ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run3_AugV5_k1_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: 0.7048
  • Qwk: 0.5125
  • Mse: 0.7048
  • Rmse: 0.8395

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 0.2857 2 4.4527 -0.0276 4.4527 2.1101
No log 0.5714 4 2.3605 -0.0052 2.3605 1.5364
No log 0.8571 6 1.1716 0.0 1.1716 1.0824
No log 1.1429 8 1.0729 -0.0533 1.0729 1.0358
No log 1.4286 10 0.9076 0.1678 0.9076 0.9527
No log 1.7143 12 0.8231 0.1505 0.8231 0.9072
No log 2.0 14 0.8507 0.1365 0.8507 0.9223
No log 2.2857 16 0.8745 0.0860 0.8745 0.9351
No log 2.5714 18 0.9777 0.0723 0.9777 0.9888
No log 2.8571 20 0.9504 0.1188 0.9504 0.9749
No log 3.1429 22 0.8071 0.1255 0.8071 0.8984
No log 3.4286 24 0.7941 0.1195 0.7941 0.8911
No log 3.7143 26 0.7505 0.1786 0.7505 0.8663
No log 4.0 28 0.8210 0.2595 0.8210 0.9061
No log 4.2857 30 0.9214 0.1623 0.9214 0.9599
No log 4.5714 32 1.0349 0.0687 1.0349 1.0173
No log 4.8571 34 0.9523 0.1123 0.9523 0.9758
No log 5.1429 36 0.8400 0.2705 0.8400 0.9165
No log 5.4286 38 0.8461 0.2534 0.8461 0.9198
No log 5.7143 40 0.7768 0.2218 0.7768 0.8814
No log 6.0 42 0.7646 0.2292 0.7646 0.8744
No log 6.2857 44 0.7620 0.2990 0.7620 0.8729
No log 6.5714 46 0.8123 0.3617 0.8123 0.9013
No log 6.8571 48 0.9615 0.3194 0.9615 0.9805
No log 7.1429 50 1.3065 0.2295 1.3065 1.1430
No log 7.4286 52 0.9800 0.3373 0.9800 0.9899
No log 7.7143 54 0.6986 0.4667 0.6986 0.8358
No log 8.0 56 0.6637 0.4581 0.6637 0.8147
No log 8.2857 58 0.6777 0.4773 0.6777 0.8232
No log 8.5714 60 0.7692 0.4651 0.7692 0.8770
No log 8.8571 62 0.8731 0.3614 0.8731 0.9344
No log 9.1429 64 0.7708 0.4487 0.7708 0.8780
No log 9.4286 66 0.6583 0.4685 0.6583 0.8114
No log 9.7143 68 0.7212 0.3951 0.7212 0.8492
No log 10.0 70 0.7656 0.5090 0.7656 0.8750
No log 10.2857 72 1.0675 0.3061 1.0675 1.0332
No log 10.5714 74 0.9348 0.4461 0.9348 0.9669
No log 10.8571 76 0.7579 0.5098 0.7579 0.8706
No log 11.1429 78 0.7284 0.4370 0.7284 0.8535
No log 11.4286 80 0.8398 0.4540 0.8398 0.9164
No log 11.7143 82 0.7445 0.4759 0.7445 0.8629
No log 12.0 84 0.6102 0.4679 0.6102 0.7812
No log 12.2857 86 0.6231 0.4567 0.6231 0.7894
No log 12.5714 88 0.6097 0.4249 0.6097 0.7809
No log 12.8571 90 0.6089 0.4177 0.6089 0.7803
No log 13.1429 92 0.6203 0.4309 0.6203 0.7876
No log 13.4286 94 0.6379 0.3566 0.6379 0.7987
No log 13.7143 96 0.7843 0.4532 0.7843 0.8856
No log 14.0 98 0.8643 0.4091 0.8643 0.9297
No log 14.2857 100 0.8060 0.4613 0.8060 0.8977
