ArabicNewSplits4_WithDuplicationsForScore5_FineTuningAraBERT_run3_AugV5_k10_task3_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: 0.7271
  • Qwk: 0.2464
  • Mse: 0.7271
  • Rmse: 0.8527

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: 10

Training results

Training Loss Epoch Step Validation Loss Qwk Mse Rmse
No log 0.0444 2 3.2300 -0.0149 3.2300 1.7972
No log 0.0889 4 1.6866 -0.0070 1.6866 1.2987
No log 0.1333 6 1.4718 0.0255 1.4718 1.2132
No log 0.1778 8 0.8949 0.1673 0.8949 0.9460
No log 0.2222 10 0.5655 0.0222 0.5655 0.7520
No log 0.2667 12 0.5613 0.0569 0.5613 0.7492
No log 0.3111 14 0.5551 0.0303 0.5551 0.7451
No log 0.3556 16 0.5454 0.0569 0.5454 0.7385
No log 0.4 18 0.5520 -0.0159 0.5520 0.7430
No log 0.4444 20 0.8311 0.2000 0.8311 0.9116
No log 0.4889 22 0.7803 0.2300 0.7803 0.8834
No log 0.5333 24 0.6153 0.0720 0.6153 0.7844
No log 0.5778 26 0.7098 0.2000 0.7098 0.8425
No log 0.6222 28 0.6655 0.1888 0.6655 0.8158
No log 0.6667 30 0.6458 -0.1007 0.6458 0.8036
No log 0.7111 32 0.7409 0.0345 0.7409 0.8607
No log 0.7556 34 0.6909 -0.0390 0.6909 0.8312
No log 0.8 36 0.6797 -0.0072 0.6797 0.8244
No log 0.8444 38 0.6871 0.0199 0.6871 0.8289
No log 0.8889 40 0.7641 0.0311 0.7641 0.8741
No log 0.9333 42 0.9004 -0.0275 0.9004 0.9489
No log 0.9778 44 0.7186 0.1628 0.7186 0.8477
No log 1.0222 46 0.7551 0.0737 0.7551 0.8690
No log 1.0667 48 0.6982 0.1373 0.6982 0.8356
No log 1.1111 50 0.7325 0.0728 0.7325 0.8559
No log 1.1556 52 1.0762 -0.0154 1.0762 1.0374
No log 1.2 54 0.7183 0.0769 0.7183 0.8476
No log 1.2444 56 0.6764 0.1345 0.6764 0.8224
No log 1.2889 58 0.7061 0.0617 0.7061 0.8403
No log 1.3333 60 1.0978 -0.0277 1.0978 1.0478
No log 1.3778 62 1.0736 0.0252 1.0736 1.0361
No log 1.4222 64 0.8701 0.0891 0.8701 0.9328
No log 1.4667 66 0.8345 0.0891 0.8345 0.9135
No log 1.5111 68 0.7870 0.0802 0.7870 0.8871
No log 1.5556 70 1.0944 0.0 1.0944 1.0461
No log 1.6 72 1.0873 0.0038 1.0873 1.0427
No log 1.6444 74 1.0292 0.0169 1.0292 1.0145
No log 1.6889 76 1.2864 0.0270 1.2864 1.1342
No log 1.7333 78 0.9784 0.0717 0.9784 0.9891
No log 1.7778 80 0.7561 0.2577 0.7561 0.8695
No log 1.8222 82 0.8099 0.2153 0.8099 0.8999
No log 1.8667 84 1.4463 0.0464 1.4463 1.2026
No log 1.9111 86 1.4901 0.0502 1.4901 1.2207
No log 1.9556 88 1.2054 0.0262 1.2054 1.0979
No log 2.0 90 0.9639 0.0308 0.9639 0.9818
No log 2.0444 92 0.7750 0.2727 0.7750 0.8804
No log 2.0889 94 0.8084 0.2444 0.8084 0.8991
No log 2.1333 96 0.9615 0.0539 0.9615 0.9805
No log 2.1778 98 1.6188 0.1111 1.6188 1.2723
No log 2.2222 100 1.3504 0.1169 1.3504 1.1621
No log 2.2667 102 0.8184 0.1538 0.8184 0.9047
No log 2.3111 104 0.8760 0.2146 0.8760 0.9359
No log 2.3556 106 0.9249 0.2489 0.9249 0.9617
