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

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_amdi_small
+  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_amdi_small
+
+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: 0.6371
+- Accuracy: 0.8443
+- F1: 0.8414
+- Precision: 0.8523
+- Recall: 0.8443
+- F1 Macro: 0.7742
+- Precision Macro: 0.7539
+- Recall Macro: 0.8118
+- F1 Micro: 0.8443
+- Precision Micro: 0.8443
+- Recall Micro: 0.8443
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 10
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:--------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|
+| 3.1817        | 0.6483 | 100  | 1.7424          | 0.6200   | 0.5455 | 0.5576    | 0.6200 | 0.2894   | 0.3465          | 0.2954       | 0.6200   | 0.6200          | 0.6200       |
+| 1.0711        | 1.2966 | 200  | 0.7171          | 0.8140   | 0.7971 | 0.7992    | 0.8140 | 0.5958   | 0.5870          | 0.6238       | 0.8140   | 0.8140          | 0.8140       |
+| 0.649         | 1.9449 | 300  | 0.6003          | 0.8275   | 0.8184 | 0.8282    | 0.8275 | 0.6797   | 0.6812          | 0.7138       | 0.8275   | 0.8275          | 0.8275       |
+| 0.4903        | 2.5932 | 400  | 0.5668          | 0.8336   | 0.8268 | 0.8375    | 0.8336 | 0.6942   | 0.6869          | 0.7271       | 0.8336   | 0.8336          | 0.8336       |
+| 0.4095        | 3.2415 | 500  | 0.5511          | 0.8387   | 0.8351 | 0.8398    | 0.8387 | 0.7224   | 0.7198          | 0.7414       | 0.8387   | 0.8387          | 0.8387       |
+| 0.3586        | 3.8898 | 600  | 0.5313          | 0.8415   | 0.8360 | 0.8452    | 0.8415 | 0.7188   | 0.7075          | 0.7481       | 0.8415   | 0.8415          | 0.8415       |
+| 0.2813        | 4.5381 | 700  | 0.5442          | 0.8485   | 0.8451 | 0.8502    | 0.8485 | 0.7290   | 0.7355          | 0.7419       | 0.8485   | 0.8485          | 0.8485       |
+| 0.2543        | 5.1864 | 800  | 0.5736          | 0.8494   | 0.8461 | 0.8515    | 0.8494 | 0.7812   | 0.7708          | 0.8047       | 0.8494   | 0.8494          | 0.8494       |
+| 0.1928        | 5.8347 | 900  | 0.5791          | 0.8448   | 0.8419 | 0.8484    | 0.8448 | 0.7646   | 0.7536          | 0.7899       | 0.8448   | 0.8448          | 0.8448       |
+| 0.1645        | 6.4830 | 1000 | 0.6371          | 0.8443   | 0.8414 | 0.8523    | 0.8443 | 0.7742   | 0.7539          | 0.8118       | 0.8443   | 0.8443          | 0.8443       |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,158 @@
+{
+  "_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"
+  },
+  "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_7": 7,
+    "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:c17b0ce5033387a36fe83a5104c9182258e5c1d94c50cdaeb346f6515ec9ddf2
+size 1343252648

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 sha256:8507961993ac7613b701b11a3e9dae232b096bb19f4bae84cd112c7f62583db5
+size 5176