section classifier from section_v4_release

classification_report.json

@@ -0,0 +1,111 @@
+{
+  "abstract": {
+    "f1-score": 1.0,
+    "precision": 1.0,
+    "recall": 1.0,
+    "support": 388.0
+  },
+  "accuracy": 0.9930157593123209,
+  "acknowledgment": {
+    "f1-score": 0.9958847736625515,
+    "precision": 1.0,
+    "recall": 0.9918032786885246,
+    "support": 244.0
+  },
+  "author_contributions": {
+    "f1-score": 0.9710144927536232,
+    "precision": 0.9710144927536232,
+    "recall": 0.9710144927536232,
+    "support": 69.0
+  },
+  "coi": {
+    "f1-score": 0.971830985915493,
+    "precision": 0.9857142857142858,
+    "recall": 0.9583333333333334,
+    "support": 72.0
+  },
+  "discussion": {
+    "f1-score": 0.9896519285042333,
+    "precision": 0.9868667917448405,
+    "recall": 0.9924528301886792,
+    "support": 530.0
+  },
+  "endnote": {
+    "f1-score": 0.9929446713702191,
+    "precision": 0.9896373056994818,
+    "recall": 0.996274217585693,
+    "support": 1342.0
+  },
+  "ethics": {
+    "f1-score": 0.9808917197452229,
+    "precision": 1.0,
+    "recall": 0.9625,
+    "support": 160.0
+  },
+  "funding": {
+    "f1-score": 0.9964664310954063,
+    "precision": 0.9964664310954063,
+    "recall": 0.9964664310954063,
+    "support": 283.0
+  },
+  "intro": {
+    "f1-score": 0.9984917043740573,
+    "precision": 0.9969879518072289,
+    "recall": 1.0,
+    "support": 331.0
+  },
+  "keywords": {
+    "f1-score": 1.0,
+    "precision": 1.0,
+    "recall": 1.0,
+    "support": 286.0
+  },
+  "macro avg": {
+    "f1-score": 0.9896559151772297,
+    "precision": 0.990745651057533,
+    "recall": 0.9886625840013419,
+    "support": 5584.0
+  },
+  "method": {
+    "f1-score": 0.9873417721518988,
+    "precision": 0.9811320754716981,
+    "recall": 0.9936305732484076,
+    "support": 157.0
+  },
+  "open_data": {
+    "f1-score": 0.9726027397260274,
+    "precision": 0.9726027397260274,
+    "recall": 0.9726027397260274,
+    "support": 73.0
+  },
+  "references": {
+    "f1-score": 1.0,
+    "precision": 1.0,
+    "recall": 1.0,
+    "support": 345.0
+  },
+  "results": {
+    "f1-score": 0.9895470383275261,
+    "precision": 0.9793103448275862,
+    "recall": 1.0,
+    "support": 142.0
+  },
+  "title": {
+    "f1-score": 0.998661311914324,
+    "precision": 0.9973262032085561,
+    "recall": 1.0,
+    "support": 373.0
+  },
+  "unknown": {
+    "f1-score": 0.9891650732950924,
+    "precision": 0.9948717948717949,
+    "recall": 0.9835234474017744,
+    "support": 789.0
+  },
+  "weighted avg": {
+    "f1-score": 0.9930047754292499,
+    "precision": 0.9930450267296388,
+    "recall": 0.9930157593123209,
+    "support": 5584.0
+  }
+}

gate.json

@@ -0,0 +1,46 @@
+{
+  "checkpoint": "/tmp/bibr-training-phasec-830a047/checkpoints/section_v4_release",
+  "config": "configs/section_classifier_v4.yaml",
+  "corpus": "/tmp/bibr-training-phasec-830a047/section_v4",
+  "corpus_papers": 2482,
+  "corpus_rows": 36517,
+  "delta": 0.09518694180243625,
+  "label_classes": [
+    "abstract",
+    "acknowledgment",
+    "author_contributions",
+    "coi",
+    "discussion",
+    "endnote",
+    "ethics",
+    "funding",
+    "intro",
+    "keywords",
+    "method",
+    "open_data",
+    "references",
+    "results",
+    "title",
+    "unknown"
+  ],
+  "metric": "test_type_macro_f1",
+  "observed": 0.9896559151772297,
+  "pass": true,
+  "reason": "pass",
+  "split_summary": {
+    "test": {
+      "papers": 373,
+      "rows": 5584
+    },
+    "train": {
+      "papers": 1860,
+      "rows": 27294
+    },
+    "val": {
+      "papers": 249,
+      "rows": 3639
+    }
+  },
+  "threshold": 0.8944689733747935,
+  "v3_reference_type_macro_f1": 0.8944689733747935
+}

inference_config.json

@@ -0,0 +1 @@
+{"template_version": 3}

label_classes.json

@@ -0,0 +1 @@
+["abstract", "acknowledgment", "author_contributions", "coi", "discussion", "endnote", "ethics", "funding", "intro", "keywords", "method", "open_data", "references", "results", "title", "unknown"]

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8827d8ead8603bdff650774f07edbb6d77e56fb8c2486de9fdc59d6ce5b1aea3
+size 90891540

test_metrics.json

@@ -0,0 +1,27 @@
+{
+  "checkpoint": "/tmp/bibr-training-phasec-830a047/checkpoints/section_v4_release",
+  "config": "configs/section_classifier_v4.yaml",
+  "corpus": "/tmp/bibr-training-phasec-830a047/section_v4",
+  "corpus_papers": 2482,
+  "corpus_rows": 36517,
+  "n_test": 5584,
+  "n_test_papers": 373,
+  "split_summary": {
+    "test": {
+      "papers": 373,
+      "rows": 5584
+    },
+    "train": {
+      "papers": 1860,
+      "rows": 27294
+    },
+    "val": {
+      "papers": 249,
+      "rows": 3639
+    }
+  },
+  "template_version": 3,
+  "test_top_level_f1": 0.988171459576777,
+  "test_type_macro_f1": 0.9896559151772297,
+  "test_type_micro_f1": 0.9930157593123209
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}