kugler/gbert-large-AmDi-synset-classifier-marked

README.md

@@ -0,0 +1,86 @@
+---
+library_name: transformers
+license: mit
+base_model: deepset/gbert-large
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: gbert_synset_classifier_marked
+  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. -->
+
+# gbert_synset_classifier_marked
+
+This model is a fine-tuned version of [deepset/gbert-large](https://huggingface.co/deepset/gbert-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5043
+- Accuracy: 0.8515
+- F1: 0.8487
+- Precision: 0.8526
+- Recall: 0.8515
+- F1 Macro: 0.7531
+- Precision Macro: 0.7471
+- Recall Macro: 0.7706
+- F1 Micro: 0.8515
+- Precision Micro: 0.8515
+- Recall Micro: 0.8515
+
+## 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: 20
+- eval_batch_size: 20
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 80
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Precision | Recall | F1 Macro | Precision Macro | Recall Macro | F1 Micro | Precision Micro | Recall Micro |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:--------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|
+| 2.9643        | 0.3891 | 100  | 1.2450          | 0.7537   | 0.7157 | 0.7077    | 0.7537 | 0.4231   | 0.4210          | 0.4559       | 0.7537   | 0.7537          | 0.7537       |
+| 0.9779        | 0.7782 | 200  | 0.6959          | 0.8138   | 0.8009 | 0.8022    | 0.8138 | 0.5690   | 0.5784          | 0.5873       | 0.8138   | 0.8138          | 0.8138       |
+| 0.6664        | 1.1673 | 300  | 0.5947          | 0.8313   | 0.8222 | 0.8313    | 0.8313 | 0.6503   | 0.6570          | 0.6716       | 0.8313   | 0.8313          | 0.8313       |
+| 0.5523        | 1.5564 | 400  | 0.5216          | 0.8448   | 0.8365 | 0.8405    | 0.8448 | 0.6824   | 0.6759          | 0.7057       | 0.8448   | 0.8448          | 0.8448       |
+| 0.5126        | 1.9455 | 500  | 0.5216          | 0.8484   | 0.8417 | 0.8499    | 0.8484 | 0.7004   | 0.6848          | 0.7357       | 0.8484   | 0.8484          | 0.8484       |
+| 0.4103        | 2.3346 | 600  | 0.5001          | 0.8533   | 0.8497 | 0.8579    | 0.8533 | 0.7212   | 0.7252          | 0.7375       | 0.8533   | 0.8533          | 0.8533       |
+| 0.3733        | 2.7237 | 700  | 0.5010          | 0.8466   | 0.8403 | 0.8484    | 0.8466 | 0.7325   | 0.7274          | 0.7538       | 0.8466   | 0.8466          | 0.8466       |
+| 0.3654        | 3.1128 | 800  | 0.4934          | 0.8524   | 0.8478 | 0.8547    | 0.8524 | 0.7439   | 0.7411          | 0.7630       | 0.8524   | 0.8524          | 0.8524       |
+| 0.2761        | 3.5019 | 900  | 0.5038          | 0.8533   | 0.8495 | 0.8536    | 0.8533 | 0.7611   | 0.7527          | 0.7808       | 0.8533   | 0.8533          | 0.8533       |
+| 0.274         | 3.8911 | 1000 | 0.5043          | 0.8515   | 0.8487 | 0.8526    | 0.8515 | 0.7531   | 0.7471          | 0.7706       | 0.8515   | 0.8515          | 0.8515       |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,178 @@
+{
+  "_name_or_path": "deepset/gbert-large",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49",
+    "50": "LABEL_50",
+    "51": "LABEL_51",
+    "52": "LABEL_52",
+    "53": "LABEL_53",
+    "54": "LABEL_54",
+    "55": "LABEL_55",
+    "56": "LABEL_56",
+    "57": "LABEL_57",
+    "58": "LABEL_58",
+    "59": "LABEL_59",
+    "60": "LABEL_60",
+    "61": "LABEL_61",
+    "62": "LABEL_62",
+    "63": "LABEL_63",
+    "64": "LABEL_64",
+    "65": "LABEL_65",
+    "66": "LABEL_66",
+    "67": "LABEL_67",
+    "68": "LABEL_68",
+    "69": "LABEL_69",
+    "70": "LABEL_70",
+    "71": "LABEL_71",
+    "72": "LABEL_72",
+    "73": "LABEL_73"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
+    "LABEL_6": 6,
+    "LABEL_60": 60,
+    "LABEL_61": 61,
+    "LABEL_62": 62,
+    "LABEL_63": 63,
+    "LABEL_64": 64,
+    "LABEL_65": 65,
+    "LABEL_66": 66,
+    "LABEL_67": 67,
+    "LABEL_68": 68,
+    "LABEL_69": 69,
+    "LABEL_7": 7,
+    "LABEL_70": 70,
+    "LABEL_71": 71,
+    "LABEL_72": 72,
+    "LABEL_73": 73,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2ddace13f62c922990267f7c481a91c864b1a6de1770f2d160357d6d78a20ad
+size 1343293648

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 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "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:c3edd9a9a0c5f72afeb6f13a16942feee4ff84dca8d512412cf1c8b2c2127bd3
+size 5176