Hugging Face's logo

vichyt
/
codet5p-770m-py-sanitized-codebleu-1-True-5e-05-0.1-lora-layer_8

Generated from Trainer
Model card Files Community
codet5p-770m-py-sanitized-codebleu-1-True-5e-05-0.1-lora-layer_8 / README.md
vichyt's picture
vichyt
update model card README.md
3c8c587
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_8
    results: []

codet5p-770m-py-sanitized-codebleu-1-True-5e-05-0.1-lora-layer_8

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: 0.7279
  • Codebleu: 0.1015
  • Ngram Match Score: 0.0151
  • Weighted Ngram Match Score: 0.0370
  • Syntax Match Score: 0.1243
  • Dataflow Match Score: 0.1165

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
0.9839 1.0 15 0.9244 0.0072 0.0000 0.0000 0.0079 0.0100
0.964 2.0 30 0.9227 0.0072 0.0000 0.0000 0.0079 0.0100
0.9714 3.0 45 0.9186 0.0080 0.0000 0.0000 0.0079 0.0120
0.942 4.0 60 0.9095 0.0096 0.0000 0.0001 0.0079 0.0161
0.9486 5.0 75 0.8923 0.0440 0.0013 0.0232 0.0397 0.0643
0.9432 6.0 90 0.8695 0.0861 0.0134 0.0388 0.1019 0.1004
0.9245 7.0 105 0.8532 0.1013 0.0182 0.0479 0.1204 0.1165
0.8732 8.0 120 0.8415 0.1006 0.0210 0.0506 0.1190 0.1145
0.8547 9.0 135 0.8311 0.1057 0.0195 0.0508 0.1283 0.1185
0.8553 10.0 150 0.8204 0.1054 0.0133 0.0380 0.1283 0.1225
0.846 11.0 165 0.8089 0.1024 0.0112 0.0339 0.1243 0.1205
0.8412 12.0 180 0.7983 0.0967 0.0098 0.0337 0.1204 0.1104
0.8242 13.0 195 0.7914 0.0965 0.0109 0.0337 0.1177 0.1124
0.8013 14.0 210 0.7851 0.0972 0.0108 0.0355 0.1151 0.1165
0.8161 15.0 225 0.7800 0.0994 0.0120 0.0369 0.1177 0.1185
0.8169 16.0 240 0.7751 0.1013 0.0125 0.0369 0.1204 0.1205
0.8037 17.0 255 0.7708 0.0970 0.0116 0.0347 0.1164 0.1145
0.7783 18.0 270 0.7663 0.0992 0.0129 0.0368 0.1190 0.1165
0.7915 19.0 285 0.7622 0.0958 0.0141 0.0366 0.1085 0.1185
0.7733 20.0 300 0.7578 0.0942 0.0150 0.0430 0.1085 0.1124
0.763 21.0 315 0.7542 0.0942 0.0150 0.0430 0.1085 0.1124
0.7627 22.0 330 0.7511 0.0941 0.0147 0.0429 0.1085 0.1124
0.759 23.0 345 0.7490 0.0976 0.0153 0.0451 0.1124 0.1165
0.7555 24.0 360 0.7471 0.0976 0.0152 0.0453 0.1124 0.1165
0.7834 25.0 375 0.7447 0.1033 0.0168 0.0452 0.1204 0.1225
0.7438 26.0 390 0.7429 0.1011 0.0148 0.0409 0.1204 0.1185
0.7364 27.0 405 0.7412 0.0963 0.0133 0.0368 0.1138 0.1145
0.7408 28.0 420 0.7401 0.1055 0.0160 0.0410 0.1270 0.1225
0.7302 29.0 435 0.7393 0.0996 0.0146 0.0369 0.1177 0.1185
0.7245 30.0 450 0.7388 0.0982 0.0153 0.0383 0.1177 0.1145
0.7263 31.0 465 0.7376 0.0985 0.0157 0.0384 0.1204 0.1124
0.7294 32.0 480 0.7360 0.0976 0.0150 0.0381 0.1204 0.1104
0.7216 33.0 495 0.7349 0.0975 0.0158 0.0384 0.1177 0.1124
0.7317 34.0 510 0.7340 0.0975 0.0158 0.0384 0.1177 0.1124
0.7035 35.0 525 0.7337 0.0966 0.0152 0.0381 0.1177 0.1104
0.7316 36.0 540 0.7335 0.0966 0.0152 0.0381 0.1177 0.1104
0.7181 37.0 555 0.7330 0.0963 0.0143 0.0363 0.1177 0.1104
0.7204 38.0 570 0.7330 0.0963 0.0143 0.0363 0.1177 0.1104
0.7109 39.0 585 0.7324 0.0974 0.0142 0.0363 0.1204 0.1104
0.7226 40.0 600 0.7321 0.0974 0.0142 0.0363 0.1204 0.1104
0.703 41.0 615 0.7319 0.0976 0.0151 0.0381 0.1204 0.1104
0.7036 42.0 630 0.7312 0.0976 0.0151 0.0381 0.1204 0.1104
0.7039 43.0 645 0.7312 0.0993 0.0153 0.0384 0.1204 0.1145
0.709 44.0 660 0.7309 0.1002 0.0159 0.0387 0.1204 0.1165
0.7077 45.0 675 0.7308 0.0999 0.0147 0.0369 0.1204 0.1165
0.7035 46.0 690 0.7303 0.0999 0.0147 0.0369 0.1204 0.1165
0.7046 47.0 705 0.7299 0.0999 0.0147 0.0369 0.1204 0.1165
0.7034 48.0 720 0.7298 0.0999 0.0147 0.0369 0.1204 0.1165
0.7025 49.0 735 0.7296 0.0991 0.0146 0.0366 0.1204 0.1145
0.691 50.0 750 0.7297 0.1007 0.0146 0.0366 0.1204 0.1185
0.7124 51.0 765 0.7297 0.1004 0.0146 0.0367 0.1217 0.1165
0.709 52.0 780 0.7293 0.1004 0.0146 0.0367 0.1217 0.1165
0.7056 53.0 795 0.7288 0.1004 0.0146 0.0367 0.1217 0.1165
0.6742 54.0 810 0.7286 0.1004 0.0146 0.0367 0.1217 0.1165
0.7027 55.0 825 0.7282 0.1004 0.0146 0.0367 0.1217 0.1165
0.7 56.0 840 0.7283 0.1004 0.0148 0.0367 0.1217 0.1165
0.7074 57.0 855 0.7282 0.1015 0.0151 0.0370 0.1243 0.1165
0.6869 58.0 870 0.7280 0.1004 0.0148 0.0367 0.1217 0.1165
0.7054 59.0 885 0.7280 0.1015 0.0151 0.0370 0.1243 0.1165
0.6902 60.0 900 0.7280 0.1004 0.0148 0.0367 0.1217 0.1165
0.7107 61.0 915 0.7280 0.1015 0.0151 0.0370 0.1243 0.1165
0.6963 62.0 930 0.7280 0.1015 0.0151 0.0370 0.1243 0.1165
0.6958 63.0 945 0.7279 0.1015 0.0151 0.0370 0.1243 0.1165
0.6883 64.0 960 0.7279 0.1015 0.0151 0.0370 0.1243 0.1165

Framework versions

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