End of training

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: distilbert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: distilbert-finetuned-ner-for-articles
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# distilbert-finetuned-ner-for-articles
+
+This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4393
+- Precision: 0.6848
+- Recall: 0.6391
+- F1: 0.6611
+- Accuracy: 0.8736
+
+## 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:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.4324        | 1.0   | 51   | 0.4654          | 0.6744    | 0.5577 | 0.6105 | 0.8598   |
+| 0.3106        | 2.0   | 102  | 0.4438          | 0.7041    | 0.6026 | 0.6494 | 0.8674   |
+| 0.2886        | 3.0   | 153  | 0.4378          | 0.6744    | 0.5987 | 0.6343 | 0.8678   |
+| 0.2724        | 4.0   | 204  | 0.4443          | 0.6788    | 0.6449 | 0.6614 | 0.8736   |
+| 0.2504        | 5.0   | 255  | 0.4393          | 0.6848    | 0.6391 | 0.6611 | 0.8736   |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,69 @@
+{
+  "_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": "S-CRIME",
+    "2": "S-CRIMINAL",
+    "3": "S-VICTIM",
+    "4": "S-TIMEDATE",
+    "5": "S-LOC",
+    "6": "S-TIMEWORD",
+    "7": "S-LOCWORD",
+    "8": "B-LOC",
+    "9": "E-LOC",
+    "10": "S-SUSPECT",
+    "11": "S-TIMEDAY",
+    "12": "S-TIMEDAYPART",
+    "13": "S-LOCDIR",
+    "14": "S-NATDISAS",
+    "15": "S-ACCIDENT",
+    "16": "S-TIMENUM",
+    "17": "I-LOC",
+    "18": "S-TIMEMISC",
+    "19": "S-OTHEROCC"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-LOC": 8,
+    "E-LOC": 9,
+    "I-LOC": 17,
+    "O": 0,
+    "S-ACCIDENT": 15,
+    "S-CRIME": 1,
+    "S-CRIMINAL": 2,
+    "S-LOC": 5,
+    "S-LOCDIR": 13,
+    "S-LOCWORD": 7,
+    "S-NATDISAS": 14,
+    "S-OTHEROCC": 19,
+    "S-SUSPECT": 10,
+    "S-TIMEDATE": 4,
+    "S-TIMEDAY": 11,
+    "S-TIMEDAYPART": 12,
+    "S-TIMEMISC": 18,
+    "S-TIMENUM": 16,
+    "S-TIMEWORD": 6,
+    "S-VICTIM": 3
+  },
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5be8dcdcd2cd18fa858da67eb5e8611c2a01358a0a282ad03717d85a25b6913
+size 260837504

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

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": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f50f34ad9df48bd891b98c07bb7a8d8ff534a564f9b71d17cbbda1e923bfdcb
+size 4984