stackoverflow_tag_classification/initial_run/deberta-v3-xsmall/adaptable-fly-271

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+license: mit
+base_model: microsoft/deberta-v3-xsmall
+tags:
+- generated_from_trainer
+model-index:
+- name: adaptable-fly-271
+  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. -->
+
+# adaptable-fly-271
+
+This model is a fine-tuned version of [microsoft/deberta-v3-xsmall](https://huggingface.co/microsoft/deberta-v3-xsmall) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1619
+- Hamming Loss: 0.0439
+- Zero One Loss: 0.886
+- Jaccard Score: 0.8648
+- Hamming Loss Optimised: 0.0437
+- Hamming Loss Threshold: 0.5933
+- Zero One Loss Optimised: 0.839
+- Zero One Loss Threshold: 0.1736
+- Jaccard Score Optimised: 0.7401
+- Jaccard Score Threshold: 0.1334
+
+## 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: 5.379556445396376e-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: 4
+
+### 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  | 0.1853          | 0.0497       | 1.0           | 1.0           | 0.0497                 | 0.9000                 | 1.0                     | 0.9000                  | 1.0                     | 0.9000                  |
+| No log        | 2.0   | 320  | 0.1830          | 0.0497       | 1.0           | 1.0           | 0.0497                 | 0.9000                 | 1.0                     | 0.9000                  | 1.0                     | 0.9000                  |
+| No log        | 3.0   | 480  | 0.1690          | 0.0442       | 0.8738        | 0.8604        | 0.0456                 | 0.4236                 | 0.8588                  | 0.2889                  | 0.8410                  | 0.2889                  |
+| 0.2169        | 4.0   | 640  | 0.1621          | 0.0441       | 0.8712        | 0.8560        | 0.0438                 | 0.5821                 | 0.8225                  | 0.1746                  | 0.7466                  | 0.1429                  |
+
+
+### Framework versions
+
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu118
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,90 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-xsmall",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "python-3.x",
+    "1": "windows",
+    "2": "django",
+    "3": "list",
+    "4": "csv",
+    "5": "json",
+    "6": "numpy",
+    "7": "dictionary",
+    "8": "matplotlib",
+    "9": "flask",
+    "10": "beautifulsoup",
+    "11": "django-models",
+    "12": "multithreading",
+    "13": "python-2.7",
+    "14": "sqlalchemy",
+    "15": "arrays",
+    "16": "tkinter",
+    "17": "google-app-engine",
+    "18": "regex",
+    "19": "mysql",
+    "20": "scipy",
+    "21": "string",
+    "22": "pandas",
+    "23": "html",
+    "24": "linux"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "arrays": 15,
+    "beautifulsoup": 10,
+    "csv": 4,
+    "dictionary": 7,
+    "django": 2,
+    "django-models": 11,
+    "flask": 9,
+    "google-app-engine": 17,
+    "html": 23,
+    "json": 5,
+    "linux": 24,
+    "list": 3,
+    "matplotlib": 8,
+    "multithreading": 12,
+    "mysql": 19,
+    "numpy": 6,
+    "pandas": 22,
+    "python-2.7": 13,
+    "python-3.x": 0,
+    "regex": 18,
+    "scipy": 20,
+    "sqlalchemy": 14,
+    "string": 21,
+    "tkinter": 16,
+    "windows": 1
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 384,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "problem_type": "multi_label_classification",
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48b909dd9be06744a8c0472e475bad44da17a7da78580e8f5ff2b6c260df72c
+size 283382868

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f842290601325e1733bb4f507b36ab67e233a264af397c7856bb3df03270f6
+size 5368