ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run2_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: 0.6803
  • Qwk: 0.6484
  • Mse: 0.6803
  • Rmse: 0.8248

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 0.0385 2 5.2185 -0.0232 5.2185 2.2844
No log 0.0769 4 3.3713 0.0490 3.3713 1.8361
No log 0.1154 6 2.2739 -0.0074 2.2739 1.5079
No log 0.1538 8 2.4338 -0.1735 2.4338 1.5601
No log 0.1923 10 1.8636 0.0128 1.8636 1.3651
No log 0.2308 12 1.3865 0.1355 1.3865 1.1775
No log 0.2692 14 1.3194 0.1606 1.3194 1.1487
No log 0.3077 16 1.4065 0.0218 1.4065 1.1860
No log 0.3462 18 1.3590 0.0692 1.3590 1.1658
No log 0.3846 20 1.3187 0.1822 1.3187 1.1483
No log 0.4231 22 1.2967 0.2659 1.2967 1.1387
No log 0.4615 24 1.2147 0.2664 1.2147 1.1021
No log 0.5 26 1.1579 0.2548 1.1579 1.0760
No log 0.5385 28 1.1277 0.2266 1.1277 1.0619
No log 0.5769 30 1.1069 0.2131 1.1069 1.0521
No log 0.6154 32 1.0860 0.1991 1.0860 1.0421
No log 0.6538 34 1.0494 0.2905 1.0494 1.0244
No log 0.6923 36 1.4130 0.2188 1.4130 1.1887
No log 0.7308 38 1.6174 0.1451 1.6174 1.2718
No log 0.7692 40 1.9059 0.1511 1.9059 1.3806
No log 0.8077 42 1.9929 0.1522 1.9929 1.4117
No log 0.8462 44 1.7692 0.1418 1.7692 1.3301
No log 0.8846 46 1.3786 0.2202 1.3786 1.1741
No log 0.9231 48 1.0805 0.3162 1.0805 1.0395
No log 0.9615 50 1.0555 0.2943 1.0555 1.0274
No log 1.0 52 1.1510 0.2564 1.1510 1.0728
No log 1.0385 54 1.2149 0.2650 1.2149 1.1022
No log 1.0769 56 1.0758 0.3504 1.0758 1.0372
No log 1.1154 58 0.9853 0.3513 0.9853 0.9926
No log 1.1538 60 1.3621 0.2274 1.3621 1.1671
No log 1.1923 62 1.7072 0.1856 1.7072 1.3066
No log 1.2308 64 1.5981 0.1449 1.5981 1.2642
No log 1.2692 66 1.1660 0.3532 1.1660 1.0798
No log 1.3077 68 0.9876 0.4650 0.9876 0.9938
No log 1.3462 70 0.9005 0.4291 0.9005 0.9490
No log 1.3846 72 0.8230 0.4303 0.8230 0.9072
No log 1.4231 74 0.8145 0.5196 0.8145 0.9025
No log 1.4615 76 0.7826 0.5794 0.7826 0.8846
No log 1.5 78 0.7838 0.5879 0.7838 0.8853
No log 1.5385 80 1.1454 0.4739 1.1454 1.0703
No log 1.5769 82 1.8943 0.3264 1.8943 1.3763
No log 1.6154 84 2.0661 0.2794 2.0661 1.4374
No log 1.6538 86 1.5226 0.4221 1.5226 1.2339
No log 1.6923 88 0.7665 0.5898 0.7665 0.8755
No log 1.7308 90 0.6617 0.6499 0.6617 0.8134
No log 1.7692 92 0.7839 0.5621 0.7839 0.8854
No log 1.8077 94 0.8003 0.5529 0.8003 0.8946
No log 1.8462 96 0.7757 0.5862 0.7757 0.8808
No log 1.8846 98 0.7522 0.6028 0.7522 0.8673