No log 2.4 108 0.9554 0.2208 0.9554 0.9774
No log 2.4444 110 1.3338 0.0789 1.3338 1.1549
No log 2.4889 112 0.8857 0.1269 0.8857 0.9411
No log 2.5333 114 0.7704 0.1919 0.7704 0.8777
No log 2.5778 116 0.8005 0.2315 0.8005 0.8947
No log 2.6222 118 0.7511 0.2350 0.7511 0.8666
No log 2.6667 120 0.8242 0.1600 0.8242 0.9079
No log 2.7111 122 1.1665 0.0312 1.1665 1.0800
No log 2.7556 124 1.1751 0.0111 1.1751 1.0840
No log 2.8 126 0.7279 0.2513 0.7279 0.8532
No log 2.8444 128 0.7175 0.2626 0.7175 0.8471
No log 2.8889 130 0.7620 0.2000 0.7620 0.8729
No log 2.9333 132 0.8253 0.1269 0.8253 0.9085
No log 2.9778 134 1.0385 -0.0164 1.0385 1.0191
No log 3.0222 136 1.0809 -0.0164 1.0809 1.0396
No log 3.0667 138 0.7979 0.1086 0.7979 0.8933
No log 3.1111 140 0.8275 0.0459 0.8275 0.9097
No log 3.1556 142 0.7615 0.2889 0.7615 0.8727
No log 3.2 144 1.1626 0.0840 1.1626 1.0783
No log 3.2444 146 1.8161 0.0787 1.8161 1.3476
No log 3.2889 148 1.3988 0.1345 1.3988 1.1827
No log 3.3333 150 0.6676 0.1910 0.6676 0.8171
No log 3.3778 152 0.6594 0.2393 0.6594 0.8120
No log 3.4222 154 0.6507 0.2749 0.6507 0.8066
No log 3.4667 156 0.6680 0.2258 0.6680 0.8173
No log 3.5111 158 0.7360 0.1568 0.7360 0.8579
No log 3.5556 160 0.7324 0.2653 0.7324 0.8558
No log 3.6 162 0.7171 0.2990 0.7171 0.8468
No log 3.6444 164 0.7418 0.2442 0.7418 0.8613
No log 3.6889 166 0.7472 0.2965 0.7472 0.8644
No log 3.7333 168 0.9124 0.1776 0.9124 0.9552
No log 3.7778 170 0.9227 0.1786 0.9227 0.9606
No log 3.8222 172 0.7126 0.2245 0.7126 0.8441
No log 3.8667 174 0.8054 0.2676 0.8054 0.8974
No log 3.9111 176 0.8899 0.1273 0.8899 0.9433
No log 3.9556 178 0.6876 0.2787 0.6876 0.8292
No log 4.0 180 0.8965 0.1453 0.8965 0.9469
No log 4.0444 182 1.2696 0.1409 1.2696 1.1268
No log 4.0889 184 1.0276 0.1027 1.0276 1.0137
No log 4.1333 186 0.6673 0.1411 0.6673 0.8169
No log 4.1778 188 0.7583 0.1357 0.7583 0.8708
No log 4.2222 190 0.7611 0.1841 0.7611 0.8724
No log 4.2667 192 0.6702 0.3023 0.6702 0.8187
No log 4.3111 194 0.8270 0.0714 0.8270 0.9094
No log 4.3556 196 1.0507 0.1292 1.0507 1.0250
No log 4.4 198 0.9032 0.1392 0.9032 0.9504
No log 4.4444 200 0.8283 0.1712 0.8283 0.9101
No log 4.4889 202 0.7188 0.2653 0.7188 0.8478
No log 4.5333 204 0.7356 0.2653 0.7356 0.8577
No log 4.5778 206 0.8409 0.0909 0.8409 0.9170
No log 4.6222 208 0.8219 0.1238 0.8219 0.9066
No log 4.6667 210 0.6988 0.2432 0.6988 0.8360
No log 4.7111 212 0.6802 0.3161 0.6802 0.8248
No log 4.7556 214 0.6128 0.3520 0.6128 0.7828
No log 4.8 216 0.6942 0.2165 0.6942 0.8332
No log 4.8444 218 0.6520 0.25 0.6520 0.8074
No log 4.8889 220 0.6064 0.2865 0.6064 0.7787
No log 4.9333 222 0.5492 0.3797 0.5492 0.7411
No log 4.9778 224 0.5589 0.3913 0.5589 0.7476
