PhoBertLexical-finetuned_70KURL_not_host

gechim/PhoBertLexical-finetuned_70KURL_not_host

PhoBertLexical-finetuned_70KURL_not_host 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

26% 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 17, 2024
Updated: Jun 17, 2024
SHA: c0e818b8

Base models

vinai/phobert-base-v2

Model card

From the Hugging Face model README

PhoBertLexical-finetuned_70KURL_not_host

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: 0.4681
Accuracy: 0.9143
F1: 0.9147

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	0.2326	200	0.2934	0.8767	0.8768
No log	0.4651	400	0.2560	0.8910	0.8910
No log	0.6977	600	0.2634	0.8938	0.8953
No log	0.9302	800	0.2293	0.9010	0.9018
0.3037	1.1628	1000	0.2435	0.8990	0.9010
0.3037	1.3953	1200	0.2281	0.9073	0.9078
0.3037	1.6279	1400	0.2286	0.9038	0.9056
0.3037	1.8605	1600	0.2566	0.8971	0.8998
0.2196	2.0930	1800	0.2380	0.9102	0.9093
0.2196	2.3256	2000	0.2344	0.9044	0.9062
0.2196	2.5581	2200	0.2245	0.9108	0.9121
0.2196	2.7907	2400	0.2144	0.9108	0.9113
0.1815	3.0233	2600	0.2328	0.9123	0.9125
0.1815	3.2558	2800	0.2300	0.9073	0.9076
0.1815	3.4884	3000	0.2308	0.9128	0.9131
0.1815	3.7209	3200	0.2210	0.9104	0.9118
0.1815	3.9535	3400	0.2362	0.9120	0.9134
0.1522	4.1860	3600	0.2372	0.9156	0.9165
0.1522	4.4186	3800	0.2270	0.9158	0.9159
0.1522	4.6512	4000	0.2409	0.9148	0.9147
0.1522	4.8837	4200	0.2461	0.9138	0.9147
0.1274	5.1163	4400	0.2397	0.9143	0.9150
0.1274	5.3488	4600	0.2467	0.9175	0.9178
0.1274	5.5814	4800	0.2394	0.9144	0.9144
0.1274	5.8140	5000	0.2712	0.9153	0.9163
0.1062	6.0465	5200	0.2551	0.9131	0.9136
0.1062	6.2791	5400	0.2861	0.9147	0.9152
0.1062	6.5116	5600	0.2834	0.9094	0.9109
0.1062	6.7442	5800	0.2624	0.9161	0.9167
0.1062	6.9767	6000	0.2752	0.9142	0.9139
0.0911	7.2093	6200	0.2836	0.9145	0.9152
0.0911	7.4419	6400	0.3296	0.9107	0.9116
0.0911	7.6744	6600	0.2723	0.9126	0.9132
0.0911	7.9070	6800	0.3090	0.9108	0.9119
0.0764	8.1395	7000	0.3215	0.9120	0.9128
0.0764	8.3721	7200	0.2989	0.9150	0.9156
0.0764	8.6047	7400	0.3112	0.9132	0.9137
0.0764	8.8372	7600	0.3274	0.9158	0.9154
0.0668	9.0698	7800	0.3578	0.9150	0.9156
0.0668	9.3023	8000	0.3280	0.9181	0.9180
0.0668	9.5349	8200	0.3267	0.9137	0.9140
0.0668	9.7674	8400	0.3287	0.9152	0.9159
0.0584	10.0	8600	0.3252	0.9156	0.9158
0.0584	10.2326	8800	0.3461	0.9113	0.9118
0.0584	10.4651	9000	0.3692	0.9150	0.9150
0.0584	10.6977	9200	0.3772	0.9134	0.9138
0.0584	10.9302	9400	0.3703	0.9117	0.9126
0.0521	11.1628	9600	0.3797	0.9168	0.9168
0.0521	11.3953	9800	0.3760	0.9130	0.9135
0.0521	11.6279	10000	0.3772	0.9148	0.9150
0.0521	11.8605	10200	0.3837	0.9146	0.9152
0.0444	12.0930	10400	0.3952	0.9158	0.9156
0.0444	12.3256	10600	0.4115	0.9132	0.9141
0.0444	12.5581	10800	0.4155	0.9108	0.9121
0.0444	12.7907	11000	0.4069	0.9139	0.9138
0.0413	13.0233	11200	0.4188	0.9130	0.9140
0.0413	13.2558	11400	0.4288	0.9113	0.9109
0.0413	13.4884	11600	0.4140	0.9149	0.9147
0.0413	13.7209	11800	0.4266	0.9165	0.9165
0.0413	13.9535	12000	0.4250	0.9108	0.9116
0.0347	14.1860	12200	0.4581	0.9117	0.9124
0.0347	14.4186	12400	0.4218	0.9133	0.9129
0.0347	14.6512	12600	0.4399	0.9118	0.9127
0.0347	14.8837	12800	0.4258	0.9131	0.9129
0.0324	15.1163	13000	0.4513	0.9142	0.9145
0.0324	15.3488	13200	0.4466	0.9132	0.9135
0.0324	15.5814	13400	0.4249	0.9150	0.9155
0.0324	15.8140	13600	0.4434	0.9128	0.9136
0.0307	16.0465	13800	0.4520	0.9133	0.9133
0.0307	16.2791	14000	0.4532	0.9142	0.9142
0.0307	16.5116	14200	0.4465	0.9140	0.9144
0.0307	16.7442	14400	0.4560	0.9152	0.9154
0.0307	16.9767	14600	0.4475	0.9141	0.9146
0.0278	17.2093	14800	0.4641	0.9148	0.9151
0.0278	17.4419	15000	0.4693	0.9125	0.9132
0.0278	17.6744	15200	0.4597	0.9131	0.9135
0.0278	17.9070	15400	0.4585	0.9143	0.9144
0.0259	18.1395	15600	0.4686	0.9131	0.9138
0.0259	18.3721	15800	0.4713	0.9144	0.9150
0.0259	18.6047	16000	0.4620	0.9134	0.9136
0.0259	18.8372	16200	0.4610	0.9142	0.9145
0.0232	19.0698	16400	0.4613	0.9152	0.9156
0.0232	19.3023	16600	0.4637	0.9151	0.9155
0.0232	19.5349	16800	0.4686	0.9143	0.9147
0.0232	19.7674	17000	0.4691	0.9146	0.9150
0.0214	20.0	17200	0.4681	0.9143	0.9147

Framework versions

Transformers 4.41.2
Pytorch 2.1.2
Datasets 2.19.1
Tokenizers 0.19.1

Library: transformers
Type: roberta
Created: Jun 17, 2024
Updated: Jun 17, 2024