ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k10_task1_organization

This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6080
  • Qwk: 0.7785
  • Mse: 0.6080
  • Rmse: 0.7798

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss Qwk Mse Rmse
No log 0.0426 2 7.2309 -0.0056 7.2309 2.6890
No log 0.0851 4 5.1133 0.0504 5.1133 2.2613
No log 0.1277 6 3.8256 -0.0104 3.8256 1.9559
No log 0.1702 8 3.4712 0.0219 3.4712 1.8631
No log 0.2128 10 3.2927 0.0118 3.2927 1.8146
No log 0.2553 12 2.0556 0.0165 2.0556 1.4337
No log 0.2979 14 1.8865 0.1770 1.8865 1.3735
No log 0.3404 16 2.1522 0.0794 2.1522 1.4670
No log 0.3830 18 2.6013 0.1241 2.6013 1.6128
No log 0.4255 20 2.1118 0.1120 2.1118 1.4532
No log 0.4681 22 2.0170 0.1301 2.0170 1.4202
No log 0.5106 24 2.1051 0.125 2.1051 1.4509
No log 0.5532 26 2.0674 0.1970 2.0674 1.4378
No log 0.5957 28 1.4782 0.3419 1.4782 1.2158
No log 0.6383 30 1.2165 0.3793 1.2165 1.1029
No log 0.6809 32 1.1450 0.4918 1.1450 1.0700
No log 0.7234 34 1.4473 0.4122 1.4473 1.2030
No log 0.7660 36 2.3856 0.2485 2.3856 1.5445
No log 0.8085 38 2.9733 0.1939 2.9733 1.7243
No log 0.8511 40 2.4958 0.2619 2.4958 1.5798
No log 0.8936 42 1.5643 0.4218 1.5643 1.2507
No log 0.9362 44 0.9565 0.6812 0.9565 0.9780
No log 0.9787 46 0.9833 0.5802 0.9833 0.9916
No log 1.0213 48 1.4463 0.4219 1.4463 1.2026
No log 1.0638 50 1.4932 0.3902 1.4932 1.2220
No log 1.1064 52 0.9269 0.5909 0.9269 0.9627
No log 1.1489 54 0.8992 0.6761 0.8992 0.9483
No log 1.1915 56 1.4354 0.4932 1.4354 1.1981
No log 1.2340 58 1.6004 0.5161 1.6004 1.2651
No log 1.2766 60 1.2666 0.4966 1.2666 1.1254
No log 1.3191 62 0.7760 0.7429 0.7760 0.8809
No log 1.3617 64 0.7331 0.7050 0.7331 0.8562
No log 1.4043 66 0.8275 0.6429 0.8275 0.9097
No log 1.4468 68 0.7125 0.7092 0.7125 0.8441
No log 1.4894 70 0.6363 0.7413 0.6363 0.7977
No log 1.5319 72 0.7595 0.7568 0.7595 0.8715
No log 1.5745 74 0.9203 0.6410 0.9203 0.9593
No log 1.6170 76 0.8649 0.6452 0.8649 0.9300
No log 1.6596 78 0.9772 0.6623 0.9772 0.9885
No log 1.7021 80 1.1036 0.6194 1.1036 1.0505
No log 1.7447 82 0.9462 0.6176 0.9462 0.9727
No log 1.7872 84 0.7600 0.6815 0.7600 0.8718
No log 1.8298 86 0.7357 0.7338 0.7357 0.8577
No log 1.8723 88 0.7578 0.7101 0.7578 0.8705
No log 1.9149 90 0.7569 0.7059 0.7569 0.8700
No log 1.9574 92 0.7285 0.6765 0.7285 0.8535
No log 2.0 94 0.6864 0.7518 0.6864 0.8285
No log 2.0426 96 0.7432 0.7083 0.7432 0.8621
No log 2.0851 98 0.7688 0.6803 0.7688 0.8768
