bert-prodcat

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: bert-prodcat
+  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. -->
+
+# bert-prodcat
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7061
+- Accuracy: 0.8372
+- F1 Macro: 0.7861
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1 Macro |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|
+| 0.3823        | 0.2912 | 500  | 0.8749          | 0.7949   | 0.7250   |
+| 0.5849        | 0.5824 | 1000 | 0.8225          | 0.8090   | 0.7437   |
+| 0.6131        | 0.8736 | 1500 | 0.7716          | 0.8175   | 0.7532   |
+| 0.4162        | 1.1648 | 2000 | 0.7270          | 0.8375   | 0.7784   |
+| 0.4578        | 1.4560 | 2500 | 0.7239          | 0.8342   | 0.7761   |
+| 0.4166        | 1.7472 | 3000 | 0.7061          | 0.8372   | 0.7861   |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.8.0+cu126
+- Datasets 4.4.1
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,230 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1",
+    "2": "2",
+    "3": "3",
+    "4": "4",
+    "5": "5",
+    "6": "6",
+    "7": "7",
+    "8": "8",
+    "9": "9",
+    "10": "10",
+    "11": "11",
+    "12": "12",
+    "13": "13",
+    "14": "14",
+    "15": "15",
+    "16": "16",
+    "17": "17",
+    "18": "18",
+    "19": "19",
+    "20": "20",
+    "21": "21",
+    "22": "22",
+    "23": "23",
+    "24": "24",
+    "25": "25",
+    "26": "26",
+    "27": "27",
+    "28": "28",
+    "29": "29",
+    "30": "30",
+    "31": "31",
+    "32": "32",
+    "33": "33",
+    "34": "34",
+    "35": "35",
+    "36": "36",
+    "37": "37",
+    "38": "38",
+    "39": "39",
+    "40": "40",
+    "41": "41",
+    "42": "42",
+    "43": "43",
+    "44": "44",
+    "45": "45",
+    "46": "46",
+    "47": "47",
+    "48": "48",
+    "49": "49",
+    "50": "50",
+    "51": "51",
+    "52": "52",
+    "53": "53",
+    "54": "54",
+    "55": "55",
+    "56": "56",
+    "57": "57",
+    "58": "58",
+    "59": "59",
+    "60": "60",
+    "61": "61",
+    "62": "62",
+    "63": "63",
+    "64": "64",
+    "65": "65",
+    "66": "66",
+    "67": "67",
+    "68": "68",
+    "69": "69",
+    "70": "70",
+    "71": "71",
+    "72": "72",
+    "73": "73",
+    "74": "74",
+    "75": "75",
+    "76": "76",
+    "77": "77",
+    "78": "78",
+    "79": "79",
+    "80": "80",
+    "81": "81",
+    "82": "82",
+    "83": "83",
+    "84": "84",
+    "85": "85",
+    "86": "86",
+    "87": "87",
+    "88": "88",
+    "89": "89",
+    "90": "90",
+    "91": "91",
+    "92": "92",
+    "93": "93",
+    "94": "94",
+    "95": "95",
+    "96": "96",
+    "97": "97",
+    "98": "98",
+    "99": "99"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "10": 10,
+    "11": 11,
+    "12": 12,
+    "13": 13,
+    "14": 14,
+    "15": 15,
+    "16": 16,
+    "17": 17,
+    "18": 18,
+    "19": 19,
+    "2": 2,
+    "20": 20,
+    "21": 21,
+    "22": 22,
+    "23": 23,
+    "24": 24,
+    "25": 25,
+    "26": 26,
+    "27": 27,
+    "28": 28,
+    "29": 29,
+    "3": 3,
+    "30": 30,
+    "31": 31,
+    "32": 32,
+    "33": 33,
+    "34": 34,
+    "35": 35,
+    "36": 36,
+    "37": 37,
+    "38": 38,
+    "39": 39,
+    "4": 4,
+    "40": 40,
+    "41": 41,
+    "42": 42,
+    "43": 43,
+    "44": 44,
+    "45": 45,
+    "46": 46,
+    "47": 47,
+    "48": 48,
+    "49": 49,
+    "5": 5,
+    "50": 50,
+    "51": 51,
+    "52": 52,
+    "53": 53,
+    "54": 54,
+    "55": 55,
+    "56": 56,
+    "57": 57,
+    "58": 58,
+    "59": 59,
+    "6": 6,
+    "60": 60,
+    "61": 61,
+    "62": 62,
+    "63": 63,
+    "64": 64,
+    "65": 65,
+    "66": 66,
+    "67": 67,
+    "68": 68,
+    "69": 69,
+    "7": 7,
+    "70": 70,
+    "71": 71,
+    "72": 72,
+    "73": 73,
+    "74": 74,
+    "75": 75,
+    "76": 76,
+    "77": 77,
+    "78": 78,
+    "79": 79,
+    "8": 8,
+    "80": 80,
+    "81": 81,
+    "82": 82,
+    "83": 83,
+    "84": 84,
+    "85": 85,
+    "86": 86,
+    "87": 87,
+    "88": 88,
+    "89": 89,
+    "9": 9,
+    "90": 90,
+    "91": 91,
+    "92": 92,
+    "93": 93,
+    "94": 94,
+    "95": 95,
+    "96": 96,
+    "97": 97,
+    "98": 98,
+    "99": 99
+  },
+  "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": "single_label_classification",
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:626dd4fdca31d4cb2d5d3b2e0edeb7153d19334c4de19ac829168ce69f646404
+size 438260096

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": true,
+  "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 sha256:263aabb7d49a1dc7d08b090ee9b964abf07404ab09560dbfc8e85b30b90c9a02
+size 5777