ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run3_AugV5_k13_task2_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: 1.1789
  • Qwk: 0.2627
  • Mse: 1.1789
  • Rmse: 1.0858

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 0.0312 2 4.5174 0.0010 4.5174 2.1254
No log 0.0625 4 2.5808 0.0202 2.5808 1.6065
No log 0.0938 6 2.4453 -0.0893 2.4453 1.5637
No log 0.125 8 2.4382 -0.1024 2.4382 1.5615
No log 0.1562 10 1.8664 0.0468 1.8664 1.3662
No log 0.1875 12 1.8688 0.0211 1.8688 1.3671
No log 0.2188 14 1.8925 -0.0102 1.8925 1.3757
No log 0.25 16 2.3204 0.0360 2.3204 1.5233
No log 0.2812 18 2.1366 0.0715 2.1366 1.4617
No log 0.3125 20 1.5691 0.1309 1.5691 1.2526
No log 0.3438 22 1.3149 0.0485 1.3149 1.1467
No log 0.375 24 1.2068 0.1423 1.2068 1.0986
No log 0.4062 26 1.4255 0.1339 1.4255 1.1939
No log 0.4375 28 1.5172 0.1992 1.5172 1.2318
No log 0.4688 30 1.5778 0.2037 1.5778 1.2561
No log 0.5 32 1.3512 0.3071 1.3512 1.1624
No log 0.5312 34 1.1977 0.2963 1.1977 1.0944
No log 0.5625 36 1.5929 0.2388 1.5929 1.2621
No log 0.5938 38 2.5650 0.0933 2.5650 1.6016
No log 0.625 40 2.3244 0.0987 2.3244 1.5246
No log 0.6562 42 1.5376 0.2679 1.5376 1.2400
No log 0.6875 44 1.2580 0.3133 1.2580 1.1216
No log 0.7188 46 1.2289 0.2851 1.2289 1.1085
No log 0.75 48 1.3845 0.2117 1.3845 1.1766
No log 0.7812 50 1.4811 0.2723 1.4811 1.2170
No log 0.8125 52 1.7197 0.2266 1.7197 1.3114
No log 0.8438 54 1.9117 0.2032 1.9117 1.3826
No log 0.875 56 1.8381 0.2032 1.8381 1.3558
No log 0.9062 58 1.6027 0.3139 1.6027 1.2660
No log 0.9375 60 1.4927 0.3542 1.4927 1.2217
No log 0.9688 62 1.4553 0.3137 1.4553 1.2063
No log 1.0 64 1.3239 0.3611 1.3239 1.1506
No log 1.0312 66 1.1779 0.3074 1.1779 1.0853
No log 1.0625 68 1.2432 0.2940 1.2432 1.1150
No log 1.0938 70 1.1409 0.2984 1.1409 1.0681
No log 1.125 72 1.1018 0.2963 1.1018 1.0497
No log 1.1562 74 1.0742 0.2913 1.0742 1.0364
No log 1.1875 76 1.1438 0.3100 1.1438 1.0695
No log 1.2188 78 1.3974 0.3540 1.3974 1.1821
No log 1.25 80 1.7751 0.2182 1.7751 1.3323
No log 1.2812 82 1.6487 0.2692 1.6487 1.2840
No log 1.3125 84 1.2988 0.3539 1.2988 1.1397
No log 1.3438 86 1.2627 0.3785 1.2627 1.1237
No log 1.375 88 1.5287 0.3126 1.5287 1.2364
No log 1.4062 90 1.7643 0.2050 1.7643 1.3283
No log 1.4375 92 1.9557 0.2058 1.9557 1.3985
No log 1.4688 94 1.6272 0.3105 1.6272 1.2756
No log 1.5 96 1.1030 0.3705 1.1030 1.0502
No log 1.5312 98 1.0025 0.2148 1.0025 1.0013
