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_A
+  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_A
+
+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: 0.0769
+- Validation Loss: 0.0717
+- Train Precision: 0.8796
+- Train Recall: 0.8706
+- Train F1: 0.8750
+- Train Accuracy: 0.9744
+- 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 |
+|:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
+| 0.0769     | 0.0717          | 0.8796          | 0.8706       | 0.8750   | 0.9744         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- TensorFlow 2.14.0
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,89 @@
+{
+  "_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-BIO",
+    "10": "I-BIO",
+    "11": "B-CEL",
+    "12": "I-CEL",
+    "13": "B-DIS",
+    "14": "I-DIS",
+    "15": "B-EVE",
+    "16": "I-EVE",
+    "17": "B-FOOD",
+    "18": "I-FOOD",
+    "19": "B-INST",
+    "20": "I-INST",
+    "21": "B-MEDIA",
+    "22": "I-MEDIA",
+    "23": "B-MYTH",
+    "24": "I-MYTH",
+    "25": "B-PLANT",
+    "26": "I-PLANT",
+    "27": "B-TIME",
+    "28": "I-TIME",
+    "29": "B-VEHI",
+    "30": "I-VEHI"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-ANIM": 7,
+    "B-BIO": 9,
+    "B-CEL": 11,
+    "B-DIS": 13,
+    "B-EVE": 15,
+    "B-FOOD": 17,
+    "B-INST": 19,
+    "B-LOC": 5,
+    "B-MEDIA": 21,
+    "B-MYTH": 23,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "B-PLANT": 25,
+    "B-TIME": 27,
+    "B-VEHI": 29,
+    "I-ANIM": 8,
+    "I-BIO": 10,
+    "I-CEL": 12,
+    "I-DIS": 14,
+    "I-EVE": 16,
+    "I-FOOD": 18,
+    "I-INST": 20,
+    "I-LOC": 6,
+    "I-MEDIA": 22,
+    "I-MYTH": 24,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "I-PLANT": 26,
+    "I-TIME": 28,
+    "I-VEHI": 30,
+    "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.1701442367.snek.4295.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec376fe4d8d44a302fa9e73405beb96dfcc100ef093a11d52b4d72883f31bb6e
+size 1606637

logs/validation/events.out.tfevents.1701443932.snek.4295.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b27a0a8afb838015294504feffdc9e4f4569eb0c8a05d894de26df530651d71
+size 233

metrics_by_entity.txt

@@ -0,0 +1 @@
+{"ANIM": {"precision": 0.7179719330013581, "recall": 0.7030141843971631, "f1": 0.7104143337066069, "number": "4512"}, "BIO": {"precision": 0.4186046511627907, "recall": 0.782608695652174, "f1": 0.5454545454545454, "number": "92"}, "CEL": {"precision": 0.8632478632478633, "recall": 0.8347107438016529, "f1": 0.8487394957983193, "number": "242"}, "DIS": {"precision": 0.7223607647547797, "recall": 0.7167995600769865, "f1": 0.7195694176097158, "number": "7274"}, "EVE": {"precision": 0.9050445103857567, "recall": 0.8815028901734104, "f1": 0.8931185944363104, "number": "692"}, "FOOD": {"precision": 0.6604984894259819, "recall": 0.5081348053457292, "f1": 0.5743842364532019, "number": "6884"}, "INST": {"precision": 0.7647058823529411, "recall": 0.6724137931034483, "f1": 0.7155963302752292, "number": "116"}, "LOC": {"precision": 0.9668465019143753, "recall": 0.9695462478184991, "f1": 0.9681944928546532, "number": "22920"}, "MEDIA": {"precision": 0.9396396396396396, "recall": 0.9362657091561939, "f1": 0.9379496402877698, "number": "2228"}, "MYTH": {"precision": 0.8831168831168831, "recall": 0.6476190476190476, "f1": 0.7472527472527473, "number": "210"}, "ORG": {"precision": 0.9344133786255553, "recall": 0.9254658385093167, "f1": 0.9299180860746327, "number": "7728"}, "PER": {"precision": 0.9824064711830132, "recall": 0.9914285714285714, "f1": 0.9868969019807008, "number": "19600"}, "PLANT": {"precision": 0.6186696900982616, "recall": 0.7275555555555555, "f1": 0.6687091503267973, "number": "4500"}, "TIME": {"precision": 0.7660098522167488, "recall": 0.7530266343825666, "f1": 0.7594627594627594, "number": "826"}, "VEHI": {"precision": 0.7655172413793103, "recall": 0.7985611510791367, "f1": 0.7816901408450705, "number": "278"}, "overall_precision": 0.8795860284605433, "overall_recall": 0.8705538910655297, "overall_f1": 0.8750466531962267, "overall_accuracy": 0.9744046905128749}

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:b45963a385a74900c21c7d5cd322a75418d69ea9968eb154e4beebefd29d5de8
+size 265674000

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]"
+}