add model

README.md

@@ -1,13 +1,56 @@
+---
+tags:
+- generated_from_keras_callback
+model-index:
+- name: CAP_coded_UK_statutory_instruments
+  results: []
+---
 
-This model was trained on UK parliamentary statutory instruments (www.legislation.gov.uk). The model is trained to predict the CAP issue codes of statutory instruments. The model is trained on the titles of ~40k statutory instruments from the UK House of Commons and the Scottish Parliament. 
+<!-- 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. -->
 
-Training data available at: https://comparativeagendas.s3.amazonaws.com/datasetfiles/uk_statutoryinstruments_v1_1.csv
+# CAP_coded_UK_statutory_instruments
 
-All statutory instruments are available at:  https://www.legislation.gov.uk/uksi 
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.1188
+- Train Sparse Categorical Accuracy: 0.9688
+- Validation Loss: 0.2032
+- Validation Sparse Categorical Accuracy: 0.9556
+- Epoch: 2
 
-Comparative Agendas Project codes: https://www.comparativeagendas.net/pages/master-codebook
+## Model description
 
+More information needed
 
----
-license: afl-3.0
----
+## 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', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
+|:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
+| 0.2167     | 0.9474                            | 0.2351          | 0.9444                                 | 0     |
+| 0.1539     | 0.9592                            | 0.2076          | 0.9536                                 | 1     |
+| 0.1188     | 0.9688                            | 0.2032          | 0.9556                                 | 2     |
+
+
+### Framework versions
+
+- Transformers 4.19.2
+- TensorFlow 2.8.2
+- Datasets 2.2.2
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/NLP_models/UK_statutory_instruments_normalised-bert-cased.t5",
+  "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": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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",
+  "transformers_version": "4.19.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161aeefafa77e085d8ab31ebaf7ff6d1d3052bf335e27bb785d3f169f159c594
+size 433590688