ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k19_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: 1.2373
  • Qwk: 0.5009
  • Mse: 1.2373
  • Rmse: 1.1123

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 0.0217 2 5.4349 -0.0328 5.4349 2.3313
No log 0.0435 4 3.0834 0.0601 3.0834 1.7560
No log 0.0652 6 2.0435 0.0427 2.0435 1.4295
No log 0.0870 8 1.4817 0.1232 1.4817 1.2173
No log 0.1087 10 1.3052 0.2078 1.3052 1.1424
No log 0.1304 12 1.3169 0.1800 1.3169 1.1476
No log 0.1522 14 1.4076 0.1119 1.4076 1.1864
No log 0.1739 16 1.3572 0.0921 1.3572 1.1650
No log 0.1957 18 1.3384 0.1218 1.3384 1.1569
No log 0.2174 20 1.3317 0.1328 1.3317 1.1540
No log 0.2391 22 1.3973 0.2038 1.3973 1.1821
No log 0.2609 24 1.4469 0.2079 1.4469 1.2029
No log 0.2826 26 1.4345 0.1860 1.4345 1.1977
No log 0.3043 28 1.3468 0.1513 1.3468 1.1605
No log 0.3261 30 1.1425 0.3145 1.1425 1.0689
No log 0.3478 32 1.0327 0.2638 1.0327 1.0162
No log 0.3696 34 1.0215 0.2217 1.0215 1.0107
No log 0.3913 36 1.0012 0.2080 1.0012 1.0006
No log 0.4130 38 0.9620 0.2386 0.9620 0.9808
No log 0.4348 40 0.9243 0.3271 0.9243 0.9614
No log 0.4565 42 0.8796 0.3800 0.8796 0.9378
No log 0.4783 44 0.8936 0.3406 0.8936 0.9453
No log 0.5 46 0.9526 0.4334 0.9526 0.9760
No log 0.5217 48 1.1988 0.2427 1.1988 1.0949
No log 0.5435 50 1.2192 0.2802 1.2192 1.1042
No log 0.5652 52 0.9686 0.4890 0.9686 0.9842
No log 0.5870 54 0.9168 0.4814 0.9168 0.9575
No log 0.6087 56 1.1307 0.4447 1.1307 1.0633
No log 0.6304 58 1.0048 0.4857 1.0048 1.0024
No log 0.6522 60 0.8534 0.5572 0.8534 0.9238
No log 0.6739 62 0.7848 0.5851 0.7848 0.8859
No log 0.6957 64 0.9106 0.5355 0.9106 0.9543
No log 0.7174 66 0.8969 0.5474 0.8969 0.9470
No log 0.7391 68 0.7455 0.6318 0.7455 0.8635
No log 0.7609 70 0.7001 0.6726 0.7001 0.8367
No log 0.7826 72 0.6204 0.6567 0.6204 0.7877
No log 0.8043 74 0.6020 0.6561 0.6020 0.7759
No log 0.8261 76 0.6627 0.6283 0.6627 0.8140
No log 0.8478 78 0.8941 0.5795 0.8941 0.9456
No log 0.8696 80 0.9204 0.5988 0.9204 0.9594
No log 0.8913 82 0.7490 0.6319 0.7490 0.8654
No log 0.9130 84 0.8222 0.6027 0.8222 0.9068
No log 0.9348 86 0.7203 0.6409 0.7203 0.8487
No log 0.9565 88 0.6856 0.6924 0.6856 0.8280
No log 0.9783 90 0.7433 0.6346 0.7433 0.8621
No log 1.0 92 0.7919 0.6159 0.7919 0.8899
No log 1.0217 94 0.7131 0.6821 0.7131 0.8444
No log 1.0435 96 0.6790 0.6965 0.6790 0.8240
No log 1.0652 98 0.6316 0.6986 0.6316 0.7947
