SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

NER - pl example (#3180)

Browse Source 
* 1. seqeval required by ner pl example. install from examples/requirements. 2. unrecognized arguments: save_steps

* pl checkpoint callback filenotfound error: make directory and pass

* #3159 pl checkpoint path difference

* 1. Updated Readme for pl 2. pl script now also correct displays logs 3. pass gpu ids compared to number of gpus

* Updated results in readme

* 1. updated readme 2. removing deprecated pl methods 3. finalizing scripts

* comment length check

* using deprecated validation_end for stable results

* style related changes
This commit is contained in:
Shubham Agarwal
2020-03-10 00:43:38 +00:00
committed by GitHub
parent f51ba059b9
commit 5ca356a464
3 changed files with 34 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/ner/README.md
View File

@@ -112,6 +112,13 @@ Here is a small comparison between BERT (large, cased), RoBERTa (large, cased) a
| `roberta-large` | 95.96 | 91.87
| `distilbert-base-uncased` | 94.34 | 90.32
#### Run PyTorch version using PyTorch-Lightning
Run `bash run_pl.sh` from the `ner` directory. This would also install `pytorch-lightning` and the `examples/requirements.txt`. It is a shell pipeline which would automatically download, pre-process the data and run the models in `germeval-model` directory. Logs are saved in `lightning_logs` directory.
Pass `--n_gpu` flag to change the number of GPUs. Default uses 1. At the end, the expected results are: `TEST RESULTS {'val_loss': tensor(0.0707), 'precision': 0.852427800698191, 'recall': 0.869537067011978, 'f1': 0.8608974358974358}`
### Run the Tensorflow 2 version
To start training, just run: