Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask2_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: 18.9834
  • Qwk: 0.4119
  • Mse: 18.9834
  • Rmse: 4.3570

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 2 294.5277 0.0029 294.5277 17.1618
No log 0.0426 4 284.9683 0.0056 284.9683 16.8810
No log 0.0638 6 260.0461 0.0058 260.0461 16.1259
No log 0.0851 8 242.7112 0.0111 242.7112 15.5792
No log 0.1064 10 229.5635 0.0033 229.5635 15.1514
No log 0.1277 12 214.6519 0.0138 214.6519 14.6510
No log 0.1489 14 206.4027 0.0090 206.4027 14.3667
No log 0.1702 16 197.7631 0.0055 197.7631 14.0628
No log 0.1915 18 184.1302 0.0103 184.1302 13.5695
No log 0.2128 20 174.3235 0.0060 174.3235 13.2032
No log 0.2340 22 168.2488 0.0074 168.2489 12.9711
No log 0.2553 24 160.8617 0.0130 160.8617 12.6831
No log 0.2766 26 153.0845 0.0062 153.0845 12.3727
No log 0.2979 28 149.6301 0.0066 149.6301 12.2323
No log 0.3191 30 143.6820 0.0143 143.6820 11.9867
No log 0.3404 32 137.8423 0.0131 137.8423 11.7406
No log 0.3617 34 136.3015 0.0109 136.3015 11.6748
No log 0.3830 36 130.5191 0.0016 130.5191 11.4245
No log 0.4043 38 126.5972 0.0 126.5972 11.2515
No log 0.4255 40 124.4252 0.0 124.4252 11.1546
No log 0.4468 42 120.9916 0.0139 120.9916 10.9996
No log 0.4681 44 117.0854 0.0050 117.0854 10.8206
No log 0.4894 46 115.4663 0.0028 115.4663 10.7455
No log 0.5106 48 112.5278 0.0017 112.5278 10.6079
No log 0.5319 50 109.1561 0.0 109.1561 10.4478
No log 0.5532 52 106.9363 0.0 106.9363 10.3410
No log 0.5745 54 108.0261 0.0 108.0261 10.3936
No log 0.5957 56 103.8041 0.0072 103.8040 10.1884
No log 0.6170 58 101.2067 0.0105 101.2067 10.0602
No log 0.6383 60 99.1556 0.0042 99.1556 9.9577
No log 0.6596 62 98.8656 0.0052 98.8656 9.9431
No log 0.6809 64 94.7354 0.0 94.7354 9.7332
No log 0.7021 66 92.9512 0.0 92.9512 9.6411
No log 0.7234 68 92.9645 0.0 92.9645 9.6418
No log 0.7447 70 90.9765 0.0 90.9765 9.5382
No log 0.7660 72 88.4626 0.0 88.4626 9.4055
No log 0.7872 74 86.8711 0.0024 86.8711 9.3205
No log 0.8085 76 85.1691 0.0158 85.1691 9.2287
No log 0.8298 78 83.7697 0.0036 83.7697 9.1526
No log 0.8511 80 81.9815 0.0024 81.9815 9.0544
No log 0.8723 82 80.6497 0.0 80.6497 8.9805
No log 0.8936 84 79.3173 0.0 79.3173 8.9060
No log 0.9149 86 78.7772 0.0 78.7772 8.8756
No log 0.9362 88 77.5746 0.0 77.5746 8.8076
No log 0.9574 90 75.9999 0.0 75.9998 8.7178
No log 0.9787 92 74.9963 0.0 74.9963 8.6600
No log 1.0 94 73.9427 0.0 73.9427 8.5990
No log 1.0213 96 73.1179 0.0 73.1179 8.5509
