stackoverflow_tag_classification/initial_run/distilbert-base-cased/popular-snail-470

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert/distilbert-base-cased
+tags:
+- generated_from_trainer
+model-index:
+- name: popular-snail-470
+  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. -->
+
+# popular-snail-470
+
+This model is a fine-tuned version of [distilbert/distilbert-base-cased](https://huggingface.co/distilbert/distilbert-base-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1428
+- Hamming Loss: 0.0394
+- Zero One Loss: 0.8140
+- Jaccard Score: 0.7792
+- Hamming Loss Optimised: 0.0378
+- Hamming Loss Threshold: 0.2878
+- Zero One Loss Optimised: 0.71
+- Zero One Loss Threshold: 0.1741
+- Jaccard Score Optimised: 0.6376
+- Jaccard Score Threshold: 0.1616
+
+## 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: 5.0943791435964314e-05
+- train_batch_size: 20
+- eval_batch_size: 20
+- seed: 2024
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Hamming Loss | Zero One Loss | Jaccard Score | Hamming Loss Optimised | Hamming Loss Threshold | Zero One Loss Optimised | Zero One Loss Threshold | Jaccard Score Optimised | Jaccard Score Threshold |
+|:-------------:|:-----:|:----:|:---------------:|:------------:|:-------------:|:-------------:|:----------------------:|:----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|
+| No log        | 1.0   | 160  | 0.1685          | 0.0438       | 0.8812        | 0.8679        | 0.0438                 | 0.5944                 | 0.8812                  | 0.7111                  | 0.8679                  | 0.7111                  |
+| No log        | 2.0   | 320  | 0.1422          | 0.0398       | 0.815         | 0.7804        | 0.0363                 | 0.2166                 | 0.6925                  | 0.1817                  | 0.621                   | 0.1587                  |
+
+
+### Framework versions
+
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu118
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,80 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "linux",
+    "1": "beautifulsoup",
+    "2": "sqlalchemy",
+    "3": "python-2.7",
+    "4": "numpy",
+    "5": "json",
+    "6": "list",
+    "7": "windows",
+    "8": "string",
+    "9": "scipy",
+    "10": "mysql",
+    "11": "flask",
+    "12": "arrays",
+    "13": "tkinter",
+    "14": "multithreading",
+    "15": "csv",
+    "16": "python-3.x",
+    "17": "django-models",
+    "18": "regex",
+    "19": "html",
+    "20": "dictionary",
+    "21": "django",
+    "22": "matplotlib",
+    "23": "google-app-engine",
+    "24": "pandas"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "arrays": 12,
+    "beautifulsoup": 1,
+    "csv": 15,
+    "dictionary": 20,
+    "django": 21,
+    "django-models": 17,
+    "flask": 11,
+    "google-app-engine": 23,
+    "html": 19,
+    "json": 5,
+    "linux": 0,
+    "list": 6,
+    "matplotlib": 22,
+    "multithreading": 14,
+    "mysql": 10,
+    "numpy": 4,
+    "pandas": 24,
+    "python-2.7": 3,
+    "python-3.x": 16,
+    "regex": 18,
+    "scipy": 9,
+    "sqlalchemy": 2,
+    "string": 8,
+    "tkinter": 13,
+    "windows": 7
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d624ae05d2638cf0a7b440330120c4336c5951620da3610f2a920561a6e33f6
+size 263215436

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:737dabb56e6cdad0135e2367841558238512caf0a8a74ffbe60ef0082ee2db4f
+size 5432