MayBashendy's picture
Training in progress, step 500
388a1c7 verified
|
raw
history blame
23.8 kB
metadata
library_name: transformers
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: >-
      ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k4_task1_organization
    results: []

ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k4_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: 1.8216
  • Qwk: 0.2734
  • Mse: 1.8216
  • Rmse: 1.3497

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 0.1111 2 7.2120 -0.0107 7.2120 2.6855
No log 0.2222 4 4.3790 0.0433 4.3790 2.0926
No log 0.3333 6 3.0495 0.0970 3.0495 1.7463
No log 0.4444 8 2.5635 0.0730 2.5635 1.6011
No log 0.5556 10 2.8778 -0.1679 2.8778 1.6964
No log 0.6667 12 2.4256 -0.1167 2.4256 1.5574
No log 0.7778 14 2.4517 -0.0976 2.4517 1.5658
No log 0.8889 16 2.6572 -0.0288 2.6572 1.6301
No log 1.0 18 2.3601 0.0571 2.3601 1.5363
No log 1.1111 20 2.1816 0.1429 2.1816 1.4770
No log 1.2222 22 2.2561 0.0 2.2561 1.5020
No log 1.3333 24 2.0987 0.1552 2.0987 1.4487
No log 1.4444 26 1.9379 0.2056 1.9379 1.3921
No log 1.5556 28 1.8651 0.2202 1.8651 1.3657
No log 1.6667 30 1.8004 0.2202 1.8004 1.3418
No log 1.7778 32 1.9475 0.2927 1.9475 1.3955
No log 1.8889 34 1.9496 0.2927 1.9496 1.3963
No log 2.0 36 2.0348 0.25 2.0348 1.4265
No log 2.1111 38 1.8641 0.2000 1.8641 1.3653
No log 2.2222 40 1.6399 0.1346 1.6399 1.2806
No log 2.3333 42 1.6196 0.0777 1.6196 1.2726
No log 2.4444 44 1.6546 0.0777 1.6546 1.2863
No log 2.5556 46 1.8154 0.3448 1.8154 1.3474
No log 2.6667 48 2.3826 0.0972 2.3826 1.5436
No log 2.7778 50 2.7759 0.0 2.7759 1.6661
No log 2.8889 52 2.5084 0.0 2.5084 1.5838
No log 3.0 54 2.2284 0.0552 2.2284 1.4928
No log 3.1111 56 2.1010 0.2406 2.1010 1.4495
No log 3.2222 58 2.0308 0.2903 2.0308 1.4251
No log 3.3333 60 2.0319 0.3740 2.0319 1.4254
No log 3.4444 62 1.9005 0.2807 1.9005 1.3786
No log 3.5556 64 1.7755 0.2783 1.7755 1.3325
No log 3.6667 66 1.8203 0.4 1.8203 1.3492
No log 3.7778 68 1.8399 0.3465 1.8399 1.3564
No log 3.8889 70 1.6294 0.2957 1.6294 1.2765
No log 4.0 72 1.3847 0.2364 1.3847 1.1767
No log 4.1111 74 1.3411 0.2569 1.3411 1.1581
No log 4.2222 76 1.4104 0.2957 1.4104 1.1876
No log 4.3333 78 1.5049 0.3448 1.5049 1.2267
No log 4.4444 80 1.5161 0.3248 1.5161 1.2313
No log 4.5556 82 1.4205 0.2957 1.4205 1.1918
No log 4.6667 84 1.3868 0.2523 1.3868 1.1776
No log 4.7778 86 1.4585 0.2632 1.4585 1.2077
No log 4.8889 88 1.5193 0.3276 1.5193 1.2326
No log 5.0 90 1.5350 0.3390 1.5350 1.2389
No log 5.1111 92 1.3284 0.3966 1.3284 1.1526
No log 5.2222 94 1.3109 0.4724 1.3109 1.1449
No log 5.3333 96 1.3258 0.4769 1.3258 1.1515