No log 1.0870 100 0.6142 0.7159 0.6142 0.7837
No log 1.1087 102 0.7440 0.6598 0.7440 0.8626
No log 1.1304 104 0.8350 0.6553 0.8350 0.9138
No log 1.1522 106 0.8318 0.6454 0.8318 0.9120
No log 1.1739 108 0.7696 0.6339 0.7696 0.8773
No log 1.1957 110 0.6641 0.6772 0.6641 0.8149
No log 1.2174 112 0.6779 0.6664 0.6779 0.8233
No log 1.2391 114 0.7501 0.6579 0.7501 0.8661
No log 1.2609 116 0.7228 0.6854 0.7228 0.8502
No log 1.2826 118 0.8090 0.6368 0.8090 0.8995
No log 1.3043 120 0.9336 0.5932 0.9336 0.9663
No log 1.3261 122 0.7274 0.6675 0.7274 0.8529
No log 1.3478 124 0.6470 0.6957 0.6470 0.8044
No log 1.3696 126 0.6383 0.6855 0.6383 0.7989
No log 1.3913 128 0.6708 0.6972 0.6708 0.8190
No log 1.4130 130 0.9643 0.5860 0.9643 0.9820
No log 1.4348 132 1.2423 0.4704 1.2423 1.1146
No log 1.4565 134 1.4348 0.4111 1.4348 1.1978
No log 1.4783 136 1.2580 0.4453 1.2580 1.1216
No log 1.5 138 0.8567 0.6046 0.8567 0.9256
No log 1.5217 140 0.6599 0.6964 0.6599 0.8123
No log 1.5435 142 0.7733 0.6626 0.7733 0.8794
No log 1.5652 144 0.7531 0.6626 0.7531 0.8678
No log 1.5870 146 0.6472 0.6930 0.6472 0.8045
No log 1.6087 148 0.7613 0.6441 0.7613 0.8726
No log 1.6304 150 0.9106 0.5869 0.9106 0.9543
No log 1.6522 152 0.9059 0.5869 0.9059 0.9518
No log 1.6739 154 0.7712 0.6330 0.7711 0.8782
No log 1.6957 156 0.7137 0.6675 0.7137 0.8448
No log 1.7174 158 0.6752 0.6803 0.6752 0.8217
No log 1.7391 160 0.7267 0.6483 0.7267 0.8524
No log 1.7609 162 0.8621 0.6236 0.8621 0.9285
No log 1.7826 164 1.0972 0.5112 1.0972 1.0475
No log 1.8043 166 1.2649 0.5043 1.2649 1.1247
No log 1.8261 168 1.1192 0.5265 1.1192 1.0579
No log 1.8478 170 0.8188 0.6230 0.8188 0.9049
No log 1.8696 172 0.6491 0.7072 0.6491 0.8056
No log 1.8913 174 0.6414 0.6699 0.6414 0.8009
No log 1.9130 176 0.6652 0.6632 0.6652 0.8156
No log 1.9348 178 0.7587 0.6543 0.7587 0.8710
No log 1.9565 180 0.8626 0.6031 0.8626 0.9288
No log 1.9783 182 0.8770 0.5814 0.8770 0.9365
No log 2.0 184 0.7691 0.6340 0.7691 0.8770
No log 2.0217 186 0.7162 0.6954 0.7162 0.8463
No log 2.0435 188 0.7059 0.7169 0.7059 0.8402
No log 2.0652 190 0.7477 0.6366 0.7477 0.8647
No log 2.0870 192 0.8957 0.5742 0.8957 0.9464
No log 2.1087 194 1.1069 0.5272 1.1069 1.0521
No log 2.1304 196 1.1707 0.4853 1.1707 1.0820
No log 2.1522 198 1.1140 0.5052 1.1140 1.0555
No log 2.1739 200 1.0591 0.5297 1.0591 1.0291
No log 2.1957 202 1.0944 0.5213 1.0944 1.0461
