Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask1_holistic

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: 19.8082
  • Qwk: 0.3999
  • Mse: 19.8082
  • Rmse: 4.4506

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 0.0213 2 317.0791 0.0003 317.0791 17.8067
No log 0.0426 4 304.3100 0.0062 304.3100 17.4445
No log 0.0638 6 282.9693 0.0024 282.9693 16.8217
No log 0.0851 8 265.8466 0.0044 265.8467 16.3048
No log 0.1064 10 250.8946 0.0000 250.8946 15.8397
No log 0.1277 12 236.1837 0.0054 236.1837 15.3683
No log 0.1489 14 222.9291 0.0051 222.9290 14.9308
No log 0.1702 16 210.9239 0.0045 210.9239 14.5232
No log 0.1915 18 204.8379 0.0073 204.8379 14.3122
No log 0.2128 20 192.6389 0.0040 192.6389 13.8794
No log 0.2340 22 182.8133 0.0089 182.8133 13.5208
No log 0.2553 24 179.9144 0.0098 179.9144 13.4132
No log 0.2766 26 171.3660 0.0071 171.3660 13.0907
No log 0.2979 28 164.4884 0.0024 164.4884 12.8253
No log 0.3191 30 159.7442 0.0025 159.7442 12.6390
No log 0.3404 32 155.9494 0.0118 155.9493 12.4880
No log 0.3617 34 150.5176 0.0070 150.5176 12.2686
No log 0.3830 36 145.1919 0.0027 145.1919 12.0496
No log 0.4043 38 142.4928 0.0027 142.4928 11.9370
No log 0.4255 40 137.9244 0.0007 137.9244 11.7441
No log 0.4468 42 134.8738 0.0158 134.8738 11.6135
No log 0.4681 44 131.7082 0.0090 131.7082 11.4764
No log 0.4894 46 130.5607 0.0076 130.5607 11.4263
No log 0.5106 48 125.1494 0.0025 125.1494 11.1870
No log 0.5319 50 122.1791 0.0008 122.1791 11.0535
No log 0.5532 52 122.9410 0.0031 122.9410 11.0879
No log 0.5745 54 118.9830 0.0016 118.9830 10.9079
No log 0.5957 56 115.5027 0.0173 115.5027 10.7472
No log 0.6170 58 113.6940 0.0138 113.6940 10.6627
No log 0.6383 60 111.5050 0.0058 111.5050 10.5596
No log 0.6596 62 109.5598 0.0030 109.5598 10.4671
No log 0.6809 64 107.1219 0.0019 107.1219 10.3500
No log 0.7021 66 106.1098 0.0019 106.1098 10.3010
No log 0.7234 68 106.1037 0.0019 106.1038 10.3007
No log 0.7447 70 101.9836 0.0009 101.9836 10.0987
No log 0.7660 72 100.5648 0.0009 100.5648 10.0282
No log 0.7872 74 101.1998 0.0009 101.1998 10.0598
No log 0.8085 76 97.8529 0.0002 97.8529 9.8921
No log 0.8298 78 96.3777 0.0151 96.3777 9.8172
No log 0.8511 80 95.1861 0.0066 95.1861 9.7563
No log 0.8723 82 93.6397 0.0036 93.6397 9.6768
No log 0.8936 84 91.7261 0.0011 91.7261 9.5774
No log 0.9149 86 90.2860 0.0011 90.2860 9.5019
No log 0.9362 88 89.5498 0.0011 89.5498 9.4631
No log 0.9574 90 86.4713 0.0011 86.4713 9.2990
No log 0.9787 92 86.0615 0.0 86.0615 9.2769
No log 1.0 94 84.5079 0.0011 84.5079 9.1928
