Uploaded the first version finetuned model

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,20 @@
+---
+language: en
+tags:
+- go-emotion
+- text-classification
+- pytorch
+datasets:
+- go_emotions
+metrics:
+- f1
+widget:
+- text: "Thanks for giving advice to the people who need it! 👌🙏"
+license: mit
+---
+
+## Model Description
+1. Based on the uncased BERT pretrained model with a linear output layer.
+2. Added several commonly-used emoji and tokens to the special token list of the tokenizer.
+3. Did label smoothing while training.
+4. Used weighted loss and focal loss to help the cases which trained badly.

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForMultiLabelClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "goemotions",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "anger",
+    "1": "disgust",
+    "2": "fear",
+    "3": "joy",
+    "4": "neutral",
+    "5": "sadness",
+    "6": "surprise"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "anger": 0,
+    "disgust": 1,
+    "fear": 2,
+    "joy": 3,
+    "neutral": 4,
+    "sadness": 5,
+    "surprise": 6
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20a21aeb15dbbbb11e92ff776bb4fa119831694e1da53a30e214b3af79453bc2
+size 438044515

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "additional_special_tokens": ["[NAME]", "[RELIGION]", "😂", "❤", "🤣", "😭", "👏", "♀", "😍", "🤔", "🦀", "👍", "🏻", "🤷", "🏼", "🙄", "😊", "🔥", "😢", "😅", "💜", "👌", "♂", "☺", "😎", "💯", "💦", "😁", "😔", "🤢", "💕", "🙏", "😉", "🙌", "🤦", "🙃", "😆", "😘", "🎶", "😤", "😏", "😀", "🤗", "😐", "🏽", "💪", "😡", "🎉", "👀", "✔", "🔪", "😄", "😬", "💖", "😥", "😒", "✌", "💃", "😩", "☹", "💅", "😪", "👑", "😳", "🤪", "😕", "🎂", "😫", "💙", "🤮", "🚫", "😞", "💎", "😱", "😑", "😖", "🏊", "🙈", "🤠", "❣", "🤩", "🙂", "👊", "💛", "💓", "👩", "✨", "😣", "💗", "🤞", "🥀", "🚓", "😰", "👅", "😝", "🍻", "🤕", "😜", "🦈", "😃", "😮", "✊", "💚", "🎵", "💨", "☁", "🌈", "💄", "👸", "💥", "🖤", "🏾", "🍩", "😋", "🤲", "🤤", "🧛", "😇", "❄", "▫", "💁", "😴", ":)", ":(", "XD", "xD", ":D", ":'("]}

tokenizer_config.json

@@ -0,0 +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]", "😂", "❤", "🤣", "😭", "👏", "♀", "😍", "🤔", "🦀", "👍", "🏻", "🤷", "🏼", "🙄", "😊", "🔥", "😢", "😅", "💜", "👌", "♂", "☺", "😎", "💯", "💦", "😁", "😔", "🤢", "💕", "🙏", "😉", "🙌", "🤦", "🙃", "😆", "😘", "🎶", "😤", "😏", "😀", "🤗", "😐", "🏽", "💪", "😡", "🎉", "👀", "✔", "🔪", "😄", "😬", "💖", "😥", "😒", "✌", "💃", "😩", "☹", "💅", "😪", "👑", "😳", "🤪", "😕", "🎂", "😫", "💙", "🤮", "🚫", "😞", "💎", "😱", "😑", "😖", "🏊", "🙈", "🤠", "❣", "🤩", "🙂", "👊", "💛", "💓", "👩", "✨", "😣", "💗", "🤞", "🥀", "🚓", "😰", "👅", "😝", "🍻", "🤕", "😜", "🦈", "😃", "😮", "✊", "💚", "🎵", "💨", "☁", "🌈", "💄", "👸", "💥", "🖤", "🏾", "🍩", "😋", "🤲", "🤤", "🧛", "😇", "❄", "▫", "💁", "😴", ":)", ":(", "XD", "xD", ":D", ":'("]}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5b648aab5a04bac52fd54a530d5c0b653f60d7ef5880a4b9677a96aa7b7a581
+size 1839