stackoverflow_tag_classification/initial_run/deberta-v3-xsmall/selective-skunk-437

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+license: mit
+base_model: microsoft/deberta-v3-xsmall
+tags:
+- generated_from_trainer
+model-index:
+- name: selective-skunk-437
+  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. -->
+
+# selective-skunk-437
+
+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: 0.3511
+- Hamming Loss: 0.1123
+- Zero One Loss: 1.0
+- Jaccard Score: 1.0
+- Hamming Loss Optimised: 0.1123
+- Hamming Loss Threshold: 0.9000
+- Zero One Loss Optimised: 1.0
+- Zero One Loss Threshold: 0.9000
+- Jaccard Score Optimised: 1.0
+- Jaccard Score Threshold: 0.9000
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 2024
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:------------:|:-------------:|:-------------:|:----------------------:|:----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|
+| 0.4991        | 1.0   | 50   | 0.3808          | 0.1123       | 1.0           | 1.0           | 0.1123                 | 0.9000                 | 1.0                     | 0.9000                  | 1.0                     | 0.9000                  |
+| 0.3696        | 2.0   | 100  | 0.3511          | 0.1123       | 1.0           | 1.0           | 0.1123                 | 0.9000                 | 1.0                     | 0.9000                  | 1.0                     | 0.9000                  |
+
+
+### Framework versions
+
+- Transformers 4.45.1
+- Pytorch 2.5.1+cu118
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,60 @@
+{
+  "_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": "numpy",
+    "2": "dictionary",
+    "3": "matplotlib",
+    "4": "pandas",
+    "5": "python-2.7",
+    "6": "regex",
+    "7": "list",
+    "8": "django",
+    "9": "string"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "dictionary": 2,
+    "django": 8,
+    "list": 7,
+    "matplotlib": 3,
+    "numpy": 1,
+    "pandas": 4,
+    "python-2.7": 5,
+    "python-3.x": 0,
+    "regex": 6,
+    "string": 9
+  },
+  "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": "4.45.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03ef429583ed7f58d9bf4914532bdc88fbdcaef7323686aba2757731d479ff07
+size 283359760

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d24c26b8cc69987e5a5ba5b7f4b3dfa2f5de3589a9cc932974333f964fd2b9aa
+size 5304