Edit model card

arabert_augWithOrig_disEquV3_k10_organization_task3_fold0

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: 2.0493
  • Qwk: -0.1198
  • Mse: 2.0493
  • Rmse: 1.4316

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: 10

Training results

Training Loss Epoch Step Validation Loss Qwk Mse Rmse
No log 0.0385 2 3.7528 0.0 3.7528 1.9372
No log 0.0769 4 3.6296 0.0 3.6296 1.9052
No log 0.1154 6 2.2094 0.0307 2.2094 1.4864
No log 0.1538 8 1.4546 0.0 1.4546 1.2061
No log 0.1923 10 1.7685 -0.1516 1.7685 1.3299
No log 0.2308 12 2.3568 0.0 2.3568 1.5352
No log 0.2692 14 2.2472 0.0 2.2472 1.4991
No log 0.3077 16 2.0316 0.0240 2.0316 1.4253
No log 0.3462 18 1.7349 0.0 1.7349 1.3171
No log 0.3846 20 1.9629 0.0265 1.9629 1.4010
No log 0.4231 22 2.3594 -0.0034 2.3594 1.5360
No log 0.4615 24 2.2278 -0.0072 2.2278 1.4926
No log 0.5 26 2.1708 -0.0115 2.1708 1.4734
No log 0.5385 28 1.3897 0.0 1.3897 1.1789
No log 0.5769 30 1.2389 0.0 1.2389 1.1131
No log 0.6154 32 1.2694 0.0 1.2694 1.1267
No log 0.6538 34 1.4514 0.0 1.4514 1.2047
No log 0.6923 36 1.5752 0.0 1.5752 1.2551
No log 0.7308 38 1.4974 0.0 1.4974 1.2237
No log 0.7692 40 1.5174 0.0 1.5174 1.2318
No log 0.8077 42 1.5835 0.0 1.5835 1.2584
No log 0.8462 44 1.8700 0.0072 1.8700 1.3675
No log 0.8846 46 1.9858 0.0240 1.9858 1.4092
No log 0.9231 48 2.0001 -0.0708 2.0001 1.4142
No log 0.9615 50 1.9219 0.0 1.9219 1.3863
No log 1.0 52 1.8574 0.0 1.8574 1.3629
No log 1.0385 54 1.7963 0.0 1.7963 1.3403
No log 1.0769 56 1.7357 0.0 1.7357 1.3174
No log 1.1154 58 1.6793 0.0 1.6793 1.2959
No log 1.1538 60 1.7357 0.0 1.7357 1.3175
No log 1.1923 62 1.9646 -0.0577 1.9646 1.4016
No log 1.2308 64 2.5181 0.0 2.5181 1.5868
No log 1.2692 66 2.7289 0.0 2.7289 1.6519
No log 1.3077 68 2.3400 -0.0034 2.3400 1.5297
No log 1.3462 70 1.8747 -0.0577 1.8747 1.3692
No log 1.3846 72 1.6106 0.0 1.6106 1.2691
No log 1.4231 74 1.4907 0.0 1.4907 1.2209
No log 1.4615 76 1.4947 0.0 1.4947 1.2226
No log 1.5 78 1.5217 0.0 1.5217 1.2336
No log 1.5385 80 1.6038 0.0 1.6038 1.2664
No log 1.5769 82 1.6980 0.0 1.6980 1.3031
No log 1.6154 84 1.8670 0.0 1.8670 1.3664
No log 1.6538 86 1.9850 0.0240 1.9850 1.4089
No log 1.6923 88 2.0374 -0.0034 2.0374 1.4274
No log 1.7308 90 2.0278 -0.0034 2.0278 1.4240
No log 1.7692 92 1.9620 0.0240 1.9620 1.4007
No log 1.8077 94 1.9806 0.0265 1.9806 1.4073
No log 1.8462 96 2.0457 -0.0034 2.0457 1.4303
No log 1.8846 98 1.9403 0.1538 1.9403 1.3930
