Hugging Face's logo

sickcell
/
bert-base-spanish-wwm-uncased-finetuned-github_cybersecurity_READMEs

Fill-Mask
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
bert-base-spanish-wwm-uncased-finetuned-github_cybersecurity_READMEs / README.md
sickcell69
End of training
d437d6c verified
preview code
|
raw
history blame contribute delete
13.8 kB
metadata
base_model: dccuchile/bert-base-spanish-wwm-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: bert-base-spanish-wwm-uncased-finetuned-github_cybersecurity_READMEs
    results: []

bert-base-spanish-wwm-uncased-finetuned-github_cybersecurity_READMEs

This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3626
  • Accuracy: 0.7721

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: 3e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 1000
  • num_epochs: 200

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 0.97 14 6.6700 0.2868
No log 2.0 29 6.1329 0.3035
No log 2.97 43 5.3933 0.3612
No log 4.0 58 5.0109 0.3777
No log 4.97 72 4.8244 0.3982
No log 6.0 87 4.3103 0.4191
No log 6.97 101 3.9390 0.4472
No log 8.0 116 3.7105 0.4643
No log 8.97 130 3.6200 0.4682
No log 10.0 145 3.3792 0.4746
No log 10.97 159 3.2035 0.5035
No log 12.0 174 3.0204 0.5292
No log 12.97 188 2.9428 0.5446
No log 14.0 203 2.8275 0.5586
No log 14.97 217 2.8530 0.5389
No log 16.0 232 2.7320 0.5552
No log 16.97 246 2.6976 0.5569
No log 18.0 261 2.6423 0.5672
No log 18.97 275 2.5589 0.5768
No log 20.0 290 2.5393 0.5725
No log 20.97 304 2.4149 0.5883
No log 22.0 319 2.3377 0.6106
No log 22.97 333 2.3686 0.6006
No log 24.0 348 2.3694 0.5896
No log 24.97 362 2.3411 0.6006
No log 26.0 377 2.1990 0.6192
No log 26.97 391 2.1937 0.6187
No log 28.0 406 2.1599 0.6263
No log 28.97 420 2.1169 0.6288
No log 30.0 435 2.1136 0.6363
No log 30.97 449 2.1705 0.6269
No log 32.0 464 1.9909 0.6551
No log 32.97 478 1.9930 0.6452
No log 34.0 493 1.9380 0.6622
3.3393 34.97 507 2.0509 0.6429
3.3393 36.0 522 1.9449 0.6556
3.3393 36.97 536 1.9595 0.6500
3.3393 38.0 551 1.8646 0.6703
3.3393 38.97 565 1.9297 0.6553
3.3393 40.0 580 1.8071 0.6820
3.3393 40.97 594 1.9239 0.6564
3.3393 42.0 609 1.7737 0.6769
3.3393 42.97 623 1.7695 0.6889
3.3393 44.0 638 1.7444 0.6842
3.3393 44.97 652 1.7503 0.6839
3.3393 46.0 667 1.7654 0.6932
3.3393 46.97 681 1.7225 0.6862
3.3393 48.0 696 1.8165 0.6815
3.3393 48.97 710 1.7971 0.6840
3.3393 50.0 725 1.7177 0.6942
3.3393 50.97 739 1.6890 0.6982
3.3393 52.0 754 1.7212 0.6990
3.3393 52.97 768 1.7562 0.6892
3.3393 54.0 783 1.7142 0.6971
3.3393 54.97 797 1.6899 0.6955
3.3393 56.0 812 1.7568 0.6898
3.3393 56.97 826 1.6427 0.7137
3.3393 58.0 841 1.5932 0.7183
3.3393 58.97 855 1.6001 0.7193
3.3393 60.0 870 1.6482 0.7109
3.3393 60.97 884 1.5384 0.7211
3.3393 62.0 899 1.6092 0.7085
3.3393 62.97 913 1.6621 0.7068
3.3393 64.0 928 1.5781 0.7108
3.3393 64.97 942 1.5365 0.7297
3.3393 66.0 957 1.5426 0.7155
3.3393 66.97 971 1.6601 0.7051
3.3393 68.0 986 1.5874 0.7218
1.654 68.97 1000 1.6337 0.7148
1.654 70.0 1015 1.5324 0.7244
1.654 70.97 1029 1.5848 0.7245
1.654 72.0 1044 1.4755 0.7301
1.654 72.97 1058 1.5183 0.7323
1.654 74.0 1073 1.4930 0.7307
1.654 74.97 1087 1.4618 0.7350
1.654 76.0 1102 1.5082 0.7381
1.654 76.97 1116 1.4550 0.7402
1.654 78.0 1131 1.4609 0.7350
1.654 78.97 1145 1.5692 0.7258
1.654 80.0 1160 1.4066 0.7524
1.654 80.97 1174 1.5256 0.7283
1.654 82.0 1189 1.4466 0.7396
1.654 82.97 1203 1.4642 0.7357
1.654 84.0 1218 1.4985 0.7364
1.654 84.97 1232 1.4829 0.7421
1.654 86.0 1247 1.4528 0.7423
1.654 86.97 1261 1.3744 0.7470
1.654 88.0 1276 1.4098 0.7534