No log 1.9231 100 0.6784 0.6334 0.6784 0.8237
No log 1.9615 102 0.6937 0.6310 0.6937 0.8329
No log 2.0 104 0.6972 0.6329 0.6972 0.8350
No log 2.0385 106 0.7079 0.6245 0.7079 0.8414
No log 2.0769 108 0.7249 0.6051 0.7249 0.8514
No log 2.1154 110 0.6905 0.6399 0.6905 0.8309
No log 2.1538 112 0.7087 0.5954 0.7087 0.8418
No log 2.1923 114 0.8700 0.5518 0.8700 0.9328
No log 2.2308 116 0.7839 0.6062 0.7839 0.8854
No log 2.2692 118 0.6806 0.6564 0.6806 0.8250
No log 2.3077 120 1.0544 0.5425 1.0544 1.0269
No log 2.3462 122 1.3553 0.3911 1.3553 1.1642
No log 2.3846 124 1.1201 0.5385 1.1201 1.0584
No log 2.4231 126 0.7187 0.6693 0.7187 0.8478
No log 2.4615 128 0.6919 0.6601 0.6919 0.8318
No log 2.5 130 0.8890 0.5620 0.8890 0.9429
No log 2.5385 132 0.7879 0.5893 0.7879 0.8876
No log 2.5769 134 0.6691 0.6171 0.6691 0.8180
No log 2.6154 136 0.7021 0.6685 0.7021 0.8379
No log 2.6538 138 0.6718 0.6749 0.6718 0.8196
No log 2.6923 140 0.6715 0.6391 0.6715 0.8194
No log 2.7308 142 0.6678 0.6380 0.6678 0.8172
No log 2.7692 144 0.6764 0.6915 0.6764 0.8225
No log 2.8077 146 0.7131 0.6974 0.7131 0.8445
No log 2.8462 148 0.6613 0.7024 0.6613 0.8132
No log 2.8846 150 0.6515 0.6963 0.6515 0.8072
No log 2.9231 152 0.7115 0.6506 0.7115 0.8435
No log 2.9615 154 0.7530 0.6486 0.7530 0.8678
No log 3.0 156 0.6663 0.6787 0.6663 0.8163
No log 3.0385 158 0.6327 0.6887 0.6327 0.7955
No log 3.0769 160 0.6298 0.6974 0.6298 0.7936
No log 3.1154 162 0.6290 0.6883 0.6290 0.7931
No log 3.1538 164 0.6531 0.6533 0.6531 0.8081
No log 3.1923 166 0.7061 0.5947 0.7061 0.8403
No log 3.2308 168 0.7030 0.5842 0.7030 0.8385
No log 3.2692 170 0.7274 0.6048 0.7274 0.8529
No log 3.3077 172 0.7153 0.6069 0.7153 0.8457
No log 3.3462 174 0.7011 0.6540 0.7011 0.8373
No log 3.3846 176 0.8383 0.6075 0.8383 0.9156
No log 3.4231 178 1.0063 0.5403 1.0063 1.0031
No log 3.4615 180 0.9104 0.5925 0.9104 0.9542
No log 3.5 182 0.8131 0.6526 0.8131 0.9017
No log 3.5385 184 0.7904 0.6702 0.7904 0.8890
No log 3.5769 186 0.7638 0.7031 0.7638 0.8740
No log 3.6154 188 0.7099 0.7043 0.7099 0.8425
No log 3.6538 190 0.6941 0.6559 0.6941 0.8331
No log 3.6923 192 0.7956 0.6166 0.7956 0.8920
No log 3.7308 194 0.8831 0.5756 0.8831 0.9397
No log 3.7692 196 0.7964 0.6177 0.7964 0.8924
No log 3.8077 198 0.6982 0.6950 0.6982 0.8356
No log 3.8462 200 0.6915 0.6950 0.6915 0.8316
No log 3.8846 202 0.7556 0.6606 0.7556 0.8692
No log 3.9231 204 0.9459 0.6180 0.9459 0.9726
