bhadresh-savani commited on
Commit
702940c
1 Parent(s): a2e4aa3

added model files

Browse files
README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ thumbnail: https://avatars3.githubusercontent.com/u/32437151?s=460&u=4ec59abc8d21d5feea3dab323d23a5860e6996a4&v=4
5
+ tags:
6
+ - text-classification
7
+ - emotion
8
+ - pytorch
9
+ - en
10
+ - distil-bert
11
+ license: apache-2.0
12
+ datasets:
13
+ - emotion
14
+ metrics:
15
+ - Accuracy, F1 Score
16
+ ---
17
+ # Distilbert-base-uncased-emotion
18
+
19
+ ## Model description:
20
+ `Distilbert-base-uncased` finetuned on the emotion dataset using HuggingFace Trainer.
21
+ ```
22
+ learning rate 2e-5,
23
+ batch size 64,
24
+ num_train_epochs=8,
25
+ ```
26
+
27
+ ## Dataset:
28
+ [Twitter-Sentiment-Analysis](https://huggingface.co/nlp/viewer/?dataset=emotion).
29
+
30
+ #### Limitations and bias
31
+ -
32
+ - [Follow me on github](https://github.com/nateraw) to get notified when code is made available.
33
+
34
+ ## Training procedure
35
+
36
+ ## Eval results
37
+ ```
38
+
39
+ ```
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "qa_dropout": 0.1,
34
+ "seq_classif_dropout": 0.2,
35
+ "sinusoidal_pos_embds": false,
36
+ "tie_weights_": true,
37
+ "transformers_version": "4.5.0",
38
+ "vocab_size": 30522
39
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa7398d830fcc94f95af88d7cc3013813668cfc58a07d75a8116cfd8af75c4d
3
+ size 267875479
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"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff