	7600	0.2269	0.9577	0.9577
0.0349	9.9744	7800	0.1990	0.9602	0.9602
0.0294	10.2302	8000	0.1987	0.9599	0.9600
0.0294	10.4859	8200	0.2066	0.9563	0.9563
0.0294	10.7417	8400	0.2149	0.9595	0.9597
0.0257	10.9974	8600	0.2179	0.9609	0.9610
0.0257	11.2532	8800	0.2337	0.9593	0.9594
0.0257	11.5090	9000	0.2499	0.9573	0.9573
0.0257	11.7647	9200	0.2323	0.9575	0.9577
0.021	12.0205	9400	0.2330	0.9599	0.9601
0.021	12.2762	9600	0.2321	0.9603	0.9604
0.021	12.5320	9800	0.2431	0.9594	0.9594
0.021	12.7877	10000	0.2487	0.9581	0.9583
0.017	13.0435	10200	0.2606	0.9570	0.9570
0.017	13.2992	10400	0.2450	0.9582	0.9583
0.017	13.5550	10600	0.2647	0.9593	0.9596
0.017	13.8107	10800	0.2494	0.9595	0.9597
0.0155	14.0665	11000	0.2482	0.9582	0.9584
0.0155	14.3223	11200	0.2552	0.9605	0.9606
0.0155	14.5780	11400	0.2581	0.9583	0.9585
0.0155	14.8338	11600	0.2553	0.9609	0.9611
0.0146	15.0895	11800	0.2601	0.9591	0.9592
0.0146	15.3453	12000	0.2574	0.9593	0.9594
0.0146	15.6010	12200	0.2562	0.9614	0.9615
0.0146	15.8568	12400	0.2588	0.9596	0.9597
0.0114	16.1125	12600	0.2621	0.9581	0.9581
0.0114	16.3683	12800	0.2593	0.9591	0.9593
0.0114	16.6240	13000	0.2611	0.9607	0.9608
0.0114	16.8798	13200	0.2668	0.9600	0.9602
0.0091	17.1355	13400	0.2554	0.9618	0.9620
0.0091	17.3913	13600	0.2707	0.9596	0.9597
0.0091	17.6471	13800	0.2742	0.9597	0.9599
0.0091	17.9028	14000	0.2777	0.9590	0.9591
0.0057	18.1586	14200	0.2737	0.9596	0.9597
0.0057	18.4143	14400	0.2731	0.9598	0.9599
0.0057	18.6701	14600	0.2693	0.9606	0.9607
0.0057	18.9258	14800	0.2754	0.9597	0.9598
0.0074	19.1816	15000	0.2729	0.9602	0.9602
0.0074	19.4373	15200	0.2784	0.9595	0.9596
0.0074	19.6931	15400	0.2766	0.9598	0.9599
0.0074	19.9488	15600	0.2741	0.9600	0.9602

Framework versions

Transformers 4.41.2
Pytorch 2.1.2
Datasets 2.19.2
Tokenizers 0.19.1

Library: transformers
Type: roberta
Created: Jun 23, 2024
Updated: Jun 23, 2024