Training in progress epoch 0

README.md

@@ -0,0 +1,54 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: inpreet/model_categorization
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# inpreet/model_categorization
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 2.4855
+- Validation Loss: 2.0873
+- Train Accuracy: 0.4226
+- Epoch: 0
+
+## 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:
+- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 7495, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Train Accuracy | Epoch |
+|:----------:|:---------------:|:--------------:|:-----:|
+| 2.4855     | 2.0873          | 0.4226         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.30.0
+- TensorFlow 2.12.0
+- Datasets 2.12.0
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,87 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Agriculture & Allied Sectors",
+    "1": "Animation",
+    "2": "Astrology",
+    "3": "Autos & Vehicles",
+    "4": "Beauty",
+    "5": "Blogs and Travel",
+    "6": "Comedy",
+    "7": "DIY",
+    "8": "Education",
+    "9": "Entertainment",
+    "10": "Events",
+    "11": "Fashion & Style",
+    "12": "Finance",
+    "13": "Food & Drinks",
+    "14": "Gaming",
+    "15": "Health & Fitness",
+    "16": "Infotainment",
+    "17": "Kids & Animation",
+    "18": "Miscellaneous",
+    "19": "Motivational",
+    "20": "Movie & Shows",
+    "21": "Music",
+    "22": "News & Politics",
+    "23": "Non profits",
+    "24": "People & Culture",
+    "25": "Pets & Animals",
+    "26": "Religious Content",
+    "27": "Science & Technology",
+    "28": "Sports",
+    "29": "Travel & Leisure"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Agriculture & Allied Sectors": 0,
+    "Animation": 1,
+    "Astrology": 2,
+    "Autos & Vehicles": 3,
+    "Beauty": 4,
+    "Blogs and Travel": 5,
+    "Comedy": 6,
+    "DIY": 7,
+    "Education": 8,
+    "Entertainment": 9,
+    "Events": 10,
+    "Fashion & Style": 11,
+    "Finance": 12,
+    "Food & Drinks": 13,
+    "Gaming": 14,
+    "Health & Fitness": 15,
+    "Infotainment": 16,
+    "Kids & Animation": 17,
+    "Miscellaneous": 18,
+    "Motivational": 19,
+    "Movie & Shows": 20,
+    "Music": 21,
+    "News & Politics": 22,
+    "Non profits": 23,
+    "People & Culture": 24,
+    "Pets & Animals": 25,
+    "Religious Content": 26,
+    "Science & Technology": 27,
+    "Sports": 28,
+    "Travel & Leisure": 29
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.30.0",
+  "vocab_size": 30522
+}

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af396f417fd64247799de51c0c7b96adb590239859258b1742cab2fa2b84257
+size 268037824

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}