justin871030 commited on
Commit
efc4e84
โ€ข
1 Parent(s): 8eb19e8

Uploaded the first version finetuned model

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - go-emotion
5
+ - text-classification
6
+ - pytorch
7
+ datasets:
8
+ - go_emotions
9
+ metrics:
10
+ - f1
11
+ widget:
12
+ - text: "Thanks for giving advice to the people who need it! ๐Ÿ‘Œ๐Ÿ™"
13
+ license: mit
14
+ ---
15
+
16
+ ## Model Description
17
+ 1. Based on the uncased BERT pretrained model with a linear output layer.
18
+ 2. Added several commonly-used emoji and tokens to the special token list of the tokenizer.
19
+ 3. Did label smoothing while training.
20
+ 4. Used weighted loss and focal loss to help the cases which trained badly.
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForMultiLabelClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "finetuning_task": "goemotions",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "anger",
15
+ "1": "disgust",
16
+ "2": "fear",
17
+ "3": "joy",
18
+ "4": "neutral",
19
+ "5": "sadness",
20
+ "6": "surprise"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "anger": 0,
26
+ "disgust": 1,
27
+ "fear": 2,
28
+ "joy": 3,
29
+ "neutral": 4,
30
+ "sadness": 5,
31
+ "surprise": 6
32
+ },
33
+ "layer_norm_eps": 1e-12,
34
+ "max_position_embeddings": 512,
35
+ "model_type": "bert",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "pad_token_id": 0,
39
+ "position_embedding_type": "absolute",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.13.0",
42
+ "type_vocab_size": 2,
43
+ "vocab_size": 30522
44
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20a21aeb15dbbbb11e92ff776bb4fa119831694e1da53a30e214b3af79453bc2
3
+ size 438044515
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "additional_special_tokens": ["[NAME]", "[RELIGION]", "๐Ÿ˜‚", "โค", "๐Ÿคฃ", "๐Ÿ˜ญ", "๐Ÿ‘", "โ™€", "๐Ÿ˜", "๐Ÿค”", "๐Ÿฆ€", "๐Ÿ‘", "๐Ÿป", "๐Ÿคท", "๐Ÿผ", "๐Ÿ™„", "๐Ÿ˜Š", "๐Ÿ”ฅ", "๐Ÿ˜ข", "๐Ÿ˜…", "๐Ÿ’œ", "๐Ÿ‘Œ", "โ™‚", "โ˜บ", "๐Ÿ˜Ž", "๐Ÿ’ฏ", "๐Ÿ’ฆ", "๐Ÿ˜", "๐Ÿ˜”", "๐Ÿคข", "๐Ÿ’•", "๐Ÿ™", "๐Ÿ˜‰", "๐Ÿ™Œ", "๐Ÿคฆ", "๐Ÿ™ƒ", "๐Ÿ˜†", "๐Ÿ˜˜", "๐ŸŽถ", "๐Ÿ˜ค", "๐Ÿ˜", "๐Ÿ˜€", "๐Ÿค—", "๐Ÿ˜", "๐Ÿฝ", "๐Ÿ’ช", "๐Ÿ˜ก", "๐ŸŽ‰", "๐Ÿ‘€", "โœ”", "๐Ÿ”ช", "๐Ÿ˜„", "๐Ÿ˜ฌ", "๐Ÿ’–", "๐Ÿ˜ฅ", "๐Ÿ˜’", "โœŒ", "๐Ÿ’ƒ", "๐Ÿ˜ฉ", "โ˜น", "๐Ÿ’…", "๐Ÿ˜ช", "๐Ÿ‘‘", "๐Ÿ˜ณ", "๐Ÿคช", "๐Ÿ˜•", "๐ŸŽ‚", "๐Ÿ˜ซ", "๐Ÿ’™", "๐Ÿคฎ", "๐Ÿšซ", "๐Ÿ˜ž", "๐Ÿ’Ž", "๐Ÿ˜ฑ", "๐Ÿ˜‘", "๐Ÿ˜–", "๐ŸŠ", "๐Ÿ™ˆ", "๐Ÿค ", "โฃ", "๐Ÿคฉ", "๐Ÿ™‚", "๐Ÿ‘Š", "๐Ÿ’›", "๐Ÿ’“", "๐Ÿ‘ฉ", "โœจ", "๐Ÿ˜ฃ", "๐Ÿ’—", "๐Ÿคž", "๐Ÿฅ€", "๐Ÿš“", "๐Ÿ˜ฐ", "๐Ÿ‘…", "๐Ÿ˜", "๐Ÿป", "๐Ÿค•", "๐Ÿ˜œ", "๐Ÿฆˆ", "๐Ÿ˜ƒ", "๐Ÿ˜ฎ", "โœŠ", "๐Ÿ’š", "๐ŸŽต", "๐Ÿ’จ", "โ˜", "๐ŸŒˆ", "๐Ÿ’„", "๐Ÿ‘ธ", "๐Ÿ’ฅ", "๐Ÿ–ค", "๐Ÿพ", "๐Ÿฉ", "๐Ÿ˜‹", "๐Ÿคฒ", "๐Ÿคค", "๐Ÿง›", "๐Ÿ˜‡", "โ„", "โ–ซ", "๐Ÿ’", "๐Ÿ˜ด", ":)", ":(", "XD", "xD", ":D", ":'("]}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "model_max_length": 512, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "additional_special_tokens": ["[NAME]", "[RELIGION]", "๐Ÿ˜‚", "โค", "๐Ÿคฃ", "๐Ÿ˜ญ", "๐Ÿ‘", "โ™€", "๐Ÿ˜", "๐Ÿค”", "๐Ÿฆ€", "๐Ÿ‘", "๐Ÿป", "๐Ÿคท", "๐Ÿผ", "๐Ÿ™„", "๐Ÿ˜Š", "๐Ÿ”ฅ", "๐Ÿ˜ข", "๐Ÿ˜…", "๐Ÿ’œ", "๐Ÿ‘Œ", "โ™‚", "โ˜บ", "๐Ÿ˜Ž", "๐Ÿ’ฏ", "๐Ÿ’ฆ", "๐Ÿ˜", "๐Ÿ˜”", "๐Ÿคข", "๐Ÿ’•", "๐Ÿ™", "๐Ÿ˜‰", "๐Ÿ™Œ", "๐Ÿคฆ", "๐Ÿ™ƒ", "๐Ÿ˜†", "๐Ÿ˜˜", "๐ŸŽถ", "๐Ÿ˜ค", "๐Ÿ˜", "๐Ÿ˜€", "๐Ÿค—", "๐Ÿ˜", "๐Ÿฝ", "๐Ÿ’ช", "๐Ÿ˜ก", "๐ŸŽ‰", "๐Ÿ‘€", "โœ”", "๐Ÿ”ช", "๐Ÿ˜„", "๐Ÿ˜ฌ", "๐Ÿ’–", "๐Ÿ˜ฅ", "๐Ÿ˜’", "โœŒ", "๐Ÿ’ƒ", "๐Ÿ˜ฉ", "โ˜น", "๐Ÿ’…", "๐Ÿ˜ช", "๐Ÿ‘‘", "๐Ÿ˜ณ", "๐Ÿคช", "๐Ÿ˜•", "๐ŸŽ‚", "๐Ÿ˜ซ", "๐Ÿ’™", "๐Ÿคฎ", "๐Ÿšซ", "๐Ÿ˜ž", "๐Ÿ’Ž", "๐Ÿ˜ฑ", "๐Ÿ˜‘", "๐Ÿ˜–", "๐ŸŠ", "๐Ÿ™ˆ", "๐Ÿค ", "โฃ", "๐Ÿคฉ", "๐Ÿ™‚", "๐Ÿ‘Š", "๐Ÿ’›", "๐Ÿ’“", "๐Ÿ‘ฉ", "โœจ", "๐Ÿ˜ฃ", "๐Ÿ’—", "๐Ÿคž", "๐Ÿฅ€", "๐Ÿš“", "๐Ÿ˜ฐ", "๐Ÿ‘…", "๐Ÿ˜", "๐Ÿป", "๐Ÿค•", "๐Ÿ˜œ", "๐Ÿฆˆ", "๐Ÿ˜ƒ", "๐Ÿ˜ฎ", "โœŠ", "๐Ÿ’š", "๐ŸŽต", "๐Ÿ’จ", "โ˜", "๐ŸŒˆ", "๐Ÿ’„", "๐Ÿ‘ธ", "๐Ÿ’ฅ", "๐Ÿ–ค", "๐Ÿพ", "๐Ÿฉ", "๐Ÿ˜‹", "๐Ÿคฒ", "๐Ÿคค", "๐Ÿง›", "๐Ÿ˜‡", "โ„", "โ–ซ", "๐Ÿ’", "๐Ÿ˜ด", ":)", ":(", "XD", "xD", ":D", ":'("]}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5b648aab5a04bac52fd54a530d5c0b653f60d7ef5880a4b9677a96aa7b7a581
3
+ size 1839
vocab.txt ADDED
The diff for this file is too large to render. See raw diff