No log 1.0213 96 86.1617 0.0011 86.1617 9.2823
No log 1.0426 98 81.4544 0.0276 81.4544 9.0252
No log 1.0638 100 81.2110 0.0261 81.2110 9.0117
No log 1.0851 102 79.8661 0.0077 79.8661 8.9368
No log 1.1064 104 81.4415 0.0084 81.4415 9.0245
No log 1.1277 106 77.2122 0.0013 77.2122 8.7870
No log 1.1489 108 76.8184 0.0013 76.8184 8.7646
No log 1.1702 110 75.6239 0.0013 75.6239 8.6962
No log 1.1915 112 75.4439 0.0013 75.4439 8.6858
No log 1.2128 114 74.0244 0.0013 74.0244 8.6037
No log 1.2340 116 73.6437 0.0 73.6437 8.5816
No log 1.2553 118 72.5285 0.0 72.5285 8.5164
No log 1.2766 120 72.0720 0.0 72.0720 8.4895
No log 1.2979 122 71.3121 0.0 71.3121 8.4446
No log 1.3191 124 70.2681 0.0 70.2681 8.3826
No log 1.3404 126 69.5570 0.0 69.5570 8.3401
No log 1.3617 128 68.7931 0.0 68.7931 8.2942
No log 1.3830 130 68.1476 0.0 68.1476 8.2552
No log 1.4043 132 67.3193 0.0216 67.3193 8.2048
No log 1.4255 134 66.3801 0.0084 66.3801 8.1474
No log 1.4468 136 65.6539 0.0052 65.6539 8.1027
No log 1.4681 138 64.9311 0.0035 64.9311 8.0580
No log 1.4894 140 64.3117 0.0016 64.3117 8.0195
No log 1.5106 142 63.4418 0.0016 63.4418 7.9650
No log 1.5319 144 62.5522 0.0016 62.5522 7.9090
No log 1.5532 146 61.9204 0.0 61.9204 7.8690
No log 1.5745 148 61.2094 0.0 61.2094 7.8236
No log 1.5957 150 61.0278 0.0 61.0278 7.8120
No log 1.6170 152 60.3565 0.0 60.3565 7.7689
No log 1.6383 154 59.2890 0.0 59.2890 7.6999
No log 1.6596 156 58.6270 0.0 58.6270 7.6568
No log 1.6809 158 58.0349 0.0 58.0349 7.6181
No log 1.7021 160 57.4679 0.0 57.4679 7.5808
No log 1.7234 162 56.9777 0.0 56.9777 7.5484
No log 1.7447 164 56.5077 0.0 56.5077 7.5172
No log 1.7660 166 55.8768 0.0 55.8768 7.4751
No log 1.7872 168 55.3693 0.0352 55.3693 7.4411
No log 1.8085 170 55.0289 0.0187 55.0289 7.4181
No log 1.8298 172 54.7453 0.0057 54.7452 7.3990
No log 1.8511 174 53.9280 0.0057 53.9280 7.3436
No log 1.8723 176 53.4455 0.0069 53.4455 7.3106
No log 1.8936 178 53.0292 0.0042 53.0292 7.2821
No log 1.9149 180 52.7051 0.0042 52.7051 7.2598
No log 1.9362 182 52.0261 0.0057 52.0261 7.2129
No log 1.9574 184 52.0140 0.0266 52.0140 7.2121
No log 1.9787 186 51.0659 0.0254 51.0659 7.1460
No log 2.0 188 50.8652 0.0100 50.8652 7.1320
No log 2.0213 190 50.1608 0.0113 50.1608 7.0824
No log 2.0426 192 49.3686 0.0277 49.3686 7.0263
No log 2.0638 194 48.9972 0.0321 48.9972 6.9998
No log 2.0851 196 48.3094 0.0331 48.3094 6.9505
No log 2.1064 198 47.7699 0.0384 47.7699 6.9116
No log 2.1277 200 47.6830 0.0889 47.6829 6.9053
No log 2.1489 202 48.4402 0.1369 48.4402 6.9599
