Thalesian's picture
transliterated-akk-en-t5-small-instruct
a4de082 verified
metadata
tags:
  - generated_from_trainer
model-index:
  - name: t5-small-p-l-akk-en-20240727-162748
    results: []

t5-small-p-l-akk-en-20240727-162748

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0378

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: 4e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • 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
0.0567 0.0552 2500 0.0478
0.051 0.1105 5000 0.0473
0.0466 0.1657 7500 0.0465
0.0442 0.2210 10000 0.0462
0.0404 0.2762 12500 0.0458
0.0499 0.3314 15000 0.0453
0.0491 0.3867 17500 0.0449
0.0449 0.4419 20000 0.0447
0.0428 0.4972 22500 0.0442
0.0474 0.5524 25000 0.0440
0.048 0.6076 27500 0.0437
0.0479 0.6629 30000 0.0435
0.0493 0.7181 32500 0.0433
0.0426 0.7734 35000 0.0431
0.0476 0.8286 37500 0.0427
0.0507 0.8838 40000 0.0427
0.048 0.9391 42500 0.0426
0.0441 0.9943 45000 0.0424
0.0452 1.0496 47500 0.0422
0.0395 1.1048 50000 0.0422
0.0508 1.1600 52500 0.0421
0.0399 1.2153 55000 0.0421
0.0412 1.2705 57500 0.0418
0.0521 1.3258 60000 0.0417
0.0427 1.3810 62500 0.0416
0.0498 1.4362 65000 0.0417
0.0396 1.4915 67500 0.0416
0.0427 1.5467 70000 0.0414
0.0397 1.6020 72500 0.0413
0.0474 1.6572 75000 0.0413
0.0469 1.7124 77500 0.0412
0.0447 1.7677 80000 0.0412
0.0388 1.8229 82500 0.0409
0.0439 1.8782 85000 0.0410
0.0476 1.9334 87500 0.0410
0.0456 1.9886 90000 0.0409
0.0349 2.0439 92500 0.0410
0.0416 2.0991 95000 0.0407
0.0381 2.1544 97500 0.0407
0.0354 2.2096 100000 0.0409
0.041 2.2648 102500 0.0406
0.0438 2.3201 105000 0.0406
0.0412 2.3753 107500 0.0406
0.0363 2.4306 110000 0.0405
0.0396 2.4858 112500 0.0403
0.0403 2.5410 115000 0.0403
0.0423 2.5963 117500 0.0404
0.0446 2.6515 120000 0.0404
0.0439 2.7068 122500 0.0402
0.0471 2.7620 125000 0.0401
0.0444 2.8172 127500 0.0401
0.0469 2.8725 130000 0.0400
0.0416 2.9277 132500 0.0400
0.0413 2.9830 135000 0.0401
0.044 3.0382 137500 0.0401
0.0377 3.0934 140000 0.0400
0.0447 3.1487 142500 0.0399
0.0404 3.2039 145000 0.0400
0.0425 3.2592 147500 0.0399
0.0462 3.3144 150000 0.0398
0.0416 3.3696 152500 0.0399
0.0478 3.4249 155000 0.0397
0.0387 3.4801 157500 0.0397
0.0445 3.5354 160000 0.0397
0.0408 3.5906 162500 0.0396
0.0398 3.6458 165000 0.0395
0.0388 3.7011 167500 0.0396
0.0379 3.7563 170000 0.0397
0.0415 3.8116 172500 0.0396
0.0395 3.8668 175000 0.0394
0.0427 3.9220 177500 0.0394
0.0392 3.9773 180000 0.0392
0.0409 4.0325 182500 0.0394
0.0429 4.0878 185000 0.0394
0.037 4.1430 187500 0.0393
0.0436 4.1982 190000 0.0393
0.0383 4.2535 192500 0.0393
0.0442 4.3087 195000 0.0392
0.0455 4.3640 197500 0.0394
0.0396 4.4192 200000 0.0392
0.0416 4.4744 202500 0.0391
0.0399 4.5297 205000 0.0392
0.0418 4.5849 207500 0.0394
0.0409 4.6402 210000 0.0391
0.0415 4.6954 212500 0.0391
