Text Classification
Transformers
PyTorch
Safetensors
English
bert
wnli
glue
kd
torchdistill
text-embeddings-inference
Instructions to use yoshitomo-matsubara/bert-base-uncased-wnli_from_bert-large-uncased-wnli with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yoshitomo-matsubara/bert-base-uncased-wnli_from_bert-large-uncased-wnli with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="yoshitomo-matsubara/bert-base-uncased-wnli_from_bert-large-uncased-wnli")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("yoshitomo-matsubara/bert-base-uncased-wnli_from_bert-large-uncased-wnli") model = AutoModelForSequenceClassification.from_pretrained("yoshitomo-matsubara/bert-base-uncased-wnli_from_bert-large-uncased-wnli", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training.log from yoshitomo-matsubara/bert-base-uncased-wnli_from_bert-large-uncased-wnli: direct link, hf CLI and curl.
- Browser
- Download file 4.95 kB
-
https://huggingface.co/yoshitomo-matsubara/bert-base-uncased-wnli_from_bert-large-uncased-wnli/resolve/main/training.log
- Command line
-
hf download hf://yoshitomo-matsubara/bert-base-uncased-wnli_from_bert-large-uncased-wnli/training.log
-
curl -L -o training.log https://huggingface.co/yoshitomo-matsubara/bert-base-uncased-wnli_from_bert-large-uncased-wnli/resolve/main/training.log
4.95 kB
| 2021-05-31 18:22:29,298 INFO __main__ Namespace(adjust_lr=False, config='torchdistill/configs/sample/glue/wnli/kd/bert_base_uncased_from_bert_large_uncased.yaml', log='log/glue/wnli/kd/bert_base_uncased_from_bert_large_uncased.txt', private_output='leaderboard/glue/kd/bert_base_uncased_from_bert_large_uncased/', seed=None, student_only=False, task_name='wnli', test_only=False, world_size=1) | |
| 2021-05-31 18:22:29,328 INFO __main__ Distributed environment: NO | |
| Num processes: 1 | |
| Process index: 0 | |
| Local process index: 0 | |
| Device: cuda | |
| Use FP16 precision: True | |
| 2021-05-31 18:22:39,133 WARNING datasets.builder Reusing dataset glue (/root/.cache/huggingface/datasets/glue/wnli/1.0.0/dacbe3125aa31d7f70367a07a8a9e72a5a0bfeb5fc42e75c9db75b96da6053ad) | |
| 2021-05-31 18:22:39,753 INFO __main__ Start training | |
| 2021-05-31 18:22:39,753 INFO torchdistill.models.util | |
| 2021-05-31 18:22:39,754 INFO torchdistill.models.util Using the original teacher model | |
| 2021-05-31 18:22:39,754 INFO torchdistill.models.util | |
| 2021-05-31 18:22:39,754 INFO torchdistill.models.util Using the original student model | |
| 2021-05-31 18:22:39,754 INFO torchdistill.core.distillation Loss = 1.0 * OrgLoss | |
| 2021-05-31 18:22:39,754 INFO torchdistill.core.distillation Freezing the whole teacher model | |
| 2021-05-31 18:22:43,520 INFO torchdistill.misc.log Epoch: | |
| 2021-05-31 18:23:41,729 INFO /usr/local/lib/python3.7/dist-packages/datasets/metric.py Removing /root/.cache/huggingface/metrics/glue/wnli/default_experiment-1-0.arrow | |
| 2021-05-31 18:23:41,729 INFO __main__ Test: accuracy = 0.5633802816901409 | |
| 2021-05-31 18:23:44,813 INFO __main__ | |
| 2021-05-31 18:23:45,056 INFO /usr/local/lib/python3.7/dist-packages/datasets/metric.py Removing /root/.cache/huggingface/metrics/glue/wnli/default_experiment-1-0.arrow | |
| 2021-05-31 18:23:45,056 INFO __main__ Test: accuracy = 0.5774647887323944 | |
| 2021-05-31 18:23:45,056 INFO __main__ Start prediction for private dataset(s) | |
| 2021-05-31 18:23:45,057 INFO __main__ wnli/test: 146 samples | |