MayBashendy's picture
End of training
03a941c verified
metadata
library_name: transformers
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask7_holistic
    results: []

Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask7_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: 19.8482
  • Qwk: 0.5185
  • Mse: 19.8482
  • Rmse: 4.4551

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 0.0202 2 313.6096 -0.0014 313.6096 17.7090
No log 0.0404 4 303.3013 0.0050 303.3013 17.4155
No log 0.0606 6 287.3861 0.0060 287.3860 16.9525
No log 0.0808 8 262.5059 0.0068 262.5059 16.2020
No log 0.1010 10 248.7620 0.0016 248.7621 15.7722
No log 0.1212 12 235.4353 0.0089 235.4353 15.3439
No log 0.1414 14 232.2507 0.0106 232.2507 15.2398
No log 0.1616 16 216.5373 0.0051 216.5373 14.7152
No log 0.1818 18 203.2328 0.0150 203.2328 14.2560
No log 0.2020 20 195.4419 0.0072 195.4419 13.9801
No log 0.2222 22 190.0526 0.0051 190.0526 13.7860
No log 0.2424 24 180.6351 0.0114 180.6351 13.4401
No log 0.2626 26 170.7146 0.0051 170.7147 13.0658
No log 0.2828 28 164.8426 0.0031 164.8426 12.8391
No log 0.3030 30 164.3818 0.0051 164.3818 12.8211
No log 0.3232 32 155.4438 0.0188 155.4438 12.4677
No log 0.3434 34 150.0850 0.0063 150.0850 12.2509
No log 0.3636 36 147.7723 0.0064 147.7723 12.1562
No log 0.3838 38 145.6931 0.0057 145.6931 12.0703
No log 0.4040 40 139.4903 0.0007 139.4903 11.8106
No log 0.4242 42 136.3576 0.0007 136.3575 11.6772
No log 0.4444 44 135.1704 0.0098 135.1704 11.6263
No log 0.4646 46 132.9338 0.0138 132.9338 11.5297
No log 0.4848 48 127.6507 0.0047 127.6507 11.2983
No log 0.5051 50 125.1254 0.0040 125.1254 11.1859
No log 0.5253 52 123.6479 0.0039 123.6480 11.1197
No log 0.5455 54 121.6862 0.0031 121.6862 11.0311
No log 0.5657 56 117.6784 0.0 117.6784 10.8480
No log 0.5859 58 116.0690 0.0043 116.0690 10.7735
No log 0.6061 60 113.6829 0.0180 113.6828 10.6622
No log 0.6263 62 111.3398 0.0076 111.3398 10.5518
No log 0.6465 64 109.2005 0.0047 109.2005 10.4499
No log 0.6667 66 107.7348 0.0036 107.7348 10.3795
No log 0.6869 68 108.6367 0.0060 108.6367 10.4229
No log 0.7071 70 103.2487 0.0 103.2487 10.1611
No log 0.7273 72 100.9237 0.0 100.9237 10.0461
No log 0.7475 74 100.5813 0.0 100.5813 10.0290
No log 0.7677 76 98.3592 0.0019 98.3592 9.9176
No log 0.7879 78 95.9004 0.0115 95.9004 9.7929
No log 0.8081 80 94.0087 0.0055 94.0087 9.6958
No log 0.8283 82 92.7210 0.0055 92.7210 9.6292
No log 0.8485 84 90.4730 0.0 90.4730 9.5117
No log 0.8687 86 89.9171 0.0 89.9171 9.4825