No log 5.0222 226 0.5724 0.4105 0.5724 0.7565
No log 5.0667 228 0.6337 0.3061 0.6337 0.7961
No log 5.1111 230 0.6528 0.3433 0.6528 0.8080
No log 5.1556 232 0.6671 0.3684 0.6671 0.8168
No log 5.2 234 0.9119 0.1756 0.9119 0.9549
No log 5.2444 236 1.0690 0.1515 1.0690 1.0339
No log 5.2889 238 0.8865 0.1673 0.8865 0.9416
No log 5.3333 240 0.6931 0.3561 0.6931 0.8325
No log 5.3778 242 0.7651 0.2432 0.7651 0.8747
No log 5.4222 244 0.7098 0.3010 0.7098 0.8425
No log 5.4667 246 0.6972 0.2653 0.6972 0.8350
No log 5.5111 248 0.7088 0.1919 0.7088 0.8419
No log 5.5556 250 0.6954 0.2941 0.6954 0.8339
No log 5.6 252 0.7927 0.2146 0.7927 0.8904
No log 5.6444 254 0.8846 0.2333 0.8846 0.9405
No log 5.6889 256 0.7679 0.2068 0.7679 0.8763
No log 5.7333 258 0.7817 0.2222 0.7817 0.8841
No log 5.7778 260 0.9592 0.1453 0.9592 0.9794
No log 5.8222 262 0.8759 0.2143 0.8759 0.9359
No log 5.8667 264 0.7547 0.2308 0.7547 0.8687
No log 5.9111 266 0.6917 0.2917 0.6917 0.8317
No log 5.9556 268 0.6913 0.2577 0.6913 0.8315
No log 6.0 270 0.7005 0.2315 0.7005 0.8369
No log 6.0444 272 0.7117 0.1753 0.7117 0.8436
No log 6.0889 274 0.6497 0.2670 0.6497 0.8061
No log 6.1333 276 0.6116 0.2179 0.6116 0.7820
No log 6.1778 278 0.6399 0.2670 0.6399 0.7999
No log 6.2222 280 0.6998 0.25 0.6998 0.8365
No log 6.2667 282 0.6563 0.2670 0.6563 0.8101
No log 6.3111 284 0.6364 0.2941 0.6364 0.7978
No log 6.3556 286 0.6643 0.2941 0.6643 0.8151
No log 6.4 288 0.7627 0.1781 0.7627 0.8733
No log 6.4444 290 0.8310 0.1855 0.8310 0.9116
No log 6.4889 292 0.8521 0.1927 0.8521 0.9231
No log 6.5333 294 0.7856 0.2442 0.7856 0.8864
No log 6.5778 296 0.7451 0.2917 0.7451 0.8632
No log 6.6222 298 0.7517 0.2871 0.7517 0.8670
No log 6.6667 300 0.8125 0.1238 0.8125 0.9014
No log 6.7111 302 0.7527 0.1238 0.7527 0.8676
No log 6.7556 304 0.6793 0.2258 0.6793 0.8242
No log 6.8 306 0.6623 0.3191 0.6623 0.8138
No log 6.8444 308 0.6702 0.3191 0.6702 0.8187
No log 6.8889 310 0.6892 0.2917 0.6892 0.8302
No log 6.9333 312 0.7084 0.2917 0.7084 0.8417
No log 6.9778 314 0.7189 0.2536 0.7189 0.8479
No log 7.0222 316 0.7330 0.2536 0.7330 0.8561
No log 7.0667 318 0.7276 0.2917 0.7276 0.8530
No log 7.1111 320 0.7215 0.2917 0.7215 0.8494
No log 7.1556 322 0.7062 0.2917 0.7062 0.8403
No log 7.2 324 0.6794 0.2727 0.6794 0.8243
No log 7.2444 326 0.6628 0.3161 0.6628 0.8141
No log 7.2889 328 0.6557 0.2941 0.6557 0.8097
No log 7.3333 330 0.6525 0.2265 0.6525 0.8078
No log 7.3778 332 0.6813 0.1556 0.6813 0.8254
No log 7.4222 334 0.7107 0.1556 0.7107 0.8430
No log 7.4667 336 0.6888 0.2258 0.6888 0.8299
No log 7.5111 338 0.6775 0.2727 0.6775 0.8231
No log 7.5556 340 0.7094 0.2549 0.7094 0.8422
No log 7.6 342 0.7099 0.2549 0.7099 0.8426