No log 2.1702 204 48.4950 0.1397 48.4950 6.9638
No log 2.1915 206 50.2358 0.1837 50.2358 7.0877
No log 2.2128 208 48.3707 0.1703 48.3707 6.9549
No log 2.2340 210 46.7935 0.0846 46.7935 6.8406
No log 2.2553 212 45.2999 0.0714 45.2999 6.7305
No log 2.2766 214 45.0995 0.0747 45.0995 6.7156
No log 2.2979 216 45.4255 0.0800 45.4255 6.7398
No log 2.3191 218 44.0512 0.1097 44.0511 6.6371
No log 2.3404 220 45.2059 0.0217 45.2059 6.7235
No log 2.3617 222 43.8629 0.0936 43.8629 6.6229
No log 2.3830 224 45.0260 0.1818 45.0260 6.7101
No log 2.4043 226 46.2234 0.1890 46.2234 6.7988
No log 2.4255 228 42.8509 0.1497 42.8509 6.5461
No log 2.4468 230 44.6606 0.0415 44.6606 6.6829
No log 2.4681 232 44.9648 0.0240 44.9648 6.7056
No log 2.4894 234 42.4572 0.0392 42.4572 6.5159
No log 2.5106 236 42.0551 0.0731 42.0551 6.4850
No log 2.5319 238 44.8979 0.1492 44.8979 6.7006
No log 2.5532 240 42.9177 0.1711 42.9177 6.5512
No log 2.5745 242 40.6765 0.1309 40.6765 6.3778
No log 2.5957 244 41.1339 0.1092 41.1339 6.4136
No log 2.6170 246 41.1397 0.1337 41.1397 6.4140
No log 2.6383 248 40.7373 0.1760 40.7373 6.3826
No log 2.6596 250 40.4487 0.1791 40.4487 6.3599
No log 2.6809 252 39.6986 0.1656 39.6986 6.3007
No log 2.7021 254 39.1906 0.1585 39.1906 6.2602
No log 2.7234 256 38.9031 0.1605 38.9031 6.2372
No log 2.7447 258 38.5480 0.1560 38.5480 6.2087
No log 2.7660 260 38.7740 0.1912 38.7740 6.2269
No log 2.7872 262 39.4011 0.2166 39.4011 6.2770
No log 2.8085 264 38.9600 0.2089 38.9600 6.2418
No log 2.8298 266 38.6228 0.2072 38.6228 6.2147
No log 2.8511 268 38.4119 0.2042 38.4119 6.1977
No log 2.8723 270 37.2276 0.1575 37.2276 6.1014
No log 2.8936 272 37.0082 0.1568 37.0082 6.0834
No log 2.9149 274 37.1867 0.1920 37.1867 6.0981
No log 2.9362 276 41.0515 0.2459 41.0515 6.4071
No log 2.9574 278 39.3787 0.2901 39.3787 6.2752
No log 2.9787 280 36.1998 0.2594 36.1998 6.0166
No log 3.0 282 35.9651 0.1496 35.9651 5.9971
No log 3.0213 284 35.5973 0.1431 35.5973 5.9663
No log 3.0426 286 34.9945 0.1473 34.9945 5.9156
No log 3.0638 288 34.9183 0.1622 34.9183 5.9092
No log 3.0851 290 35.0473 0.2063 35.0473 5.9201
No log 3.1064 292 34.6565 0.2306 34.6565 5.8870
No log 3.1277 294 35.0177 0.2715 35.0177 5.9176
No log 3.1489 296 35.1918 0.2799 35.1918 5.9323
No log 3.1702 298 35.0845 0.2726 35.0845 5.9232
No log 3.1915 300 34.7743 0.2253 34.7743 5.8970
No log 3.2128 302 34.5373 0.2522 34.5373 5.8768
No log 3.2340 304 35.6763 0.3002 35.6763 5.9730
No log 3.2553 306 34.0929 0.2663 34.0929 5.8389
No log 3.2766 308 32.8618 0.1936 32.8618 5.7325
