new model

config.json

@@ -1,232 +1,23 @@
 {
-  "_name_or_path": "experiments_final/model_dbmdz_bert_medium_historic_multilingual_cased_max_sequence_length_512_epochs_5_run_extended_suffix_baseline/checkpoint-450",
   "architectures": [
-    "ExtendedMultitaskModelForTokenClassification"
+    "MultitaskTimeModelForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "auto_map": {
-    "AutoConfig": "configuration_stacked.ImpressoConfig",
-    "AutoModelForTokenClassification": "modeling_stacked.ExtendedMultitaskModelForTokenClassification"
-  },
   "classifier_dropout": null,
-  "custom_pipelines": {
-    "generic-ner": {
-      "impl": "generic_ner.MultitaskTokenClassificationPipeline",
-      "pt": "AutoModelForTokenClassification"
-    }
-  },
+  "dtype": "float32",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 512,
   "initializer_range": 0.02,
   "intermediate_size": 2048,
-  "label_map": {
-    "NE-COARSE-LIT": {
-      "B-loc": 8,
-      "B-org": 0,
-      "B-pers": 7,
-      "B-prod": 4,
-      "B-time": 5,
-      "I-loc": 1,
-      "I-org": 2,
-      "I-pers": 9,
-      "I-prod": 10,
-      "I-time": 6,
-      "O": 3
-    },
-    "NE-COARSE-METO": {
-      "B-loc": 3,
-      "B-org": 0,
-      "B-time": 5,
-      "I-loc": 4,
-      "I-org": 2,
-      "O": 1
-    },
-    "NE-FINE-COMP": {
-      "B-comp.demonym": 8,
-      "B-comp.function": 5,
-      "B-comp.name": 1,
-      "B-comp.qualifier": 9,
-      "B-comp.title": 2,
-      "I-comp.demonym": 7,
-      "I-comp.function": 3,
-      "I-comp.name": 0,
-      "I-comp.qualifier": 10,
-      "I-comp.title": 4,
-      "O": 6
-    },
-    "NE-FINE-LIT": {
-      "B-loc.add.elec": 32,
-      "B-loc.add.phys": 5,
-      "B-loc.adm.nat": 34,
-      "B-loc.adm.reg": 39,
-      "B-loc.adm.sup": 12,
-      "B-loc.adm.town": 33,
-      "B-loc.fac": 36,
-      "B-loc.oro": 19,
-      "B-loc.phys.geo": 13,
-      "B-loc.phys.hydro": 28,
-      "B-loc.unk": 4,
-      "B-org.adm": 3,
-      "B-org.ent": 24,
-      "B-org.ent.pressagency": 37,
-      "B-pers.coll": 9,
-      "B-pers.ind": 0,
-      "B-pers.ind.articleauthor": 20,
-      "B-prod.doctr": 2,
-      "B-prod.media": 10,
-      "B-time.date.abs": 23,
-      "I-loc.add.elec": 22,
-      "I-loc.add.phys": 6,
-      "I-loc.adm.nat": 11,
-      "I-loc.adm.reg": 35,
-      "I-loc.adm.sup": 15,
-      "I-loc.adm.town": 8,
-      "I-loc.fac": 27,
-      "I-loc.oro": 21,
-      "I-loc.phys.geo": 25,
-      "I-loc.phys.hydro": 17,
-      "I-loc.unk": 40,
-      "I-org.adm": 29,
-      "I-org.ent": 1,
-      "I-org.ent.pressagency": 14,
-      "I-pers.coll": 26,
-      "I-pers.ind": 16,
-      "I-pers.ind.articleauthor": 31,
-      "I-prod.doctr": 30,
-      "I-prod.media": 38,
-      "I-time.date.abs": 7,
-      "O": 18
-    },
-    "NE-FINE-METO": {
-      "B-loc.adm.town": 6,
-      "B-loc.fac": 3,
-      "B-loc.oro": 5,
-      "B-org.adm": 1,
-      "B-org.ent": 7,
-      "B-time.date.abs": 9,
-      "I-loc.fac": 8,
-      "I-org.adm": 2,
-      "I-org.ent": 0,
-      "O": 4
-    },
-    "NE-NESTED": {
-      "B-loc.adm.nat": 13,
-      "B-loc.adm.reg": 15,
-      "B-loc.adm.sup": 10,
-      "B-loc.adm.town": 9,
-      "B-loc.fac": 18,
-      "B-loc.oro": 17,
-      "B-loc.phys.geo": 11,
-      "B-loc.phys.hydro": 1,
-      "B-org.adm": 4,
-      "B-org.ent": 20,
-      "B-pers.coll": 7,
-      "B-pers.ind": 2,
-      "B-prod.media": 23,
-      "I-loc.adm.nat": 8,
-      "I-loc.adm.reg": 14,
-      "I-loc.adm.town": 6,
-      "I-loc.fac": 0,
-      "I-loc.oro": 19,
-      "I-loc.phys.geo": 21,
-      "I-loc.phys.hydro": 22,
-      "I-org.adm": 5,
-      "I-org.ent": 3,
-      "I-pers.ind": 12,
-      "I-prod.media": 24,
-      "O": 16
-    }
-  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "stacked_bert",
+  "model_type": "bert",
   "num_attention_heads": 8,
   "num_hidden_layers": 8,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "pretrained_config": {
-    "_name_or_path": "dbmdz/bert-medium-historic-multilingual-cased",
-    "add_cross_attention": false,
-    "architectures": [
-      "BertForMaskedLM"
-    ],
-    "attention_probs_dropout_prob": 0.1,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
-    "classifier_dropout": null,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.1,
-    "hidden_size": 512,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_range": 0.02,
-    "intermediate_size": 2048,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-12,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 512,
-    "min_length": 0,
-    "model_type": "bert",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 8,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_hidden_layers": 8,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 0,
-    "position_embedding_type": "absolute",
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "type_vocab_size": 2,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": true,
-    "vocab_size": 32000
-  },
-  "torch_dtype": "float32",
-  "transformers_version": "4.40.0.dev0",
+  "transformers_version": "4.57.0.dev0",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 32000

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -45,6 +45,7 @@
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": false,
+  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "max_len": 512,
   "model_max_length": 512,

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc92dca5d693d80c40bfa708d0ee9551d1f85b832c57710b3edfc72dc86707e1
+size 2104