stackoverflow_tag_classification/initial_run/roberta-base/bold-cod-455

README.md

@@ -0,0 +1,75 @@
+---
+library_name: transformers
+license: mit
+base_model: FacebookAI/roberta-base
+tags:
+- generated_from_trainer
+model-index:
+- name: bold-cod-455
+  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. -->
+
+# bold-cod-455
+
+This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1686
+- Hamming Loss: 0.0605
+- Zero One Loss: 0.38
+- Jaccard Score: 0.3247
+- Hamming Loss Optimised: 0.0579
+- Hamming Loss Threshold: 0.5913
+- Zero One Loss Optimised: 0.3862
+- Zero One Loss Threshold: 0.4581
+- Jaccard Score Optimised: 0.3111
+- Jaccard Score Threshold: 0.3022
+
+## 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: 2.6795250522175907e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- 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: 9
+
+### 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   | 100  | 0.2399          | 0.0751       | 0.6375        | 0.6196        | 0.0736                 | 0.4031                 | 0.5413                  | 0.2884                  | 0.4770                  | 0.2690                  |
+| No log        | 2.0   | 200  | 0.1861          | 0.062        | 0.4600        | 0.4166        | 0.0617                 | 0.6009                 | 0.4487                  | 0.4640                  | 0.3375                  | 0.2916                  |
+| No log        | 3.0   | 300  | 0.1692          | 0.0583       | 0.4525        | 0.4103        | 0.0579                 | 0.5425                 | 0.4087                  | 0.4147                  | 0.3241                  | 0.2491                  |
+| No log        | 4.0   | 400  | 0.1648          | 0.0589       | 0.4237        | 0.3791        | 0.0576                 | 0.5207                 | 0.4                     | 0.4601                  | 0.3181                  | 0.2985                  |
+| 0.2003        | 5.0   | 500  | 0.1648          | 0.0594       | 0.4087        | 0.3603        | 0.0574                 | 0.5612                 | 0.4113                  | 0.4029                  | 0.3139                  | 0.3039                  |
+| 0.2003        | 6.0   | 600  | 0.1707          | 0.0617       | 0.4025        | 0.3389        | 0.0587                 | 0.6338                 | 0.3988                  | 0.5041                  | 0.3148                  | 0.2846                  |
+| 0.2003        | 7.0   | 700  | 0.1701          | 0.0606       | 0.3888        | 0.3359        | 0.0586                 | 0.6001                 | 0.39                    | 0.4468                  | 0.3147                  | 0.2914                  |
+| 0.2003        | 8.0   | 800  | 0.1690          | 0.0614       | 0.385         | 0.3303        | 0.0584                 | 0.6970                 | 0.3838                  | 0.5334                  | 0.3155                  | 0.2859                  |
+| 0.2003        | 9.0   | 900  | 0.1686          | 0.0605       | 0.38          | 0.3247        | 0.0579                 | 0.5913                 | 0.3862                  | 0.4581                  | 0.3111                  | 0.3022                  |
+
+
+### Framework versions
+
+- Transformers 4.47.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a037c1216f3578d3d733d8b20b1d628b00d98e9e546d1ba278482f250bcdb31
+size 498637432

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4318faaca9779d192172db2ed09a213ed45508c336e3c56e0bb2fe38be9b12c9
+size 5496