RJuro commited on
Commit
68a17f9
1 Parent(s): 5dcb31b

Upload with huggingface_hub

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/content/drive/MyDrive/Colab/NER-bert-sci/ner-scibert-model_ddsa",
3
  "architectures": [
4
  "BertForTokenClassification"
5
  ],
@@ -9,36 +9,36 @@
9
  "hidden_dropout_prob": 0.1,
10
  "hidden_size": 768,
11
  "id2label": {
12
- "0": "B-Material",
13
- "1": "O",
14
- "2": "B-OtherScientificTerm",
15
- "3": "I-OtherScientificTerm",
16
- "4": "B-Generic",
17
- "5": "B-Method",
18
- "6": "I-Method",
19
- "7": "B-Task",
20
- "8": "I-Task",
21
- "9": "I-Material",
22
- "10": "B-Metric",
23
- "11": "I-Metric",
24
- "12": "I-Generic"
25
  },
26
  "initializer_range": 0.02,
27
  "intermediate_size": 3072,
28
  "label2id": {
29
- "B-Generic": 4,
30
- "B-Material": 0,
31
- "B-Method": 5,
32
- "B-Metric": 10,
33
- "B-OtherScientificTerm": 2,
34
- "B-Task": 7,
35
- "I-Generic": 12,
36
- "I-Material": 9,
37
- "I-Method": 6,
38
- "I-Metric": 11,
39
- "I-OtherScientificTerm": 3,
40
- "I-Task": 8,
41
- "O": 1
42
  },
43
  "layer_norm_eps": 1e-12,
44
  "max_position_embeddings": 512,
@@ -48,7 +48,7 @@
48
  "pad_token_id": 0,
49
  "position_embedding_type": "absolute",
50
  "torch_dtype": "float32",
51
- "transformers_version": "4.24.0",
52
  "type_vocab_size": 2,
53
  "use_cache": true,
54
  "vocab_size": 31116
 
1
  {
2
+ "_name_or_path": "allenai/scibert_scivocab_cased",
3
  "architectures": [
4
  "BertForTokenClassification"
5
  ],
 
9
  "hidden_dropout_prob": 0.1,
10
  "hidden_size": 768,
11
  "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12"
25
  },
26
  "initializer_range": 0.02,
27
  "intermediate_size": 3072,
28
  "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1,
31
+ "LABEL_10": 10,
32
+ "LABEL_11": 11,
33
+ "LABEL_12": 12,
34
+ "LABEL_2": 2,
35
+ "LABEL_3": 3,
36
+ "LABEL_4": 4,
37
+ "LABEL_5": 5,
38
+ "LABEL_6": 6,
39
+ "LABEL_7": 7,
40
+ "LABEL_8": 8,
41
+ "LABEL_9": 9
42
  },
43
  "layer_norm_eps": 1e-12,
44
  "max_position_embeddings": 512,
 
48
  "pad_token_id": 0,
49
  "position_embedding_type": "absolute",
50
  "torch_dtype": "float32",
51
+ "transformers_version": "4.12.5",
52
  "type_vocab_size": 2,
53
  "use_cache": true,
54
  "vocab_size": 31116
model_args.json ADDED
@@ -0,0 +1 @@
 
 
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 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d83abaa088500f60b311217a283ece7af9e343870723353ddd81d3a2fafa0c0d
3
- size 437498929
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc517e76fb87a4f030ce42995c9ce99bc3466dd0d90316326015a1a228ceb09
3
+ size 437514737
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json CHANGED
@@ -1,15 +1 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "do_basic_tokenize": true,
4
- "do_lower_case": false,
5
- "mask_token": "[MASK]",
6
- "name_or_path": "/content/drive/MyDrive/Colab/NER-bert-sci/ner-scibert-model_ddsa",
7
- "never_split": null,
8
- "pad_token": "[PAD]",
9
- "sep_token": "[SEP]",
10
- "special_tokens_map_file": null,
11
- "strip_accents": null,
12
- "tokenize_chinese_chars": true,
13
- "tokenizer_class": "BertTokenizer",
14
- "unk_token": "[UNK]"
15
- }
 
1
+ {"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"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
vocab.txt ADDED
The diff for this file is too large to render. See raw diff