No log 3.2979 310 32.6739 0.1441 32.6739 5.7161
No log 3.3191 312 32.4115 0.1431 32.4115 5.6931
No log 3.3404 314 32.2998 0.1360 32.2998 5.6833
No log 3.3617 316 32.1730 0.1437 32.1730 5.6721
No log 3.3830 318 32.0368 0.1782 32.0368 5.6601
No log 3.4043 320 33.0547 0.2445 33.0547 5.7493
No log 3.4255 322 33.3684 0.2707 33.3684 5.7765
No log 3.4468 324 32.3286 0.2642 32.3286 5.6858
No log 3.4681 326 31.7479 0.2235 31.7479 5.6345
No log 3.4894 328 31.8325 0.1980 31.8325 5.6420
No log 3.5106 330 31.0975 0.2384 31.0975 5.5765
No log 3.5319 332 32.4857 0.2935 32.4857 5.6996
No log 3.5532 334 35.7575 0.3287 35.7575 5.9798
No log 3.5745 336 34.1945 0.3157 34.1945 5.8476
No log 3.5957 338 31.6997 0.2892 31.6997 5.6303
No log 3.6170 340 31.1772 0.2832 31.1772 5.5837
No log 3.6383 342 32.7824 0.3186 32.7824 5.7256
No log 3.6596 344 31.4779 0.2952 31.4779 5.6105
No log 3.6809 346 30.1778 0.2573 30.1778 5.4934
No log 3.7021 348 29.6293 0.2345 29.6293 5.4433
No log 3.7234 350 29.2617 0.2093 29.2617 5.4094
No log 3.7447 352 28.8516 0.2631 28.8516 5.3714
No log 3.7660 354 28.5804 0.3229 28.5804 5.3461
No log 3.7872 356 29.9250 0.3759 29.9250 5.4704
No log 3.8085 358 33.3537 0.3917 33.3537 5.7753
No log 3.8298 360 31.2946 0.4045 31.2946 5.5942
No log 3.8511 362 28.5392 0.3395 28.5392 5.3422
No log 3.8723 364 28.3611 0.2679 28.3611 5.3255
No log 3.8936 366 28.3651 0.2614 28.3651 5.3259
No log 3.9149 368 27.8395 0.2775 27.8395 5.2763
No log 3.9362 370 27.5942 0.2948 27.5942 5.2530
No log 3.9574 372 28.2609 0.3372 28.2609 5.3161
No log 3.9787 374 29.7348 0.3780 29.7348 5.4530
No log 4.0 376 30.2716 0.3906 30.2716 5.5020
No log 4.0213 378 28.7940 0.3742 28.7940 5.3660
No log 4.0426 380 27.0300 0.3016 27.0300 5.1990
No log 4.0638 382 27.0623 0.2433 27.0623 5.2021
No log 4.0851 384 27.0121 0.2321 27.0121 5.1973
No log 4.1064 386 26.5470 0.2842 26.5470 5.1524
No log 4.1277 388 26.7485 0.3428 26.7485 5.1719
No log 4.1489 390 29.1792 0.3935 29.1792 5.4018
No log 4.1702 392 27.8766 0.3846 27.8766 5.2798
No log 4.1915 394 26.3824 0.3480 26.3824 5.1364
No log 4.2128 396 25.9533 0.3262 25.9533 5.0944
No log 4.2340 398 25.7191 0.3255 25.7190 5.0714
No log 4.2553 400 25.7355 0.3447 25.7355 5.0730
No log 4.2766 402 25.9772 0.3745 25.9772 5.0968
No log 4.2979 404 26.0583 0.3857 26.0583 5.1047
No log 4.3191 406 26.7253 0.4060 26.7253 5.1697
No log 4.3404 408 25.1125 0.3661 25.1125 5.0112
No log 4.3617 410 24.7014 0.2795 24.7014 4.9700
No log 4.3830 412 24.9394 0.2323 24.9394 4.9939
No log 4.4043 414 24.9771 0.2081 24.9771 4.9977