1.654 88.97 1290 1.4666 0.7439
1.654 90.0 1305 1.3889 0.7606
1.654 90.97 1319 1.4525 0.7436
1.654 92.0 1334 1.3673 0.7547
1.654 92.97 1348 1.4549 0.7430
1.654 94.0 1363 1.4008 0.7417
1.654 94.97 1377 1.3820 0.7472
1.654 96.0 1392 1.3900 0.7592
1.654 96.97 1406 1.4227 0.7458
1.654 98.0 1421 1.4179 0.7546
1.654 98.97 1435 1.4474 0.7476
1.654 100.0 1450 1.4092 0.7485
1.654 100.97 1464 1.3163 0.7678
1.654 102.0 1479 1.3801 0.7631
1.654 102.97 1493 1.4153 0.7496
1.1613 104.0 1508 1.3168 0.7616
1.1613 104.97 1522 1.3385 0.7607
1.1613 106.0 1537 1.4633 0.7406
1.1613 106.97 1551 1.4509 0.7473
1.1613 108.0 1566 1.3938 0.7577
1.1613 108.97 1580 1.4659 0.7451
1.1613 110.0 1595 1.4536 0.7403
1.1613 110.97 1609 1.4069 0.7529
1.1613 112.0 1624 1.2818 0.7721
1.1613 112.97 1638 1.3530 0.7618
1.1613 114.0 1653 1.3854 0.7555
1.1613 114.97 1667 1.3213 0.7589
1.1613 116.0 1682 1.3547 0.7578
1.1613 116.97 1696 1.4230 0.7544
1.1613 118.0 1711 1.3296 0.7650
1.1613 118.97 1725 1.3777 0.7616
1.1613 120.0 1740 1.3832 0.7639
1.1613 120.97 1754 1.4333 0.7524
1.1613 122.0 1769 1.3613 0.7655
1.1613 122.97 1783 1.4481 0.7533
1.1613 124.0 1798 1.4398 0.7550
1.1613 124.97 1812 1.3509 0.7678
1.1613 126.0 1827 1.3034 0.7705
1.1613 126.97 1841 1.4733 0.7468
1.1613 128.0 1856 1.4400 0.7557
1.1613 128.97 1870 1.3901 0.7599
1.1613 130.0 1885 1.3529 0.7683
1.1613 130.97 1899 1.3677 0.7568
1.1613 132.0 1914 1.4481 0.7561
1.1613 132.97 1928 1.2518 0.7826
1.1613 134.0 1943 1.4324 0.7527
1.1613 134.97 1957 1.3740 0.7591
1.1613 136.0 1972 1.3782 0.7628
1.1613 136.97 1986 1.2933 0.7735
0.9181 138.0 2001 1.3451 0.7709
0.9181 138.97 2015 1.4064 0.7646
0.9181 140.0 2030 1.3908 0.7661
0.9181 140.97 2044 1.3139 0.7692
0.9181 142.0 2059 1.3602 0.7698
0.9181 142.97 2073 1.3171 0.7763
0.9181 144.0 2088 1.3736 0.7627
0.9181 144.97 2102 1.3348 0.7670
0.9181 146.0 2117 1.3745 0.7672
0.9181 146.97 2131 1.3725 0.7657
0.9181 148.0 2146 1.3939 0.7662
0.9181 148.97 2160 1.3793 0.7654
0.9181 150.0 2175 1.3246 0.7713
0.9181 150.97 2189 1.2930 0.7767
0.9181 152.0 2204 1.2810 0.7786
0.9181 152.97 2218 1.3552 0.7677
0.9181 154.0 2233 1.4365 0.7662
0.9181 154.97 2247 1.3108 0.7701
0.9181 156.0 2262 1.2976 0.7802
0.9181 156.97 2276 1.3652 0.7743
0.9181 158.0 2291 1.3912 0.7628
0.9181 158.97 2305 1.3401 0.7689
0.9181 160.0 2320 1.2996 0.7723
0.9181 160.97 2334 1.3340 0.7764
0.9181 162.0 2349 1.2927 0.7751
0.9181 162.97 2363 1.3123 0.7766
0.9181 164.0 2378 1.3185 0.7712
0.9181 164.97 2392 1.3288 0.7737
0.9181 166.0 2407 1.3510 0.7685
0.9181 166.97 2421 1.3598 0.7699
0.9181 168.0 2436 1.3490 0.7638
0.9181 168.97 2450 1.3381 0.7643
0.9181 170.0 2465 1.3074 0.7761
0.9181 170.97 2479 1.3886 0.7631
0.9181 172.0 2494 1.3931 0.7634
0.7949 172.97 2508 1.3627 0.7662
0.7949 174.0 2523 1.4032 0.7653
0.7949 174.97 2537 1.3016 0.7740
0.7949 176.0 2552 1.3341 0.7710
0.7949 176.97 2566 1.3820 0.7624
0.7949 178.0 2581 1.3502 0.7761
0.7949 178.97 2595 1.3273 0.7752
0.7949 180.0 2610 1.3915 0.7623
0.7949 180.97 2624 1.4012 0.7616
0.7949 182.0 2639 1.3881 0.7692
0.7949 182.97 2653 1.2757 0.7807
0.7949 184.0 2668 1.3941 0.7629
0.7949 184.97 2682 1.3301 0.7800
0.7949 186.0 2697 1.3781 0.7735
0.7949 186.97 2711 1.3267 0.7782
0.7949 188.0 2726 1.3695 0.7688
0.7949 188.97 2740 1.3516 0.7752
0.7949 190.0 2755 1.3627 0.7733
0.7949 190.97 2769 1.3846 0.7713
0.7949 192.0 2784 1.3710 0.7662
0.7949 192.97 2798 1.3902 0.7660
0.7949 193.1 2800 1.4705 0.7550

Framework versions

  • Transformers 4.40.0.dev0
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2