julien-c HF staff commited on
Commit
52ecf84
1 Parent(s): 094a409

Migrate model card from transformers-repo

Browse files

Read announcement at https://discuss.huggingface.co/t/announcement-all-model-cards-will-be-migrated-to-hf-co-model-repos/2755
Original file history: https://github.com/huggingface/transformers/commits/master/model_cards/twmkn9/bert-base-uncased-squad2/README.md

Files changed (1) hide show
  1. README.md +45 -0
README.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ This model is [BERT base uncased](https://huggingface.co/bert-base-uncased) trained on SQuAD v2 as:
2
+
3
+ ```
4
+ export SQUAD_DIR=../../squad2
5
+ python3 run_squad.py
6
+ --model_type bert
7
+ --model_name_or_path bert-base-uncased
8
+ --do_train
9
+ --do_eval
10
+ --overwrite_cache
11
+ --do_lower_case
12
+ --version_2_with_negative
13
+ --save_steps 100000
14
+ --train_file $SQUAD_DIR/train-v2.0.json
15
+ --predict_file $SQUAD_DIR/dev-v2.0.json
16
+ --per_gpu_train_batch_size 8
17
+ --num_train_epochs 3
18
+ --learning_rate 3e-5
19
+ --max_seq_length 384
20
+ --doc_stride 128
21
+ --output_dir ./tmp/bert_fine_tuned/
22
+ ```
23
+
24
+ Performance on a dev subset is close to the original paper:
25
+
26
+ ```
27
+ Results:
28
+ {
29
+ 'exact': 72.35932872655479,
30
+ 'f1': 75.75355132564763,
31
+ 'total': 6078,
32
+ 'HasAns_exact': 74.29553264604812,
33
+ 'HasAns_f1': 81.38490892002987,
34
+ 'HasAns_total': 2910,
35
+ 'NoAns_exact': 70.58080808080808,
36
+ 'NoAns_f1': 70.58080808080808,
37
+ 'NoAns_total': 3168,
38
+ 'best_exact': 72.35932872655479,
39
+ 'best_exact_thresh': 0.0,
40
+ 'best_f1': 75.75355132564766,
41
+ 'best_f1_thresh': 0.0
42
+ }
43
+ ```
44
+
45
+ We are hopeful this might save you time, energy, and compute. Cheers!