Hugging Face's logo

vichyt
/
codet5p-770m-py-sanitized-codebleu-1-True-5e-05-0.1-lora-layer_9

Generated from Trainer
Model card Files Community
codet5p-770m-py-sanitized-codebleu-1-True-5e-05-0.1-lora-layer_9 / README.md
vichyt's picture
vichyt
update model card README.md
6b81836
preview code
|
raw history blame
No virus
11.7 kB
metadata
license: bsd-3-clause
base_model: Salesforce/codet5p-770m-py
tags:
  - generated_from_trainer
datasets:
  - mbpp
model-index:
  - name: codet5p-770m-py-sanitized-codebleu-1-True-5e-05-0.1-lora-layer_9
    results: []

codet5p-770m-py-sanitized-codebleu-1-True-5e-05-0.1-lora-layer_9

This model is a fine-tuned version of Salesforce/codet5p-770m-py on the mbpp dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7314
  • Codebleu: 0.1102
  • Ngram Match Score: 0.0199
  • Weighted Ngram Match Score: 0.0416
  • Syntax Match Score: 0.1296
  • Dataflow Match Score: 0.1305

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 64

Training results

Training Loss Epoch Step Validation Loss Codebleu Ngram Match Score Weighted Ngram Match Score Syntax Match Score Dataflow Match Score
0.9846 1.0 15 0.9244 0.0072 0.0000 0.0000 0.0079 0.0100
0.9657 2.0 30 0.9227 0.0072 0.0000 0.0000 0.0079 0.0100
0.9697 3.0 45 0.9188 0.0080 0.0000 0.0000 0.0079 0.0120
0.9408 4.0 60 0.9100 0.0080 0.0000 0.0000 0.0079 0.0120
0.9463 5.0 75 0.8926 0.0386 0.0004 0.0207 0.0370 0.0542
0.9393 6.0 90 0.8669 0.0729 0.0083 0.0317 0.0820 0.0904
0.9176 7.0 105 0.8475 0.1012 0.0187 0.0481 0.1177 0.1185
0.8691 8.0 120 0.8337 0.1005 0.0185 0.0500 0.1217 0.1124
0.8468 9.0 135 0.8223 0.0984 0.0111 0.0331 0.1204 0.1145
0.8444 10.0 150 0.8119 0.1023 0.0100 0.0307 0.1230 0.1225
0.8293 11.0 165 0.8013 0.1010 0.0096 0.0318 0.1257 0.1165
0.8248 12.0 180 0.7905 0.1003 0.0101 0.0321 0.1217 0.1185
0.8103 13.0 195 0.7838 0.1017 0.0106 0.0323 0.1230 0.1205
0.7907 14.0 210 0.7778 0.1050 0.0109 0.0328 0.1270 0.1245
0.8004 15.0 225 0.7735 0.1066 0.0123 0.0369 0.1296 0.1245
0.7995 16.0 240 0.7694 0.1029 0.0114 0.0353 0.1230 0.1225
0.7906 17.0 255 0.7662 0.1010 0.0105 0.0329 0.1190 0.1225
0.766 18.0 270 0.7626 0.0976 0.0104 0.0313 0.1151 0.1185
0.7761 19.0 285 0.7592 0.0984 0.0105 0.0313 0.1190 0.1165
0.7647 20.0 300 0.7564 0.0941 0.0102 0.0310 0.1124 0.1124
0.7511 21.0 315 0.7532 0.1006 0.0126 0.0328 0.1177 0.1225
0.755 22.0 330 0.7510 0.0950 0.0116 0.0306 0.1124 0.1145
0.7491 23.0 345 0.7501 0.0963 0.0120 0.0303 0.1138 0.1165