No log 14.5714 102 0.6940 0.4289 0.6940 0.8330
No log 14.8571 104 0.7744 0.4540 0.7744 0.8800
No log 15.1429 106 0.9055 0.4146 0.9055 0.9516
No log 15.4286 108 0.8448 0.4077 0.8448 0.9191
No log 15.7143 110 0.8142 0.4322 0.8142 0.9023
No log 16.0 112 0.9153 0.3898 0.9153 0.9567
No log 16.2857 114 0.8647 0.4014 0.8647 0.9299
No log 16.5714 116 0.7475 0.4491 0.7475 0.8646
No log 16.8571 118 0.7795 0.4119 0.7795 0.8829
No log 17.1429 120 0.7976 0.4566 0.7976 0.8931
No log 17.4286 122 0.8043 0.4421 0.8043 0.8968
No log 17.7143 124 0.8272 0.4509 0.8272 0.9095
No log 18.0 126 0.8385 0.4557 0.8385 0.9157
No log 18.2857 128 0.7624 0.4763 0.7624 0.8731
No log 18.5714 130 0.7410 0.4910 0.7410 0.8608
No log 18.8571 132 0.7542 0.4691 0.7542 0.8684
No log 19.1429 134 0.7511 0.4910 0.7511 0.8667
No log 19.4286 136 0.7392 0.4636 0.7392 0.8598
No log 19.7143 138 0.7038 0.4371 0.7038 0.8389
No log 20.0 140 0.7037 0.4255 0.7037 0.8389
No log 20.2857 142 0.7707 0.4198 0.7707 0.8779
No log 20.5714 144 0.7675 0.4045 0.7675 0.8761
No log 20.8571 146 0.6941 0.4209 0.6941 0.8331
No log 21.1429 148 0.6973 0.4764 0.6973 0.8351
No log 21.4286 150 0.6768 0.4732 0.6768 0.8227
No log 21.7143 152 0.6658 0.4869 0.6658 0.8159
No log 22.0 154 0.6799 0.4805 0.6799 0.8245
No log 22.2857 156 0.6453 0.5037 0.6453 0.8033
No log 22.5714 158 0.6520 0.4672 0.6520 0.8075
No log 22.8571 160 0.7031 0.4025 0.7031 0.8385
No log 23.1429 162 0.6978 0.4026 0.6978 0.8354
No log 23.4286 164 0.6425 0.4812 0.6425 0.8016
No log 23.7143 166 0.6448 0.4903 0.6448 0.8030
No log 24.0 168 0.6995 0.4703 0.6995 0.8363
No log 24.2857 170 0.7371 0.4511 0.7371 0.8586
No log 24.5714 172 0.6879 0.4337 0.6879 0.8294
No log 24.8571 174 0.6706 0.3870 0.6706 0.8189
No log 25.1429 176 0.6753 0.4201 0.6753 0.8218
No log 25.4286 178 0.6846 0.4477 0.6846 0.8274
No log 25.7143 180 0.6863 0.4960 0.6863 0.8284
No log 26.0 182 0.6889 0.5219 0.6889 0.8300
No log 26.2857 184 0.7073 0.4631 0.7073 0.8410
No log 26.5714 186 0.7038 0.4943 0.7038 0.8389
No log 26.8571 188 0.7024 0.4636 0.7024 0.8381
No log 27.1429 190 0.6983 0.4170 0.6983 0.8356
No log 27.4286 192 0.6289 0.4751 0.6289 0.7930
No log 27.7143 194 0.6010 0.4958 0.6010 0.7752
No log 28.0 196 0.6129 0.5337 0.6129 0.7829
No log 28.2857 198 0.6185 0.5077 0.6185 0.7864
No log 28.5714 200 0.6245 0.5183 0.6245 0.7903
No log 28.8571 202 0.6267 0.4965 0.6267 0.7917
No log 29.1429 204 0.6390 0.4537 0.6390 0.7994
