pip install simpletransformers pip uninstall torch, then run latest install script from pytorch.org
environment variables:
$ PORCH_N=100_000 PORCH_CUDA=True python bmark_distil.py
Last active
October 20, 2022 00:33
-
-
Save nro-bot/90789bdeb699069460f19ccbd54357e7 to your computer and use it in GitHub Desktop.
benchmark_distilbert_simpletransformers
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| ########## | |
| # Part 1 # | |
| ########## | |
| import pandas as pd | |
| prefix = 'data/' | |
| train_df = pd.read_csv(prefix + 'train.csv', header=None) | |
| train_df.head() | |
| eval_df = pd.read_csv(prefix + 'test.csv', header=None) | |
| eval_df.head() | |
| train_df[0] = (train_df[0] == 2).astype(int) | |
| eval_df[0] = (eval_df[0] == 2).astype(int) | |
| train_df = pd.DataFrame({ | |
| 'text': train_df[1].replace(r'\n', ' ', regex=True), | |
| 'label':train_df[0] | |
| }) | |
| #print(train_df.head()) | |
| eval_df = pd.DataFrame({ | |
| 'text': eval_df[1].replace(r'\n', ' ', regex=True), | |
| 'label':eval_df[0] | |
| }) | |
| #print(eval_df.head()) | |
| ########## | |
| # Part 2 # | |
| ########## | |
| from simpletransformers.classification import ClassificationArgs, ClassificationModel | |
| import os | |
| os.environ["TOKENIZERS_PARALLELISM"] = "false" | |
| model_args = ClassificationArgs( | |
| use_multiprocessing=False, | |
| use_multiprocessing_for_evaluation=False, | |
| overwrite_output_dir=True, | |
| ) | |
| use_cuda = bool(os.environ.get('PORCH_CUDA', False)) | |
| n = int(os.environ.get('PORCH_N', '10_000')) | |
| print(f"{n=} {use_cuda=}") | |
| model = ClassificationModel( | |
| "distilbert", "distilbert-base-uncased", | |
| use_cuda=use_cuda, | |
| args=model_args | |
| ) | |
| #model = ClassificationModel('roberta', 'roberta-base', args=model_args) | |
| # Train the model | |
| model.train_model(train_df.sample(n=n)) | |
| # Evaluate the model | |
| #result, model_outputs, wrong_predictions = model.eval_model(eval_df) | |
| # CPU: 1.35 it/s using 6 cores @ 2.6 GHz | |
| # n=10_000: CUDA 3.28 it/s; 768 CUDA cores @ 1.5 GHz | |
| # a = core-cycles / sec | |
| # b = iter / sec | |
| # | |
| # want: core-cycles / iter | |
| # cores * clock_rate / (iter / sec) | |
| # CPU: 11.6 giga core-cycles / iter | |
| # GPU: 351 giga core-cycles / iter |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment