Initial model upload

README.md

@@ -1,3 +1,5 @@
+# German GBERT LARGE Trained on Archival Data Containing Local History Facts
+
 ---
-license: cc-by-sa-4.0
----
+
+## license: cc-by-sa-4.0

config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "deepset/gbert-large",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-REGISTER",
+    "2": "I-REGISTER",
+    "3": "B-ZEIT",
+    "4": "I-ZEIT",
+    "5": "B-ORT",
+    "6": "I-ORT",
+    "7": "B-QUELLE",
+    "8": "I-QUELLE",
+    "9": "B-HAUS",
+    "10": "I-HAUS",
+    "11": "B-BERUF",
+    "12": "I-BERUF",
+    "13": "B-POI",
+    "14": "I-POI",
+    "15": "B-PERS",
+    "16": "I-PERS",
+    "17": "B-FIRMA",
+    "18": "I-FIRMA",
+    "19": "B-STRASSE",
+    "20": "I-STRASSE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-BERUF": 11,
+    "B-FIRMA": 17,
+    "B-HAUS": 9,
+    "B-ORT": 5,
+    "B-PERS": 15,
+    "B-POI": 13,
+    "B-QUELLE": 7,
+    "B-REGISTER": 1,
+    "B-STRASSE": 19,
+    "B-ZEIT": 3,
+    "I-BERUF": 12,
+    "I-FIRMA": 18,
+    "I-HAUS": 10,
+    "I-ORT": 6,
+    "I-PERS": 16,
+    "I-POI": 14,
+    "I-QUELLE": 8,
+    "I-REGISTER": 2,
+    "I-STRASSE": 20,
+    "I-ZEIT": 4,
+    "O": 0
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.2",
+  "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 sha256:592635d4fab5ae641981f0cc5a2fe748ecf99b47a93575fafa17f586e5ba1f9e
+size 1338877748

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bb5772ca8991d038ef4b954f83f57713eab658c380c09d1b6361c7f3c1549f3
+size 2677978087

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:013d13e4b269a8648da58d2f40bf48e004388ea0631771b8c8e588ab75375092
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa9d0002a7093b476e437f7fc9349f4919b728c176911d2ad82b8fe71e4a24ef
+size 1064

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 +1,59 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "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]"
+}

trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": 0.2930234372615814,
+  "best_model_checkpoint": "hf-ner-sample_004-gbert-large.model/checkpoint-115",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 115,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.3486529318541997,
+      "eval_loss": 0.8595609068870544,
+      "eval_precision": 0.32934131736526945,
+      "eval_recall": 0.37037037037037035,
+      "eval_runtime": 1.0185,
+      "eval_samples_per_second": 57.93,
+      "eval_steps_per_second": 2.946,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.6369230769230769,
+      "eval_loss": 0.47271719574928284,
+      "eval_precision": 0.5864022662889519,
+      "eval_recall": 0.696969696969697,
+      "eval_runtime": 0.9355,
+      "eval_samples_per_second": 63.071,
+      "eval_steps_per_second": 3.207,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.7248764415156508,
+      "eval_loss": 0.33701092004776,
+      "eval_precision": 0.7096774193548387,
+      "eval_recall": 0.7407407407407407,
+      "eval_runtime": 0.9711,
+      "eval_samples_per_second": 60.758,
+      "eval_steps_per_second": 3.089,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.765472312703583,
+      "eval_loss": 0.296609491109848,
+      "eval_precision": 0.7413249211356467,
+      "eval_recall": 0.7912457912457912,
+      "eval_runtime": 0.9576,
+      "eval_samples_per_second": 61.61,
+      "eval_steps_per_second": 3.133,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.7568438003220611,
+      "eval_loss": 0.2930234372615814,
+      "eval_precision": 0.7253086419753086,
+      "eval_recall": 0.7912457912457912,
+      "eval_runtime": 0.9995,
+      "eval_samples_per_second": 59.03,
+      "eval_steps_per_second": 3.002,
+      "step": 115
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 230,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 555656517635304.0,
+  "train_batch_size": 24,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da153a41811865f9d39826675d0707e386cba820ad73e3cf4b1f8b57adcd9dda
+size 5368