No log 2.2174 204 1.1549 0.5057 1.1549 1.0747
No log 2.2391 206 1.1462 0.5022 1.1462 1.0706
No log 2.2609 208 1.1176 0.5016 1.1176 1.0571
No log 2.2826 210 0.9697 0.5935 0.9697 0.9848
No log 2.3043 212 0.8978 0.5856 0.8978 0.9475
No log 2.3261 214 0.8968 0.5856 0.8968 0.9470
No log 2.3478 216 0.9610 0.5861 0.9610 0.9803
No log 2.3696 218 0.9713 0.6076 0.9713 0.9855
No log 2.3913 220 1.1673 0.5327 1.1673 1.0804
No log 2.4130 222 1.3520 0.4774 1.3520 1.1628
No log 2.4348 224 1.2968 0.4858 1.2968 1.1388
No log 2.4565 226 1.0158 0.5896 1.0158 1.0079
No log 2.4783 228 0.7831 0.6177 0.7831 0.8849
No log 2.5 230 0.7375 0.6420 0.7375 0.8588
No log 2.5217 232 0.7949 0.6030 0.7949 0.8916
No log 2.5435 234 0.9461 0.5900 0.9461 0.9727
No log 2.5652 236 1.0069 0.5884 1.0069 1.0034
No log 2.5870 238 0.9296 0.5884 0.9296 0.9642
No log 2.6087 240 0.7076 0.6229 0.7076 0.8412
No log 2.6304 242 0.6529 0.6747 0.6529 0.8080
No log 2.6522 244 0.6551 0.6545 0.6551 0.8094
No log 2.6739 246 0.7671 0.6200 0.7671 0.8759
No log 2.6957 248 1.0365 0.5965 1.0365 1.0181
No log 2.7174 250 1.1231 0.5213 1.1231 1.0598
No log 2.7391 252 0.9925 0.5915 0.9925 0.9963
No log 2.7609 254 0.8538 0.6301 0.8538 0.9240
No log 2.7826 256 0.7258 0.6101 0.7258 0.8519
No log 2.8043 258 0.6951 0.6751 0.6951 0.8337
No log 2.8261 260 0.6683 0.6752 0.6683 0.8175
No log 2.8478 262 0.6866 0.6654 0.6866 0.8286
No log 2.8696 264 0.8057 0.6193 0.8057 0.8976
No log 2.8913 266 0.9429 0.6179 0.9429 0.9710
No log 2.9130 268 0.8453 0.6058 0.8453 0.9194
No log 2.9348 270 0.6659 0.6927 0.6659 0.8160
No log 2.9565 272 0.5817 0.7051 0.5817 0.7627
No log 2.9783 274 0.5809 0.7258 0.5809 0.7622
No log 3.0 276 0.6721 0.6655 0.6721 0.8198
No log 3.0217 278 0.9002 0.6605 0.9002 0.9488
No log 3.0435 280 0.9243 0.6578 0.9243 0.9614
No log 3.0652 282 0.8548 0.6559 0.8548 0.9246
No log 3.0870 284 0.7423 0.6890 0.7423 0.8616
No log 3.1087 286 0.6323 0.7036 0.6323 0.7951
No log 3.1304 288 0.6231 0.7203 0.6231 0.7894
No log 3.1522 290 0.6595 0.6714 0.6595 0.8121
No log 3.1739 292 0.8477 0.6258 0.8477 0.9207
No log 3.1957 294 1.1609 0.5686 1.1609 1.0775
No log 3.2174 296 1.2180 0.5242 1.2180 1.1037
No log 3.2391 298 1.0414 0.5971 1.0414 1.0205
No log 3.2609 300 0.8067 0.6092 0.8067 0.8982
No log 3.2826 302 0.6892 0.6050 0.6892 0.8302
No log 3.3043 304 0.6826 0.6241 0.6826 0.8262
No log 3.3261 306 0.7247 0.5955 0.7247 0.8513
No log 3.3478 308 0.8261 0.6200 0.8261 0.9089