No log 29.4286 206 0.6646 0.4037 0.6646 0.8153
No log 29.7143 208 0.6747 0.3947 0.6747 0.8214
No log 30.0 210 0.6668 0.3641 0.6668 0.8166
No log 30.2857 212 0.6740 0.3922 0.6740 0.8210
No log 30.5714 214 0.6870 0.4442 0.6870 0.8288
No log 30.8571 216 0.7245 0.5099 0.7245 0.8512
No log 31.1429 218 0.7410 0.5405 0.7410 0.8608
No log 31.4286 220 0.7282 0.5029 0.7282 0.8533
No log 31.7143 222 0.6883 0.4999 0.6883 0.8297
No log 32.0 224 0.6570 0.5320 0.6570 0.8105
No log 32.2857 226 0.6291 0.4774 0.6291 0.7932
No log 32.5714 228 0.6281 0.4476 0.6281 0.7925
No log 32.8571 230 0.6459 0.3947 0.6459 0.8036
No log 33.1429 232 0.6304 0.4190 0.6304 0.7940
No log 33.4286 234 0.6159 0.4169 0.6159 0.7848
No log 33.7143 236 0.6099 0.4205 0.6099 0.7810
No log 34.0 238 0.6218 0.4636 0.6218 0.7886
No log 34.2857 240 0.6475 0.4829 0.6475 0.8047
No log 34.5714 242 0.6973 0.5024 0.6973 0.8350
No log 34.8571 244 0.7091 0.5023 0.7091 0.8421
No log 35.1429 246 0.7199 0.4812 0.7199 0.8485
No log 35.4286 248 0.7020 0.4857 0.7020 0.8378
No log 35.7143 250 0.6784 0.5228 0.6784 0.8236
No log 36.0 252 0.6780 0.5106 0.6780 0.8234
No log 36.2857 254 0.6714 0.5253 0.6714 0.8194
No log 36.5714 256 0.6542 0.5158 0.6542 0.8088
No log 36.8571 258 0.6578 0.5038 0.6578 0.8110
No log 37.1429 260 0.6750 0.4980 0.6750 0.8216
No log 37.4286 262 0.6902 0.5297 0.6902 0.8308
No log 37.7143 264 0.6778 0.5287 0.6778 0.8233
No log 38.0 266 0.6857 0.4835 0.6857 0.8280
No log 38.2857 268 0.6912 0.4642 0.6912 0.8314
No log 38.5714 270 0.6682 0.5005 0.6682 0.8174
No log 38.8571 272 0.6712 0.4934 0.6712 0.8193
No log 39.1429 274 0.6924 0.5050 0.6924 0.8321
No log 39.4286 276 0.6979 0.4928 0.6979 0.8354
No log 39.7143 278 0.6849 0.4594 0.6849 0.8276
No log 40.0 280 0.6729 0.4594 0.6729 0.8203
No log 40.2857 282 0.6672 0.4866 0.6672 0.8168
No log 40.5714 284 0.6701 0.4829 0.6701 0.8186
No log 40.8571 286 0.6782 0.4882 0.6782 0.8235
No log 41.1429 288 0.6791 0.5304 0.6791 0.8241
No log 41.4286 290 0.6619 0.5162 0.6619 0.8136
No log 41.7143 292 0.6504 0.4920 0.6504 0.8065
No log 42.0 294 0.6429 0.5314 0.6429 0.8018
No log 42.2857 296 0.6113 0.5081 0.6113 0.7818
No log 42.5714 298 0.6016 0.5081 0.6016 0.7757
No log 42.8571 300 0.6055 0.5081 0.6055 0.7781
No log 43.1429 302 0.6069 0.4750 0.6069 0.7790
No log 43.4286 304 0.6190 0.4469 0.6190 0.7867
No log 43.7143 306 0.6140 0.4469 0.6140 0.7836
No log 44.0 308 0.6150 0.4462 0.6150 0.7842
No log 44.2857 310 0.6270 0.4543 0.6270 0.7918