No log 1.9231 100 1.7498 0.0 1.7498 1.3228
No log 1.9615 102 1.5560 0.0 1.5560 1.2474
No log 2.0 104 1.4080 0.0 1.4080 1.1866
No log 2.0385 106 1.3268 0.0 1.3268 1.1519
No log 2.0769 108 1.3304 0.0 1.3304 1.1534
No log 2.1154 110 1.3345 0.0 1.3345 1.1552
No log 2.1538 112 1.2809 0.0 1.2809 1.1317
No log 2.1923 114 1.2737 0.0 1.2737 1.1286
No log 2.2308 116 1.3568 0.0 1.3568 1.1648
No log 2.2692 118 1.5053 0.0 1.5053 1.2269
No log 2.3077 120 1.6667 0.0 1.6667 1.2910
No log 2.3462 122 1.5965 0.0 1.5965 1.2635
No log 2.3846 124 1.5256 0.0 1.5256 1.2352
No log 2.4231 126 1.5950 0.0 1.5950 1.2629
No log 2.4615 128 1.7211 0.0 1.7211 1.3119
No log 2.5 130 1.8318 0.0866 1.8318 1.3534
No log 2.5385 132 1.7319 0.0 1.7319 1.3160
No log 2.5769 134 1.6608 0.0 1.6608 1.2887
No log 2.6154 136 1.5965 0.0 1.5965 1.2635
No log 2.6538 138 1.6086 0.0 1.6086 1.2683
No log 2.6923 140 1.7105 0.0 1.7105 1.3079
No log 2.7308 142 1.7433 0.0 1.7433 1.3203
No log 2.7692 144 1.6934 0.0 1.6934 1.3013
No log 2.8077 146 1.5925 0.0 1.5925 1.2619
No log 2.8462 148 1.5473 0.0 1.5473 1.2439
No log 2.8846 150 1.5897 0.0 1.5897 1.2608
No log 2.9231 152 1.6956 0.0 1.6956 1.3022
No log 2.9615 154 1.7923 0.0 1.7923 1.3388
No log 3.0 156 1.7772 0.0 1.7772 1.3331
No log 3.0385 158 1.6442 0.0 1.6442 1.2823
No log 3.0769 160 1.8199 -0.0722 1.8199 1.3490
No log 3.1154 162 1.8975 -0.1987 1.8975 1.3775
No log 3.1538 164 1.9719 -0.1095 1.9719 1.4042
No log 3.1923 166 1.9601 -0.1987 1.9601 1.4000
No log 3.2308 168 1.8245 -0.0722 1.8245 1.3507
No log 3.2692 170 1.8051 0.0 1.8051 1.3435
No log 3.3077 172 1.6220 0.0 1.6220 1.2736
No log 3.3462 174 1.4126 0.0 1.4126 1.1885
No log 3.3846 176 1.3796 0.0 1.3796 1.1746
No log 3.4231 178 1.4130 0.0 1.4130 1.1887
No log 3.4615 180 1.4409 0.0 1.4409 1.2004
No log 3.5 182 1.4899 0.0 1.4899 1.2206
No log 3.5385 184 1.4892 0.0 1.4892 1.2203
No log 3.5769 186 1.5182 0.0 1.5182 1.2322
No log 3.6154 188 1.5491 0.0 1.5491 1.2446
No log 3.6538 190 1.5288 0.0 1.5288 1.2364
No log 3.6923 192 1.5208 0.0 1.5208 1.2332
No log 3.7308 194 1.5667 0.0 1.5667 1.2517
No log 3.7692 196 1.6042 0.0 1.6042 1.2666
No log 3.8077 198 1.6645 0.0 1.6645 1.2901
No log 3.8462 200 1.7610 0.0 1.7610 1.3270
No log 3.8846 202 1.8720 0.0 1.8720 1.3682
No log 3.9231 204 1.9263 0.0 1.9263 1.3879
No log 3.9615 206 1.9994 -0.0708 1.9994 1.4140
No log 4.0 208 2.0411 -0.0072 2.0411 1.4287
No log 4.0385 210 2.0577 0.0323 2.0577 1.4345