No log 3.3696 310 0.9357 0.6109 0.9357 0.9673
No log 3.3913 312 0.9024 0.6140 0.9024 0.9499
No log 3.4130 314 0.7974 0.6318 0.7974 0.8930
No log 3.4348 316 0.7703 0.6265 0.7703 0.8777
No log 3.4565 318 0.8199 0.6204 0.8199 0.9055
No log 3.4783 320 0.9337 0.6030 0.9337 0.9663
No log 3.5 322 0.9660 0.5831 0.9660 0.9828
No log 3.5217 324 0.9251 0.5795 0.9251 0.9618
No log 3.5435 326 0.8827 0.5851 0.8827 0.9395
No log 3.5652 328 0.8177 0.5855 0.8177 0.9043
No log 3.5870 330 0.8183 0.5855 0.8183 0.9046
No log 3.6087 332 0.8772 0.6020 0.8772 0.9366
No log 3.6304 334 1.0638 0.5564 1.0638 1.0314
No log 3.6522 336 1.1190 0.5463 1.1190 1.0578
No log 3.6739 338 1.0502 0.5776 1.0502 1.0248
No log 3.6957 340 1.0263 0.5741 1.0263 1.0131
No log 3.7174 342 0.9389 0.5998 0.9389 0.9690
No log 3.7391 344 0.8336 0.6183 0.8336 0.9130
No log 3.7609 346 0.7794 0.5910 0.7794 0.8829
No log 3.7826 348 0.7724 0.5928 0.7724 0.8789
No log 3.8043 350 0.7355 0.6171 0.7355 0.8576
No log 3.8261 352 0.7736 0.6244 0.7736 0.8795
No log 3.8478 354 0.8690 0.6187 0.8690 0.9322
No log 3.8696 356 0.8693 0.6343 0.8693 0.9324
No log 3.8913 358 0.7792 0.6603 0.7792 0.8827
No log 3.9130 360 0.6898 0.7151 0.6898 0.8305
No log 3.9348 362 0.6768 0.7090 0.6768 0.8226
No log 3.9565 364 0.6777 0.7030 0.6777 0.8232
No log 3.9783 366 0.6897 0.6775 0.6897 0.8305
No log 4.0 368 0.6740 0.6651 0.6740 0.8210
No log 4.0217 370 0.6454 0.6733 0.6454 0.8034
No log 4.0435 372 0.6406 0.6601 0.6406 0.8004
No log 4.0652 374 0.6450 0.6496 0.6450 0.8031
No log 4.0870 376 0.6344 0.6759 0.6344 0.7965
No log 4.1087 378 0.6696 0.6475 0.6696 0.8183
No log 4.1304 380 0.8100 0.6106 0.8100 0.9000
No log 4.1522 382 0.9600 0.5982 0.9600 0.9798
No log 4.1739 384 0.9173 0.5810 0.9173 0.9578
No log 4.1957 386 0.8490 0.6098 0.8490 0.9214
No log 4.2174 388 0.7473 0.6021 0.7473 0.8645
No log 4.2391 390 0.6268 0.6987 0.6268 0.7917
No log 4.2609 392 0.6124 0.7216 0.6124 0.7826
No log 4.2826 394 0.6101 0.7138 0.6101 0.7811
No log 4.3043 396 0.6756 0.6930 0.6756 0.8219
No log 4.3261 398 0.8166 0.6258 0.8166 0.9037
No log 4.3478 400 0.9271 0.6264 0.9271 0.9628
No log 4.3696 402 1.0219 0.6077 1.0219 1.0109
No log 4.3913 404 0.9345 0.6041 0.9345 0.9667
No log 4.4130 406 0.8198 0.6234 0.8198 0.9055
No log 4.4348 408 0.7328 0.6330 0.7328 0.8560
No log 4.4565 410 0.7080 0.6244 0.7080 0.8414
No log 4.4783 412 0.6751 0.6422 0.6751 0.8217