No log 0.8889 88 88.2410 0.0 88.2410 9.3937
No log 0.9091 90 86.7016 0.0 86.7016 9.3114
No log 0.9293 92 85.4934 0.0 85.4934 9.2463
No log 0.9495 94 85.5961 0.0 85.5961 9.2518
No log 0.9697 96 83.4744 0.0 83.4744 9.1364
No log 0.9899 98 82.7393 -0.0016 82.7393 9.0961
No log 1.0101 100 80.9662 0.0150 80.9662 8.9981
No log 1.0303 102 80.8035 0.0177 80.8035 8.9891
No log 1.0505 104 79.4126 0.0097 79.4126 8.9114
No log 1.0707 106 78.2397 0.0015 78.2397 8.8453
No log 1.0909 108 77.0818 0.0013 77.0818 8.7796
No log 1.1111 110 77.4486 0.0053 77.4486 8.8005
No log 1.1313 112 76.8616 0.0053 76.8616 8.7671
No log 1.1515 114 74.4138 0.0 74.4138 8.6263
No log 1.1717 116 73.6612 0.0 73.6612 8.5826
No log 1.1919 118 72.5666 0.0 72.5665 8.5186
No log 1.2121 120 72.2171 0.0 72.2171 8.4981
No log 1.2323 122 70.7458 0.0 70.7458 8.4111
No log 1.2525 124 69.9484 0.0 69.9484 8.3635
No log 1.2727 126 69.0810 0.0 69.0810 8.3115
No log 1.2929 128 68.2466 0.0367 68.2466 8.2612
No log 1.3131 130 67.7117 0.0266 67.7117 8.2287
No log 1.3333 132 66.7545 0.0101 66.7545 8.1703
No log 1.3535 134 65.9703 0.0046 65.9703 8.1222
No log 1.3737 136 65.2437 0.0046 65.2437 8.0774
No log 1.3939 138 65.0233 0.0016 65.0233 8.0637
No log 1.4141 140 64.4882 0.0016 64.4882 8.0305
No log 1.4343 142 63.1718 0.0 63.1718 7.9481
No log 1.4545 144 63.1882 0.0 63.1882 7.9491
No log 1.4747 146 62.1410 0.0 62.1410 7.8830
No log 1.4949 148 62.1609 0.0 62.1609 7.8842
No log 1.5152 150 61.7181 0.0 61.7181 7.8561
No log 1.5354 152 60.4788 0.0 60.4788 7.7768
No log 1.5556 154 60.0267 0.0 60.0267 7.7477
No log 1.5758 156 59.4185 0.0 59.4185 7.7083
No log 1.5960 158 59.4573 0.0 59.4573 7.7109
No log 1.6162 160 58.5096 0.0 58.5096 7.6492
No log 1.6364 162 57.8821 0.0 57.8821 7.6080
No log 1.6566 164 57.3682 0.0 57.3682 7.5742
No log 1.6768 166 57.0274 0.0127 57.0274 7.5516
No log 1.6970 168 56.5082 0.0291 56.5082 7.5172
No log 1.7172 170 56.0240 0.0194 56.0240 7.4849
No log 1.7374 172 55.4895 0.0076 55.4895 7.4491
No log 1.7576 174 55.0521 0.0076 55.0521 7.4197
No log 1.7778 176 54.6253 0.0076 54.6253 7.3909
No log 1.7980 178 54.7938 0.0095 54.7938 7.4023
No log 1.8182 180 54.1072 0.0055 54.1072 7.3558
No log 1.8384 182 53.3115 0.0 53.3115 7.3015
No log 1.8586 184 53.0090 0.0 53.0090 7.2807
No log 1.8788 186 52.4051 0.0 52.4051 7.2391
No log 1.8990 188 52.2213 0.0 52.2213 7.2264
No log 1.9192 190 51.7862 0.0 51.7862 7.1963
No log 1.9394 192 51.1557 0.0 51.1557 7.1523
No log 1.9596 194 51.0565 0.0 51.0565 7.1454
No log 1.9798 196 50.3683 0.0 50.3683 7.0971
