Hugging Face's logo

fatimaMb
/
custom_ABB_KUKA_model

Transformers
TensorBoard
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
 Metrics Community

custom_ABB_KUKA_model

This model is a fine-tuned version of google-t5/t5-small on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1607
  • Bleu: 97.4345
  • Gen Len: 128.0

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: 0.0008
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 150
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
No log 1.0 4 0.1512 97.4345 128.0
No log 2.0 8 0.1533 97.4345 128.0
No log 3.0 12 0.1570 97.4345 128.0
No log 4.0 16 0.1593 97.4345 128.0
No log 5.0 20 0.1700 97.4345 128.0
No log 6.0 24 0.1552 97.4345 128.0
No log 7.0 28 0.1441 97.4345 128.0
No log 8.0 32 0.1260 97.4345 128.0
No log 9.0 36 0.1141 97.4345 128.0
No log 10.0 40 0.1074 78.6326 114.0
No log 11.0 44 0.0879 97.4345 128.0
No log 12.0 48 0.0906 97.4345 128.0
No log 13.0 52 0.0919 97.4345 128.0
No log 14.0 56 0.0971 97.4345 128.0
No log 15.0 60 0.1060 97.4345 128.0
No log 16.0 64 0.1145 97.4345 128.0
No log 17.0 68 0.1161 97.4345 128.0
No log 18.0 72 0.1231 97.4345 128.0
No log 19.0 76 0.1277 97.4345 128.0
No log 20.0 80 0.1247 97.4345 128.0
No log 21.0 84 0.1157 97.4345 128.0
No log 22.0 88 0.1180 97.4345 128.0
No log 23.0 92 0.1195 97.4345 128.0
No log 24.0 96 0.1231 97.4345 128.0
No log 25.0 100 0.1274 97.4345 128.0
No log 26.0 104 0.1315 97.4345 128.0
No log 27.0 108 0.1342 97.4345 128.0
No log 28.0 112 0.1397 97.4345 128.0
No log 29.0 116 0.1438 97.4345 128.0
No log 30.0 120 0.1453 97.4345 128.0
No log 31.0 124 0.1459 97.4345 128.0
No log 32.0 128 0.1459 97.4345 128.0
No log 33.0 132 0.1453 97.4345 128.0
No log 34.0 136 0.1448 97.4345 128.0
No log 35.0 140 0.1436 97.4345 128.0
No log 36.0 144 0.1431 97.4345 128.0
No log 37.0 148 0.1432 97.4345 128.0
No log 38.0 152 0.1433 97.4345 128.0
No log 39.0 156 0.1434 97.4345 128.0
No log 40.0 160 0.1434 97.4345 128.0
No log 41.0 164 0.1432 97.4345 128.0
No log 42.0 168 0.1436 97.4345 128.0
No log 43.0 172 0.1437 97.4345 128.0
No log 44.0 176 0.1439 97.4345 128.0
No log 45.0 180 0.1443 97.4345 128.0
No log 46.0 184 0.1454 97.4345 128.0
No log 47.0 188 0.1477 97.4345 128.0
No log 48.0 192 0.1492 97.4345 128.0
No log 49.0 196 0.1504 97.4345 128.0
No log 50.0 200 0.1513 97.4345 128.0
No log 51.0 204 0.1517 97.4345 128.0
No log 52.0 208 0.1519 97.4345 128.0
No log 53.0 212 0.1520 97.4345 128.0
No log 54.0 216 0.1522 97.4345 128.0
No log 55.0 220 0.1523 97.4345 128.0
No log 56.0 224 0.1523 97.4345 128.0
No log 57.0 228 0.1523 97.4345 128.0
No log 58.0 232 0.1525 97.4345 128.0
No log 59.0 236 0.1526 97.4345 128.0
No log 60.0 240 0.1530 97.4345 128.0
No log 61.0 244 0.1533 97.4345 128.0
No log 62.0 248 0.1536 97.4345 128.0
No log 63.0 252 0.1564 97.4345 128.0
No log 64.0 256 0.1582 97.4345 128.0
No log 65.0 260 0.1589 97.4345 128.0
No log 66.0 264 0.1593 97.4345 128.0
No log 67.0 268 0.1596 97.4345 128.0
No log 68.0 272 0.1597 97.4345 128.0
No log 69.0 276 0.1592 97.4345 128.0
No log 70.0 280 0.1588 97.4345 128.0
No log 71.0 284 0.1592 97.4345 128.0
No log 72.0 288 0.1594 97.4345 128.0
No log 73.0 292 0.1595 97.4345 128.0