No log 1.5625 100 1.0039 0.1967 1.0039 1.0020
No log 1.5938 102 1.1078 0.3601 1.1078 1.0525
No log 1.625 104 1.6129 0.2458 1.6129 1.2700
No log 1.6562 106 1.9677 0.2290 1.9677 1.4028
No log 1.6875 108 1.7713 0.2268 1.7713 1.3309
No log 1.7188 110 1.3137 0.3162 1.3137 1.1462
No log 1.75 112 1.0309 0.3169 1.0309 1.0153
No log 1.7812 114 1.0022 0.2778 1.0022 1.0011
No log 1.8125 116 1.0510 0.4015 1.0510 1.0252
No log 1.8438 118 1.1575 0.4186 1.1575 1.0759
No log 1.875 120 1.4431 0.3715 1.4431 1.2013
No log 1.9062 122 1.5552 0.3746 1.5552 1.2471
No log 1.9375 124 1.2680 0.3826 1.2680 1.1261
No log 1.9688 126 1.1200 0.3265 1.1200 1.0583
No log 2.0 128 1.0810 0.3907 1.0810 1.0397
No log 2.0312 130 1.0569 0.3429 1.0569 1.0280
No log 2.0625 132 1.2739 0.3163 1.2739 1.1287
No log 2.0938 134 1.5238 0.3198 1.5238 1.2344
No log 2.125 136 1.3058 0.3096 1.3058 1.1427
No log 2.1562 138 1.3262 0.3513 1.3262 1.1516
No log 2.1875 140 1.3812 0.3313 1.3812 1.1753
No log 2.2188 142 1.3899 0.3414 1.3899 1.1789
No log 2.25 144 1.4545 0.3684 1.4545 1.2060
No log 2.2812 146 1.3138 0.3351 1.3138 1.1462
No log 2.3125 148 1.2792 0.3876 1.2792 1.1310
No log 2.3438 150 1.4291 0.3056 1.4291 1.1955
No log 2.375 152 1.1971 0.3530 1.1971 1.0941
No log 2.4062 154 1.0827 0.4413 1.0827 1.0405
No log 2.4375 156 1.0892 0.4234 1.0892 1.0437
No log 2.4688 158 1.0477 0.3062 1.0477 1.0236
No log 2.5 160 1.2452 0.2515 1.2452 1.1159
No log 2.5312 162 1.3798 0.3121 1.3798 1.1746
No log 2.5625 164 1.2124 0.2788 1.2124 1.1011
No log 2.5938 166 1.1875 0.2771 1.1875 1.0897
No log 2.625 168 1.3769 0.2868 1.3769 1.1734
No log 2.6562 170 1.3047 0.2714 1.3047 1.1422
No log 2.6875 172 1.2435 0.2515 1.2435 1.1151
No log 2.7188 174 1.1235 0.2647 1.1235 1.0600
No log 2.75 176 1.1178 0.2647 1.1178 1.0572
No log 2.7812 178 1.1848 0.1590 1.1848 1.0885
No log 2.8125 180 1.1738 0.2076 1.1738 1.0834
No log 2.8438 182 1.1612 0.3119 1.1612 1.0776
No log 2.875 184 1.2395 0.2568 1.2395 1.1133
No log 2.9062 186 1.2311 0.3086 1.2311 1.1096
No log 2.9375 188 1.1768 0.3210 1.1768 1.0848
No log 2.9688 190 1.1370 0.3151 1.1370 1.0663
No log 3.0 192 1.0773 0.3527 1.0773 1.0379
No log 3.0312 194 1.0752 0.3371 1.0752 1.0369
No log 3.0625 196 1.2542 0.3111 1.2542 1.1199
No log 3.0938 198 1.6402 0.2981 1.6402 1.2807
No log 3.125 200 1.6469 0.2515 1.6469 1.2833
No log 3.1562 202 1.3190 0.3184 1.3190 1.1485
