Training in progress epoch 0

README.md

@@ -0,0 +1,54 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: LovenOO/distilBERT_without_preprocessing
+  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. -->
+
+# LovenOO/distilBERT_without_preprocessing
+
+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: 1.2967
+- Validation Loss: 0.6749
+- Train Accuracy: 0.8333
+- 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', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2570, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, '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 |
+|:----------:|:---------------:|:--------------:|:-----:|
+| 1.2967     | 0.6749          | 0.8333         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.24.0
+- TensorFlow 2.13.0
+- Datasets 2.14.2
+- Tokenizers 0.11.0

config.json

@@ -0,0 +1,67 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Population and Society",
+    "1": "Children Education and Skills",
+    "2": "Gaps",
+    "3": "Covid",
+    "4": "Crime and Security",
+    "5": "Climate change",
+    "6": "Transport",
+    "7": "Economy",
+    "8": "Poverty",
+    "9": "Children Education and Skills (Post-16)",
+    "10": "Environment",
+    "11": "census_accounts",
+    "12": "Health and Social Care",
+    "13": "Housing Planning and Local Services",
+    "14": "Statistical Literacy",
+    "15": "accounts",
+    "16": "Children",
+    "17": "NI Health",
+    "18": "Ukraine",
+    "19": "Labour Market and Welfare"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Children": 16,
+    "Children Education and Skills": 1,
+    "Children Education and Skills (Post-16)": 9,
+    "Climate change": 5,
+    "Covid": 3,
+    "Crime and Security": 4,
+    "Economy": 7,
+    "Environment": 10,
+    "Gaps": 2,
+    "Health and Social Care": 12,
+    "Housing Planning and Local Services": 13,
+    "Labour Market and Welfare": 19,
+    "NI Health": 17,
+    "Population and Society": 0,
+    "Poverty": 8,
+    "Statistical Literacy": 14,
+    "Transport": 6,
+    "Ukraine": 18,
+    "accounts": 15,
+    "census_accounts": 11
+  },
+  "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": "4.24.0",
+  "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 sha256:4e36b932f4d0db0d0a8eb5f77cd4c472b65ea53d7d25b294c8de611e0d704442
+size 268010440

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "distilbert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}