0.7467 24.0 360 0.7485 0.1038 0.0133 0.0319 0.1296 0.1185
0.7709 25.0 375 0.7460 0.1038 0.0134 0.0319 0.1296 0.1185
0.7397 26.0 390 0.7445 0.1130 0.0175 0.0408 0.1415 0.1265
0.7266 27.0 405 0.7434 0.1131 0.0176 0.0408 0.1415 0.1265
0.7362 28.0 420 0.7420 0.1125 0.0176 0.0404 0.1402 0.1265
0.7254 29.0 435 0.7418 0.1125 0.0176 0.0404 0.1402 0.1265
0.722 30.0 450 0.7413 0.1151 0.0176 0.0403 0.1429 0.1305
0.7253 31.0 465 0.7406 0.1194 0.0184 0.0417 0.1468 0.1365
0.7271 32.0 480 0.7392 0.1194 0.0184 0.0417 0.1468 0.1365
0.7187 33.0 495 0.7382 0.1186 0.0184 0.0418 0.1468 0.1345
0.7253 34.0 510 0.7375 0.1193 0.0192 0.0433 0.1481 0.1345
0.6948 35.0 525 0.7367 0.1205 0.0212 0.0451 0.1481 0.1365
0.7327 36.0 540 0.7361 0.1212 0.0207 0.0449 0.1481 0.1386
0.7205 37.0 555 0.7357 0.1205 0.0212 0.0451 0.1481 0.1365
0.718 38.0 570 0.7356 0.1202 0.0203 0.0434 0.1481 0.1365
0.7128 39.0 585 0.7353 0.1202 0.0203 0.0434 0.1481 0.1365
0.7159 40.0 600 0.7350 0.1171 0.0204 0.0433 0.1442 0.1325
0.7016 41.0 615 0.7346 0.1171 0.0204 0.0433 0.1442 0.1325
0.7003 42.0 630 0.7343 0.1171 0.0204 0.0433 0.1442 0.1325
0.7018 43.0 645 0.7341 0.1171 0.0204 0.0433 0.1442 0.1325
0.7105 44.0 660 0.7346 0.1171 0.0204 0.0433 0.1442 0.1325
0.7084 45.0 675 0.7345 0.1133 0.0203 0.0432 0.1349 0.1325
0.6965 46.0 690 0.7342 0.1137 0.0203 0.0418 0.1323 0.1365
0.7062 47.0 705 0.7339 0.1137 0.0203 0.0418 0.1323 0.1365
0.6993 48.0 720 0.7339 0.1137 0.0203 0.0418 0.1323 0.1365
0.7039 49.0 735 0.7337 0.1111 0.0203 0.0420 0.1296 0.1325
0.6941 50.0 750 0.7335 0.1155 0.0199 0.0417 0.1389 0.1345
0.7144 51.0 765 0.7329 0.1110 0.0198 0.0417 0.1296 0.1325
0.7027 52.0 780 0.7325 0.1110 0.0198 0.0417 0.1296 0.1325
0.7042 53.0 795 0.7318 0.1110 0.0198 0.0417 0.1296 0.1325
0.6756 54.0 810 0.7314 0.1110 0.0198 0.0417 0.1296 0.1325
0.6979 55.0 825 0.7311 0.1110 0.0198 0.0417 0.1296 0.1325
0.7013 56.0 840 0.7314 0.1110 0.0198 0.0417 0.1296 0.1325
0.7 57.0 855 0.7313 0.1110 0.0198 0.0417 0.1296 0.1325
0.6918 58.0 870 0.7313 0.1110 0.0198 0.0417 0.1296 0.1325
0.7043 59.0 885 0.7312 0.1110 0.0198 0.0417 0.1296 0.1325
0.6889 60.0 900 0.7313 0.1110 0.0198 0.0417 0.1296 0.1325
0.7044 61.0 915 0.7314 0.1110 0.0198 0.0417 0.1296 0.1325
0.6901 62.0 930 0.7314 0.1102 0.0199 0.0416 0.1296 0.1305
0.6919 63.0 945 0.7313 0.1102 0.0199 0.0416 0.1296 0.1305
0.686 64.0 960 0.7314 0.1102 0.0199 0.0416 0.1296 0.1305

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1
  • Datasets 2.14.4
  • Tokenizers 0.13.3