No log 4.4255 416 24.2774 0.2599 24.2774 4.9272
No log 4.4468 418 24.1309 0.3259 24.1309 4.9123
No log 4.4681 420 24.6531 0.3765 24.6531 4.9652
No log 4.4894 422 27.0557 0.4229 27.0557 5.2015
No log 4.5106 424 25.2419 0.4005 25.2419 5.0241
No log 4.5319 426 23.6064 0.4226 23.6064 4.8586
No log 4.5532 428 23.6248 0.3650 23.6248 4.8605
No log 4.5745 430 23.8781 0.3149 23.8781 4.8865
No log 4.5957 432 23.7196 0.3302 23.7196 4.8703
No log 4.6170 434 23.2508 0.3886 23.2508 4.8219
No log 4.6383 436 23.2863 0.4395 23.2863 4.8256
No log 4.6596 438 24.6750 0.4663 24.6750 4.9674
No log 4.6809 440 25.0474 0.4774 25.0474 5.0047
No log 4.7021 442 23.2791 0.4529 23.2791 4.8248
No log 4.7234 444 23.0018 0.4305 23.0018 4.7960
No log 4.7447 446 22.9324 0.3999 22.9324 4.7888
No log 4.7660 448 22.8946 0.3773 22.8946 4.7848
No log 4.7872 450 22.8036 0.3730 22.8036 4.7753
No log 4.8085 452 22.6806 0.3872 22.6806 4.7624
No log 4.8298 454 22.5616 0.4348 22.5616 4.7499
No log 4.8511 456 22.6718 0.4604 22.6718 4.7615
No log 4.8723 458 23.1100 0.4604 23.1100 4.8073
No log 4.8936 460 22.2069 0.4328 22.2069 4.7124
No log 4.9149 462 21.6034 0.3953 21.6034 4.6479
No log 4.9362 464 21.4998 0.3631 21.4998 4.6368
No log 4.9574 466 21.5524 0.4062 21.5524 4.6425
No log 4.9787 468 23.4588 0.4548 23.4588 4.8434
No log 5.0 470 23.5428 0.4708 23.5428 4.8521
No log 5.0213 472 21.2959 0.4551 21.2959 4.6147
No log 5.0426 474 21.0216 0.4362 21.0216 4.5849
No log 5.0638 476 21.0968 0.4457 21.0968 4.5931
No log 5.0851 478 22.2503 0.4887 22.2503 4.7170
No log 5.1064 480 24.6489 0.4990 24.6489 4.9648
No log 5.1277 482 23.5017 0.4950 23.5017 4.8479
No log 5.1489 484 21.1860 0.4710 21.1860 4.6028
No log 5.1702 486 20.8041 0.3750 20.8041 4.5612
No log 5.1915 488 21.6194 0.2791 21.6194 4.6497
No log 5.2128 490 21.8099 0.2575 21.8099 4.6701
No log 5.2340 492 21.0911 0.3012 21.0911 4.5925
No log 5.2553 494 20.3676 0.4014 20.3676 4.5130
No log 5.2766 496 22.4543 0.4994 22.4543 4.7386
No log 5.2979 498 24.8409 0.5045 24.8409 4.9841
56.6361 5.3191 500 22.4647 0.4979 22.4647 4.7397
56.6361 5.3404 502 20.6446 0.4575 20.6446 4.5436
56.6361 5.3617 504 20.4198 0.4117 20.4198 4.5188
56.6361 5.3830 506 20.4887 0.3651 20.4887 4.5264
56.6361 5.4043 508 20.2914 0.3626 20.2914 4.5046
56.6361 5.4255 510 19.8082 0.3999 19.8082 4.4506

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
-
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/Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask1_holistic

Finetuned
(4019)
this model