No log 1.0426 98 72.0142 0.0258 72.0142 8.4861
No log 1.0638 100 70.7826 0.0231 70.7826 8.4132
No log 1.0851 102 69.6198 0.0083 69.6198 8.3438
No log 1.1064 104 68.7014 0.0029 68.7014 8.2886
No log 1.1277 106 67.7416 0.0029 67.7417 8.2305
No log 1.1489 108 66.8934 0.0029 66.8934 8.1788
No log 1.1702 110 65.8038 0.0012 65.8038 8.1120
No log 1.1915 112 64.7535 0.0 64.7535 8.0470
No log 1.2128 114 63.8778 0.0 63.8778 7.9924
No log 1.2340 116 63.3081 0.0 63.3081 7.9566
No log 1.2553 118 62.6961 0.0 62.6961 7.9181
No log 1.2766 120 61.5638 0.0 61.5638 7.8463
No log 1.2979 122 60.6439 0.0 60.6439 7.7874
No log 1.3191 124 60.0245 0.0 60.0245 7.7475
No log 1.3404 126 60.8350 0.0012 60.8350 7.7997
No log 1.3617 128 58.6322 0.0286 58.6322 7.6572
No log 1.3830 130 58.8933 0.0099 58.8933 7.6742
No log 1.4043 132 57.4677 0.0100 57.4677 7.5807
No log 1.4255 134 57.7882 0.0220 57.7882 7.6019
No log 1.4468 136 56.3308 0.0035 56.3308 7.5054
No log 1.4681 138 56.0139 0.0035 56.0139 7.4842
No log 1.4894 140 55.4628 0.0055 55.4628 7.4473
No log 1.5106 142 55.6454 0.0100 55.6454 7.4596
No log 1.5319 144 54.4196 0.0035 54.4196 7.3770
No log 1.5532 146 53.9059 0.0015 53.9059 7.3421
No log 1.5745 148 53.3312 0.0015 53.3312 7.3028
No log 1.5957 150 52.9115 0.0015 52.9115 7.2740
No log 1.6170 152 52.4679 0.0035 52.4679 7.2435
No log 1.6383 154 51.8636 0.0015 51.8636 7.2016
No log 1.6596 156 51.3677 0.0015 51.3677 7.1671
No log 1.6809 158 50.8752 0.0015 50.8752 7.1327
No log 1.7021 160 51.3232 0.0035 51.3232 7.1640
No log 1.7234 162 49.9291 0.0035 49.9291 7.0661
No log 1.7447 164 49.3457 0.0076 49.3457 7.0246
No log 1.7660 166 48.8590 0.0149 48.8590 6.9899
No log 1.7872 168 48.3783 0.0668 48.3783 6.9554
No log 1.8085 170 48.6127 0.0768 48.6127 6.9723
No log 1.8298 172 47.8258 0.0924 47.8259 6.9156
No log 1.8511 174 47.0185 0.0572 47.0185 6.8570
No log 1.8723 176 46.6431 0.0527 46.6431 6.8296
No log 1.8936 178 46.2970 0.0613 46.2970 6.8042
No log 1.9149 180 45.8756 0.0527 45.8756 6.7732
No log 1.9362 182 45.4417 0.0400 45.4417 6.7410
No log 1.9574 184 45.0464 0.0395 45.0464 6.7117
No log 1.9787 186 44.6168 0.0574 44.6168 6.6796
No log 2.0 188 44.3570 0.0808 44.3570 6.6601
No log 2.0213 190 43.8455 0.0813 43.8455 6.6216
No log 2.0426 192 43.3171 0.0834 43.3171 6.5816
No log 2.0638 194 42.9629 0.1016 42.9629 6.5546
No log 2.0851 196 43.2146 0.1344 43.2146 6.5738
No log 2.1064 198 42.2811 0.1096 42.2811 6.5024
No log 2.1277 200 42.1195 0.0595 42.1195 6.4900
No log 2.1489 202 41.4397 0.0680 41.4397 6.4374