No log 3.9615 206 0.9460 0.6236 0.9460 0.9726
No log 4.0 208 0.7842 0.6524 0.7842 0.8856
No log 4.0385 210 0.6671 0.6963 0.6671 0.8168
No log 4.0769 212 0.7191 0.6753 0.7191 0.8480
No log 4.1154 214 0.6853 0.6328 0.6853 0.8278
No log 4.1538 216 0.6952 0.6455 0.6952 0.8338
No log 4.1923 218 0.8378 0.6027 0.8378 0.9153
No log 4.2308 220 0.7900 0.6078 0.7900 0.8888
No log 4.2692 222 0.7091 0.6558 0.7091 0.8421
No log 4.3077 224 0.6560 0.6987 0.6560 0.8099
No log 4.3462 226 0.6459 0.6810 0.6459 0.8037
No log 4.3846 228 0.6704 0.6986 0.6704 0.8188
No log 4.4231 230 0.6743 0.6833 0.6743 0.8212
No log 4.4615 232 0.7029 0.7083 0.7029 0.8384
No log 4.5 234 0.8426 0.6493 0.8426 0.9179
No log 4.5385 236 0.8214 0.6579 0.8214 0.9063
No log 4.5769 238 0.7256 0.6969 0.7256 0.8518
No log 4.6154 240 0.7209 0.6649 0.7209 0.8491
No log 4.6538 242 0.7426 0.7039 0.7426 0.8618
No log 4.6923 244 0.8263 0.6407 0.8263 0.9090
No log 4.7308 246 0.8042 0.6352 0.8042 0.8967
No log 4.7692 248 0.7403 0.6769 0.7403 0.8604
No log 4.8077 250 0.6917 0.6650 0.6917 0.8317
No log 4.8462 252 0.6896 0.6485 0.6896 0.8304
No log 4.8846 254 0.6910 0.6317 0.6910 0.8313
No log 4.9231 256 0.6798 0.6508 0.6798 0.8245
No log 4.9615 258 0.6719 0.6443 0.6719 0.8197
No log 5.0 260 0.6826 0.6908 0.6826 0.8262
No log 5.0385 262 0.6795 0.7092 0.6795 0.8243
No log 5.0769 264 0.7182 0.6922 0.7182 0.8475
No log 5.1154 266 0.7704 0.6758 0.7704 0.8777
No log 5.1538 268 0.8703 0.6516 0.8703 0.9329
No log 5.1923 270 0.8068 0.6497 0.8068 0.8982
No log 5.2308 272 0.7310 0.6519 0.7310 0.8550
No log 5.2692 274 0.6940 0.6802 0.6940 0.8331
No log 5.3077 276 0.6823 0.6878 0.6823 0.8260
No log 5.3462 278 0.7083 0.6811 0.7083 0.8416
No log 5.3846 280 0.7872 0.6951 0.7872 0.8873
No log 5.4231 282 0.7521 0.7254 0.7521 0.8672
No log 5.4615 284 0.7706 0.7313 0.7706 0.8778
No log 5.5 286 0.8147 0.7269 0.8147 0.9026
No log 5.5385 288 0.7603 0.7269 0.7603 0.8719
No log 5.5769 290 0.7863 0.6824 0.7863 0.8867
No log 5.6154 292 0.9392 0.5693 0.9392 0.9691
No log 5.6538 294 1.0713 0.4985 1.0713 1.0350
No log 5.6923 296 1.0273 0.5073 1.0273 1.0136
No log 5.7308 298 0.7949 0.6117 0.7949 0.8916
No log 5.7692 300 0.6936 0.6642 0.6936 0.8328
No log 5.8077 302 0.6711 0.6886 0.6711 0.8192
No log 5.8462 304 0.7354 0.6976 0.7354 0.8575
No log 5.8846 306 0.9082 0.6027 0.9082 0.9530
No log 5.9231 308 0.8873 0.6173 0.8873 0.9420
No log 5.9615 310 0.8258 0.6389 0.8258 0.9087