No log 2.0 198 50.7586 0.0 50.7586 7.1245
No log 2.0202 200 50.1009 0.0 50.1009 7.0782
No log 2.0404 202 49.0958 0.0 49.0958 7.0068
No log 2.0606 204 48.6622 0.0 48.6622 6.9758
No log 2.0808 206 48.1149 0.0 48.1149 6.9365
No log 2.1010 208 47.6448 0.0 47.6448 6.9025
No log 2.1212 210 47.1662 0.0619 47.1662 6.8678
No log 2.1414 212 46.8140 0.0400 46.8140 6.8421
No log 2.1616 214 46.4828 0.0330 46.4828 6.8178
No log 2.1818 216 46.1059 0.0267 46.1059 6.7901
No log 2.2020 218 45.7524 0.0475 45.7524 6.7641
No log 2.2222 220 45.5347 0.0660 45.5347 6.7479
No log 2.2424 222 46.2435 0.1036 46.2435 6.8003
No log 2.2626 224 44.5269 0.1038 44.5269 6.6728
No log 2.2828 226 44.1864 0.0620 44.1864 6.6473
No log 2.3030 228 43.6927 0.0785 43.6927 6.6100
No log 2.3232 230 43.1780 0.0951 43.1780 6.5710
No log 2.3434 232 42.8442 0.0987 42.8442 6.5455
No log 2.3636 234 42.4852 0.1054 42.4852 6.5181
No log 2.3838 236 42.0698 0.1133 42.0698 6.4861
No log 2.4040 238 41.6548 0.1301 41.6548 6.4541
No log 2.4242 240 41.7304 0.1905 41.7304 6.4599
No log 2.4444 242 41.4197 0.2006 41.4197 6.4358
No log 2.4646 244 40.9641 0.1905 40.9641 6.4003
No log 2.4848 246 40.6662 0.1416 40.6662 6.3770
No log 2.5051 248 40.4449 0.1083 40.4449 6.3596
No log 2.5253 250 40.1699 0.1012 40.1699 6.3380
No log 2.5455 252 40.4848 0.1525 40.4848 6.3628
No log 2.5657 254 40.0965 0.1780 40.0965 6.3322
No log 2.5859 256 39.2421 0.1680 39.2421 6.2644
No log 2.6061 258 38.9448 0.1681 38.9448 6.2406
No log 2.6263 260 39.5211 0.2269 39.5211 6.2866
No log 2.6465 262 43.0647 0.2717 43.0647 6.5624
No log 2.6667 264 43.3970 0.2700 43.3970 6.5876
No log 2.6869 266 38.5528 0.2003 38.5528 6.2091
No log 2.7071 268 37.9256 0.1531 37.9256 6.1584
No log 2.7273 270 37.5868 0.1912 37.5868 6.1308
No log 2.7475 272 37.4952 0.1826 37.4952 6.1233
No log 2.7677 274 37.3202 0.1730 37.3202 6.1090
No log 2.7879 276 37.1997 0.2283 37.1997 6.0992
No log 2.8081 278 37.3151 0.2594 37.3151 6.1086
No log 2.8283 280 36.7898 0.2675 36.7898 6.0655
No log 2.8485 282 36.2162 0.2148 36.2162 6.0180
No log 2.8687 284 36.1519 0.2140 36.1519 6.0126
No log 2.8889 286 35.9905 0.2052 35.9905 5.9992
No log 2.9091 288 35.6044 0.2403 35.6044 5.9669
No log 2.9293 290 35.6877 0.2763 35.6877 5.9739
No log 2.9495 292 35.3662 0.2580 35.3662 5.9470
No log 2.9697 294 35.1502 0.1725 35.1502 5.9288
No log 2.9899 296 35.3864 0.1154 35.3864 5.9486
No log 3.0101 298 35.3901 0.0969 35.3901 5.9490
No log 3.0303 300 35.0459 0.1014 35.0459 5.9200
No log 3.0505 302 34.8086 0.1041 34.8086 5.8999