No log 2.1702 204 41.0589 0.1065 41.0589 6.4077
No log 2.1915 206 41.4072 0.1391 41.4072 6.4348
No log 2.2128 208 40.6475 0.1374 40.6475 6.3755
No log 2.2340 210 39.8219 0.1002 39.8219 6.3105
No log 2.2553 212 39.5644 0.1023 39.5644 6.2900
No log 2.2766 214 40.4805 0.1735 40.4805 6.3624
No log 2.2979 216 42.7949 0.2188 42.7949 6.5418
No log 2.3191 218 38.6581 0.2159 38.6580 6.2176
No log 2.3404 220 38.5652 0.1486 38.5652 6.2101
No log 2.3617 222 37.9833 0.1673 37.9833 6.1631
No log 2.3830 224 37.9797 0.2012 37.9797 6.1628
No log 2.4043 226 37.3697 0.1958 37.3697 6.1131
No log 2.4255 228 38.0823 0.2666 38.0823 6.1711
No log 2.4468 230 36.9631 0.2254 36.9631 6.0797
No log 2.4681 232 36.5655 0.1906 36.5655 6.0469
No log 2.4894 234 36.2042 0.1837 36.2042 6.0170
No log 2.5106 236 36.1034 0.1401 36.1034 6.0086
No log 2.5319 238 36.2009 0.1272 36.2009 6.0167
No log 2.5532 240 36.0189 0.1331 36.0188 6.0016
No log 2.5745 242 35.3544 0.1411 35.3544 5.9460
No log 2.5957 244 35.0735 0.1480 35.0735 5.9223
No log 2.6170 246 34.8942 0.1513 34.8942 5.9071
No log 2.6383 248 34.6016 0.1954 34.6016 5.8823
No log 2.6596 250 37.4554 0.2802 37.4554 6.1201
No log 2.6809 252 35.1479 0.2570 35.1479 5.9286
No log 2.7021 254 33.9229 0.1834 33.9229 5.8243
No log 2.7234 256 33.6736 0.1813 33.6736 5.8029
No log 2.7447 258 34.1109 0.2513 34.1109 5.8405
No log 2.7660 260 34.5953 0.2674 34.5953 5.8818
No log 2.7872 262 32.8755 0.2044 32.8755 5.7337
No log 2.8085 264 32.7087 0.1414 32.7087 5.7192
No log 2.8298 266 32.8560 0.1026 32.8560 5.7320
No log 2.8511 268 32.3639 0.1119 32.3639 5.6889
No log 2.8723 270 32.2203 0.1536 32.2203 5.6763
No log 2.8936 272 33.8949 0.2378 33.8949 5.8219
No log 2.9149 274 32.9565 0.2456 32.9565 5.7408
No log 2.9362 276 31.5825 0.3081 31.5825 5.6198
No log 2.9574 278 31.6418 0.1671 31.6418 5.6251
No log 2.9787 280 31.5354 0.1742 31.5354 5.6156
No log 3.0 282 31.0342 0.1934 31.0342 5.5708
No log 3.0213 284 30.4988 0.2437 30.4987 5.5226
No log 3.0426 286 31.7874 0.2935 31.7874 5.6380
No log 3.0638 288 32.6490 0.3282 32.6490 5.7139
No log 3.0851 290 30.6115 0.3362 30.6115 5.5328
No log 3.1064 292 29.7019 0.2582 29.7019 5.4499
No log 3.1277 294 29.8808 0.2436 29.8808 5.4663
No log 3.1489 296 29.4492 0.2525 29.4492 5.4267
No log 3.1702 298 29.2190 0.3157 29.2190 5.4055
No log 3.1915 300 30.3895 0.3645 30.3895 5.5127
No log 3.2128 302 30.0146 0.3571 30.0146 5.4786
No log 3.2340 304 28.5155 0.3081 28.5155 5.3400
No log 3.2553 306 28.2131 0.2127 28.2131 5.3116