No log 2.1277 100 0.6345 0.7974 0.6345 0.7965
No log 2.1702 102 0.8065 0.6883 0.8065 0.8981
No log 2.2128 104 1.1117 0.6024 1.1117 1.0544
No log 2.2553 106 1.1955 0.5952 1.1955 1.0934
No log 2.2979 108 0.8087 0.6338 0.8087 0.8993
No log 2.3404 110 0.6576 0.7465 0.6576 0.8109
No log 2.3830 112 0.6951 0.7234 0.6951 0.8337
No log 2.4255 114 0.6522 0.7552 0.6522 0.8076
No log 2.4681 116 0.6497 0.7778 0.6497 0.8061
No log 2.5106 118 0.6606 0.7862 0.6606 0.8128
No log 2.5532 120 0.6635 0.7724 0.6635 0.8145
No log 2.5957 122 0.7505 0.7162 0.7505 0.8663
No log 2.6383 124 0.8792 0.6338 0.8792 0.9377
No log 2.6809 126 0.9788 0.5693 0.9788 0.9894
No log 2.7234 128 0.8359 0.6906 0.8359 0.9143
No log 2.7660 130 0.9219 0.5797 0.9219 0.9602
No log 2.8085 132 1.2609 0.5455 1.2609 1.1229
No log 2.8511 134 1.1282 0.5658 1.1282 1.0622
No log 2.8936 136 0.7880 0.7286 0.7880 0.8877
No log 2.9362 138 0.7712 0.7143 0.7712 0.8782
No log 2.9787 140 0.7261 0.7413 0.7261 0.8521
No log 3.0213 142 0.7236 0.7368 0.7236 0.8507
No log 3.0638 144 0.7133 0.7643 0.7133 0.8446
No log 3.1064 146 0.6684 0.7383 0.6684 0.8176
No log 3.1489 148 0.7456 0.6980 0.7456 0.8635
No log 3.1915 150 0.8047 0.6757 0.8047 0.8970
No log 3.2340 152 0.7673 0.6986 0.7673 0.8760
No log 3.2766 154 0.6982 0.75 0.6982 0.8356
No log 3.3191 156 0.9545 0.6040 0.9545 0.9770
No log 3.3617 158 0.9866 0.6040 0.9866 0.9933
No log 3.4043 160 0.7495 0.7483 0.7495 0.8657
No log 3.4468 162 0.7201 0.7619 0.7201 0.8486
No log 3.4894 164 0.7997 0.6897 0.7997 0.8942
No log 3.5319 166 0.7341 0.7517 0.7341 0.8568
No log 3.5745 168 0.6535 0.7808 0.6535 0.8084
No log 3.6170 170 0.7529 0.6933 0.7529 0.8677
No log 3.6596 172 0.8076 0.6351 0.8076 0.8987
No log 3.7021 174 0.6932 0.7020 0.6932 0.8326
No log 3.7447 176 0.6287 0.8129 0.6287 0.7929
No log 3.7872 178 0.6755 0.7467 0.6755 0.8219
No log 3.8298 180 0.6711 0.7532 0.6711 0.8192
No log 3.8723 182 0.6007 0.7975 0.6007 0.7750
No log 3.9149 184 0.5720 0.8050 0.5720 0.7563
No log 3.9574 186 0.6465 0.7778 0.6465 0.8041
No log 4.0 188 0.6523 0.8 0.6523 0.8076
No log 4.0426 190 0.6050 0.7975 0.6050 0.7778
No log 4.0851 192 0.6297 0.8148 0.6297 0.7936
No log 4.1277 194 0.6544 0.7949 0.6544 0.8090
No log 4.1702 196 0.6497 0.7975 0.6497 0.8061
No log 4.2128 198 0.7391 0.7799 0.7391 0.8597
No log 4.2553 200 0.7962 0.7879 0.7962 0.8923
No log 4.2979 202 0.7265 0.8025 0.7265 0.8523
No log 4.3404 204 0.6265 0.7826 0.6265 0.7915
No log 4.3830 206 0.6444 0.7901 0.6444 0.8028
