Training in progress epoch 0

README.md

@@ -0,0 +1,53 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: aalogan/bert-ner-nsm2
+  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. -->
+
+# aalogan/bert-ner-nsm2
+
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.4885
+- Validation Loss: 0.2361
+- 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2982, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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 | Epoch |
+|:----------:|:---------------:|:-----:|
+| 0.4885     | 0.2361          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.18.0
+- TensorFlow 2.8.0
+- Datasets 2.1.0
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,63 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "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": "O",
+    "1": "B-ORG",
+    "10": "I-PER",
+    "11": "B-ORT",
+    "12": "I-ORT",
+    "13": "B-DTR",
+    "14": "I-DTR",
+    "15": "B-ACL",
+    "16": "I-ACL",
+    "2": "I-ORG",
+    "3": "B-DTA",
+    "4": "I-DTA",
+    "5": "B-ACJ",
+    "6": "I-ACJ",
+    "7": "B-ROL",
+    "8": "I-ROL",
+    "9": "B-PER"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ACJ": "5",
+    "B-ACL": "15",
+    "B-DTA": "3",
+    "B-DTR": "13",
+    "B-ORG": "1",
+    "B-ORT": "11",
+    "B-PER": "9",
+    "B-ROL": "7",
+    "I-ACJ": "6",
+    "I-ACL": "16",
+    "I-DTA": "4",
+    "I-DTR": "14",
+    "I-ORG": "2",
+    "I-ORT": "12",
+    "I-PER": "10",
+    "I-ROL": "8",
+    "O": "0"
+  },
+  "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": "4.18.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a535a4a302e81677c93201930f2f6b8ec20b97751c950f70b72f7a4fc80e5c4e
+size 431204428

tokenizer_config.json

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