Multilabel classifier v1.0 (micro-F1=0.86, macro-F1=0.26)

README.md

@@ -0,0 +1,62 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+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:
+- Loss: 0.0219
+- Micro F1: 0.8570
+- Macro F1: 0.2635
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Micro F1 | Macro F1 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
+| 0.0383        | 1.0   | 703  | 0.0328          | 0.7591   | 0.1626   |
+| 0.0279        | 2.0   | 1406 | 0.0245          | 0.8379   | 0.2323   |
+| 0.0237        | 3.0   | 2109 | 0.0219          | 0.8570   | 0.2635   |
+
+
+### Framework versions
+
+- Transformers 4.57.3
+- Pytorch 2.9.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,202 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "API",
+    "1": "Array API",
+    "2": "Blocker",
+    "3": "Breaking Change",
+    "4": "Bug",
+    "5": "Build / CI",
+    "6": "C/C++",
+    "7": "Closing candidate",
+    "8": "Developer API",
+    "9": "Documentation",
+    "10": "Easy",
+    "11": "Enhancement",
+    "12": "Hard",
+    "13": "High Priority",
+    "14": "Low Priority",
+    "15": "Meta-issue",
+    "16": "Metadata Routing",
+    "17": "Moderate",
+    "18": "Needs Benchmarks",
+    "19": "Needs Decision",
+    "20": "Needs Decision - Close",
+    "21": "Needs Decision - Include Feature",
+    "22": "Needs Info",
+    "23": "Needs Investigation",
+    "24": "Needs Reproducible Code",
+    "25": "Needs Triage",
+    "26": "New Feature",
+    "27": "Numerical Stability",
+    "28": "OS:Windows",
+    "29": "OS:macOS",
+    "30": "Packaging",
+    "31": "Pandas compatibility",
+    "32": "Performance",
+    "33": "Question",
+    "34": "RFC",
+    "35": "Refactor",
+    "36": "Regression",
+    "37": "Sprint",
+    "38": "Validation",
+    "39": "arch:arm",
+    "40": "cython",
+    "41": "float32",
+    "42": "free-threading",
+    "43": "frontend",
+    "44": "good first PR to review",
+    "45": "good first issue",
+    "46": "help wanted",
+    "47": "module:base",
+    "48": "module:calibration",
+    "49": "module:cluster",
+    "50": "module:compose",
+    "51": "module:covariance",
+    "52": "module:cross_decomposition",
+    "53": "module:datasets",
+    "54": "module:decomposition",
+    "55": "module:discriminant_analysis",
+    "56": "module:ensemble",
+    "57": "module:feature_extraction",
+    "58": "module:feature_selection",
+    "59": "module:gaussian_process",
+    "60": "module:impute",
+    "61": "module:inspection",
+    "62": "module:isotonic",
+    "63": "module:kernel_approximation",
+    "64": "module:linear_model",
+    "65": "module:manifold",
+    "66": "module:metrics",
+    "67": "module:mixture",
+    "68": "module:model_selection",
+    "69": "module:multiclass",
+    "70": "module:multioutput",
+    "71": "module:naive_bayes",
+    "72": "module:neighbors",
+    "73": "module:neural_network",
+    "74": "module:pipeline",
+    "75": "module:preprocessing",
+    "76": "module:semi_supervised",
+    "77": "module:svm",
+    "78": "module:test-suite",
+    "79": "module:tree",
+    "80": "module:utils",
+    "81": "pypy",
+    "82": "spam",
+    "83": "upstream bug",
+    "84": "wasm",
+    "85": "wontfix",
+    "86": "workflow"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "API": 0,
+    "Array API": 1,
+    "Blocker": 2,
+    "Breaking Change": 3,
+    "Bug": 4,
+    "Build / CI": 5,
+    "C/C++": 6,
+    "Closing candidate": 7,
+    "Developer API": 8,
+    "Documentation": 9,
+    "Easy": 10,
+    "Enhancement": 11,
+    "Hard": 12,
+    "High Priority": 13,
+    "Low Priority": 14,
+    "Meta-issue": 15,
+    "Metadata Routing": 16,
+    "Moderate": 17,
+    "Needs Benchmarks": 18,
+    "Needs Decision": 19,
+    "Needs Decision - Close": 20,
+    "Needs Decision - Include Feature": 21,
+    "Needs Info": 22,
+    "Needs Investigation": 23,
+    "Needs Reproducible Code": 24,
+    "Needs Triage": 25,
+    "New Feature": 26,
+    "Numerical Stability": 27,
+    "OS:Windows": 28,
+    "OS:macOS": 29,
+    "Packaging": 30,
+    "Pandas compatibility": 31,
+    "Performance": 32,
+    "Question": 33,
+    "RFC": 34,
+    "Refactor": 35,
+    "Regression": 36,
+    "Sprint": 37,
+    "Validation": 38,
+    "arch:arm": 39,
+    "cython": 40,
+    "float32": 41,
+    "free-threading": 42,
+    "frontend": 43,
+    "good first PR to review": 44,
+    "good first issue": 45,
+    "help wanted": 46,
+    "module:base": 47,
+    "module:calibration": 48,
+    "module:cluster": 49,
+    "module:compose": 50,
+    "module:covariance": 51,
+    "module:cross_decomposition": 52,
+    "module:datasets": 53,
+    "module:decomposition": 54,
+    "module:discriminant_analysis": 55,
+    "module:ensemble": 56,
+    "module:feature_extraction": 57,
+    "module:feature_selection": 58,
+    "module:gaussian_process": 59,
+    "module:impute": 60,
+    "module:inspection": 61,
+    "module:isotonic": 62,
+    "module:kernel_approximation": 63,
+    "module:linear_model": 64,
+    "module:manifold": 65,
+    "module:metrics": 66,
+    "module:mixture": 67,
+    "module:model_selection": 68,
+    "module:multiclass": 69,
+    "module:multioutput": 70,
+    "module:naive_bayes": 71,
+    "module:neighbors": 72,
+    "module:neural_network": 73,
+    "module:pipeline": 74,
+    "module:preprocessing": 75,
+    "module:semi_supervised": 76,
+    "module:svm": 77,
+    "module:test-suite": 78,
+    "module:tree": 79,
+    "module:utils": 80,
+    "pypy": 81,
+    "spam": 82,
+    "upstream bug": 83,
+    "wasm": 84,
+    "wontfix": 85,
+    "workflow": 86
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "multi_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.57.3",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb69ae8c4084811a8f52da55b8a82373c9faea52a4f9208e874c6f391f6c0f8
+size 268094036

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 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e06f4d876e1b28352bd8d5003ec12757b0878724530de8003fcbfab66cbb05fe
+size 5841