No log 6.0 312 0.7707 0.6912 0.7707 0.8779
No log 6.0385 314 0.7428 0.7006 0.7428 0.8618
No log 6.0769 316 0.7204 0.7028 0.7204 0.8488
No log 6.1154 318 0.7472 0.7025 0.7472 0.8644
No log 6.1538 320 0.8197 0.6309 0.8197 0.9054
No log 6.1923 322 0.7176 0.7069 0.7176 0.8471
No log 6.2308 324 0.6413 0.7071 0.6413 0.8008
No log 6.2692 326 0.6515 0.6915 0.6515 0.8071
No log 6.3077 328 0.6484 0.7180 0.6484 0.8052
No log 6.3462 330 0.7360 0.6892 0.7360 0.8579
No log 6.3846 332 0.7944 0.6648 0.7944 0.8913
No log 6.4231 334 0.7525 0.6813 0.7525 0.8675
No log 6.4615 336 0.6752 0.7054 0.6752 0.8217
No log 6.5 338 0.6638 0.7006 0.6638 0.8147
No log 6.5385 340 0.6278 0.6963 0.6278 0.7924
No log 6.5769 342 0.6303 0.7045 0.6303 0.7939
No log 6.6154 344 0.6635 0.6633 0.6635 0.8145
No log 6.6538 346 0.8778 0.5989 0.8778 0.9369
No log 6.6923 348 0.9861 0.5381 0.9861 0.9930
No log 6.7308 350 0.8924 0.5745 0.8924 0.9447
No log 6.7692 352 0.7729 0.5887 0.7729 0.8791
No log 6.8077 354 0.7065 0.5986 0.7065 0.8405
No log 6.8462 356 0.6937 0.6148 0.6937 0.8329
No log 6.8846 358 0.7580 0.6418 0.7580 0.8707
No log 6.9231 360 0.9020 0.6043 0.9020 0.9497
No log 6.9615 362 0.8225 0.6016 0.8225 0.9069
No log 7.0 364 0.7200 0.6571 0.7200 0.8485
No log 7.0385 366 0.6849 0.6498 0.6849 0.8276
No log 7.0769 368 0.6821 0.6217 0.6821 0.8259
No log 7.1154 370 0.6654 0.6408 0.6654 0.8157
No log 7.1538 372 0.6727 0.6377 0.6727 0.8202
No log 7.1923 374 0.7415 0.6407 0.7415 0.8611
No log 7.2308 376 0.7251 0.6615 0.7251 0.8515
No log 7.2692 378 0.6761 0.6877 0.6761 0.8223
No log 7.3077 380 0.6614 0.6987 0.6614 0.8133
No log 7.3462 382 0.6692 0.7048 0.6692 0.8180
No log 7.3846 384 0.6893 0.7006 0.6893 0.8302
No log 7.4231 386 0.7601 0.6745 0.7601 0.8718
No log 7.4615 388 0.8984 0.6423 0.8984 0.9478
No log 7.5 390 1.0468 0.6193 1.0468 1.0231
No log 7.5385 392 0.9869 0.5953 0.9869 0.9934
No log 7.5769 394 0.9023 0.5849 0.9023 0.9499
No log 7.6154 396 0.7508 0.6743 0.7508 0.8665
No log 7.6538 398 0.7105 0.6951 0.7105 0.8429
No log 7.6923 400 0.7226 0.6722 0.7226 0.8501
No log 7.7308 402 0.7973 0.6574 0.7973 0.8929
No log 7.7692 404 0.7650 0.6674 0.7650 0.8746
No log 7.8077 406 0.6877 0.7079 0.6877 0.8293
No log 7.8462 408 0.6754 0.6991 0.6754 0.8218
No log 7.8846 410 0.6832 0.6902 0.6832 0.8266
No log 7.9231 412 0.6647 0.7027 0.6647 0.8153
No log 7.9615 414 0.6928 0.6943 0.6928 0.8323
No log 8.0 416 0.6830 0.6796 0.6830 0.8264