No log 4.4255 208 0.6643 0.8193 0.6643 0.8150
No log 4.4681 210 0.5915 0.7952 0.5915 0.7691
No log 4.5106 212 0.5980 0.7952 0.5980 0.7733
No log 4.5532 214 0.7653 0.7802 0.7653 0.8748
No log 4.5957 216 0.8515 0.7374 0.8515 0.9228
No log 4.6383 218 0.7889 0.7730 0.7889 0.8882
No log 4.6809 220 0.6477 0.7875 0.6477 0.8048
No log 4.7234 222 0.6280 0.7919 0.6280 0.7925
No log 4.7660 224 0.6784 0.7712 0.6784 0.8237
No log 4.8085 226 0.7255 0.7848 0.7255 0.8518
No log 4.8511 228 0.6978 0.7733 0.6978 0.8353
No log 4.8936 230 0.6391 0.7808 0.6391 0.7994
No log 4.9362 232 0.6336 0.7862 0.6336 0.7960
No log 4.9787 234 0.6958 0.7273 0.6958 0.8341
No log 5.0213 236 0.7007 0.7517 0.7007 0.8371
No log 5.0638 238 0.6546 0.7639 0.6546 0.8091
No log 5.1064 240 0.6761 0.8028 0.6761 0.8222
No log 5.1489 242 0.6653 0.8138 0.6653 0.8156
No log 5.1915 244 0.5982 0.8219 0.5982 0.7734
No log 5.2340 246 0.6351 0.7898 0.6351 0.7969
No log 5.2766 248 0.7026 0.7333 0.7026 0.8382
No log 5.3191 250 0.6433 0.7568 0.6433 0.8021
No log 5.3617 252 0.5777 0.8054 0.5777 0.7601
No log 5.4043 254 0.5887 0.8158 0.5887 0.7672
No log 5.4468 256 0.6011 0.8105 0.6011 0.7753
No log 5.4894 258 0.6309 0.7763 0.6309 0.7943
No log 5.5319 260 0.6257 0.7763 0.6257 0.7910
No log 5.5745 262 0.5538 0.825 0.5538 0.7442
No log 5.6170 264 0.5348 0.8272 0.5348 0.7313
No log 5.6596 266 0.5205 0.8242 0.5205 0.7214
No log 5.7021 268 0.5701 0.8315 0.5701 0.7550
No log 5.7447 270 0.6184 0.7933 0.6184 0.7864
No log 5.7872 272 0.5593 0.8202 0.5593 0.7478
No log 5.8298 274 0.5145 0.8452 0.5145 0.7173
No log 5.8723 276 0.5252 0.8344 0.5252 0.7247
No log 5.9149 278 0.5610 0.8344 0.5610 0.7490
No log 5.9574 280 0.6435 0.7949 0.6435 0.8022
No log 6.0 282 0.7302 0.75 0.7302 0.8545
No log 6.0426 284 0.7222 0.7237 0.7222 0.8498
No log 6.0851 286 0.6464 0.8026 0.6464 0.8040
No log 6.1277 288 0.6164 0.8052 0.6164 0.7851
No log 6.1702 290 0.6410 0.7771 0.6410 0.8006
No log 6.2128 292 0.5791 0.7975 0.5791 0.7610
No log 6.2553 294 0.5080 0.8554 0.5080 0.7127
No log 6.2979 296 0.5154 0.8415 0.5154 0.7179
No log 6.3404 298 0.5307 0.8415 0.5307 0.7285
No log 6.3830 300 0.5313 0.8519 0.5313 0.7289
No log 6.4255 302 0.6257 0.7901 0.6257 0.7910
No log 6.4681 304 0.7058 0.7285 0.7058 0.8401
No log 6.5106 306 0.6977 0.7483 0.6977 0.8353
No log 6.5532 308 0.6365 0.8026 0.6365 0.7978
No log 6.5957 310 0.6716 0.7949 0.6716 0.8195
No log 6.6383 312 0.7605 0.6839 0.7605 0.8721
