pknayak/bert-news-class

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: outputs
+  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. -->
+
+# outputs
+
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6401
+- Precision: 0.8329
+- Recall: 0.8329
+- F1: 0.8326
+- Accuracy: 0.8329
+
+## 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: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.7876        | 1.0   | 3267 | 0.7410          | 0.8115    | 0.8067 | 0.8065 | 0.8067   |
+| 0.5802        | 2.0   | 6534 | 0.6335          | 0.8323    | 0.8304 | 0.8305 | 0.8304   |
+| 0.408         | 3.0   | 9801 | 0.6401          | 0.8329    | 0.8329 | 0.8326 | 0.8329   |
+
+
+### Framework versions
+
+- Transformers 4.45.1
+- Pytorch 2.4.0
+- Datasets 3.0.1
+- Tokenizers 0.20.0

config.json

@@ -0,0 +1,81 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "academic interests",
+    "1": "arts and culture",
+    "2": "automotives",
+    "3": "books and literature",
+    "4": "business and finance",
+    "5": "careers",
+    "6": "family and relationships",
+    "7": "food and drinks",
+    "8": "health",
+    "9": "healthy living",
+    "10": "hobbies and interests",
+    "11": "home and garden",
+    "12": "movies",
+    "13": "music and audio",
+    "14": "news and politics",
+    "15": "personal finance",
+    "16": "pets",
+    "17": "pharmaceuticals, conditions, and symptoms",
+    "18": "real estate",
+    "19": "shopping",
+    "20": "sports",
+    "21": "style and fashion",
+    "22": "technology and computing",
+    "23": "television",
+    "24": "travel",
+    "25": "video gaming"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "academic interests": 0,
+    "arts and culture": 1,
+    "automotives": 2,
+    "books and literature": 3,
+    "business and finance": 4,
+    "careers": 5,
+    "family and relationships": 6,
+    "food and drinks": 7,
+    "health": 8,
+    "healthy living": 9,
+    "hobbies and interests": 10,
+    "home and garden": 11,
+    "movies": 12,
+    "music and audio": 13,
+    "news and politics": 14,
+    "personal finance": 15,
+    "pets": 16,
+    "pharmaceuticals, conditions, and symptoms": 17,
+    "real estate": 18,
+    "shopping": 19,
+    "sports": 20,
+    "style and fashion": 21,
+    "technology and computing": 22,
+    "television": 23,
+    "travel": 24,
+    "video gaming": 25
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9a73a5101c6a889621640d7eb435b0cfb8d38eaa4b486845f4e306188ee125d
+size 267906392

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": false,
+  "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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbdf1d45ed000d3d7a21634e1d405db8a6de4cdd1b49408ad4164bd81edd1e80
+size 5176