Training in progress epoch 0

README.md

@@ -0,0 +1,53 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: silviacamplani/distilbert-uncase-finetuned-ai-ner
+  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. -->
+
+# silviacamplani/distilbert-uncase-finetuned-ai-ner
+
+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: 3.2660
+- Validation Loss: 3.0039
+- 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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 18, '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}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
+- training_precision: mixed_float16
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 3.2660     | 3.0039          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.18.0
+- TensorFlow 2.6.4
+- Datasets 2.1.0
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,85 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-product",
+    "10": "B-programlang",
+    "11": "B-algorithm",
+    "12": "I-algorithm",
+    "13": "B-misc",
+    "14": "I-misc",
+    "15": "I-university",
+    "16": "B-metrics",
+    "17": "B-organisation",
+    "18": "I-organisation",
+    "19": "I-metrics",
+    "2": "I-product",
+    "20": "B-conference",
+    "21": "I-conference",
+    "22": "B-country",
+    "23": "I-programlang",
+    "24": "B-location",
+    "25": "B-person",
+    "26": "I-person",
+    "27": "I-country",
+    "28": "I-location",
+    "3": "B-field",
+    "4": "I-field",
+    "5": "B-task",
+    "6": "I-task",
+    "7": "B-researcher",
+    "8": "I-researcher",
+    "9": "B-university"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-algorithm": "11",
+    "B-conference": "20",
+    "B-country": "22",
+    "B-field": "3",
+    "B-location": "24",
+    "B-metrics": "16",
+    "B-misc": "13",
+    "B-organisation": "17",
+    "B-person": "25",
+    "B-product": "1",
+    "B-programlang": "10",
+    "B-researcher": "7",
+    "B-task": "5",
+    "B-university": "9",
+    "I-algorithm": "12",
+    "I-conference": "21",
+    "I-country": "27",
+    "I-field": "4",
+    "I-location": "28",
+    "I-metrics": "19",
+    "I-misc": "14",
+    "I-organisation": "18",
+    "I-person": "26",
+    "I-product": "2",
+    "I-programlang": "23",
+    "I-researcher": "8",
+    "I-task": "6",
+    "I-university": "15",
+    "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": "4.18.0",
+  "vocab_size": 30522
+}

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:a6390c08454a3eaef46ba61bea4b188e91b1bc2a5f5b516fde7182cb832700e9
+size 265666976

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "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": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}