No log 6.6809 314 0.7395 0.7205 0.7395 0.8599
No log 6.7234 316 0.5583 0.8193 0.5583 0.7472
No log 6.7660 318 0.4933 0.8221 0.4933 0.7023
No log 6.8085 320 0.5605 0.7975 0.5605 0.7487
No log 6.8511 322 0.5536 0.7975 0.5536 0.7440
No log 6.8936 324 0.5002 0.8272 0.5002 0.7073
No log 6.9362 326 0.4862 0.8434 0.4862 0.6973
No log 6.9787 328 0.5369 0.8313 0.5369 0.7328
No log 7.0213 330 0.5488 0.8323 0.5488 0.7408
No log 7.0638 332 0.5946 0.8052 0.5946 0.7711
No log 7.1064 334 0.6941 0.7483 0.6941 0.8331
No log 7.1489 336 0.7092 0.7260 0.7092 0.8422
No log 7.1915 338 0.6160 0.7815 0.6160 0.7849
No log 7.2340 340 0.5810 0.8428 0.5810 0.7622
No log 7.2766 342 0.6896 0.7799 0.6896 0.8304
No log 7.3191 344 0.7783 0.7665 0.7783 0.8822
No log 7.3617 346 0.6677 0.7853 0.6677 0.8171
No log 7.4043 348 0.5470 0.8129 0.5470 0.7396
No log 7.4468 350 0.6549 0.7545 0.6549 0.8092
No log 7.4894 352 0.7394 0.7073 0.7394 0.8599
No log 7.5319 354 0.6950 0.7162 0.6950 0.8337
No log 7.5745 356 0.5799 0.7792 0.5799 0.7615
No log 7.6170 358 0.5828 0.8052 0.5828 0.7634
No log 7.6596 360 0.6118 0.8105 0.6118 0.7822
No log 7.7021 362 0.6091 0.7838 0.6091 0.7804
No log 7.7447 364 0.5802 0.8153 0.5802 0.7617
No log 7.7872 366 0.5492 0.8199 0.5492 0.7411
No log 7.8298 368 0.5634 0.8199 0.5634 0.7506
No log 7.8723 370 0.5564 0.8199 0.5564 0.7459
No log 7.9149 372 0.5106 0.8199 0.5106 0.7146
No log 7.9574 374 0.5049 0.8199 0.5049 0.7106
No log 8.0 376 0.5398 0.7922 0.5398 0.7347
No log 8.0426 378 0.5722 0.7692 0.5722 0.7564
No log 8.0851 380 0.5619 0.7838 0.5619 0.7496
No log 8.1277 382 0.5572 0.8272 0.5572 0.7465
No log 8.1702 384 0.6847 0.7673 0.6847 0.8274
No log 8.2128 386 0.7853 0.7037 0.7853 0.8862
No log 8.2553 388 0.7117 0.7375 0.7117 0.8436
No log 8.2979 390 0.5640 0.8199 0.5640 0.7510
No log 8.3404 392 0.5213 0.825 0.5213 0.7220
No log 8.3830 394 0.5683 0.7838 0.5683 0.7539
No log 8.4255 396 0.5706 0.7919 0.5706 0.7553
No log 8.4681 398 0.5469 0.8054 0.5469 0.7395
No log 8.5106 400 0.5216 0.8133 0.5216 0.7222
No log 8.5532 402 0.5287 0.8212 0.5287 0.7271
No log 8.5957 404 0.5535 0.8212 0.5535 0.7440
No log 8.6383 406 0.5653 0.8212 0.5653 0.7519
No log 8.6809 408 0.5857 0.7973 0.5857 0.7653
No log 8.7234 410 0.5819 0.7973 0.5819 0.7628
No log 8.7660 412 0.5561 0.8212 0.5561 0.7457
No log 8.8085 414 0.5187 0.8212 0.5187 0.7202
No log 8.8511 416 0.4900 0.8312 0.4900 0.7000
No log 8.8936 418 0.5010 0.8105 0.5010 0.7078
No log 8.9362 420 0.5142 0.8105 0.5142 0.7171
