add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,83 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- nerd
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model_index:
+- name: ner_nerd_fine
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: nerd
+      type: nerd
+      args: nerd
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.907666728485449
+---
+
+<!-- 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. -->
+
+# ner_nerd_fine
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the nerd dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3754
+- Precision: 0.6353
+- Recall: 0.6808
+- F1: 0.6573
+- Accuracy: 0.9077
+
+## 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: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.5486        | 1.0   | 8235  | 0.3279          | 0.6152    | 0.6643 | 0.6388 | 0.9034   |
+| 0.286         | 2.0   | 16470 | 0.3147          | 0.6392    | 0.6702 | 0.6543 | 0.9076   |
+| 0.2186        | 3.0   | 24705 | 0.3301          | 0.6402    | 0.6804 | 0.6597 | 0.9085   |
+| 0.1662        | 4.0   | 32940 | 0.3450          | 0.6369    | 0.6818 | 0.6586 | 0.9081   |
+| 0.1291        | 5.0   | 41175 | 0.3718          | 0.6398    | 0.6833 | 0.6608 | 0.9081   |
+
+
+### Framework versions
+
+- Transformers 4.9.1
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.2

config.json

@@ -0,0 +1,163 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "I-ART-broadcastprogram",
+    "2": "I-ART-film",
+    "3": "I-ART-music",
+    "4": "I-ART-other",
+    "5": "I-ART-painting",
+    "6": "I-ART-writtenart",
+    "7": "I-BUILDING-airport",
+    "8": "I-BUILDING-hospital",
+    "9": "I-BUILDING-hotel",
+    "10": "I-BUILDING-library",
+    "11": "I-BUILDING-other",
+    "12": "I-BUILDING-restaurant",
+    "13": "I-BUILDING-sportsfacility",
+    "14": "I-BUILDING-theater",
+    "15": "I-EVENT-attack/battle/war/militaryconflict",
+    "16": "I-EVENT-disaster",
+    "17": "I-EVENT-election",
+    "18": "I-EVENT-other",
+    "19": "I-EVENT-protest",
+    "20": "I-EVENT-sportsevent",
+    "21": "I-LOC-GPE",
+    "22": "I-LOC-bodiesofwater",
+    "23": "I-LOC-island",
+    "24": "I-LOC-mountain",
+    "25": "I-LOC-other",
+    "26": "I-LOC-park",
+    "27": "I-LOC-road/railway/highway/transit",
+    "28": "I-ORG-company",
+    "29": "I-ORG-education",
+    "30": "I-ORG-government/governmentagency",
+    "31": "I-ORG-media/newspaper",
+    "32": "I-ORG-other",
+    "33": "I-ORG-politicalparty",
+    "34": "I-ORG-religion",
+    "35": "I-ORG-showorganization",
+    "36": "I-ORG-sportsleague",
+    "37": "I-ORG-sportsteam",
+    "38": "I-MISC-astronomything",
+    "39": "I-MISC-award",
+    "40": "I-MISC-biologything",
+    "41": "I-MISC-chemicalthing",
+    "42": "I-MISC-currency",
+    "43": "I-MISC-disease",
+    "44": "I-MISC-educationaldegree",
+    "45": "I-MISC-god",
+    "46": "I-MISC-language",
+    "47": "I-MISC-law",
+    "48": "I-MISC-livingthing",
+    "49": "I-MISC-medical",
+    "50": "I-PER-actor",
+    "51": "I-PER-artist/author",
+    "52": "I-PER-athlete",
+    "53": "I-PER-director",
+    "54": "I-PER-other",
+    "55": "I-PER-politician",
+    "56": "I-PER-scholar",
+    "57": "I-PER-soldier",