No log 3.0707 304 34.4878 0.1083 34.4878 5.8726
No log 3.0909 306 34.1211 0.1247 34.1211 5.8413
No log 3.1111 308 33.5569 0.1869 33.5569 5.7928
No log 3.1313 310 33.3186 0.2390 33.3186 5.7722
No log 3.1515 312 33.7149 0.3026 33.7149 5.8065
No log 3.1717 314 34.3335 0.3314 34.3335 5.8595
No log 3.1919 316 32.5910 0.2868 32.5910 5.7088
No log 3.2121 318 32.5891 0.2402 32.5891 5.7087
No log 3.2323 320 33.7934 0.1687 33.7934 5.8132
No log 3.2525 322 32.2790 0.1852 32.2790 5.6815
No log 3.2727 324 31.4869 0.2278 31.4869 5.6113
No log 3.2929 326 32.9224 0.2968 32.9224 5.7378
No log 3.3131 328 32.2501 0.2873 32.2501 5.6789
No log 3.3333 330 31.0698 0.2586 31.0698 5.5740
No log 3.3535 332 31.1886 0.1982 31.1886 5.5847
No log 3.3737 334 31.5733 0.1663 31.5733 5.6190
No log 3.3939 336 30.4100 0.3279 30.4100 5.5145
No log 3.4141 338 30.4516 0.3782 30.4516 5.5183
No log 3.4343 340 29.9108 0.3435 29.9108 5.4691
No log 3.4545 342 30.2912 0.2451 30.2912 5.5037
No log 3.4747 344 30.3551 0.2292 30.3551 5.5095
No log 3.4949 346 29.6730 0.2985 29.6730 5.4473
No log 3.5152 348 29.5346 0.3499 29.5346 5.4346
No log 3.5354 350 29.4710 0.3295 29.4710 5.4287
No log 3.5556 352 29.5791 0.2903 29.5791 5.4387
No log 3.5758 354 29.4683 0.2953 29.4683 5.4285
No log 3.5960 356 29.3370 0.3771 29.3370 5.4164
No log 3.6162 358 31.0564 0.4272 31.0564 5.5728
No log 3.6364 360 29.2179 0.4027 29.2179 5.4054
No log 3.6566 362 28.4184 0.3322 28.4184 5.3309
No log 3.6768 364 29.6017 0.2297 29.6017 5.4407
No log 3.6970 366 29.3444 0.2208 29.3444 5.4170
No log 3.7172 368 28.7767 0.2007 28.7767 5.3644
No log 3.7374 370 27.9020 0.2760 27.9020 5.2822
No log 3.7576 372 28.0036 0.3425 28.0036 5.2918
No log 3.7778 374 27.8043 0.3536 27.8043 5.2730
No log 3.7980 376 27.2479 0.2683 27.2479 5.2200
No log 3.8182 378 27.1392 0.2634 27.1392 5.2095
No log 3.8384 380 27.0030 0.2629 27.0030 5.1964
No log 3.8586 382 26.8354 0.2715 26.8354 5.1803
No log 3.8788 384 26.3804 0.2985 26.3804 5.1362
No log 3.8990 386 26.3306 0.3793 26.3306 5.1313
No log 3.9192 388 26.1103 0.3699 26.1103 5.1098
No log 3.9394 390 26.1086 0.3247 26.1086 5.1097
No log 3.9596 392 26.0750 0.3256 26.0750 5.1064
No log 3.9798 394 25.9473 0.3406 25.9473 5.0939
No log 4.0 396 25.9115 0.3329 25.9115 5.0903
No log 4.0202 398 25.9785 0.3114 25.9785 5.0969
No log 4.0404 400 26.1388 0.2832 26.1388 5.1126
No log 4.0606 402 26.5899 0.2362 26.5899 5.1565
No log 4.0808 404 26.2992 0.2459 26.2992 5.1283
No log 4.1010 406 25.3586 0.3266 25.3586 5.0357
No log 4.1212 408 25.4218 0.3801 25.4218 5.0420