No log 4.0769 212 1.9997 0.0307 1.9997 1.4141
No log 4.1154 214 1.8516 0.0 1.8516 1.3608
No log 4.1538 216 1.7462 0.0 1.7462 1.3214
No log 4.1923 218 1.6728 0.0 1.6728 1.2934
No log 4.2308 220 1.7828 0.0 1.7828 1.3352
No log 4.2692 222 1.9462 -0.0164 1.9462 1.3951
No log 4.3077 224 1.7513 -0.1516 1.7513 1.3234
No log 4.3462 226 1.2859 0.0 1.2859 1.1340
No log 4.3846 228 1.1093 0.0 1.1093 1.0532
No log 4.4231 230 1.0759 0.0 1.0759 1.0372
No log 4.4615 232 1.0792 0.0 1.0792 1.0389
No log 4.5 234 1.0928 0.0 1.0928 1.0454
No log 4.5385 236 1.2065 0.0 1.2065 1.0984
No log 4.5769 238 1.3946 0.0 1.3946 1.1810
No log 4.6154 240 1.3239 0.0 1.3239 1.1506
No log 4.6538 242 1.2122 0.0 1.2122 1.1010
No log 4.6923 244 1.3372 0.0 1.3372 1.1564
No log 4.7308 246 1.7482 -0.1516 1.7482 1.3222
No log 4.7692 248 2.1288 -0.0164 2.1288 1.4591
No log 4.8077 250 2.0769 -0.0164 2.0769 1.4411
No log 4.8462 252 1.8216 -0.1282 1.8216 1.3497
No log 4.8846 254 1.4944 0.0 1.4944 1.2224
No log 4.9231 256 1.1288 0.0 1.1288 1.0624
No log 4.9615 258 1.0150 0.0 1.0150 1.0075
No log 5.0 260 1.0337 0.0 1.0337 1.0167
No log 5.0385 262 1.2076 0.0 1.2076 1.0989
No log 5.0769 264 1.4007 0.0 1.4007 1.1835
No log 5.1154 266 1.7195 0.0072 1.7195 1.3113
No log 5.1538 268 1.9381 -0.1095 1.9381 1.3922
No log 5.1923 270 2.0710 -0.0815 2.0710 1.4391
No log 5.2308 272 2.0576 -0.1518 2.0576 1.4344
No log 5.2692 274 2.0434 -0.1518 2.0434 1.4295
No log 5.3077 276 1.8905 -0.1282 1.8905 1.3750
No log 5.3462 278 1.7121 0.0 1.7121 1.3085
No log 5.3846 280 1.5222 0.0 1.5222 1.2338
No log 5.4231 282 1.3874 0.0 1.3874 1.1779
No log 5.4615 284 1.3036 0.0 1.3036 1.1418
No log 5.5 286 1.3416 0.0 1.3416 1.1583
No log 5.5385 288 1.5579 0.0 1.5579 1.2481
No log 5.5769 290 1.9653 0.0240 1.9653 1.4019
No log 5.6154 292 2.2139 0.0307 2.2139 1.4879
No log 5.6538 294 2.1479 0.0307 2.1479 1.4656
No log 5.6923 296 1.8112 -0.0461 1.8112 1.3458
No log 5.7308 298 1.5924 -0.1516 1.5924 1.2619
No log 5.7692 300 1.5760 -0.1516 1.5760 1.2554
No log 5.8077 302 1.6521 -0.1516 1.6521 1.2853
No log 5.8462 304 1.6990 -0.1516 1.6990 1.3035
No log 5.8846 306 1.5367 -0.1516 1.5367 1.2396
No log 5.9231 308 1.5148 -0.1516 1.5148 1.2308
No log 5.9615 310 1.7146 -0.1516 1.7146 1.3094
No log 6.0 312 1.7602 -0.1516 1.7602 1.3267
No log 6.0385 314 1.7293 -0.1516 1.7293 1.3150
No log 6.0769 316 1.7292 -0.1516 1.7292 1.3150
No log 6.1154 318 1.5902 -0.1516 1.5902 1.2610
No log 6.1538 320 1.3531 0.0 1.3531 1.1632