No log 74.0 296 0.1597 97.4345 128.0
No log 75.0 300 0.1599 97.4345 128.0
No log 76.0 304 0.1600 97.4345 128.0
No log 77.0 308 0.1603 97.4345 128.0
No log 78.0 312 0.1605 97.4345 128.0
No log 79.0 316 0.1606 97.4345 128.0
No log 80.0 320 0.1608 97.4345 128.0
No log 81.0 324 0.1609 97.4345 128.0
No log 82.0 328 0.1608 97.4345 128.0
No log 83.0 332 0.1608 97.4345 128.0
No log 84.0 336 0.1596 97.4345 128.0
No log 85.0 340 0.1584 97.4345 128.0
No log 86.0 344 0.1576 97.4345 128.0
No log 87.0 348 0.1570 97.4345 128.0
No log 88.0 352 0.1594 97.4345 128.0
No log 89.0 356 0.1611 97.4345 128.0
No log 90.0 360 0.1624 97.4345 128.0
No log 91.0 364 0.1631 97.4345 128.0
No log 92.0 368 0.1636 97.4345 128.0
No log 93.0 372 0.1640 97.4345 128.0
No log 94.0 376 0.1642 97.4345 128.0
No log 95.0 380 0.1644 97.4345 128.0
No log 96.0 384 0.1646 97.4345 128.0
No log 97.0 388 0.1649 97.4345 128.0
No log 98.0 392 0.1650 97.4345 128.0
No log 99.0 396 0.1652 97.4345 128.0
No log 100.0 400 0.1652 97.4345 128.0
No log 101.0 404 0.1652 97.4345 128.0
No log 102.0 408 0.1666 97.4345 128.0
No log 103.0 412 0.1674 97.4345 128.0
No log 104.0 416 0.1677 97.4345 128.0
No log 105.0 420 0.1678 97.4345 128.0
No log 106.0 424 0.1678 97.4345 128.0
No log 107.0 428 0.1678 97.4345 128.0
No log 108.0 432 0.1677 97.4345 128.0
No log 109.0 436 0.1676 97.4345 128.0
No log 110.0 440 0.1674 97.4345 128.0
No log 111.0 444 0.1672 97.4345 128.0
No log 112.0 448 0.1672 97.4345 128.0
No log 113.0 452 0.1665 97.4345 128.0
No log 114.0 456 0.1650 97.4345 128.0
No log 115.0 460 0.1622 97.4345 128.0
No log 116.0 464 0.1602 97.4345 128.0
No log 117.0 468 0.1589 97.4345 128.0
No log 118.0 472 0.1580 97.4345 128.0
No log 119.0 476 0.1575 97.4345 128.0
No log 120.0 480 0.1572 97.4345 128.0
No log 121.0 484 0.1572 97.4345 128.0
No log 122.0 488 0.1571 97.4345 128.0
No log 123.0 492 0.1572 97.4345 128.0
No log 124.0 496 0.1571 97.4345 128.0
0.001 125.0 500 0.1572 97.4345 128.0
0.001 126.0 504 0.1572 97.4345 128.0
0.001 127.0 508 0.1571 97.4345 128.0
0.001 128.0 512 0.1571 97.4345 128.0
0.001 129.0 516 0.1577 97.4345 128.0
0.001 130.0 520 0.1581 97.4345 128.0
0.001 131.0 524 0.1590 97.4345 128.0
0.001 132.0 528 0.1595 97.4345 128.0
0.001 133.0 532 0.1599 97.4345 128.0
0.001 134.0 536 0.1602 97.4345 128.0
0.001 135.0 540 0.1603 97.4345 128.0
0.001 136.0 544 0.1603 97.4345 128.0
0.001 137.0 548 0.1605 97.4345 128.0
0.001 138.0 552 0.1605 97.4345 128.0
0.001 139.0 556 0.1605 97.4345 128.0
0.001 140.0 560 0.1606 97.4345 128.0
0.001 141.0 564 0.1606 97.4345 128.0
0.001 142.0 568 0.1606 97.4345 128.0
0.001 143.0 572 0.1607 97.4345 128.0
0.001 144.0 576 0.1606 97.4345 128.0
0.001 145.0 580 0.1607 97.4345 128.0
0.001 146.0 584 0.1606 97.4345 128.0
0.001 147.0 588 0.1607 97.4345 128.0
0.001 148.0 592 0.1606 97.4345 128.0
0.001 149.0 596 0.1607 97.4345 128.0
0.001 150.0 600 0.1607 97.4345 128.0

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.6.0+cu124
  • Datasets 2.14.4
  • Tokenizers 0.20.3
Downloads last month
7
Safetensors
Model size
60.5M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for fatimaMb/custom_ABB_KUKA_model

Base model

google-t5/t5-small
Finetuned
(2339)
this model