No log 44.5714 312 0.6246 0.4908 0.6246 0.7903
No log 44.8571 314 0.6247 0.5037 0.6247 0.7904
No log 45.1429 316 0.6262 0.5231 0.6262 0.7913
No log 45.4286 318 0.6301 0.5171 0.6301 0.7938
No log 45.7143 320 0.6280 0.5077 0.6280 0.7925
No log 46.0 322 0.6290 0.4966 0.6290 0.7931
No log 46.2857 324 0.6303 0.4959 0.6303 0.7939
No log 46.5714 326 0.6405 0.4979 0.6405 0.8003
No log 46.8571 328 0.6528 0.4737 0.6528 0.8080
No log 47.1429 330 0.6761 0.4703 0.6761 0.8222
No log 47.4286 332 0.6758 0.4094 0.6758 0.8221
No log 47.7143 334 0.6784 0.4442 0.6784 0.8237
No log 48.0 336 0.6869 0.4775 0.6869 0.8288
No log 48.2857 338 0.6774 0.4873 0.6774 0.8230
No log 48.5714 340 0.6692 0.4711 0.6692 0.8181
No log 48.8571 342 0.6683 0.4974 0.6683 0.8175
No log 49.1429 344 0.6745 0.4858 0.6745 0.8213
No log 49.4286 346 0.6751 0.4890 0.6751 0.8216
No log 49.7143 348 0.6582 0.4462 0.6582 0.8113
No log 50.0 350 0.6299 0.4640 0.6299 0.7937
No log 50.2857 352 0.6147 0.5088 0.6147 0.7840
No log 50.5714 354 0.6157 0.5508 0.6157 0.7847
No log 50.8571 356 0.6398 0.5542 0.6398 0.7998
No log 51.1429 358 0.6685 0.5377 0.6685 0.8176
No log 51.4286 360 0.6648 0.5730 0.6648 0.8154
No log 51.7143 362 0.6455 0.5397 0.6455 0.8034
No log 52.0 364 0.6540 0.5050 0.6540 0.8087
No log 52.2857 366 0.6830 0.5018 0.6830 0.8264
No log 52.5714 368 0.6904 0.4579 0.6904 0.8309
No log 52.8571 370 0.6914 0.4579 0.6914 0.8315
No log 53.1429 372 0.6806 0.4837 0.6806 0.8250
No log 53.4286 374 0.6590 0.4651 0.6590 0.8118
No log 53.7143 376 0.6509 0.4802 0.6509 0.8068
No log 54.0 378 0.6651 0.5274 0.6651 0.8155
No log 54.2857 380 0.6861 0.5393 0.6861 0.8283
No log 54.5714 382 0.7019 0.5564 0.7019 0.8378
No log 54.8571 384 0.7093 0.5144 0.7093 0.8422
No log 55.1429 386 0.7151 0.4883 0.7151 0.8456
No log 55.4286 388 0.7116 0.4857 0.7116 0.8435
No log 55.7143 390 0.7013 0.4801 0.7013 0.8375
No log 56.0 392 0.6857 0.4397 0.6857 0.8281
No log 56.2857 394 0.6747 0.4269 0.6747 0.8214
No log 56.5714 396 0.6701 0.4514 0.6701 0.8186
No log 56.8571 398 0.6801 0.4403 0.6801 0.8247
No log 57.1429 400 0.7012 0.4801 0.7012 0.8374
No log 57.4286 402 0.7104 0.4791 0.7104 0.8429
No log 57.7143 404 0.7075 0.4791 0.7075 0.8411
No log 58.0 406 0.6955 0.4612 0.6955 0.8339
No log 58.2857 408 0.6746 0.4491 0.6746 0.8213
No log 58.5714 410 0.6635 0.4483 0.6635 0.8145
No log 58.8571 412 0.6563 0.4498 0.6563 0.8101
No log 59.1429 414 0.6487 0.4411 0.6487 0.8054
No log 59.4286 416 0.6483 0.4552 0.6483 0.8052
