emotion_classifier_bert_mini

README.md

@@ -0,0 +1,73 @@
+---
+license: mit
+base_model: prajjwal1/bert-mini
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- accuracy
+model-index:
+- name: bert-mini-emotion_classifier
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# bert-mini-emotion_classifier
+
+This model is a fine-tuned version of [prajjwal1/bert-mini](https://huggingface.co/prajjwal1/bert-mini) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0648
+- F1: 0.9315
+- Roc Auc: 0.9589
+- Accuracy: 0.9224
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 5
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
+| 0.4176        | 0.1   | 500  | 0.2929          | 0.6755 | 0.7687  | 0.5550   |
+| 0.2278        | 0.19  | 1000 | 0.1623          | 0.8931 | 0.9246  | 0.8630   |
+| 0.1513        | 0.29  | 1500 | 0.1184          | 0.9185 | 0.9450  | 0.9022   |
+| 0.1198        | 0.38  | 2000 | 0.0957          | 0.9274 | 0.9536  | 0.9197   |
+| 0.1011        | 0.48  | 2500 | 0.0815          | 0.9306 | 0.9568  | 0.9230   |
+| 0.0881        | 0.58  | 3000 | 0.0729          | 0.9320 | 0.9575  | 0.9237   |
+| 0.0815        | 0.67  | 3500 | 0.0669          | 0.9337 | 0.9596  | 0.9256   |
+| 0.0767        | 0.77  | 4000 | 0.0633          | 0.9346 | 0.9609  | 0.9260   |
+| 0.0721        | 0.86  | 4500 | 0.0612          | 0.9333 | 0.9602  | 0.9233   |
+| 0.071         | 0.96  | 5000 | 0.0601          | 0.9339 | 0.9607  | 0.9251   |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "prajjwal1/bert-mini",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "sadness",
+    "1": "joy",
+    "2": "love",
+    "3": "anger",
+    "4": "fear",
+    "5": "surprise"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "anger": 3,
+    "fear": 4,
+    "joy": 1,
+    "love": 2,
+    "sadness": 0,
+    "surprise": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fea424e925459af0fff990071c58f6b5197d5be63d7c9d2f5a22107a2479360
+size 44696720

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809bcb71655e8d5375bcc7d461f4b0588fecefbd50ec9fc916ff7fd41a38d5db
+size 4728