No log 5.4444 98 1.2287 0.4762 1.2287 1.1085
No log 5.5556 100 1.2988 0.4567 1.2988 1.1397
No log 5.6667 102 1.2234 0.4677 1.2234 1.1061
No log 5.7778 104 1.1998 0.4878 1.1998 1.0954
No log 5.8889 106 1.1864 0.4706 1.1864 1.0892
No log 6.0 108 1.1963 0.4706 1.1963 1.0938
No log 6.1111 110 1.2430 0.4138 1.2430 1.1149
No log 6.2222 112 1.2475 0.4132 1.2475 1.1169
No log 6.3333 114 1.2466 0.48 1.2466 1.1165
No log 6.4444 116 1.4014 0.4242 1.4014 1.1838
No log 6.5556 118 1.6660 0.3382 1.6660 1.2907
No log 6.6667 120 1.7443 0.3235 1.7443 1.3207
No log 6.7778 122 1.5509 0.4030 1.5509 1.2454
No log 6.8889 124 1.4751 0.3939 1.4751 1.2145
No log 7.0 126 1.4508 0.3939 1.4508 1.2045
No log 7.1111 128 1.5136 0.4296 1.5136 1.2303
No log 7.2222 130 1.6707 0.3824 1.6707 1.2926
No log 7.3333 132 1.6326 0.3704 1.6326 1.2777
No log 7.4444 134 1.5050 0.3969 1.5050 1.2268
No log 7.5556 136 1.4384 0.3721 1.4384 1.1993
No log 7.6667 138 1.5279 0.3824 1.5279 1.2361
No log 7.7778 140 1.6482 0.3824 1.6482 1.2838
No log 7.8889 142 1.7303 0.3188 1.7303 1.3154
No log 8.0 144 1.6590 0.3504 1.6590 1.2880
No log 8.1111 146 1.4836 0.3438 1.4836 1.2180
No log 8.2222 148 1.4363 0.35 1.4363 1.1984
No log 8.3333 150 1.4203 0.3810 1.4203 1.1918
No log 8.4444 152 1.5348 0.3759 1.5348 1.2389
No log 8.5556 154 1.6968 0.3824 1.6968 1.3026
No log 8.6667 156 1.6534 0.3881 1.6534 1.2858
No log 8.7778 158 1.4818 0.3939 1.4818 1.2173
No log 8.8889 160 1.3329 0.4228 1.3329 1.1545
No log 9.0 162 1.3148 0.4480 1.3148 1.1466
No log 9.1111 164 1.3430 0.4 1.3430 1.1589
No log 9.2222 166 1.5220 0.4118 1.5220 1.2337
No log 9.3333 168 1.7257 0.3478 1.7257 1.3137
No log 9.4444 170 1.7547 0.3453 1.7547 1.3247
No log 9.5556 172 1.6000 0.3504 1.6000 1.2649
No log 9.6667 174 1.4376 0.4242 1.4376 1.1990
No log 9.7778 176 1.3756 0.4615 1.3756 1.1729
No log 9.8889 178 1.3936 0.4511 1.3936 1.1805
No log 10.0 180 1.4747 0.3824 1.4747 1.2144
No log 10.1111 182 1.5191 0.3582 1.5191 1.2325
No log 10.2222 184 1.4709 0.4308 1.4709 1.2128
No log 10.3333 186 1.3943 0.4603 1.3943 1.1808
No log 10.4444 188 1.3127 0.4160 1.3127 1.1457
No log 10.5556 190 1.2921 0.4409 1.2921 1.1367
No log 10.6667 192 1.4083 0.4361 1.4083 1.1867
No log 10.7778 194 1.5922 0.3407 1.5922 1.2618
No log 10.8889 196 1.5802 0.3582 1.5802 1.2571
No log 11.0 198 1.4947 0.4427 1.4947 1.2226
No log 11.1111 200 1.4529 0.4427 1.4529 1.2054
No log 11.2222 202 1.4502 0.4154 1.4502 1.2042
No log 11.3333 204 1.4773 0.4154 1.4773 1.2155
No log 11.4444 206 1.6745 0.3704 1.6745 1.2940
No log 11.5556 208 1.8441 0.3043 1.8441 1.3580
No log 11.6667 210 1.7917 0.3429 1.7917 1.3386
No log 11.7778 212 1.5594 0.4361 1.5594 1.2488