+    "58": "I-PRODUCT-airplane",
+    "59": "I-PRODUCT-car",
+    "60": "I-PRODUCT-food",
+    "61": "I-PRODUCT-game",
+    "62": "I-PRODUCT-other",
+    "63": "I-PRODUCT-ship",
+    "64": "I-PRODUCT-software",
+    "65": "I-PRODUCT-train",
+    "66": "I-PRODUCT-weapon"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "I-ART-broadcastprogram": 1,
+    "I-ART-film": 2,
+    "I-ART-music": 3,
+    "I-ART-other": 4,
+    "I-ART-painting": 5,
+    "I-ART-writtenart": 6,
+    "I-BUILDING-airport": 7,
+    "I-BUILDING-hospital": 8,
+    "I-BUILDING-hotel": 9,
+    "I-BUILDING-library": 10,
+    "I-BUILDING-other": 11,
+    "I-BUILDING-restaurant": 12,
+    "I-BUILDING-sportsfacility": 13,
+    "I-BUILDING-theater": 14,
+    "I-EVENT-attack/battle/war/militaryconflict": 15,
+    "I-EVENT-disaster": 16,
+    "I-EVENT-election": 17,
+    "I-EVENT-other": 18,
+    "I-EVENT-protest": 19,
+    "I-EVENT-sportsevent": 20,
+    "I-LOC-GPE": 21,
+    "I-LOC-bodiesofwater": 22,
+    "I-LOC-island": 23,
+    "I-LOC-mountain": 24,
+    "I-LOC-other": 25,
+    "I-LOC-park": 26,
+    "I-LOC-road/railway/highway/transit": 27,
+    "I-MISC-astronomything": 38,
+    "I-MISC-award": 39,
+    "I-MISC-biologything": 40,
+    "I-MISC-chemicalthing": 41,
+    "I-MISC-currency": 42,
+    "I-MISC-disease": 43,
+    "I-MISC-educationaldegree": 44,
+    "I-MISC-god": 45,
+    "I-MISC-language": 46,
+    "I-MISC-law": 47,
+    "I-MISC-livingthing": 48,
+    "I-MISC-medical": 49,
+    "I-ORG-company": 28,
+    "I-ORG-education": 29,
+    "I-ORG-government/governmentagency": 30,
+    "I-ORG-media/newspaper": 31,
+    "I-ORG-other": 32,
+    "I-ORG-politicalparty": 33,
+    "I-ORG-religion": 34,
+    "I-ORG-showorganization": 35,
+    "I-ORG-sportsleague": 36,
+    "I-ORG-sportsteam": 37,
+    "I-PER-actor": 50,
+    "I-PER-artist/author": 51,
+    "I-PER-athlete": 52,
+    "I-PER-director": 53,
+    "I-PER-other": 54,
+    "I-PER-politician": 55,
+    "I-PER-scholar": 56,
+    "I-PER-soldier": 57,
+    "I-PRODUCT-airplane": 58,
+    "I-PRODUCT-car": 59,
+    "I-PRODUCT-food": 60,
+    "I-PRODUCT-game": 61,
+    "I-PRODUCT-other": 62,
+    "I-PRODUCT-ship": 63,
+    "I-PRODUCT-software": 64,
+    "I-PRODUCT-train": 65,
+    "I-PRODUCT-weapon": 66,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a614c0c6661455ee3d3c32b116229343fbd5cb0cbd2d4f5788a6911f9b26c5
+size 435856113

runs/Aug06_17-51-05_ip-172-31-23-147/1628272270.5875435/events.out.tfevents.1628272270.ip-172-31-23-147.9006.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ae323c7622d3dea29b8fd4efce13c7fa5a6be535366f9f5f432359eaa28202
+size 4214

runs/Aug06_17-51-05_ip-172-31-23-147/events.out.tfevents.1628272270.ip-172-31-23-147.9006.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2f593ad3136f8932d28c19630f6579ec3d3ff83b8d257388cbff0a4c4bc5e53
+size 10430

runs/Aug06_17-51-05_ip-172-31-23-147/events.out.tfevents.1628276889.ip-172-31-23-147.9006.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1dc890f6707c7924c5df4a6dec3cc1586c1a04df96faf8cc4d68bd070d08e83
+size 521

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

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac04fdef66105a39ad34870b24f4f33e177844b76833594869fd5afd1c02e96
+size 2607