No log 3.1875 204 1.1192 0.2832 1.1192 1.0579
No log 3.2188 206 1.1382 0.3154 1.1382 1.0669
No log 3.25 208 1.3916 0.2873 1.3916 1.1797
No log 3.2812 210 1.6184 0.3087 1.6184 1.2722
No log 3.3125 212 1.4914 0.3108 1.4914 1.2212
No log 3.3438 214 1.3753 0.3159 1.3753 1.1727
No log 3.375 216 1.1522 0.3249 1.1522 1.0734
No log 3.4062 218 1.1402 0.3260 1.1402 1.0678
No log 3.4375 220 1.1547 0.3243 1.1547 1.0746
No log 3.4688 222 1.2606 0.1997 1.2606 1.1227
No log 3.5 224 1.2831 0.2658 1.2831 1.1327
No log 3.5312 226 1.1749 0.2927 1.1749 1.0839
No log 3.5625 228 1.0580 0.2820 1.0580 1.0286
No log 3.5938 230 1.0416 0.3176 1.0416 1.0206
No log 3.625 232 1.0380 0.3293 1.0380 1.0188
No log 3.6562 234 1.0867 0.2438 1.0867 1.0424
No log 3.6875 236 1.1727 0.3260 1.1727 1.0829
No log 3.7188 238 1.0996 0.3074 1.0996 1.0486
No log 3.75 240 1.0173 0.3305 1.0173 1.0086
No log 3.7812 242 1.0058 0.4385 1.0058 1.0029
No log 3.8125 244 0.9969 0.4750 0.9969 0.9984
No log 3.8438 246 1.0886 0.3644 1.0886 1.0433
No log 3.875 248 1.3726 0.4108 1.3726 1.1716
No log 3.9062 250 1.4505 0.4066 1.4505 1.2044
No log 3.9375 252 1.2359 0.3992 1.2359 1.1117
No log 3.9688 254 1.0285 0.2581 1.0285 1.0141
No log 4.0 256 1.0497 0.3219 1.0497 1.0246
No log 4.0312 258 1.0763 0.2838 1.0763 1.0374
No log 4.0625 260 1.0741 0.3318 1.0741 1.0364
No log 4.0938 262 1.0551 0.3304 1.0551 1.0272
No log 4.125 264 1.1761 0.3287 1.1761 1.0845
No log 4.1562 266 1.4675 0.3162 1.4675 1.2114
No log 4.1875 268 1.6497 0.2820 1.6497 1.2844
No log 4.2188 270 1.5589 0.3559 1.5589 1.2485
No log 4.25 272 1.3545 0.3026 1.3545 1.1638
No log 4.2812 274 1.1768 0.3095 1.1768 1.0848
No log 4.3125 276 1.1496 0.2806 1.1496 1.0722
No log 4.3438 278 1.1388 0.2806 1.1388 1.0672
No log 4.375 280 1.2218 0.2688 1.2218 1.1053
No log 4.4062 282 1.3594 0.3493 1.3594 1.1659
No log 4.4375 284 1.3355 0.3192 1.3355 1.1556
No log 4.4688 286 1.2056 0.3354 1.2056 1.0980
No log 4.5 288 1.1540 0.2857 1.1540 1.0743
No log 4.5312 290 1.0923 0.3126 1.0923 1.0451
No log 4.5625 292 1.1084 0.3126 1.1084 1.0528
No log 4.5938 294 1.1924 0.2920 1.1924 1.0920
No log 4.625 296 1.2514 0.3027 1.2514 1.1186
No log 4.6562 298 1.2380 0.2965 1.2380 1.1126
No log 4.6875 300 1.1918 0.2924 1.1918 1.0917
No log 4.7188 302 1.1637 0.2654 1.1637 1.0788
No log 4.75 304 1.1200 0.2968 1.1200 1.0583
No log 4.7812 306 1.1079 0.2795 1.1079 1.0526
No log 4.8125 308 1.1506 0.2796 1.1506 1.0727
