metadata

license: apache-2.0
base_model: albert/albert-base-v2
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: classify-phishing_real_1
    results: []

classify-phishing_real_1

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

Loss: 0.1185
Accuracy: 0.9645
F1: 0.9645
Precision: 0.9645
Recall: 0.9645
Accuracy Label 0: 0.9708
Accuracy Label 1: 0.9559

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: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Accuracy Label 0	Accuracy Label 1
0.4991	0.1030	100	0.4748	0.7925	0.7819	0.8136	0.7925	0.9508	0.5747
0.3087	0.2060	200	0.3052	0.8799	0.8793	0.8799	0.8799	0.9189	0.8262
0.2974	0.3090	300	0.2390	0.9093	0.9094	0.9095	0.9093	0.9181	0.8972
0.2644	0.4119	400	0.3068	0.8663	0.8670	0.8887	0.8663	0.7899	0.9715
0.223	0.5149	500	0.2122	0.9154	0.9158	0.9195	0.9154	0.8905	0.9495
0.215	0.6179	600	0.2011	0.9229	0.9222	0.9252	0.9229	0.9714	0.8561
0.1419	0.7209	700	0.1836	0.9305	0.9300	0.9318	0.9305	0.9690	0.8775
0.1511	0.8239	800	0.1828	0.9305	0.9308	0.9327	0.9305	0.9145	0.9526
0.173	0.9269	900	0.1544	0.9430	0.9428	0.9433	0.9430	0.9666	0.9107
0.0986	1.0299	1000	0.1513	0.9429	0.9430	0.9435	0.9429	0.9384	0.9491
0.1403	1.1329	1100	0.1515	0.9426	0.9429	0.9444	0.9426	0.9278	0.9631
0.1133	1.2358	1200	0.1394	0.9475	0.9475	0.9475	0.9475	0.9531	0.9397
0.1117	1.3388	1300	0.1525	0.9457	0.9459	0.9467	0.9457	0.9371	0.9576
0.1277	1.4418	1400	0.1311	0.9490	0.9491	0.9492	0.9490	0.9501	0.9475
0.0886	1.5448	1500	0.1375	0.9503	0.9503	0.9503	0.9503	0.9628	0.9331
0.1273	1.6478	1600	0.1297	0.9533	0.9533	0.9535	0.9533	0.9536	0.9529
0.1102	1.7508	1700	0.1136	0.9578	0.9578	0.9578	0.9578	0.9637	0.9498
0.0793	1.8538	1800	0.1269	0.9562	0.9561	0.9563	0.9562	0.9718	0.9348
0.0995	1.9567	1900	0.1129	0.9591	0.9590	0.9591	0.9591	0.9702	0.9437
0.0846	2.0597	2000	0.1362	0.9533	0.9534	0.9543	0.9533	0.9422	0.9685
0.096	2.1627	2100	0.1383	0.9563	0.9564	0.9572	0.9563	0.9467	0.9696
0.0797	2.2657	2200	0.1137	0.9620	0.9619	0.9619	0.9620	0.9711	0.9494
0.0602	2.3687	2300	0.1211	0.9609	0.9609	0.9609	0.9609	0.9664	0.9532
0.0951	2.4717	2400	0.1194	0.9614	0.9615	0.9615	0.9614	0.9628	0.9596
0.0343	2.5747	2500	0.1237	0.9629	0.9629	0.9630	0.9629	0.9624	0.9634
0.0512	2.6777	2600	0.1263	0.9625	0.9625	0.9625	0.9625	0.9738	0.9471
0.0532	2.7806	2700	0.1229	0.9633	0.9633	0.9633	0.9633	0.9706	0.9533
0.0673	2.8836	2800	0.1206	0.9644	0.9644	0.9644	0.9644	0.9679	0.9596
0.0209	2.9866	2900	0.1185	0.9645	0.9645	0.9645	0.9645	0.9709	0.9556

Framework versions

Transformers 4.42.3
Pytorch 2.2.1
Datasets 2.20.0
Tokenizers 0.19.1