No log 3.2766 308 28.7516 0.1492 28.7516 5.3620
No log 3.2979 310 29.0466 0.1125 29.0466 5.3895
No log 3.3191 312 28.3327 0.1507 28.3327 5.3228
No log 3.3404 314 27.7644 0.1976 27.7644 5.2692
No log 3.3617 316 27.6457 0.2665 27.6457 5.2579
No log 3.3830 318 28.2751 0.3412 28.2751 5.3174
No log 3.4043 320 28.2678 0.3619 28.2678 5.3167
No log 3.4255 322 27.2171 0.3175 27.2172 5.2170
No log 3.4468 324 27.3344 0.2603 27.3344 5.2282
No log 3.4681 326 29.1512 0.1453 29.1512 5.3992
No log 3.4894 328 29.5930 0.0620 29.5930 5.4399
No log 3.5106 330 29.0445 0.0542 29.0445 5.3893
No log 3.5319 332 28.8975 0.0458 28.8974 5.3756
No log 3.5532 334 28.6963 0.0440 28.6963 5.3569
No log 3.5745 336 28.4244 0.0539 28.4244 5.3315
No log 3.5957 338 27.9755 0.0738 27.9755 5.2892
No log 3.6170 340 26.9903 0.1718 26.9903 5.1952
No log 3.6383 342 26.3773 0.2326 26.3773 5.1359
No log 3.6596 344 25.8766 0.2482 25.8766 5.0869
No log 3.6809 346 25.6193 0.3501 25.6193 5.0616
No log 3.7021 348 25.5397 0.4009 25.5397 5.0537
No log 3.7234 350 25.9568 0.4214 25.9568 5.0948
No log 3.7447 352 25.4714 0.4264 25.4714 5.0469
No log 3.7660 354 24.9441 0.3728 24.9441 4.9944
No log 3.7872 356 24.7507 0.3469 24.7507 4.9750
No log 3.8085 358 24.3971 0.3731 24.3971 4.9393
No log 3.8298 360 24.4582 0.4066 24.4582 4.9455
No log 3.8511 362 24.1711 0.3636 24.1711 4.9164
No log 3.8723 364 24.1774 0.3247 24.1774 4.9171
No log 3.8936 366 24.0257 0.3328 24.0257 4.9016
No log 3.9149 368 24.0892 0.2993 24.0892 4.9081
No log 3.9362 370 23.9195 0.3287 23.9195 4.8908
No log 3.9574 372 23.8058 0.3344 23.8058 4.8791
No log 3.9787 374 23.7726 0.3185 23.7726 4.8757
No log 4.0 376 23.8377 0.3008 23.8377 4.8824
No log 4.0213 378 23.6650 0.3061 23.6650 4.8647
No log 4.0426 380 23.3612 0.3315 23.3612 4.8333
No log 4.0638 382 23.1933 0.3324 23.1933 4.8159
No log 4.0851 384 23.1200 0.3182 23.1200 4.8083
No log 4.1064 386 23.0846 0.3026 23.0846 4.8046
No log 4.1277 388 22.9161 0.3073 22.9161 4.7871
No log 4.1489 390 22.5559 0.3749 22.5559 4.7493
No log 4.1702 392 22.7474 0.4058 22.7474 4.7694
No log 4.1915 394 22.7174 0.4093 22.7174 4.7663
No log 4.2128 396 22.0650 0.3668 22.0650 4.6973
No log 4.2340 398 22.1757 0.4042 22.1757 4.7091
No log 4.2553 400 22.3998 0.4237 22.3998 4.7328
No log 4.2766 402 22.0057 0.4120 22.0057 4.6910
No log 4.2979 404 21.8561 0.3852 21.8561 4.6751
No log 4.3191 406 22.7619 0.2974 22.7619 4.7709
No log 4.3404 408 23.4800 0.2380 23.4800 4.8456
No log 4.3617 410 22.7955 0.2694 22.7955 4.7745