0.0359 4.7506 215000 0.0391
0.038 4.8059 217500 0.0392
0.0416 4.8611 220000 0.0389
0.0358 4.9164 222500 0.0390
0.039 4.9716 225000 0.0389
0.042 5.0268 227500 0.0390
0.0406 5.0821 230000 0.0389
0.0407 5.1373 232500 0.0391
0.0362 5.1926 235000 0.0390
0.0424 5.2478 237500 0.0387
0.0428 5.3030 240000 0.0388
0.0433 5.3583 242500 0.0388
0.0364 5.4135 245000 0.0387
0.0414 5.4688 247500 0.0387
0.0398 5.5240 250000 0.0388
0.0395 5.5792 252500 0.0386
0.0403 5.6345 255000 0.0387
0.0392 5.6897 257500 0.0387
0.0418 5.7450 260000 0.0386
0.0423 5.8002 262500 0.0386
0.0424 5.8554 265000 0.0385
0.0356 5.9107 267500 0.0386
0.0357 5.9659 270000 0.0385
0.0413 6.0212 272500 0.0385
0.0382 6.0764 275000 0.0385
0.0372 6.1316 277500 0.0386
0.0423 6.1869 280000 0.0386
0.0349 6.2421 282500 0.0385
0.0375 6.2974 285000 0.0386
0.0382 6.3526 287500 0.0384
0.045 6.4078 290000 0.0385
0.0391 6.4631 292500 0.0383
0.0308 6.5183 295000 0.0384
0.0438 6.5736 297500 0.0383
0.039 6.6288 300000 0.0384
0.0432 6.6840 302500 0.0382
0.0362 6.7393 305000 0.0384
0.0372 6.7945 307500 0.0383
0.0421 6.8498 310000 0.0383
0.0402 6.9050 312500 0.0382
0.0384 6.9602 315000 0.0382
0.0413 7.0155 317500 0.0382
0.0445 7.0707 320000 0.0382
0.0377 7.1260 322500 0.0383
0.0422 7.1812 325000 0.0383
0.0351 7.2364 327500 0.0382
0.0405 7.2917 330000 0.0382
0.0345 7.3469 332500 0.0383
0.0352 7.4022 335000 0.0382
0.0372 7.4574 337500 0.0381
0.0366 7.5126 340000 0.0382
0.0385 7.5679 342500 0.0381
0.0411 7.6231 345000 0.0381
0.0425 7.6784 347500 0.0380
0.0381 7.7336 350000 0.0379
0.0398 7.7889 352500 0.0381
0.0411 7.8441 355000 0.0379
0.0346 7.8993 357500 0.0380
0.0394 7.9546 360000 0.0380
0.0357 8.0098 362500 0.0381
0.0419 8.0651 365000 0.0380
0.036 8.1203 367500 0.0380
0.0371 8.1755 370000 0.0380
0.0402 8.2308 372500 0.0380
0.0381 8.2860 375000 0.0380
0.0364 8.3413 377500 0.0380
0.0466 8.3965 380000 0.0380
0.0381 8.4517 382500 0.0379
0.0375 8.5070 385000 0.0379
0.0394 8.5622 387500 0.0380
0.0387 8.6175 390000 0.0379
0.0397 8.6727 392500 0.0379
0.0379 8.7279 395000 0.0379
0.0402 8.7832 397500 0.0379
0.0386 8.8384 400000 0.0379
0.0359 8.8937 402500 0.0379
0.0369 8.9489 405000 0.0378
0.039 9.0041 407500 0.0379
0.0399 9.0594 410000 0.0379
0.0359 9.1146 412500 0.0379
0.0373 9.1699 415000 0.0379
0.0415 9.2251 417500 0.0379
0.0382 9.2803 420000 0.0379
0.0372 9.3356 422500 0.0379
0.0376 9.3908 425000 0.0379
0.0418 9.4461 427500 0.0378
0.0382 9.5013 430000 0.0379
0.038 9.5565 432500 0.0378
0.038 9.6118 435000 0.0378
0.0329 9.6670 437500 0.0378
0.0383 9.7223 440000 0.0378
0.0371 9.7775 442500 0.0378
0.0437 9.8327 445000 0.0378
0.0424 9.8880 447500 0.0378
0.0402 9.9432 450000 0.0378
0.0401 9.9985 452500 0.0378

Framework versions

  • Transformers 4.44.0.dev0
  • Pytorch 2.5.0.dev20240625
  • Datasets 2.20.0
  • Tokenizers 0.19.1