Hugging Face's logo

andreaschandra
/
unifiedqa-v2-t5-base-1363200-finetuned-causalqa-squad

Text2Text Generation
Transformers
PyTorch
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
1
unifiedqa-v2-t5-base-1363200-finetuned-causalqa-squad / README.md
andreaschandra's picture
andreaschandra
update model card README.md
4ccc9e0
preview code
|
raw
history blame contribute delete
6.44 kB
metadata
tags:
  - generated_from_trainer
model-index:
  - name: unifiedqa-v2-t5-base-1363200-finetuned-causalqa-squad
    results: []

unifiedqa-v2-t5-base-1363200-finetuned-causalqa-squad

This model is a fine-tuned version of allenai/unifiedqa-v2-t5-base-1363200 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2574

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: 5e-05
  • 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: 5

Training results

Training Loss Epoch Step Validation Loss
0.7378 0.05 73 1.1837
0.6984 0.1 146 0.8918
0.4511 0.15 219 0.8342
0.4696 0.2 292 0.7642
0.295 0.25 365 0.7996
0.266 0.3 438 0.7773
0.2372 0.35 511 0.8592
0.2881 0.39 584 0.8440
0.2578 0.44 657 0.8306
0.2733 0.49 730 0.8228
0.2073 0.54 803 0.8419
0.2683 0.59 876 0.8241
0.2693 0.64 949 0.8573
0.355 0.69 1022 0.8204
0.2246 0.74 1095 0.8530
0.2468 0.79 1168 0.8410
0.3102 0.84 1241 0.8035
0.2115 0.89 1314 0.8262
0.1855 0.94 1387 0.8560
0.1772 0.99 1460 0.8747
0.1509 1.04 1533 0.9132
0.1871 1.09 1606 0.8920
0.1624 1.14 1679 0.9085
0.1404 1.18 1752 0.9460
0.1639 1.23 1825 0.9812
0.0983 1.28 1898 0.9790
0.1395 1.33 1971 0.9843
0.1439 1.38 2044 0.9877
0.1397 1.43 2117 1.0338
0.1095 1.48 2190 1.0589
0.1228 1.53 2263 1.0498
0.1246 1.58 2336 1.0923
0.1438 1.63 2409 1.0995
0.1305 1.68 2482 1.0867
0.1077 1.73 2555 1.1013
0.2104 1.78 2628 1.0765
0.1633 1.83 2701 1.0796
0.1658 1.88 2774 1.0314
0.1358 1.92 2847 0.9823
0.1571 1.97 2920 0.9826
0.1127 2.02 2993 1.0324
0.0927 2.07 3066 1.0679
0.0549 2.12 3139 1.1069
0.0683 2.17 3212 1.1624
0.0677 2.22 3285 1.1174
0.0615 2.27 3358 1.1431
0.0881 2.32 3431 1.1721
0.0807 2.37 3504 1.1885
0.0955 2.42 3577 1.1991
0.0779 2.47 3650 1.1999
0.11 2.52 3723 1.1774
0.0852 2.57 3796 1.2095
0.0616 2.62 3869 1.1824
0.072 2.67 3942 1.2397
0.1055 2.71 4015 1.2181
0.0806 2.76 4088 1.2159
0.0684 2.81 4161 1.1864
0.0869 2.86 4234 1.1816
0.1023 2.91 4307 1.1717
0.0583 2.96 4380 1.1477
0.0684 3.01 4453 1.1662
0.0319 3.06 4526 1.2174
0.0609 3.11 4599 1.1947
0.0435 3.16 4672 1.1821
0.0417 3.21 4745 1.1964
0.0502 3.26 4818 1.2140
0.0844 3.31 4891 1.2028
0.0692 3.36 4964 1.2215
0.0366 3.41 5037 1.2136
0.0615 3.46 5110 1.2224
0.0656 3.5 5183 1.2468
0.0469 3.55 5256 1.2554
0.0475 3.6 5329 1.2804
0.0998 3.65 5402 1.2035
0.0505 3.7 5475 1.2095
0.0459 3.75 5548 1.2064
0.0256 3.8 5621 1.2164
0.0831 3.85 5694 1.2154
0.0397 3.9 5767 1.2126
0.0449 3.95 5840 1.2174
0.0322 4.0 5913 1.2288
0.059 4.05 5986 1.2274
0.0382 4.1 6059 1.2228
0.0202 4.15 6132 1.2177
0.0328 4.2 6205 1.2305
0.0407 4.24 6278 1.2342
0.0356 4.29 6351 1.2448
0.0414 4.34 6424 1.2537
0.0448 4.39 6497 1.2540
0.0545 4.44 6570 1.2552
0.0492 4.49 6643 1.2570
0.0293 4.54 6716 1.2594
0.0498 4.59 6789 1.2562
0.0349 4.64 6862 1.2567
0.0497 4.69 6935 1.2550
0.0194 4.74 7008 1.2605
0.0255 4.79 7081 1.2590
0.0212 4.84 7154 1.2571
0.0231 4.89 7227 1.2583
0.0399 4.94 7300 1.2580
0.0719 4.99 7373 1.2574

Framework versions

  • Transformers 4.24.0
  • Pytorch 1.12.1+cu113
  • Datasets 2.7.0
  • Tokenizers 0.13.2