No log 4.1414 410 25.2046 0.4427 25.2046 5.0204
No log 4.1616 412 24.7695 0.4298 24.7695 4.9769
No log 4.1818 414 25.1530 0.3501 25.1530 5.0153
No log 4.2020 416 25.1526 0.3363 25.1526 5.0152
No log 4.2222 418 24.5258 0.4247 24.5258 4.9524
No log 4.2424 420 24.7982 0.4413 24.7982 4.9798
No log 4.2626 422 24.6345 0.4477 24.6345 4.9633
No log 4.2828 424 23.9895 0.4171 23.9895 4.8979
No log 4.3030 426 23.9652 0.4023 23.9652 4.8954
No log 4.3232 428 24.1749 0.3729 24.1749 4.9168
No log 4.3434 430 24.6210 0.3337 24.6210 4.9620
No log 4.3636 432 24.9426 0.2913 24.9426 4.9943
No log 4.3838 434 24.3046 0.3314 24.3046 4.9300
No log 4.4040 436 23.5075 0.3943 23.5075 4.8485
No log 4.4242 438 23.7393 0.3552 23.7393 4.8723
No log 4.4444 440 23.7689 0.3435 23.7689 4.8753
No log 4.4646 442 23.1292 0.4221 23.1292 4.8093
No log 4.4848 444 23.5685 0.4775 23.5685 4.8547
No log 4.5051 446 23.0964 0.4618 23.0963 4.8059
No log 4.5253 448 22.8020 0.4029 22.8020 4.7751
No log 4.5455 450 22.6749 0.4006 22.6749 4.7618
No log 4.5657 452 22.3928 0.4420 22.3928 4.7321
No log 4.5859 454 22.3228 0.4457 22.3228 4.7247
No log 4.6061 456 22.3472 0.4040 22.3472 4.7273
No log 4.6263 458 23.2466 0.3215 23.2466 4.8215
No log 4.6465 460 23.9401 0.2725 23.9401 4.8929
No log 4.6667 462 23.6667 0.2744 23.6667 4.8648
No log 4.6869 464 21.9051 0.3972 21.9051 4.6803
No log 4.7071 466 21.8483 0.4459 21.8483 4.6742
No log 4.7273 468 21.7361 0.4455 21.7361 4.6622
No log 4.7475 470 21.8188 0.3723 21.8188 4.6711
No log 4.7677 472 22.0060 0.3424 22.0060 4.6911
No log 4.7879 474 22.0850 0.3292 22.0850 4.6995
No log 4.8081 476 21.2656 0.4110 21.2656 4.6115
No log 4.8283 478 21.6750 0.4539 21.6750 4.6556
No log 4.8485 480 21.7082 0.4615 21.7082 4.6592
No log 4.8687 482 21.2142 0.3812 21.2142 4.6059
No log 4.8889 484 22.9422 0.2863 22.9422 4.7898
No log 4.9091 486 22.8473 0.2817 22.8473 4.7799
No log 4.9293 488 21.1785 0.3738 21.1785 4.6020
No log 4.9495 490 20.8883 0.3803 20.8883 4.5704
No log 4.9697 492 21.2646 0.4659 21.2646 4.6114
No log 4.9899 494 21.9531 0.4148 21.9531 4.6854
No log 5.0101 496 21.3876 0.4596 21.3876 4.6247
No log 5.0303 498 20.5088 0.5456 20.5088 4.5287
66.0898 5.0505 500 20.9869 0.5733 20.9869 4.5811
66.0898 5.0707 502 20.2372 0.5324 20.2372 4.4986
66.0898 5.0909 504 21.6449 0.4181 21.6449 4.6524
66.0898 5.1111 506 22.0606 0.3813 22.0606 4.6969
66.0898 5.1313 508 21.2345 0.4193 21.2345 4.6081
66.0898 5.1515 510 19.8482 0.5185 19.8482 4.4551

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1