Training in progress epoch 0

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+base_model: distilbert/distilbert-base-uncased
+tags:
+- generated_from_keras_callback
+model-index:
+- name: aadhistii/distilbert-ner-model
+  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. -->
+
+# aadhistii/distilbert-ner-model
+
+This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.3520
+- Validation Loss: 0.3146
+- Train Precision: 0.4870
+- Train Recall: 0.1567
+- Train F1: 0.2371
+- Train Accuracy: 0.9304
+- 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': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 636, '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, 'weight_decay_rate': 0.01}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
+|:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
+| 0.3520     | 0.3146          | 0.4870          | 0.1567       | 0.2371   | 0.9304         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- TensorFlow 2.15.0
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-corporation",
+    "2": "I-corporation",
+    "3": "B-creative-work",
+    "4": "I-creative-work",
+    "5": "B-group",
+    "6": "I-group",
+    "7": "B-location",
+    "8": "I-location",
+    "9": "B-person",
+    "10": "I-person",
+    "11": "B-product",
+    "12": "I-product"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-corporation": 1,
+    "B-creative-work": 3,
+    "B-group": 5,
+    "B-location": 7,
+    "B-person": 9,
+    "B-product": 11,
+    "I-corporation": 2,
+    "I-creative-work": 4,
+    "I-group": 6,
+    "I-location": 8,
+    "I-person": 10,
+    "I-product": 12,
+    "O": 0
+  },
+  "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": "4.41.1",
+  "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 sha256:44b8b3060f3cb1c53037e21a42cd05476bbfef8497ccc25ad9494aef9c93842f
+size 265618704

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