bert finetuned model for intent detection

README.md

@@ -1,3 +1,109 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+base_model: google-bert/bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: bert_intent
+  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_intent
+
+This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0169
+- Accuracy: 0.9982
+
+## 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: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.2615        | 1.0   | 692   | 0.0516          | 0.9809   |
+| 0.0191        | 2.0   | 1384  | 0.0231          | 0.9947   |
+| 0.0083        | 3.0   | 2076  | 0.0140          | 0.9982   |
+| 0.0051        | 4.0   | 2768  | 0.0101          | 0.9975   |
+| 0.0028        | 5.0   | 3460  | 0.0075          | 0.9979   |
+| 0.0013        | 6.0   | 4152  | 0.0064          | 0.9979   |
+| 0.0008        | 7.0   | 4844  | 0.0073          | 0.9979   |
+| 0.0004        | 8.0   | 5536  | 0.0069          | 0.9979   |
+| 0.0003        | 9.0   | 6228  | 0.0072          | 0.9979   |
+| 0.0002        | 10.0  | 6920  | 0.0075          | 0.9979   |
+| 0.0002        | 11.0  | 7612  | 0.0077          | 0.9979   |
+| 0.0001        | 12.0  | 8304  | 0.0080          | 0.9979   |
+| 0.0001        | 13.0  | 8996  | 0.0083          | 0.9979   |
+| 0.0001        | 14.0  | 9688  | 0.0087          | 0.9979   |
+| 0.0           | 15.0  | 10380 | 0.0093          | 0.9979   |
+| 0.0           | 16.0  | 11072 | 0.0097          | 0.9982   |
+| 0.0           | 17.0  | 11764 | 0.0096          | 0.9979   |
+| 0.0           | 18.0  | 12456 | 0.0106          | 0.9979   |
+| 0.0           | 19.0  | 13148 | 0.0108          | 0.9979   |
+| 0.0           | 20.0  | 13840 | 0.0110          | 0.9979   |
+| 0.0           | 21.0  | 14532 | 0.0111          | 0.9979   |
+| 0.0           | 22.0  | 15224 | 0.0116          | 0.9979   |
+| 0.0           | 23.0  | 15916 | 0.0116          | 0.9979   |
+| 0.0           | 24.0  | 16608 | 0.0125          | 0.9982   |
+| 0.0           | 25.0  | 17300 | 0.0130          | 0.9982   |
+| 0.0           | 26.0  | 17992 | 0.0124          | 0.9979   |
+| 0.0           | 27.0  | 18684 | 0.0129          | 0.9979   |
+| 0.0           | 28.0  | 19376 | 0.0138          | 0.9982   |
+| 0.0           | 29.0  | 20068 | 0.0140          | 0.9982   |
+| 0.0           | 30.0  | 20760 | 0.0145          | 0.9982   |
+| 0.0           | 31.0  | 21452 | 0.0144          | 0.9982   |
+| 0.0           | 32.0  | 22144 | 0.0146          | 0.9982   |
+| 0.0           | 33.0  | 22836 | 0.0152          | 0.9982   |
+| 0.0           | 34.0  | 23528 | 0.0151          | 0.9982   |
+| 0.0           | 35.0  | 24220 | 0.0151          | 0.9982   |
+| 0.0           | 36.0  | 24912 | 0.0153          | 0.9982   |
+| 0.0           | 37.0  | 25604 | 0.0155          | 0.9982   |
+| 0.0           | 38.0  | 26296 | 0.0158          | 0.9982   |
+| 0.0           | 39.0  | 26988 | 0.0159          | 0.9982   |
+| 0.0           | 40.0  | 27680 | 0.0163          | 0.9982   |
+| 0.0           | 41.0  | 28372 | 0.0168          | 0.9982   |
+| 0.0           | 42.0  | 29064 | 0.0167          | 0.9982   |
+| 0.0           | 43.0  | 29756 | 0.0167          | 0.9982   |
+| 0.0           | 44.0  | 30448 | 0.0168          | 0.9982   |
+| 0.0           | 45.0  | 31140 | 0.0168          | 0.9982   |
+| 0.0           | 46.0  | 31832 | 0.0168          | 0.9982   |
+| 0.0           | 47.0  | 32524 | 0.0168          | 0.9982   |
+| 0.0           | 48.0  | 33216 | 0.0168          | 0.9982   |
+| 0.0           | 49.0  | 33908 | 0.0169          | 0.9982   |
+| 0.0           | 50.0  | 34600 | 0.0169          | 0.9982   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.1
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "storage-system-details",
+    "1": "tenant-notifications",
+    "2": "storage-system-volume",
+    "3": "storage-system-notification",
+    "4": "Tenant-List",
+    "5": "tenant-alerts",
+    "6": "storage-list",
+    "7": "storage-system-metric",
+    "8": "storage-system-alert",
+    "9": "chatbot-capabilities",
+    "10": "unknown",
+    "11": "greetings",
+    "12": "thanking"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Tenant-List": 4,
+    "chatbot-capabilities": 9,
+    "greetings": 11,
+    "storage-list": 6,
+    "storage-system-alert": 8,
+    "storage-system-details": 0,
+    "storage-system-metric": 7,
+    "storage-system-notification": 3,
+    "storage-system-volume": 2,
+    "tenant-alerts": 5,
+    "tenant-notifications": 1,
+    "thanking": 12,
+    "unknown": 10
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "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 sha256:944efb2c5f66f8bbc0282522f089f390a1a71f17772101cc20e537cc7ea6f709
+size 437992484

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 sha256:967858ef3b30321a441863808d225cba0200a775cf3db7d0d4d352e073565a1f
+size 5048