No log 4.8438 310 1.2349 0.2727 1.2349 1.1113
No log 4.875 312 1.3206 0.2335 1.3206 1.1492
No log 4.9062 314 1.3826 0.2647 1.3826 1.1758
No log 4.9375 316 1.3214 0.2335 1.3214 1.1495
No log 4.9688 318 1.2982 0.2040 1.2982 1.1394
No log 5.0 320 1.3279 0.2335 1.3279 1.1523
No log 5.0312 322 1.2504 0.2255 1.2504 1.1182
No log 5.0625 324 1.1485 0.2170 1.1485 1.0717
No log 5.0938 326 1.0928 0.2667 1.0928 1.0454
No log 5.125 328 1.1105 0.2654 1.1105 1.0538
No log 5.1562 330 1.2151 0.3188 1.2151 1.1023
No log 5.1875 332 1.4611 0.3581 1.4611 1.2088
No log 5.2188 334 1.7515 0.2336 1.7515 1.3234
No log 5.25 336 1.7809 0.2395 1.7809 1.3345
No log 5.2812 338 1.5505 0.3621 1.5505 1.2452
No log 5.3125 340 1.2810 0.3118 1.2810 1.1318
No log 5.3438 342 1.2887 0.3169 1.2887 1.1352
No log 5.375 344 1.3762 0.3705 1.3762 1.1731
No log 5.4062 346 1.3364 0.3741 1.3364 1.1560
No log 5.4375 348 1.3344 0.4139 1.3344 1.1552
No log 5.4688 350 1.1819 0.3008 1.1819 1.0872
No log 5.5 352 1.1357 0.3030 1.1357 1.0657
No log 5.5312 354 1.1764 0.3175 1.1764 1.0846
No log 5.5625 356 1.1476 0.2084 1.1476 1.0712
No log 5.5938 358 1.1504 0.2170 1.1504 1.0726
No log 5.625 360 1.1558 0.2259 1.1558 1.0751
No log 5.6562 362 1.1054 0.2299 1.1054 1.0514
No log 5.6875 364 1.0839 0.2943 1.0839 1.0411
No log 5.7188 366 1.1476 0.2920 1.1476 1.0712
No log 5.75 368 1.3993 0.2984 1.3993 1.1829
No log 5.7812 370 1.4416 0.2836 1.4416 1.2006
No log 5.8125 372 1.3467 0.3265 1.3467 1.1605
No log 5.8438 374 1.1390 0.2876 1.1390 1.0672
No log 5.875 376 1.0197 0.3886 1.0197 1.0098
No log 5.9062 378 1.0278 0.4125 1.0278 1.0138
No log 5.9375 380 1.0063 0.4230 1.0063 1.0032
No log 5.9688 382 1.0467 0.3812 1.0467 1.0231
No log 6.0 384 1.1834 0.2797 1.1834 1.0878
No log 6.0312 386 1.2747 0.2674 1.2747 1.1290
No log 6.0625 388 1.2290 0.2574 1.2290 1.1086
No log 6.0938 390 1.1648 0.2876 1.1648 1.0793
No log 6.125 392 1.0950 0.3685 1.0950 1.0464
No log 6.1562 394 1.1080 0.3556 1.1080 1.0526
No log 6.1875 396 1.2002 0.2438 1.2002 1.0955
No log 6.2188 398 1.2279 0.2438 1.2279 1.1081
No log 6.25 400 1.3146 0.2742 1.3146 1.1466
No log 6.2812 402 1.3454 0.2742 1.3454 1.1599
No log 6.3125 404 1.3229 0.2136 1.3229 1.1502
No log 6.3438 406 1.1915 0.2900 1.1915 1.0916
No log 6.375 408 1.1013 0.4088 1.1013 1.0494
No log 6.4062 410 1.0970 0.4088 1.0970 1.0474
No log 6.4375 412 1.1178 0.3812 1.1178 1.0573
