Upload with huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/content/drive/MyDrive/Colab/NER-bert-sci/ner-scibert-model_ddsa",
+  "_name_or_path": "allenai/scibert_scivocab_cased",
   "architectures": [
     "BertForTokenClassification"
   ],
@@ -9,36 +9,36 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "B-Material",
-    "1": "O",
-    "2": "B-OtherScientificTerm",
-    "3": "I-OtherScientificTerm",
-    "4": "B-Generic",
-    "5": "B-Method",
-    "6": "I-Method",
-    "7": "B-Task",
-    "8": "I-Task",
-    "9": "I-Material",
-    "10": "B-Metric",
-    "11": "I-Metric",
-    "12": "I-Generic"
+    "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"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "B-Generic": 4,
-    "B-Material": 0,
-    "B-Method": 5,
-    "B-Metric": 10,
-    "B-OtherScientificTerm": 2,
-    "B-Task": 7,
-    "I-Generic": 12,
-    "I-Material": 9,
-    "I-Method": 6,
-    "I-Metric": 11,
-    "I-OtherScientificTerm": 3,
-    "I-Task": 8,
-    "O": 1
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
@@ -48,7 +48,7 @@
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.24.0",
+  "transformers_version": "4.12.5",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 31116

model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": false, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 2e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "allenai/scibert_scivocab_cased", "model_type": "bert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 1, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 55, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": false, "labels_list": ["B-Material", "O", "B-OtherScientificTerm", "I-OtherScientificTerm", "B-Generic", "B-Method", "I-Method", "B-Task", "I-Task", "I-Material", "B-Metric", "I-Metric", "I-Generic"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d83abaa088500f60b311217a283ece7af9e343870723353ddd81d3a2fafa0c0d
-size 437498929
+oid sha256:9bc517e76fb87a4f030ce42995c9ce99bc3466dd0d90316326015a1a228ceb09
+size 437514737

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -1,15 +1 @@
-{
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": false,
-  "mask_token": "[MASK]",
-  "name_or_path": "/content/drive/MyDrive/Colab/NER-bert-sci/ner-scibert-model_ddsa",
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "special_tokens_map_file": null,
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
-}
+{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "allenai/scibert_scivocab_cased", "tokenizer_class": "BertTokenizer"}