No log 11.8889 214 1.4663 0.4275 1.4663 1.2109
No log 12.0 216 1.4636 0.4275 1.4636 1.2098
No log 12.1111 218 1.5501 0.4427 1.5501 1.2450
No log 12.2222 220 1.5728 0.4242 1.5728 1.2541
No log 12.3333 222 1.4575 0.4427 1.4575 1.2073
No log 12.4444 224 1.3914 0.4545 1.3914 1.1796
No log 12.5556 226 1.3865 0.4812 1.3865 1.1775
No log 12.6667 228 1.5882 0.3913 1.5882 1.2602
No log 12.7778 230 1.6451 0.3571 1.6451 1.2826
No log 12.8889 232 1.4741 0.4706 1.4741 1.2141
No log 13.0 234 1.2321 0.5038 1.2321 1.1100
No log 13.1111 236 1.1875 0.4463 1.1875 1.0897
No log 13.2222 238 1.2260 0.4333 1.2260 1.1073
No log 13.3333 240 1.3695 0.4427 1.3695 1.1703
No log 13.4444 242 1.6288 0.3796 1.6288 1.2762
No log 13.5556 244 1.7425 0.3286 1.7425 1.3200
No log 13.6667 246 1.6850 0.3546 1.6850 1.2981
No log 13.7778 248 1.4924 0.4526 1.4924 1.2217
No log 13.8889 250 1.3186 0.4806 1.3186 1.1483
No log 14.0 252 1.2521 0.4567 1.2521 1.1190
No log 14.1111 254 1.2785 0.4724 1.2785 1.1307
No log 14.2222 256 1.4271 0.4511 1.4271 1.1946
No log 14.3333 258 1.6936 0.3497 1.6936 1.3014
No log 14.4444 260 1.8057 0.3239 1.8057 1.3438
No log 14.5556 262 1.7329 0.3239 1.7329 1.3164
No log 14.6667 264 1.5891 0.4088 1.5891 1.2606
No log 14.7778 266 1.5274 0.4308 1.5274 1.2359
No log 14.8889 268 1.4718 0.4127 1.4718 1.2132
No log 15.0 270 1.4708 0.3780 1.4708 1.2127
No log 15.1111 272 1.5092 0.4062 1.5092 1.2285
No log 15.2222 274 1.6503 0.4058 1.6503 1.2846
No log 15.3333 276 1.7871 0.2837 1.7871 1.3368
No log 15.4444 278 1.7279 0.3043 1.7279 1.3145
No log 15.5556 280 1.6094 0.4328 1.6094 1.2686
No log 15.6667 282 1.4877 0.3721 1.4877 1.2197
No log 15.7778 284 1.4500 0.4252 1.4500 1.2042
No log 15.8889 286 1.4913 0.4511 1.4913 1.2212
No log 16.0 288 1.6393 0.3741 1.6393 1.2803
No log 16.1111 290 1.6888 0.3597 1.6888 1.2995
No log 16.2222 292 1.7545 0.3571 1.7545 1.3246
No log 16.3333 294 1.8445 0.2979 1.8445 1.3581
No log 16.4444 296 1.9036 0.2817 1.9036 1.3797
No log 16.5556 298 1.8105 0.3239 1.8105 1.3456
No log 16.6667 300 1.7854 0.2958 1.7854 1.3362
No log 16.7778 302 1.7783 0.3262 1.7783 1.3335
No log 16.8889 304 1.7341 0.3546 1.7341 1.3169
No log 17.0 306 1.7762 0.3286 1.7762 1.3327
No log 17.1111 308 1.9034 0.2817 1.9034 1.3796
No log 17.2222 310 1.9536 0.2553 1.9536 1.3977
No log 17.3333 312 1.9263 0.2553 1.9263 1.3879
No log 17.4444 314 1.7527 0.3165 1.7527 1.3239
No log 17.5556 316 1.6210 0.3200 1.6210 1.2732
No log 17.6667 318 1.5669 0.2564 1.5669 1.2518
No log 17.7778 320 1.5733 0.3415 1.5733 1.2543
No log 17.8889 322 1.6711 0.3158 1.6711 1.2927
No log 18.0 324 1.9137 0.2714 1.9137 1.3834
No log 18.1111 326 1.9895 0.2553 1.9895 1.4105
