riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 33 Packages Projects Releases Wiki Activity

Updated/added model cards (#3435)

Browse Source
This commit is contained in:
Travis McGuire 2020-03-25 13:40:03 -07:00 committed by GitHub
parent ffa17fe322
commit 010e0460b2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 127 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
model_cards/twmkn9/albert-base-v2-squad2/README.md
View File

@ -1,22 +1,24 @@
This model is ALBERT base v2 trained on SQuAD v2 as:
This model is [ALBERT base v2](https://huggingface.co/albert-base-v2) trained on SQuAD v2 as:
```
python run_squad.py
--model_type albert
--model_name_or_path albert-base-v2
--do_train
--do_eval
--overwrite_cache
--do_lower_case
--version_2_with_negative
--train_file $SQUAD_DIR/train-v2.0.json
--predict_file $SQUAD_DIR/dev-v2.0.json
--per_gpu_train_batch_size 8
--num_train_epochs 3
--learning_rate 3e-5
--max_seq_length 384
--doc_stride 128
--output_dir ./tmp/albert_base_fine/
export SQUAD_DIR=../../squad2
python3 run_squad.py
--model_type albert
--model_name_or_path albert-base-v2
--do_train
--do_eval
--overwrite_cache
--do_lower_case
--version_2_with_negative
--save_steps 100000
--train_file $SQUAD_DIR/train-v2.0.json
--predict_file $SQUAD_DIR/dev-v2.0.json
--per_gpu_train_batch_size 8
--num_train_epochs 3
--learning_rate 3e-5
--max_seq_length 384
--doc_stride 128
--output_dir ./tmp/albert_fine/
```
Performance on a dev subset is close to the original paper:

36
model_cards/twmkn9/bert-base-uncased-squad2/README.md
View File

@ -1,22 +1,24 @@
This model is BERT base uncased trained on SQuAD v2 as:
This model is [BERT base uncased](https://huggingface.co/bert-base-uncased) trained on SQuAD v2 as:
```
python run_squad.py
--model_type bert
--model_name_or_path bert-base-uncased
--do_train
--do_eval
--overwrite_cache
--do_lower_case
--version_2_with_negative
--train_file $SQUAD_DIR/train-v2.0.json
--predict_file $SQUAD_DIR/dev-v2.0.json
--per_gpu_train_batch_size 8
--num_train_epochs 3
--learning_rate 3e-5
--max_seq_length 384
--doc_stride 128
--output_dir ./tmp/bert_base_fine/
export SQUAD_DIR=../../squad2
python3 run_squad.py
--model_type bert
--model_name_or_path bert-base-uncased
--do_train
--do_eval
--overwrite_cache
--do_lower_case
--version_2_with_negative
--save_steps 100000
--train_file $SQUAD_DIR/train-v2.0.json
--predict_file $SQUAD_DIR/dev-v2.0.json
--per_gpu_train_batch_size 8
--num_train_epochs 3
--learning_rate 3e-5
--max_seq_length 384
--doc_stride 128
--output_dir ./tmp/bert_fine_tuned/
```
Performance on a dev subset is close to the original paper:

45
model_cards/twmkn9/distilbert-base-uncased-squad2/README.md Normal file
View File

@ -0,0 +1,45 @@
This model is [Distilbert base uncased](https://huggingface.co/distilbert-base-uncased) trained on SQuAD v2 as:
```
export SQUAD_DIR=../../squad2
python3 run_squad.py
--model_type distilbert
--model_name_or_path distilbert-base-uncased
--do_train
--do_eval
--overwrite_cache
--do_lower_case
--version_2_with_negative
--save_steps 100000
--train_file $SQUAD_DIR/train-v2.0.json
--predict_file $SQUAD_DIR/dev-v2.0.json
--per_gpu_train_batch_size 8
--num_train_epochs 3
--learning_rate 3e-5
--max_seq_length 384
--doc_stride 128
--output_dir ./tmp/distilbert_fine_tuned/
```
Performance on a dev subset is close to the original paper:
```
Results:
{
'exact': 64.88976637051661,
'f1': 68.1776176526635,
'total': 6078,
'HasAns_exact': 69.7594501718213,
'HasAns_f1': 76.62665295288285,
'HasAns_total': 2910,
'NoAns_exact': 60.416666666666664,
'NoAns_f1': 60.416666666666664,
'NoAns_total': 3168,
'best_exact': 64.88976637051661,
'best_exact_thresh': 0.0,
'best_f1': 68.17761765266337,
'best_f1_thresh': 0.0
}
```
We are hopeful this might save you time, energy, and compute. Cheers!

44
model_cards/twmkn9/distilroberta-base-squad2/README.md Normal file
View File

@ -0,0 +1,44 @@
This model is [Distilroberta base](https://huggingface.co/distilroberta-base) trained on SQuAD v2 as:
```
export SQUAD_DIR=../../squad2
python3 run_squad.py
--model_type robberta
--model_name_or_path distilroberta-base
--do_train
--do_eval
--overwrite_cache
--do_lower_case
--version_2_with_negative
--save_steps 100000
--train_file $SQUAD_DIR/train-v2.0.json
--predict_file $SQUAD_DIR/dev-v2.0.json
--per_gpu_train_batch_size 8
--num_train_epochs 3
--learning_rate 3e-5
--max_seq_length 384
--doc_stride 128
--output_dir ./tmp/distilroberta_fine_tuned/
```
Performance on a dev subset is close to the original paper:
```
Results:
{
'exact': 70.9279368213228,
'f1': 74.60439802429168,
'total': 6078,
'HasAns_exact': 67.62886597938144,
'HasAns_f1': 75.30774267754136,
'HasAns_total': 2910,
'NoAns_exact': 73.95833333333333,
'NoAns_f1': 73.95833333333333, 'NoAns_total': 3168,
'best_exact': 70.94438960184272,
'best_exact_thresh': 0.0,
'best_f1': 74.62085080481161,
'best_f1_thresh': 0.0
}
```
We are hopeful this might save you time, energy, and compute. Cheers!