echarlaix HF staff commited on
Commit
46a71ae
1 Parent(s): 04b8f60

Uploading model

Browse files
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "finetuning_task": "sst2",
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": 0,
14
+ "1": 1
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "0": 0,
19
+ "1": 1
20
+ },
21
+ "max_position_embeddings": 512,
22
+ "model_type": "distilbert",
23
+ "n_heads": 12,
24
+ "n_layers": 6,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.12.3",
34
+ "vocab_size": 30522
35
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9059633027522935,
4
+ "eval_loss": 0.3885285258293152,
5
+ "eval_runtime": 37.4629,
6
+ "eval_samples_per_second": 23.276,
7
+ "eval_steps_per_second": 2.91
8
+ }
prune.yml ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #
2
+ # Copyright (c) 2021 Intel Corporation
3
+ #
4
+ # Licensed under the Apache License, Version 2.0 (the "License");
5
+ # you may not use this file except in compliance with the License.
6
+ # You may obtain a copy of the License at
7
+ #
8
+ # http://www.apache.org/licenses/LICENSE-2.0
9
+ #
10
+ # Unless required by applicable law or agreed to in writing, software
11
+ # distributed under the License is distributed on an "AS IS" BASIS,
12
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13
+ # See the License for the specific language governing permissions and
14
+ # limitations under the License.
15
+
16
+ version: 1.0
17
+
18
+ model:
19
+ name: bert_prune
20
+ framework: pytorch
21
+
22
+ pruning:
23
+ approach:
24
+ weight_compression:
25
+ initial_sparsity: 0.0
26
+ target_sparsity: 0.1 # targeted sparsity of 10%
27
+ start_epoch: 0
28
+ end_epoch: 1
29
+ pruners:
30
+ - !Pruner
31
+ prune_type: basic_magnitude
32
+ tuning:
33
+ accuracy_criterion:
34
+ relative: 0.1 # only verifying workflow, accuracy loss percentage: 10%
35
+ exit_policy:
36
+ timeout: 0 # tuning timeout (seconds)
37
+ random_seed: 9527 # random seed
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:191b7bdb58a59d8512d5c73e3591e4a34e21aa1982263daf97f7aa4cdb93ab5b
3
+ size 267858673
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
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, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased-finetuned-sst-2-english", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "DistilBertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c3d60d1de8cfbc8b786cde9fb52df69cf662b0e0c2dad5306890bc5c447ce6e
3
+ size 2799
vocab.txt ADDED
The diff for this file is too large to render. See raw diff