No log 4.3830 412 22.2166 0.3100 22.2166 4.7135
No log 4.4043 414 22.1363 0.4016 22.1363 4.7049
No log 4.4255 416 23.3659 0.4322 23.3659 4.8338
No log 4.4468 418 21.8376 0.4138 21.8376 4.6731
No log 4.4681 420 21.1465 0.3830 21.1465 4.5985
No log 4.4894 422 21.4481 0.3870 21.4481 4.6312
No log 4.5106 424 21.0600 0.4076 21.0600 4.5891
No log 4.5319 426 20.4948 0.4746 20.4948 4.5271
No log 4.5532 428 20.4109 0.4783 20.4109 4.5178
No log 4.5745 430 20.3865 0.4542 20.3865 4.5151
No log 4.5957 432 20.4550 0.4392 20.4550 4.5227
No log 4.6170 434 20.0917 0.4725 20.0917 4.4824
No log 4.6383 436 20.4285 0.5308 20.4285 4.5198
No log 4.6596 438 19.9617 0.5149 19.9617 4.4679
No log 4.6809 440 19.6884 0.4989 19.6884 4.4372
No log 4.7021 442 20.1002 0.4180 20.1002 4.4833
No log 4.7234 444 19.8960 0.4336 19.8960 4.4605
No log 4.7447 446 19.5800 0.4461 19.5800 4.4249
No log 4.7660 448 19.9628 0.3993 19.9628 4.4680
No log 4.7872 450 20.4320 0.3646 20.4320 4.5202
No log 4.8085 452 20.1736 0.3824 20.1736 4.4915
No log 4.8298 454 19.3128 0.4485 19.3128 4.3946
No log 4.8511 456 18.9459 0.5013 18.9459 4.3527
No log 4.8723 458 18.8516 0.4687 18.8516 4.3418
No log 4.8936 460 18.7200 0.4728 18.7200 4.3267
No log 4.9149 462 18.8251 0.5177 18.8251 4.3388
No log 4.9362 464 20.5530 0.5462 20.5530 4.5335
No log 4.9574 466 19.4966 0.5353 19.4966 4.4155
No log 4.9787 468 18.3969 0.4768 18.3969 4.2892
No log 5.0 470 19.3278 0.3947 19.3278 4.3963
No log 5.0213 472 19.5029 0.3793 19.5029 4.4162
No log 5.0426 474 18.6170 0.4594 18.6170 4.3147
No log 5.0638 476 18.3887 0.5135 18.3887 4.2882
No log 5.0851 478 19.3707 0.5482 19.3707 4.4012
No log 5.1064 480 19.6703 0.5478 19.6703 4.4351
No log 5.1277 482 20.4654 0.5424 20.4654 4.5239
No log 5.1489 484 18.1189 0.5177 18.1189 4.2566
No log 5.1702 486 18.3242 0.4142 18.3242 4.2807
No log 5.1915 488 18.9063 0.3665 18.9063 4.3481
No log 5.2128 490 18.5556 0.3754 18.5556 4.3076
No log 5.2340 492 18.1038 0.4109 18.1038 4.2549
No log 5.2553 494 17.9074 0.4368 17.9074 4.2317
No log 5.2766 496 17.9988 0.4683 17.9988 4.2425
No log 5.2979 498 18.1203 0.4648 18.1203 4.2568
58.2538 5.3191 500 18.5092 0.4328 18.5092 4.3022
58.2538 5.3404 502 19.4776 0.3763 19.4776 4.4133
58.2538 5.3617 504 20.0370 0.3477 20.0370 4.4763
58.2538 5.3830 506 19.6332 0.3780 19.6332 4.4309
58.2538 5.4043 508 19.0801 0.4216 19.0801 4.3681
58.2538 5.4255 510 18.9834 0.4119 18.9834 4.3570

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_TestTask2_holistic

Finetuned
(4019)
this model