No log 18.2222 328 1.7658 0.3404 1.7658 1.3288
No log 18.3333 330 1.5348 0.3538 1.5348 1.2389
No log 18.4444 332 1.4588 0.3594 1.4588 1.2078
No log 18.5556 334 1.4965 0.3721 1.4965 1.2233
No log 18.6667 336 1.5372 0.3969 1.5372 1.2398
No log 18.7778 338 1.5446 0.4154 1.5446 1.2428
No log 18.8889 340 1.5172 0.4031 1.5172 1.2318
No log 19.0 342 1.6134 0.3556 1.6134 1.2702
No log 19.1111 344 1.6798 0.3597 1.6798 1.2961
No log 19.2222 346 1.6343 0.3650 1.6343 1.2784
No log 19.3333 348 1.5139 0.4122 1.5139 1.2304
No log 19.4444 350 1.4588 0.4341 1.4588 1.2078
No log 19.5556 352 1.4673 0.4308 1.4673 1.2113
No log 19.6667 354 1.6010 0.3597 1.6010 1.2653
No log 19.7778 356 1.6815 0.3239 1.6815 1.2967
No log 19.8889 358 1.6475 0.3239 1.6475 1.2835
No log 20.0 360 1.5336 0.4328 1.5336 1.2384
No log 20.1111 362 1.4339 0.4651 1.4339 1.1975
No log 20.2222 364 1.4291 0.4651 1.4291 1.1954
No log 20.3333 366 1.4415 0.4615 1.4415 1.2006
No log 20.4444 368 1.5695 0.3597 1.5695 1.2528
No log 20.5556 370 1.6471 0.3597 1.6471 1.2834
No log 20.6667 372 1.6124 0.3597 1.6124 1.2698
No log 20.7778 374 1.6174 0.3597 1.6174 1.2718
No log 20.8889 376 1.6305 0.3478 1.6305 1.2769
No log 21.0 378 1.5597 0.4328 1.5597 1.2489
No log 21.1111 380 1.4677 0.4375 1.4677 1.2115
No log 21.2222 382 1.4165 0.4409 1.4165 1.1902
No log 21.3333 384 1.4078 0.4219 1.4078 1.1865
No log 21.4444 386 1.4337 0.4427 1.4337 1.1974
No log 21.5556 388 1.5386 0.4148 1.5386 1.2404
No log 21.6667 390 1.5519 0.3971 1.5519 1.2457
No log 21.7778 392 1.4956 0.4148 1.4956 1.2229
No log 21.8889 394 1.4863 0.4328 1.4863 1.2191
No log 22.0 396 1.5332 0.3650 1.5332 1.2382
No log 22.1111 398 1.6917 0.3121 1.6917 1.3006
No log 22.2222 400 1.8540 0.2817 1.8540 1.3616
No log 22.3333 402 1.8065 0.2817 1.8065 1.3441
No log 22.4444 404 1.6732 0.3022 1.6732 1.2935
No log 22.5556 406 1.6577 0.2941 1.6577 1.2875
No log 22.6667 408 1.6467 0.3382 1.6467 1.2832
No log 22.7778 410 1.6444 0.3333 1.6444 1.2823
No log 22.8889 412 1.6000 0.3650 1.6000 1.2649
No log 23.0 414 1.4935 0.4242 1.4935 1.2221
No log 23.1111 416 1.5036 0.4328 1.5036 1.2262
No log 23.2222 418 1.6332 0.3309 1.6332 1.2780
No log 23.3333 420 1.7320 0.2857 1.7320 1.3161
No log 23.4444 422 1.8167 0.2657 1.8167 1.3478
No log 23.5556 424 1.7633 0.2302 1.7633 1.3279
No log 23.6667 426 1.6748 0.3382 1.6748 1.2941
No log 23.7778 428 1.5905 0.4154 1.5905 1.2612
No log 23.8889 430 1.5837 0.4154 1.5837 1.2585
No log 24.0 432 1.6418 0.4148 1.6418 1.2813
No log 24.1111 434 1.8162 0.2553 1.8162 1.3477
No log 24.2222 436 1.9180 0.2657 1.9180 1.3849
No log 24.3333 438 1.7874 0.2695 1.7874 1.3369
No log 24.4444 440 1.6517 0.3309 1.6517 1.2852
