jsoutherland commited on
Commit
40d2b6c
1 Parent(s): c4a75c3

initial version

Browse files
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - emotion
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ model_index:
11
+ - name: distilbert-base-uncased-finetuned-emotion
12
+ results:
13
+ - task:
14
+ name: Text Classification
15
+ type: text-classification
16
+ dataset:
17
+ name: emotion
18
+ type: emotion
19
+ args: default
20
+ metric:
21
+ name: F1
22
+ type: f1
23
+ value: 0.9327347950817506
24
+ ---
25
+
26
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
27
+ should probably proofread and complete it, then remove this comment. -->
28
+
29
+ # distilbert-base-uncased-finetuned-emotion
30
+
31
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
32
+ It achieves the following results on the evaluation set:
33
+ - Loss: 0.1649
34
+ - Accuracy: 0.9325
35
+ - F1: 0.9327
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 2e-05
55
+ - train_batch_size: 64
56
+ - eval_batch_size: 64
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - num_epochs: 3
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
66
+ | No log | 1.0 | 250 | 0.2838 | 0.9065 | 0.9036 |
67
+ | No log | 2.0 | 500 | 0.1795 | 0.9255 | 0.9255 |
68
+ | No log | 3.0 | 750 | 0.1649 | 0.9325 | 0.9327 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.8.2
74
+ - Pytorch 1.9.0+cu102
75
+ - Datasets 2.1.0
76
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4,
26
+ "LABEL_5": 5
27
+ },
28
+ "max_position_embeddings": 512,
29
+ "model_type": "distilbert",
30
+ "n_heads": 12,
31
+ "n_layers": 6,
32
+ "pad_token_id": 0,
33
+ "problem_type": "single_label_classification",
34
+ "qa_dropout": 0.1,
35
+ "seq_classif_dropout": 0.2,
36
+ "sinusoidal_pos_embds": false,
37
+ "tie_weights_": true,
38
+ "transformers_version": "4.8.2",
39
+ "vocab_size": 30522
40
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c7e35bd73660b3973417f88244e3a3d915ed369bad2ef78a35125878c07f149
3
+ size 267872369
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 sha256:39d9d3da002f14d2e49831e58a45fe73a030a144d84d3dfaf132aff561808a79
3
+ size 2671
vocab.txt ADDED
The diff for this file is too large to render. See raw diff