No log 59.7143 418 0.6531 0.4972 0.6531 0.8081
No log 60.0 420 0.6619 0.4934 0.6619 0.8135
No log 60.2857 422 0.6541 0.4934 0.6541 0.8088
No log 60.5714 424 0.6467 0.4946 0.6467 0.8042
No log 60.8571 426 0.6327 0.5318 0.6327 0.7954
No log 61.1429 428 0.6271 0.4763 0.6271 0.7919
No log 61.4286 430 0.6272 0.4731 0.6272 0.7920
No log 61.7143 432 0.6247 0.4763 0.6247 0.7904
No log 62.0 434 0.6217 0.4903 0.6217 0.7885
No log 62.2857 436 0.6251 0.5071 0.6251 0.7906
No log 62.5714 438 0.6364 0.4934 0.6364 0.7978
No log 62.8571 440 0.6368 0.4908 0.6368 0.7980
No log 63.1429 442 0.6287 0.5487 0.6287 0.7929
No log 63.4286 444 0.6151 0.5427 0.6151 0.7843
No log 63.7143 446 0.6120 0.5203 0.6120 0.7823
No log 64.0 448 0.6117 0.5203 0.6117 0.7821
No log 64.2857 450 0.6154 0.5331 0.6154 0.7845
No log 64.5714 452 0.6148 0.5331 0.6148 0.7841
No log 64.8571 454 0.6141 0.5636 0.6141 0.7837
No log 65.1429 456 0.6168 0.5427 0.6168 0.7853
No log 65.4286 458 0.6230 0.5590 0.6230 0.7893
No log 65.7143 460 0.6277 0.5590 0.6277 0.7923
No log 66.0 462 0.6226 0.5464 0.6226 0.7890
No log 66.2857 464 0.6183 0.5469 0.6183 0.7863
No log 66.5714 466 0.6232 0.5415 0.6232 0.7895
No log 66.8571 468 0.6288 0.5638 0.6288 0.7930
No log 67.1429 470 0.6328 0.5640 0.6328 0.7955
No log 67.4286 472 0.6338 0.5298 0.6338 0.7961
No log 67.7143 474 0.6361 0.5024 0.6361 0.7975
No log 68.0 476 0.6500 0.5244 0.6500 0.8062
No log 68.2857 478 0.6669 0.5512 0.6669 0.8166
No log 68.5714 480 0.6703 0.5056 0.6703 0.8187
No log 68.8571 482 0.6599 0.5051 0.6599 0.8124
No log 69.1429 484 0.6550 0.5287 0.6550 0.8093
No log 69.4286 486 0.6459 0.5260 0.6459 0.8037
No log 69.7143 488 0.6431 0.4998 0.6431 0.8020
No log 70.0 490 0.6438 0.4998 0.6438 0.8024
No log 70.2857 492 0.6457 0.5083 0.6457 0.8035
No log 70.5714 494 0.6493 0.5069 0.6493 0.8058
No log 70.8571 496 0.6521 0.53 0.6521 0.8075
No log 71.1429 498 0.6551 0.5316 0.6551 0.8094
0.2208 71.4286 500 0.6666 0.5421 0.6666 0.8165
0.2208 71.7143 502 0.6890 0.5393 0.6890 0.8301
0.2208 72.0 504 0.7101 0.5003 0.7101 0.8427
0.2208 72.2857 506 0.7192 0.5080 0.7192 0.8480
0.2208 72.5714 508 0.7187 0.5182 0.7187 0.8478
0.2208 72.8571 510 0.7048 0.5125 0.7048 0.8395

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
135M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for MayBashendy/ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run3_AugV5_k1_task2_organization

Finetuned
(4206)
this model