No log 24.5556 442 1.5518 0.4427 1.5518 1.2457
No log 24.6667 444 1.4727 0.3840 1.4727 1.2135
No log 24.7778 446 1.4710 0.3710 1.4710 1.2128
No log 24.8889 448 1.5572 0.4154 1.5572 1.2479
No log 25.0 450 1.6551 0.3556 1.6551 1.2865
No log 25.1111 452 1.7411 0.2590 1.7411 1.3195
No log 25.2222 454 1.7352 0.2590 1.7352 1.3173
No log 25.3333 456 1.6406 0.3881 1.6406 1.2808
No log 25.4444 458 1.5332 0.3937 1.5332 1.2382
No log 25.5556 460 1.5161 0.3937 1.5161 1.2313
No log 25.6667 462 1.4917 0.3871 1.4917 1.2213
No log 25.7778 464 1.5170 0.3651 1.5170 1.2317
No log 25.8889 466 1.5906 0.3359 1.5906 1.2612
No log 26.0 468 1.6153 0.3359 1.6153 1.2710
No log 26.1111 470 1.5748 0.3876 1.5748 1.2549
No log 26.2222 472 1.5245 0.3651 1.5245 1.2347
No log 26.3333 474 1.4600 0.3802 1.4600 1.2083
No log 26.4444 476 1.4865 0.3810 1.4865 1.2192
No log 26.5556 478 1.6437 0.3478 1.6437 1.2821
No log 26.6667 480 1.7435 0.2695 1.7435 1.3204
No log 26.7778 482 1.6852 0.3309 1.6852 1.2982
No log 26.8889 484 1.5950 0.3731 1.5950 1.2629
No log 27.0 486 1.6245 0.3556 1.6245 1.2746
No log 27.1111 488 1.6273 0.3556 1.6273 1.2756
No log 27.2222 490 1.5781 0.3906 1.5781 1.2562
No log 27.3333 492 1.5299 0.3607 1.5299 1.2369
No log 27.4444 494 1.5557 0.3906 1.5557 1.2473
No log 27.5556 496 1.6141 0.3556 1.6141 1.2705
No log 27.6667 498 1.7174 0.3309 1.7174 1.3105
0.4218 27.7778 500 1.8291 0.3000 1.8291 1.3524
0.4218 27.8889 502 1.7950 0.3000 1.7950 1.3398
0.4218 28.0 504 1.6501 0.3212 1.6501 1.2846
0.4218 28.1111 506 1.5616 0.3876 1.5616 1.2496
0.4218 28.2222 508 1.5771 0.3906 1.5771 1.2558
0.4218 28.3333 510 1.6246 0.3731 1.6246 1.2746
0.4218 28.4444 512 1.6495 0.3556 1.6495 1.2843
0.4218 28.5556 514 1.6700 0.3478 1.6700 1.2923
0.4218 28.6667 516 1.6563 0.3650 1.6563 1.2870
0.4218 28.7778 518 1.6445 0.3913 1.6445 1.2824
0.4218 28.8889 520 1.6336 0.3913 1.6336 1.2781
0.4218 29.0 522 1.5765 0.3556 1.5765 1.2556
0.4218 29.1111 524 1.5451 0.3437 1.5451 1.2430
0.4218 29.2222 526 1.5515 0.3411 1.5515 1.2456
0.4218 29.3333 528 1.6013 0.3556 1.6013 1.2654
0.4218 29.4444 530 1.6529 0.3382 1.6529 1.2857
0.4218 29.5556 532 1.7337 0.2734 1.7337 1.3167
0.4218 29.6667 534 1.8089 0.2979 1.8089 1.3450
0.4218 29.7778 536 1.7644 0.2734 1.7644 1.3283
0.4218 29.8889 538 1.6886 0.3212 1.6886 1.2994
0.4218 30.0 540 1.7016 0.3382 1.7016 1.3044
0.4218 30.1111 542 1.8134 0.2734 1.8134 1.3466
0.4218 30.2222 544 1.9162 0.2553 1.9162 1.3843
0.4218 30.3333 546 1.9447 0.2286 1.9447 1.3945
0.4218 30.4444 548 1.9209 0.2714 1.9209 1.3860
0.4218 30.5556 550 1.8216 0.2734 1.8216 1.3497

Framework versions

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