No log 7.6444 344 0.6920 0.3469 0.6920 0.8319
No log 7.6889 346 0.7077 0.2692 0.7077 0.8413
No log 7.7333 348 0.7609 0.2593 0.7609 0.8723
No log 7.7778 350 0.7693 0.2593 0.7693 0.8771
No log 7.8222 352 0.7346 0.2165 0.7346 0.8571
No log 7.8667 354 0.7092 0.2165 0.7092 0.8421
No log 7.9111 356 0.7082 0.2165 0.7082 0.8415
No log 7.9556 358 0.7406 0.2986 0.7406 0.8606
No log 8.0 360 0.7697 0.1928 0.7697 0.8773
No log 8.0444 362 0.7529 0.2294 0.7529 0.8677
No log 8.0889 364 0.7204 0.2709 0.7204 0.8488
No log 8.1333 366 0.6796 0.2593 0.6796 0.8244
No log 8.1778 368 0.6777 0.3171 0.6777 0.8233
No log 8.2222 370 0.7068 0.3498 0.7068 0.8407
No log 8.2667 372 0.7092 0.2762 0.7092 0.8422
No log 8.3111 374 0.7129 0.2692 0.7129 0.8443
No log 8.3556 376 0.7594 0.1855 0.7594 0.8715
No log 8.4 378 0.7809 0.2212 0.7809 0.8837
No log 8.4444 380 0.7525 0.1855 0.7525 0.8675
No log 8.4889 382 0.7375 0.2637 0.7375 0.8588
No log 8.5333 384 0.7134 0.2464 0.7134 0.8446
No log 8.5778 386 0.7030 0.2549 0.7030 0.8385
No log 8.6222 388 0.6981 0.2762 0.6981 0.8355
No log 8.6667 390 0.6956 0.2821 0.6956 0.8340
No log 8.7111 392 0.7130 0.2653 0.7130 0.8444
No log 8.7556 394 0.7340 0.2637 0.7340 0.8567
No log 8.8 396 0.7224 0.2637 0.7224 0.8499
No log 8.8444 398 0.7143 0.2637 0.7143 0.8451
No log 8.8889 400 0.6927 0.2670 0.6927 0.8323
No log 8.9333 402 0.6840 0.2081 0.6840 0.8270
No log 8.9778 404 0.6870 0.2081 0.6870 0.8289
No log 9.0222 406 0.6872 0.2709 0.6872 0.8290
No log 9.0667 408 0.6931 0.2727 0.6931 0.8325
No log 9.1111 410 0.6994 0.28 0.6994 0.8363
No log 9.1556 412 0.7122 0.2475 0.7122 0.8439
No log 9.2 414 0.7208 0.2464 0.7208 0.8490
No log 9.2444 416 0.7320 0.2637 0.7320 0.8556
No log 9.2889 418 0.7426 0.2986 0.7426 0.8618
No log 9.3333 420 0.7568 0.2593 0.7568 0.8699
No log 9.3778 422 0.7503 0.2593 0.7503 0.8662
No log 9.4222 424 0.7452 0.2986 0.7452 0.8632
No log 9.4667 426 0.7371 0.3010 0.7371 0.8585
No log 9.5111 428 0.7352 0.2637 0.7352 0.8574
No log 9.5556 430 0.7263 0.2464 0.7263 0.8522
No log 9.6 432 0.7211 0.2475 0.7211 0.8492
No log 9.6444 434 0.7223 0.2475 0.7223 0.8499
No log 9.6889 436 0.7235 0.2475 0.7235 0.8506
No log 9.7333 438 0.7236 0.2475 0.7236 0.8507
No log 9.7778 440 0.7228 0.2475 0.7228 0.8502
No log 9.8222 442 0.7237 0.2475 0.7237 0.8507
No log 9.8667 444 0.7248 0.2475 0.7248 0.8513
No log 9.9111 446 0.7260 0.2464 0.7260 0.8521
No log 9.9556 448 0.7270 0.2464 0.7270 0.8526
No log 10.0 450 0.7271 0.2464 0.7271 0.8527

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
4
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/ArabicNewSplits4_WithDuplicationsForScore5_FineTuningAraBERT_run3_AugV5_k10_task3_organization

Finetuned
(4040)
this model