Training in progress epoch 0

README.md

@@ -0,0 +1,54 @@
+---
+license: apache-2.0
+base_model: distilbert-base-cased
+tags:
+- generated_from_keras_callback
+model-index:
+- name: nikoslefkos/nerbert_ontonotes
+  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. -->
+
+# nikoslefkos/nerbert_ontonotes
+
+This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.2213
+- Validation Loss: 0.1077
+- 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': 3e-05, 'decay_steps': 9360, '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 | Epoch |
+|:----------:|:---------------:|:-----:|
+| 0.2213     | 0.1077          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- TensorFlow 2.13.0
+- Datasets 2.14.0
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,102 @@
+{
+  "_name_or_path": "distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-CARDINAL",
+    "2": "B-DATE",
+    "3": "I-DATE",
+    "4": "B-PERSON",
+    "5": "I-PERSON",
+    "6": "B-NORP",
+    "7": "B-GPE",
+    "8": "I-GPE",
+    "9": "B-LAW",
+    "10": "I-LAW",
+    "11": "B-ORG",
+    "12": "I-ORG",
+    "13": "B-PERCENT",
+    "14": "I-PERCENT",
+    "15": "B-ORDINAL",
+    "16": "B-MONEY",
+    "17": "I-MONEY",
+    "18": "B-WORK_OF_ART",
+    "19": "I-WORK_OF_ART",
+    "20": "B-FAC",
+    "21": "B-TIME",
+    "22": "I-CARDINAL",
+    "23": "B-LOC",
+    "24": "B-QUANTITY",
+    "25": "I-QUANTITY",
+    "26": "I-NORP",
+    "27": "I-LOC",
+    "28": "B-PRODUCT",
+    "29": "I-TIME",
+    "30": "B-EVENT",
+    "31": "I-EVENT",
+    "32": "I-FAC",
+    "33": "B-LANGUAGE",
+    "34": "I-PRODUCT",
+    "35": "I-ORDINAL",
+    "36": "I-LANGUAGE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-CARDINAL": 1,
+    "B-DATE": 2,
+    "B-EVENT": 30,
+    "B-FAC": 20,
+    "B-GPE": 7,
+    "B-LANGUAGE": 33,
+    "B-LAW": 9,
+    "B-LOC": 23,
+    "B-MONEY": 16,
+    "B-NORP": 6,
+    "B-ORDINAL": 15,
+    "B-ORG": 11,
+    "B-PERCENT": 13,
+    "B-PERSON": 4,
+    "B-PRODUCT": 28,
+    "B-QUANTITY": 24,
+    "B-TIME": 21,
+    "B-WORK_OF_ART": 18,
+    "I-CARDINAL": 22,
+    "I-DATE": 3,
+    "I-EVENT": 31,
+    "I-FAC": 32,
+    "I-GPE": 8,
+    "I-LANGUAGE": 36,
+    "I-LAW": 10,
+    "I-LOC": 27,
+    "I-MONEY": 17,
+    "I-NORP": 26,
+    "I-ORDINAL": 35,
+    "I-ORG": 12,
+    "I-PERCENT": 14,
+    "I-PERSON": 5,
+    "I-PRODUCT": 34,
+    "I-QUANTITY": 25,
+    "I-TIME": 29,
+    "I-WORK_OF_ART": 19,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.31.0",
+  "vocab_size": 28996
+}

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 sha256:66dda3a250c9c832e5de13c5e879f60e8b868e03269de888106b06bd4af10831
+size 261004560

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "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]"
+}