No log 8.9787 422 0.5496 0.7973 0.5496 0.7414
No log 9.0213 424 0.5839 0.7919 0.5839 0.7641
No log 9.0638 426 0.6297 0.7568 0.6297 0.7935
No log 9.1064 428 0.5889 0.7838 0.5889 0.7674
No log 9.1489 430 0.5299 0.7973 0.5299 0.7280
No log 9.1915 432 0.4961 0.8129 0.4961 0.7043
No log 9.2340 434 0.4778 0.8395 0.4778 0.6912
No log 9.2766 436 0.4715 0.8148 0.4715 0.6866
No log 9.3191 438 0.4862 0.8153 0.4862 0.6973
No log 9.3617 440 0.4947 0.8052 0.4947 0.7034
No log 9.4043 442 0.4764 0.8153 0.4764 0.6902
No log 9.4468 444 0.5104 0.825 0.5104 0.7145
No log 9.4894 446 0.6228 0.7799 0.6228 0.7892
No log 9.5319 448 0.6146 0.8 0.6146 0.7839
No log 9.5745 450 0.5593 0.8176 0.5593 0.7479
No log 9.6170 452 0.5031 0.8212 0.5031 0.7093
No log 9.6596 454 0.4920 0.8228 0.4920 0.7014
No log 9.7021 456 0.5090 0.8199 0.5090 0.7134
No log 9.7447 458 0.5955 0.8024 0.5955 0.7717
No log 9.7872 460 0.5730 0.8024 0.5730 0.7570
No log 9.8298 462 0.5040 0.8148 0.5040 0.7099
No log 9.8723 464 0.4741 0.8121 0.4741 0.6886
No log 9.9149 466 0.5055 0.8182 0.5055 0.7110
No log 9.9574 468 0.5164 0.8205 0.5164 0.7186
No log 10.0 470 0.5378 0.7973 0.5378 0.7334
No log 10.0426 472 0.5383 0.8163 0.5383 0.7337
No log 10.0851 474 0.5218 0.8052 0.5218 0.7224
No log 10.1277 476 0.5335 0.8153 0.5335 0.7304
No log 10.1702 478 0.5159 0.8052 0.5159 0.7183
No log 10.2128 480 0.5351 0.8082 0.5351 0.7315
No log 10.2553 482 0.5353 0.8163 0.5353 0.7317
No log 10.2979 484 0.5299 0.8054 0.5299 0.7279
No log 10.3404 486 0.5277 0.8163 0.5277 0.7265
No log 10.3830 488 0.5288 0.8027 0.5288 0.7272
No log 10.4255 490 0.5969 0.7724 0.5969 0.7726
No log 10.4681 492 0.6086 0.7639 0.6086 0.7801
No log 10.5106 494 0.6046 0.7724 0.6046 0.7776
No log 10.5532 496 0.5758 0.7808 0.5758 0.7588
No log 10.5957 498 0.5506 0.8235 0.5506 0.7420
0.3984 10.6383 500 0.5223 0.8182 0.5223 0.7227
0.3984 10.6809 502 0.5216 0.8354 0.5216 0.7222
0.3984 10.7234 504 0.5605 0.8344 0.5605 0.7487
0.3984 10.7660 506 0.5493 0.8153 0.5493 0.7412
0.3984 10.8085 508 0.5561 0.8243 0.5561 0.7457
0.3984 10.8511 510 0.6123 0.8163 0.6123 0.7825
0.3984 10.8936 512 0.6276 0.8082 0.6276 0.7922
0.3984 10.9362 514 0.6075 0.7972 0.6075 0.7794
0.3984 10.9787 516 0.5857 0.7945 0.5857 0.7653
0.3984 11.0213 518 0.6080 0.7785 0.6080 0.7798

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for MayBashendy/ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k10_task1_organization

Finetuned
(4040)
this model