No log 6.1923 322 1.1823 0.0 1.1823 1.0873
No log 6.2308 324 1.1569 0.0 1.1569 1.0756
No log 6.2692 326 1.3053 0.0 1.3053 1.1425
No log 6.3077 328 1.3452 -0.1516 1.3452 1.1598
No log 6.3462 330 1.3872 -0.1516 1.3872 1.1778
No log 6.3846 332 1.4360 -0.1516 1.4360 1.1983
No log 6.4231 334 1.5114 -0.1516 1.5114 1.2294
No log 6.4615 336 1.6106 -0.1516 1.6106 1.2691
No log 6.5 338 1.7521 -0.1516 1.7521 1.3237
No log 6.5385 340 1.6937 -0.1516 1.6937 1.3014
No log 6.5769 342 1.7026 -0.1282 1.7026 1.3048
No log 6.6154 344 1.8548 -0.1282 1.8548 1.3619
No log 6.6538 346 2.0419 -0.0366 2.0419 1.4290
No log 6.6923 348 2.1526 0.0739 2.1526 1.4672
No log 6.7308 350 2.3227 0.0739 2.3227 1.5240
No log 6.7692 352 2.2024 0.0739 2.2024 1.4840
No log 6.8077 354 1.8586 -0.1282 1.8586 1.3633
No log 6.8462 356 1.7130 -0.1282 1.7130 1.3088
No log 6.8846 358 1.6858 -0.1282 1.6858 1.2984
No log 6.9231 360 1.6532 -0.1282 1.6532 1.2858
No log 6.9615 362 1.6230 -0.1516 1.6230 1.2740
No log 7.0 364 1.5354 -0.1516 1.5354 1.2391
No log 7.0385 366 1.5030 -0.1516 1.5030 1.2260
No log 7.0769 368 1.6088 -0.1516 1.6088 1.2684
No log 7.1154 370 1.8048 -0.1282 1.8048 1.3434
No log 7.1538 372 1.9356 -0.0366 1.9356 1.3913
No log 7.1923 374 2.1289 -0.0288 2.1289 1.4591
No log 7.2308 376 2.3487 -0.0288 2.3487 1.5325
No log 7.2692 378 2.5657 -0.0536 2.5657 1.6018
No log 7.3077 380 2.4918 -0.0708 2.4918 1.5785
No log 7.3462 382 2.1614 -0.0288 2.1614 1.4702
No log 7.3846 384 1.7855 -0.1516 1.7855 1.3362
No log 7.4231 386 1.5377 -0.1516 1.5377 1.2400
No log 7.4615 388 1.4576 -0.1516 1.4576 1.2073
No log 7.5 390 1.4956 -0.1516 1.4956 1.2230
No log 7.5385 392 1.6738 -0.1516 1.6738 1.2938
No log 7.5769 394 1.9359 -0.1095 1.9359 1.3914
No log 7.6154 396 2.1932 -0.0942 2.1932 1.4810
No log 7.6538 398 2.5062 -0.0708 2.5062 1.5831
No log 7.6923 400 2.6047 -0.0164 2.6047 1.6139
No log 7.7308 402 2.4632 -0.0708 2.4632 1.5695
No log 7.7692 404 2.1491 -0.0942 2.1491 1.4660
No log 7.8077 406 1.8486 -0.1516 1.8486 1.3596
No log 7.8462 408 1.6513 -0.1667 1.6513 1.2850
No log 7.8846 410 1.4893 -0.0956 1.4893 1.2204
No log 7.9231 412 1.4724 -0.0956 1.4724 1.2134
No log 7.9615 414 1.4631 -0.0956 1.4631 1.2096
No log 8.0 416 1.5837 -0.1667 1.5837 1.2585
No log 8.0385 418 1.7818 -0.1667 1.7818 1.3348
No log 8.0769 420 2.0324 -0.0942 2.0324 1.4256
No log 8.1154 422 2.2556 -0.0942 2.2556 1.5019
No log 8.1538 424 2.3110 -0.0942 2.3110 1.5202