No log 4.5 414 0.6749 0.6489 0.6749 0.8215
No log 4.5217 416 0.6084 0.6959 0.6084 0.7800
No log 4.5435 418 0.5744 0.7292 0.5744 0.7579
No log 4.5652 420 0.5784 0.7300 0.5784 0.7605
No log 4.5870 422 0.5897 0.7316 0.5897 0.7679
No log 4.6087 424 0.5931 0.7283 0.5931 0.7702
No log 4.6304 426 0.6121 0.7128 0.6121 0.7823
No log 4.6522 428 0.6129 0.7015 0.6129 0.7829
No log 4.6739 430 0.6509 0.6768 0.6509 0.8068
No log 4.6957 432 0.7176 0.6239 0.7176 0.8471
No log 4.7174 434 0.7311 0.5941 0.7311 0.8550
No log 4.7391 436 0.6939 0.6382 0.6939 0.8330
No log 4.7609 438 0.6977 0.6117 0.6977 0.8353
No log 4.7826 440 0.8099 0.6145 0.8099 0.8999
No log 4.8043 442 0.8608 0.6375 0.8608 0.9278
No log 4.8261 444 0.7630 0.6695 0.7630 0.8735
No log 4.8478 446 0.7033 0.6817 0.7033 0.8386
No log 4.8696 448 0.6347 0.7182 0.6347 0.7967
No log 4.8913 450 0.6253 0.7076 0.6253 0.7908
No log 4.9130 452 0.6162 0.7125 0.6162 0.7850
No log 4.9348 454 0.6338 0.7015 0.6338 0.7961
No log 4.9565 456 0.6466 0.7055 0.6466 0.8041
No log 4.9783 458 0.7124 0.6772 0.7124 0.8440
No log 5.0 460 0.7202 0.6772 0.7202 0.8487
No log 5.0217 462 0.7049 0.6772 0.7049 0.8396
No log 5.0435 464 0.6616 0.6781 0.6616 0.8134
No log 5.0652 466 0.6397 0.6933 0.6397 0.7998
No log 5.0870 468 0.6746 0.6802 0.6746 0.8213
No log 5.1087 470 0.6811 0.6753 0.6811 0.8253
No log 5.1304 472 0.6710 0.6753 0.6710 0.8192
No log 5.1522 474 0.6882 0.6714 0.6882 0.8296
No log 5.1739 476 0.6948 0.6836 0.6948 0.8336
No log 5.1957 478 0.6462 0.7139 0.6462 0.8039
No log 5.2174 480 0.6385 0.7209 0.6385 0.7990
No log 5.2391 482 0.6081 0.7500 0.6081 0.7798
No log 5.2609 484 0.6439 0.7262 0.6439 0.8025
No log 5.2826 486 0.7150 0.7279 0.7150 0.8456
No log 5.3043 488 0.7637 0.6897 0.7637 0.8739
No log 5.3261 490 0.8184 0.6402 0.8184 0.9046
No log 5.3478 492 0.8171 0.6339 0.8171 0.9039
No log 5.3696 494 0.7886 0.6356 0.7886 0.8880
No log 5.3913 496 0.7497 0.6774 0.7497 0.8659
No log 5.4130 498 0.6904 0.7217 0.6904 0.8309
0.4306 5.4348 500 0.7403 0.7250 0.7403 0.8604
0.4306 5.4565 502 0.9276 0.6661 0.9276 0.9631
0.4306 5.4783 504 1.2376 0.6052 1.2376 1.1125
0.4306 5.5 506 1.4278 0.5539 1.4278 1.1949
0.4306 5.5217 508 1.3205 0.5121 1.3205 1.1491
0.4306 5.5435 510 1.2373 0.5009 1.2373 1.1123

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_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k19_task1_organization

Finetuned
(4040)
this model