phobert-v2-UIT-VSMEC-ep20

datht/phobert-v2-UIT-VSMEC-ep20

phobert-v2-UIT-VSMEC-ep20 is a text classification model from datht. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as agpl-3.0.

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

Downloads · 30 days

24% of all-time downloads

All-time downloads

Public

Parameters

135M

1.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors270 MB · 98%

At a glance

Task: Text Classification
Library: transformers
License: agpl-3.0
Model type: roberta
Access: Public
Created: May 15, 2025
Updated: May 15, 2025
SHA: 808157eb

Try a prompt

Base models

vinai/phobert-base-v2

Model card

From the Hugging Face model README

phobert-v2-UIT-VSMEC-ep20

This model is a fine-tuned version of vinai/phobert-base-v2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.7445
Micro F1: 31.1953
Micro Precision: 31.1953
Micro Recall: 31.1953
Macro F1: 6.7937
Macro Precision: 4.4565
Macro Recall: 14.2857

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: 0.0002
train_batch_size: 16
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.01
num_epochs: 20.0

Training results

Training Loss	Epoch	Step	Validation Loss	Micro F1	Micro Precision	Micro Recall	Macro F1	Macro Precision	Macro Recall
1.6508	1.0	87	1.6280	38.1924	38.1924	38.1924	13.6689	11.0672	19.7948
1.6617	2.0	174	1.6283	41.8367	41.8367	41.8367	18.9235	16.9137	23.0805
1.7109	3.0	261	1.7474	32.6531	32.6531	32.6531	10.8742	8.5221	17.8755
1.7516	4.0	348	1.7299	33.0904	33.0904	33.0904	9.5104	10.4580	15.7395
1.6395	5.0	435	1.6963	36.1516	36.1516	36.1516	12.0999	10.4591	18.0399
1.7109	6.0	522	1.6895	36.1516	36.1516	36.1516	12.1304	10.5941	18.0399
1.6211	7.0	609	1.6557	39.2128	39.2128	39.2128	14.3600	10.8292	21.3168
1.6352	8.0	696	1.6453	36.8805	36.8805	36.8805	14.3207	11.9547	21.6941
1.7352	9.0	783	1.7116	30.7580	30.7580	30.7580	11.9946	11.8060	19.2029
1.5836	10.0	870	1.6459	37.4636	37.4636	37.4636	14.4364	11.7582	21.8830
1.6883	11.0	957	1.6196	38.6297	38.6297	38.6297	14.8475	11.9901	22.4561
1.7379	12.0	1044	1.6837	38.4840	38.4840	38.4840	13.8374	10.6984	20.2799
1.6898	13.0	1131	1.6709	37.7551	37.7551	37.7551	13.4848	10.5169	19.7508
1.8129	14.0	1218	1.7437	32.0700	32.0700	32.0700	8.2124	12.2136	14.9597
1.702	15.0	1305	1.7436	31.1953	31.1953	31.1953	6.7937	4.4565	14.2857
1.773	16.0	1392	1.7405	31.1953	31.1953	31.1953	6.7937	4.4565	14.2857
1.8234	17.0	1479	1.7439	31.1953	31.1953	31.1953	6.7937	4.4565	14.2857
1.7848	18.0	1566	1.7449	31.1953	31.1953	31.1953	6.7937	4.4565	14.2857
1.8039	19.0	1653	1.7440	31.1953	31.1953	31.1953	6.7937	4.4565	14.2857
1.777	19.7723	1720	1.7445	31.1953	31.1953	31.1953	6.7937	4.4565	14.2857

Framework versions

Transformers 4.50.0
Pytorch 2.6.0+cu124
Datasets 2.15.0
Tokenizers 0.21.1

Task: Text Classification
Library: transformers
Type: roberta
License: agpl-3.0
Created: May 15, 2025
Updated: May 15, 2025