my_awesome_t5 / README.md
Patcas's picture
End of training
d008c37
|
raw
history blame
3.84 kB
metadata
license: apache-2.0
base_model: Salesforce/codet5-base
tags:
  - generated_from_trainer
model-index:
  - name: my_awesome_t5
    results: []

my_awesome_t5

This model is a fine-tuned version of Salesforce/codet5-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2171

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: 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: 50

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 230 1.2051
No log 2.0 460 1.1370
0.6555 3.0 690 1.0823
0.6555 4.0 920 1.0613
0.6297 5.0 1150 1.0527
0.6297 6.0 1380 1.0374
0.5191 7.0 1610 1.0325
0.5191 8.0 1840 1.0476
0.3767 9.0 2070 1.0445
0.3767 10.0 2300 1.0559
0.3019 11.0 2530 1.0426
0.3019 12.0 2760 1.0470
0.3019 13.0 2990 1.0517
0.2442 14.0 3220 1.0504
0.2442 15.0 3450 1.0704
0.2052 16.0 3680 1.0704
0.2052 17.0 3910 1.0751
0.1635 18.0 4140 1.0692
0.1635 19.0 4370 1.1003
0.1434 20.0 4600 1.0987
0.1434 21.0 4830 1.1031
0.1245 22.0 5060 1.1043
0.1245 23.0 5290 1.1033
0.1124 24.0 5520 1.1323
0.1124 25.0 5750 1.1335
0.1124 26.0 5980 1.1224
0.1033 27.0 6210 1.1446
0.1033 28.0 6440 1.1607
0.0816 29.0 6670 1.1571
0.0816 30.0 6900 1.1723
0.0783 31.0 7130 1.1534
0.0783 32.0 7360 1.1756
0.0704 33.0 7590 1.1762
0.0704 34.0 7820 1.1752
0.0635 35.0 8050 1.1784
0.0635 36.0 8280 1.1868
0.0564 37.0 8510 1.1890
0.0564 38.0 8740 1.1972
0.0564 39.0 8970 1.2013
0.0524 40.0 9200 1.1970
0.0524 41.0 9430 1.2033
0.0503 42.0 9660 1.2091
0.0503 43.0 9890 1.2124
0.048 44.0 10120 1.2094
0.048 45.0 10350 1.2155
0.0405 46.0 10580 1.2146
0.0405 47.0 10810 1.2163
0.0457 48.0 11040 1.2156
0.0457 49.0 11270 1.2167
0.0407 50.0 11500 1.2171

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.0
  • Tokenizers 0.15.0