No log 8.1923 426 2.1822 -0.0942 2.1822 1.4772
No log 8.2308 428 1.9574 -0.0942 1.9574 1.3991
No log 8.2692 430 1.8606 -0.1282 1.8606 1.3640
No log 8.3077 432 1.7730 -0.1282 1.7730 1.3315
No log 8.3462 434 1.8038 -0.1282 1.8038 1.3431
No log 8.3846 436 1.9419 -0.1095 1.9419 1.3935
No log 8.4231 438 2.0183 -0.0942 2.0183 1.4207
No log 8.4615 440 2.0605 -0.0942 2.0605 1.4354
No log 8.5 442 2.1385 -0.0942 2.1385 1.4624
No log 8.5385 444 2.1961 -0.0942 2.1961 1.4819
No log 8.5769 446 2.2579 -0.0942 2.2579 1.5026
No log 8.6154 448 2.3632 -0.0942 2.3632 1.5373
No log 8.6538 450 2.3341 -0.0942 2.3341 1.5278
No log 8.6923 452 2.2334 -0.0942 2.2334 1.4945
No log 8.7308 454 2.1092 -0.0942 2.1092 1.4523
No log 8.7692 456 2.0702 -0.1030 2.0702 1.4388
No log 8.8077 458 1.9895 -0.1030 1.9895 1.4105
No log 8.8462 460 1.9056 -0.1405 1.9056 1.3804
No log 8.8846 462 1.7946 -0.1405 1.7946 1.3396
No log 8.9231 464 1.7203 -0.1667 1.7203 1.3116
No log 8.9615 466 1.7294 -0.1667 1.7294 1.3151
No log 9.0 468 1.7733 -0.1405 1.7733 1.3317
No log 9.0385 470 1.8494 -0.1405 1.8494 1.3599
No log 9.0769 472 1.9468 -0.1405 1.9468 1.3953
No log 9.1154 474 2.0616 -0.1198 2.0616 1.4358
No log 9.1538 476 2.1368 -0.1030 2.1368 1.4618
No log 9.1923 478 2.1817 -0.1030 2.1817 1.4771
No log 9.2308 480 2.1455 -0.1030 2.1455 1.4648
No log 9.2692 482 2.1310 -0.1030 2.1310 1.4598
No log 9.3077 484 2.0875 -0.1198 2.0875 1.4448
No log 9.3462 486 2.0476 -0.1198 2.0476 1.4309
No log 9.3846 488 1.9885 -0.1198 1.9885 1.4101
No log 9.4231 490 1.9393 -0.1405 1.9393 1.3926
No log 9.4615 492 1.9167 -0.1405 1.9167 1.3845
No log 9.5 494 1.8768 -0.1405 1.8768 1.3699
No log 9.5385 496 1.8686 -0.1405 1.8686 1.3670
No log 9.5769 498 1.8730 -0.1405 1.8730 1.3686
0.74 9.6154 500 1.8716 -0.1405 1.8716 1.3681
0.74 9.6538 502 1.8930 -0.1405 1.8930 1.3758
0.74 9.6923 504 1.9242 -0.1405 1.9242 1.3872
0.74 9.7308 506 1.9657 -0.1405 1.9657 1.4020
0.74 9.7692 508 2.0076 -0.1198 2.0076 1.4169
0.74 9.8077 510 2.0318 -0.1198 2.0318 1.4254
0.74 9.8462 512 2.0484 -0.1198 2.0484 1.4312
0.74 9.8846 514 2.0484 -0.1198 2.0484 1.4312
0.74 9.9231 516 2.0485 -0.1198 2.0485 1.4313
0.74 9.9615 518 2.0492 -0.1198 2.0492 1.4315
0.74 10.0 520 2.0493 -0.1198 2.0493 1.4316

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
135M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for MayBashendy/arabert_augWithOrig_disEquV3_k10_organization_task3_fold0

Finetuned
(702)
this model