hwaQing commited on
Commit
3418215
·
1 Parent(s): 3ffd458
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - glue
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ model-index:
11
+ - name: distilbert-base-uncased-finetuned-mrpc
12
+ results:
13
+ - task:
14
+ name: Text Classification
15
+ type: text-classification
16
+ dataset:
17
+ name: glue
18
+ type: glue
19
+ args: mrpc
20
+ metrics:
21
+ - name: Accuracy
22
+ type: accuracy
23
+ value: 0.7034313725490197
24
+ - name: F1
25
+ type: f1
26
+ value: 0.8207407407407408
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # distilbert-base-uncased-finetuned-mrpc
33
+
34
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.5708
37
+ - Accuracy: 0.7034
38
+ - F1: 0.8207
39
+
40
+ ## Model description
41
+
42
+ More information needed
43
+
44
+ ## Intended uses & limitations
45
+
46
+ More information needed
47
+
48
+ ## Training and evaluation data
49
+
50
+ More information needed
51
+
52
+ ## Training procedure
53
+
54
+ ### Training hyperparameters
55
+
56
+ The following hyperparameters were used during training:
57
+ - learning_rate: 2e-05
58
+ - train_batch_size: 64
59
+ - eval_batch_size: 64
60
+ - seed: 42
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - num_epochs: 1
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
69
+ | No log | 1.0 | 58 | 0.5708 | 0.7034 | 0.8207 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.10.2
75
+ - Pytorch 1.9.0+cu102
76
+ - Datasets 1.11.0
77
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.10.2",
24
+ "vocab_size": 30522
25
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc43c2fe9d1cf4b263008e6ae5c1f9a72a6cdca961984619a7b9fe8ccf76d255
3
+ size 267858673
runs/Sep11_03-34-52_86833adb3053/1631331338.0071108/events.out.tfevents.1631331338.86833adb3053.62.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5f0edf6b33c7ea0ec4d60fe68c089199d3b42fde5b04f5dbdbac9e3538aec70
3
+ size 4209
runs/Sep11_03-34-52_86833adb3053/events.out.tfevents.1631331337.86833adb3053.62.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a31cb9cdf91548edae44c37f0c06ec692eecfdfbe4cfa234765a33b4477db04
3
+ size 3566
runs/Sep11_03-34-52_86833adb3053/events.out.tfevents.1631333427.86833adb3053.62.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baeb3f144cd766c71ec416cf2cc1c0ec58ae448fb958a978e4c9eee4655be945
3
+ size 402
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.json ADDED
The diff for this file is too large to render. See raw diff
 
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", "tokenizer_class": "DistilBertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cc6a14c58a417cee089cf48fad4313e68c2ed2d763e70ddcda92a8153cd8ca1
3
+ size 2671
vocab.txt ADDED
The diff for this file is too large to render. See raw diff