metadata

base_model: vinai/phobert-base-v2
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: PhoBert_Lexical_lc
    results: []

PhoBert_Lexical_lc

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: 0.6002
Accuracy: 0.8324
F1: 0.8697

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.1927	200	0.7068	0.6753	0.7632
No log	0.3854	400	0.7343	0.6772	0.7646
No log	0.5780	600	0.5764	0.7641	0.8248
No log	0.7707	800	0.7871	0.6153	0.7178
No log	0.9634	1000	0.5685	0.7548	0.8186
0.358	1.1561	1200	0.6231	0.7569	0.8203
0.358	1.3487	1400	0.5796	0.7737	0.8314
0.358	1.5414	1600	0.5651	0.7758	0.8327
0.358	1.7341	1800	0.6171	0.7502	0.8157
0.358	1.9268	2000	0.5711	0.7645	0.8254
0.2472	2.1195	2200	0.6046	0.7615	0.8235
0.2472	2.3121	2400	0.8503	0.6871	0.7718
0.2472	2.5048	2600	0.7907	0.7136	0.7908
0.2472	2.6975	2800	0.6425	0.7575	0.8209
0.2472	2.8902	3000	0.5584	0.8067	0.8530
0.2065	3.0829	3200	0.6602	0.7627	0.8244
0.2065	3.2755	3400	0.7031	0.7570	0.8206
0.2065	3.4682	3600	0.6166	0.7832	0.8382
0.2065	3.6609	3800	0.7400	0.7279	0.8008
0.2065	3.8536	4000	0.5337	0.8066	0.8531
0.1757	4.0462	4200	0.7663	0.7600	0.8227
0.1757	4.2389	4400	0.6286	0.7849	0.8392
0.1757	4.4316	4600	0.6379	0.8031	0.8511
0.1757	4.6243	4800	0.6865	0.7751	0.8328
0.1757	4.8170	5000	0.5512	0.8216	0.8629
0.1511	5.0096	5200	0.6118	0.8058	0.8529
0.1511	5.2023	5400	0.8038	0.7545	0.8191
0.1511	5.3950	5600	0.6799	0.8170	0.8600
0.1511	5.5877	5800	0.8013	0.7679	0.8282
0.1511	5.7803	6000	0.7806	0.7809	0.8365
0.1511	5.9730	6200	0.7302	0.7738	0.8320
0.129	6.1657	6400	0.6002	0.8324	0.8697
0.129	6.3584	6600	0.7237	0.8069	0.8534
0.129	6.5511	6800	0.7118	0.8072	0.8536
0.129	6.7437	7000	0.7674	0.7933	0.8447
0.129	6.9364	7200	0.7735	0.7737	0.8319
0.1133	7.1291	7400	0.6940	0.8152	0.8588
0.1133	7.3218	7600	0.8333	0.7880	0.8413
0.1133	7.5145	7800	0.7050	0.8016	0.8502
0.1133	7.7071	8000	0.8503	0.7763	0.8336
0.1133	7.8998	8200	0.8677	0.7734	0.8318
0.0964	8.0925	8400	0.7368	0.7994	0.8488
0.0964	8.2852	8600	0.7291	0.8161	0.8594
0.0964	8.4778	8800	0.8928	0.7948	0.8457
0.0964	8.6705	9000	0.9070	0.7799	0.8360
0.0964	8.8632	9200	0.8584	0.7961	0.8465
0.085	9.0559	9400	0.8249	0.8081	0.8543
0.085	9.2486	9600	0.8202	0.7929	0.8446
0.085	9.4412	9800	0.9296	0.7757	0.8332
0.085	9.6339	10000	0.9153	0.7931	0.8447
0.085	9.8266	10200	0.9087	0.7868	0.8405
0.0749	10.0193	10400	0.8043	0.8054	0.8526
0.0749	10.2119	10600	0.9692	0.7916	0.8436
0.0749	10.4046	10800	0.8181	0.8190	0.8614
0.0749	10.5973	11000	0.8767	0.8010	0.8498
0.0749	10.7900	11200	0.9470	0.7944	0.8455
0.0749	10.9827	11400	0.9699	0.7796	0.8358
0.0668	11.1753	11600	0.9448	0.7862	0.8402
0.0668	11.3680	11800	0.9925	0.7982	0.8480
0.0668	11.5607	12000	1.0677	0.7826	0.8378
0.0668	11.7534	12200	0.8985	0.7994	0.8487
0.0668	11.9461	12400	0.9710	0.7969	0.8471
0.0601	12.1387	12600	1.0032	0.7924	0.8442
0.0601	12.3314	12800	1.0084	0.7911	0.8432
0.0601	12.5241	13000	1.1361	0.7666	0.8272
0.0601	12.7168	13200	0.9933	0.7935	0.8449
0.0601	12.9094	13400	1.0405	0.7888	0.8419
0.0528	13.1021	13600	1.0769	0.7822	0.8375
0.0528	13.2948	13800	1.0596	0.7906	0.8431
0.0528	13.4875	14000	1.0612	0.7848	0.8393
0.0528	13.6802	14200	1.0330	0.7909	0.8434
0.0528	13.8728	14400	1.0386	0.7967	0.8471
0.0477	14.0655	14600	0.9948	0.7956	0.8464
0.0477	14.2582	14800	1.0767	0.7897	0.8425
0.0477	14.4509	15000	1.0176	0.7938	0.8451
0.0477	14.6435	15200	1.0246	0.7945	0.8456
0.0477	14.8362	15400	1.0230	0.7969	0.8472

Framework versions

Transformers 4.44.0
Pytorch 2.1.2
Datasets 2.20.0
Tokenizers 0.19.1