End of training

README.md

@@ -0,0 +1,99 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- anno_ctr
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: annoctr_bert_uncased
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: anno_ctr
+      type: anno_ctr
+      config: all_tags
+      split: test
+      args: all_tags
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.7928388746803069
+    - name: Recall
+      type: recall
+      value: 0.7809920945182869
+    - name: F1
+      type: f1
+      value: 0.7868708971553611
+    - name: Accuracy
+      type: accuracy
+      value: 0.936522196415268
+---
+
+<!-- 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. -->
+
+# annoctr_bert_uncased
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the anno_ctr dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3322
+- Precision: 0.7928
+- Recall: 0.7810
+- F1: 0.7869
+- Accuracy: 0.9365
+
+## 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: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.54          | 1.0   | 474  | 0.3452          | 0.6983    | 0.6601 | 0.6786 | 0.9137   |
+| 0.3013        | 2.0   | 948  | 0.3466          | 0.7774    | 0.7018 | 0.7376 | 0.9240   |
+| 0.0392        | 3.0   | 1422 | 0.3071          | 0.7851    | 0.7517 | 0.7680 | 0.9303   |
+| 0.5695        | 4.0   | 1896 | 0.2941          | 0.7810    | 0.7617 | 0.7712 | 0.9334   |
+| 0.0021        | 5.0   | 2370 | 0.3109          | 0.7928    | 0.7720 | 0.7823 | 0.9351   |
+| 0.0419        | 6.0   | 2844 | 0.3020          | 0.7772    | 0.7796 | 0.7784 | 0.9341   |
+| 0.2979        | 7.0   | 3318 | 0.3169          | 0.8019    | 0.7814 | 0.7915 | 0.9374   |
+| 0.0017        | 8.0   | 3792 | 0.3260          | 0.7972    | 0.7778 | 0.7874 | 0.9365   |
+| 0.0166        | 9.0   | 4266 | 0.3349          | 0.7935    | 0.7789 | 0.7861 | 0.9364   |
+| 0.0685        | 10.0  | 4740 | 0.3322          | 0.7928    | 0.7810 | 0.7869 | 0.9365   |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-SECTOR",
+    "1": "B-DATE",
+    "2": "B-TECHNIQUE",
+    "3": "I-LOC",
+    "4": "B-CON",
+    "5": "I-TACTIC",
+    "6": "I-CON",
+    "7": "I-DATE",
+    "8": "B-TOOL",
+    "9": "I-TECHNIQUE",
+    "10": "I-ORG",
+    "11": "B-MALWARE",
+    "12": "B-ORG",
+    "13": "I-TOOL",
+    "14": "B-GROUP",
+    "15": "O",
+    "16": "I-MALWARE",
+    "17": "B-TACTIC",
+    "18": "B-LOC",
+    "19": "I-GROUP",
+    "20": "B-CLICommand/CodeSnippet",
+    "21": "I-SECTOR",
+    "22": "I-CLICommand/CodeSnippet"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-CLICommand/CodeSnippet": 20,
+    "B-CON": 4,
+    "B-DATE": 1,
+    "B-GROUP": 14,
+    "B-LOC": 18,
+    "B-MALWARE": 11,
+    "B-ORG": 12,
+    "B-SECTOR": 0,
+    "B-TACTIC": 17,
+    "B-TECHNIQUE": 2,
+    "B-TOOL": 8,
+    "I-CLICommand/CodeSnippet": 22,
+    "I-CON": 6,
+    "I-DATE": 7,
+    "I-GROUP": 19,
+    "I-LOC": 3,
+    "I-MALWARE": 16,
+    "I-ORG": 10,
+    "I-SECTOR": 21,
+    "I-TACTIC": 5,
+    "I-TECHNIQUE": 9,
+    "I-TOOL": 13,
+    "O": 15
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bd33366def77d1563c5f1fe88f535e4b2824bb1c288d258dc2bf7361cfc70d7
+size 435660684

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": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52e2f34d902c0dd69a62a8a5bb82d7cc5fc827859a38bb0eb57dd316cdb3e29c
+size 4984