No log 6.4688 414 1.1150 0.3506 1.1150 1.0559
No log 6.5 416 1.1187 0.3052 1.1187 1.0577
No log 6.5312 418 1.1684 0.2672 1.1684 1.0809
No log 6.5625 420 1.2457 0.2589 1.2457 1.1161
No log 6.5938 422 1.2127 0.2814 1.2127 1.1012
No log 6.625 424 1.2273 0.2515 1.2273 1.1078
No log 6.6562 426 1.2004 0.2304 1.2004 1.0956
No log 6.6875 428 1.1304 0.3189 1.1304 1.0632
No log 6.7188 430 1.1015 0.2664 1.1015 1.0495
No log 6.75 432 1.1110 0.2302 1.1110 1.0540
No log 6.7812 434 1.1088 0.2572 1.1088 1.0530
No log 6.8125 436 1.1104 0.4014 1.1104 1.0538
No log 6.8438 438 1.1431 0.3074 1.1431 1.0692
No log 6.875 440 1.1828 0.2545 1.1828 1.0876
No log 6.9062 442 1.2624 0.2262 1.2624 1.1235
No log 6.9375 444 1.2155 0.2672 1.2155 1.1025
No log 6.9688 446 1.1264 0.3871 1.1264 1.0613
No log 7.0 448 1.1066 0.3313 1.1066 1.0520
No log 7.0312 450 1.1183 0.3958 1.1183 1.0575
No log 7.0625 452 1.1241 0.3709 1.1241 1.0602
No log 7.0938 454 1.2861 0.3067 1.2861 1.1341
No log 7.125 456 1.4129 0.3020 1.4129 1.1886
No log 7.1562 458 1.3222 0.2767 1.3222 1.1499
No log 7.1875 460 1.2107 0.2797 1.2107 1.1003
No log 7.2188 462 1.1392 0.3031 1.1392 1.0674
No log 7.25 464 1.1119 0.3221 1.1119 1.0544
No log 7.2812 466 1.1177 0.2906 1.1177 1.0572
No log 7.3125 468 1.1675 0.2920 1.1675 1.0805
No log 7.3438 470 1.2711 0.3044 1.2711 1.1274
No log 7.375 472 1.3808 0.2942 1.3808 1.1751
No log 7.4062 474 1.3199 0.3222 1.3199 1.1489
No log 7.4375 476 1.2087 0.2714 1.2087 1.0994
No log 7.4688 478 1.1228 0.2944 1.1228 1.0596
No log 7.5 480 1.1182 0.3313 1.1182 1.0575
No log 7.5312 482 1.1688 0.3050 1.1688 1.0811
No log 7.5625 484 1.3164 0.2965 1.3164 1.1473
No log 7.5938 486 1.4138 0.2476 1.4138 1.1890
No log 7.625 488 1.3249 0.2688 1.3249 1.1511
No log 7.6562 490 1.2512 0.2515 1.2512 1.1186
No log 7.6875 492 1.2477 0.2515 1.2477 1.1170
No log 7.7188 494 1.2352 0.2515 1.2352 1.1114
No log 7.75 496 1.1654 0.2832 1.1654 1.0795
No log 7.7812 498 1.1008 0.3412 1.1008 1.0492
0.3383 7.8125 500 1.0903 0.3412 1.0903 1.0442
0.3383 7.8438 502 1.1006 0.3412 1.1006 1.0491
0.3383 7.875 504 1.1219 0.3321 1.1219 1.0592
0.3383 7.9062 506 1.1240 0.2851 1.1240 1.0602
0.3383 7.9375 508 1.1499 0.2760 1.1499 1.0724
0.3383 7.9688 510 1.1789 0.2627 1.1789 1.0858

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/ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run3_AugV5_k13_task2_organization

Finetuned
(4019)
this model