Training in progress epoch 0

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_keras_callback
+model-index:
+- name: i-be-snek/distilbert-base-uncased-finetuned-ner-exp_B
+  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. -->
+
+# i-be-snek/distilbert-base-uncased-finetuned-ner-exp_B
+
+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: 0.0430
+- Validation Loss: 0.0424
+- Train Precision: 0.9177
+- Train Recall: 0.9270
+- Train F1: 0.9224
+- Train Accuracy: 0.9855
+- 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': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.0}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
+|:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
+| 0.0430     | 0.0424          | 0.9177          | 0.9270       | 0.9224   | 0.9855         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- TensorFlow 2.14.0
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,49 @@
+{
+  "_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-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-ANIM",
+    "8": "I-ANIM",
+    "9": "B-DIS",
+    "10": "I-DIS"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-ANIM": 7,
+    "B-DIS": 9,
+    "B-LOC": 5,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-ANIM": 8,
+    "I-DIS": 10,
+    "I-LOC": 6,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "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": "4.35.2",
+  "vocab_size": 30522
+}

logs/train/events.out.tfevents.1701531296.efd32f896b60.189.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:831f0df9ebd0b1c2dbf96da22736eea307edf51e0dd7c02c83f992d4ddc26ce7
+size 1606637

logs/validation/events.out.tfevents.1701533308.efd32f896b60.189.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d2daeea90ee2621d0ed806d762ee5b433d89527fbeb26c0095298ac0c2369cc
+size 233

metrics_by_entity.txt

@@ -0,0 +1 @@
+{"ANIM": {"precision": 0.7207253886010363, "recall": 0.6165780141843972, "f1": 0.6645962732919255, "number": "4512"}, "DIS": {"precision": 0.7083734359961501, "recall": 0.7907601396723073, "f1": 0.7473029572280746, "number": "7446"}, "LOC": {"precision": 0.9684916006615023, "recall": 0.9709424083769633, "f1": 0.969715456011155, "number": "22920"}, "ORG": {"precision": 0.9265191965420798, "recall": 0.943064182194617, "f1": 0.934718481467231, "number": "7728"}, "PER": {"precision": 0.9815356674402179, "recall": 0.9926530612244898, "f1": 0.9870630612348434, "number": "19600"}, "overall_precision": 0.9177249435055221, "overall_recall": 0.9270488377326946, "overall_f1": 0.9223633281085059, "overall_accuracy": 0.9854759246787036}

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 sha256:8312773d9625c3eb7dd4887ea0328aac15a04e69f8ea56cfad53ff5dfb6b7c81
+size 265612560

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]"
+}