stackoverflow_tag_classification/initial_run/bert-base-cased/calm-toad-592

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google-bert/bert-base-cased
+tags:
+- generated_from_trainer
+model-index:
+- name: calm-toad-592
+  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. -->
+
+# calm-toad-592
+
+This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2100
+- Hamming Loss: 0.0635
+- Zero One Loss: 0.37
+- Jaccard Score: 0.3135
+- Hamming Loss Optimised: 0.0596
+- Hamming Loss Threshold: 0.7821
+- Zero One Loss Optimised: 0.3688
+- Zero One Loss Threshold: 0.5845
+- Jaccard Score Optimised: 0.3081
+- Jaccard Score Threshold: 0.4331
+
+## 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: 2.8076328160265536e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- 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: 7
+
+### 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 |
+|:-------------:|:-----:|:----:|:---------------:|:------------:|:-------------:|:-------------:|:----------------------:|:----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|
+| 0.2771        | 1.0   | 800  | 0.1783          | 0.0614       | 0.4938        | 0.4535        | 0.0606                 | 0.4706                 | 0.4275                  | 0.3518                  | 0.3479                  | 0.2844                  |
+| 0.1522        | 2.0   | 1600 | 0.1701          | 0.0585       | 0.38          | 0.3341        | 0.0579                 | 0.5975                 | 0.3738                  | 0.4904                  | 0.3057                  | 0.3508                  |
+| 0.1174        | 3.0   | 2400 | 0.1704          | 0.0616       | 0.405         | 0.3534        | 0.058                  | 0.7566                 | 0.3862                  | 0.3655                  | 0.3061                  | 0.2510                  |
+| 0.0897        | 4.0   | 3200 | 0.1823          | 0.0599       | 0.3738        | 0.3224        | 0.0581                 | 0.7112                 | 0.3688                  | 0.4400                  | 0.3068                  | 0.3538                  |
+| 0.0637        | 5.0   | 4000 | 0.1978          | 0.062        | 0.365         | 0.3132        | 0.0595                 | 0.6567                 | 0.3612                  | 0.4636                  | 0.3008                  | 0.2970                  |
+| 0.0486        | 6.0   | 4800 | 0.2055          | 0.0615       | 0.3625        | 0.3054        | 0.0595                 | 0.6736                 | 0.3638                  | 0.5862                  | 0.3029                  | 0.3143                  |
+| 0.038         | 7.0   | 5600 | 0.2100          | 0.0635       | 0.37          | 0.3135        | 0.0596                 | 0.7821                 | 0.3688                  | 0.5845                  | 0.3081                  | 0.4331                  |
+
+
+### Framework versions
+
+- Transformers 4.47.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "google-bert/bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "matplotlib",
+    "1": "dictionary",
+    "2": "list",
+    "3": "python-3.x",
+    "4": "django",
+    "5": "python-2.7",
+    "6": "pandas",
+    "7": "numpy",
+    "8": "string",
+    "9": "regex"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "dictionary": 1,
+    "django": 4,
+    "list": 2,
+    "matplotlib": 0,
+    "numpy": 7,
+    "pandas": 6,
+    "python-2.7": 5,
+    "python-3.x": 3,
+    "regex": 9,
+    "string": 8
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403dc2b40c88afe3ce2adc135cce6319dc75afbe509f0e52f3f94e56c9fb2c7e
+size 433295376

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": false,
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a3b711edcfe0f98454311ca206b154501f505438923afd12074bb50c6a2d287
+size 5496