No log 8.0385 418 0.6709 0.6621 0.6709 0.8191
No log 8.0769 420 0.7121 0.6806 0.7121 0.8438
No log 8.1154 422 0.7048 0.6876 0.7048 0.8395
No log 8.1538 424 0.6649 0.6740 0.6649 0.8154
No log 8.1923 426 0.7287 0.6926 0.7287 0.8536
No log 8.2308 428 0.8907 0.6015 0.8907 0.9437
No log 8.2692 430 0.9618 0.5887 0.9618 0.9807
No log 8.3077 432 0.8976 0.5819 0.8976 0.9474
No log 8.3462 434 0.7858 0.6125 0.7858 0.8865
No log 8.3846 436 0.7252 0.5561 0.7252 0.8516
No log 8.4231 438 0.7215 0.5092 0.7215 0.8494
No log 8.4615 440 0.6948 0.5929 0.6948 0.8336
No log 8.5 442 0.6967 0.6223 0.6967 0.8347
No log 8.5385 444 0.7112 0.6439 0.7112 0.8433
No log 8.5769 446 0.6776 0.6663 0.6776 0.8232
No log 8.6154 448 0.6554 0.6549 0.6554 0.8096
No log 8.6538 450 0.6486 0.6651 0.6486 0.8054
No log 8.6923 452 0.6682 0.6703 0.6682 0.8174
No log 8.7308 454 0.7256 0.6614 0.7256 0.8518
No log 8.7692 456 0.6935 0.6675 0.6935 0.8328
No log 8.8077 458 0.6911 0.6653 0.6911 0.8313
No log 8.8462 460 0.7246 0.6645 0.7246 0.8512
No log 8.8846 462 0.7085 0.6852 0.7085 0.8417
No log 8.9231 464 0.6751 0.6791 0.6751 0.8216
No log 8.9615 466 0.6750 0.6692 0.6750 0.8216
No log 9.0 468 0.7148 0.6929 0.7148 0.8455
No log 9.0385 470 0.7871 0.6657 0.7871 0.8872
No log 9.0769 472 0.8266 0.6575 0.8266 0.9092
No log 9.1154 474 0.8416 0.6477 0.8416 0.9174
No log 9.1538 476 0.7605 0.6350 0.7605 0.8721
No log 9.1923 478 0.7116 0.6795 0.7116 0.8435
No log 9.2308 480 0.7247 0.6905 0.7247 0.8513
No log 9.2692 482 0.8129 0.6174 0.8129 0.9016
No log 9.3077 484 0.9033 0.6146 0.9033 0.9504
No log 9.3462 486 0.9290 0.6136 0.9290 0.9638
No log 9.3846 488 0.8260 0.6239 0.8260 0.9088
No log 9.4231 490 0.6955 0.6589 0.6955 0.8339
No log 9.4615 492 0.6686 0.6417 0.6686 0.8177
No log 9.5 494 0.6628 0.6504 0.6628 0.8141
No log 9.5385 496 0.6561 0.6599 0.6561 0.8100
No log 9.5769 498 0.6924 0.6802 0.6924 0.8321
0.4486 9.6154 500 0.7156 0.6714 0.7156 0.8460
0.4486 9.6538 502 0.6842 0.6779 0.6842 0.8272
0.4486 9.6923 504 0.6728 0.6827 0.6728 0.8203
0.4486 9.7308 506 0.7119 0.6605 0.7119 0.8437
0.4486 9.7692 508 0.7558 0.6535 0.7558 0.8694
0.4486 9.8077 510 0.7412 0.6383 0.7412 0.8609
0.4486 9.8462 512 0.6962 0.6377 0.6962 0.8344
0.4486 9.8846 514 0.6803 0.6484 0.6803 0.8248

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/ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run2_AugV5_k10_task1_organization

Finetuned
(4040)
this model