Initial commit

README.md

@@ -0,0 +1,74 @@
+# BERT-tiny model finetuned with M-FAC
+
+This model is finetuned on SQuAD version 2 dataset with state-of-the-art second-order optimizer M-FAC.
+Check NeurIPS 2021 paper for more details on M-FAC: [https://arxiv.org/pdf/2107.03356.pdf](https://arxiv.org/pdf/2107.03356.pdf).
+
+## Finetuning setup
+
+For fair comparison against default Adam baseline, we finetune the model in the same framework as described here [https://github.com/huggingface/transformers/tree/master/examples/pytorch/question-answering](https://github.com/huggingface/transformers/tree/master/examples/pytorch/question-answering) and just swap Adam optimizer with M-FAC.
+Hyperparameters used by M-FAC optimizer:
+
+```bash
+learning rate = 1e-4
+number of gradients = 1024
+dampening = 1e-6
+```
+
+## Results
+
+We share the best model out of 5 runs with the following score on SQuAD version 2 validation set:
+
+```bash
+exact_match = 50.29
+f1 = 52.43
+```
+
+Mean and standard deviation for 5 runs on SQuAD version 2 validation set:
+| | Exact Match | F1  |
+|:----:|:-----------:|:----:|
+| Adam | 48.41 ± 0.57 | 49.99 ± 0.54 |
+| M-FAC | 49.80 ± 0.43 | 52.18 ± 0.20 |
+
+Results can be reproduced by adding M-FAC optimizer code in [https://github.com/huggingface/transformers/blob/master/examples/pytorch/question-answering/run_qa.py](https://github.com/huggingface/transformers/blob/master/examples/pytorch/question-answering/run_qa.py) and running the following bash script:
+
+```bash
+CUDA_VISIBLE_DEVICES=0 python run_qa.py \
+    --seed 42 \
+    --model_name_or_path prajjwal1/bert-tiny \
+    --dataset_name squad_v2 \
+    --version_2_with_negative \
+    --do_train \
+    --do_eval \
+    --per_device_train_batch_size 12 \
+    --learning_rate 1e-4 \
+    --num_train_epochs 2 \
+    --max_seq_length 384 \
+    --doc_stride 128 \
+    --output_dir out_dir/ \
+    --optim MFAC \
+    --optim_args '{"lr": 1e-4, "num_grads": 1024, "damp": 1e-6}'
+```
+
+We believe these results could be improved with modest tuning of hyperparameters: `per_device_train_batch_size`, `learning_rate`, `num_train_epochs`, `num_grads` and `damp`. For the sake of fair comparison  and a robust default setup we use the same hyperparameters across all models (`bert-tiny`, `bert-mini`) and all datasets (SQuAD version 2 and GLUE).
+
+## BibTeX entry and citation info
+
+```bibtex
+@article{DBLP:journals/corr/abs-2107-03356,
+  author    = {Elias Frantar and
+               Eldar Kurtic and
+               Dan Alistarh},
+  title     = {Efficient Matrix-Free Approximations of Second-Order Information,
+               with Applications to Pruning and Optimization},
+  journal   = {CoRR},
+  volume    = {abs/2107.03356},
+  year      = {2021},
+  url       = {https://arxiv.org/abs/2107.03356},
+  eprinttype = {arXiv},
+  eprint    = {2107.03356},
+  timestamp = {Tue, 20 Jul 2021 15:08:33 +0200},
+  biburl    = {https://dblp.org/rec/journals/corr/abs-2107-03356.bib},
+  bibsource = {dblp computer science bibliography, https://dblp.org}
+}
+
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "prajjwal1/bert-tiny",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:727327d191770ce207fa29c05693941f47e235a9afe750ba41bd158c7a86969c
+size 17497773

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "prajjwal1/bert-tiny", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}