Upload 10 files

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1.929975843125117e+16,
+    "train_loss": 0.1132796828881914,
+    "train_runtime": 2485.5568,
+    "train_samples_per_second": 211.269,
+    "train_steps_per_second": 4.401
+}

config.json

@@ -0,0 +1,92 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-ANIM",
+    "8": "I-ANIM",
+    "9": "B-BIO",
+    "10": "I-BIO",
+    "11": "B-CEL",
+    "12": "I-CEL",
+    "13": "B-DIS",
+    "14": "I-DIS",
+    "15": "B-EVE",
+    "16": "I-EVE",
+    "17": "B-FOOD",
+    "18": "I-FOOD",
+    "19": "B-INST",
+    "20": "I-INST",
+    "21": "B-MEDIA",
+    "22": "I-MEDIA",
+    "23": "B-MYTH",
+    "24": "I-MYTH",
+    "25": "B-PLANT",
+    "26": "I-PLANT",
+    "27": "B-TIME",
+    "28": "I-TIME",
+    "29": "B-VEHI",
+    "30": "I-VEHI"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ANIM": 7,
+    "B-BIO": 9,
+    "B-CEL": 11,
+    "B-DIS": 13,
+    "B-EVE": 15,
+    "B-FOOD": 17,
+    "B-INST": 19,
+    "B-LOC": 5,
+    "B-MEDIA": 21,
+    "B-MYTH": 23,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "B-PLANT": 25,
+    "B-TIME": 27,
+    "B-VEHI": 29,
+    "I-ANIM": 8,
+    "I-BIO": 10,
+    "I-CEL": 12,
+    "I-DIS": 14,
+    "I-EVE": 16,
+    "I-FOOD": 18,
+    "I-INST": 20,
+    "I-LOC": 6,
+    "I-MEDIA": 22,
+    "I-MYTH": 24,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "I-PLANT": 26,
+    "I-TIME": 28,
+    "I-VEHI": 30,
+    "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": "4.33.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8ae503b7cc85256bdd8d206cb41cb5e51c49dcf386f4d730d63b6b183b9d0e4
+size 431040051

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 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1.929975843125117e+16,
+    "train_loss": 0.1132796828881914,
+    "train_runtime": 2485.5568,
+    "train_samples_per_second": 211.269,
+    "train_steps_per_second": 4.401
+}

trainer_state.json

@@ -0,0 +1,286 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 10940,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.9998171846435103e-05,
+      "loss": 3.4748,
+      "step": 1
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7714808043875687e-05,
+      "loss": 0.3223,
+      "step": 1250
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.5429616087751372e-05,
+      "loss": 0.1466,
+      "step": 2500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.3144424131627058e-05,
+      "loss": 0.1219,
+      "step": 3750
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.0859232175502743e-05,
+      "loss": 0.1025,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0,
+      "eval_ANIM": {
+        "f1": 0.6988922457200403,
+        "number": 3208,
+        "precision": 0.5861486486486487,
+        "recall": 0.8653366583541147
+      },
+      "eval_BIO": {
+        "f1": 0.5263157894736842,
+        "number": 16,
+        "precision": 0.45454545454545453,
+        "recall": 0.625
+      },
+      "eval_CEL": {
+        "f1": 0.7659574468085106,
+        "number": 82,
+        "precision": 0.6792452830188679,
+        "recall": 0.8780487804878049
+      },
+      "eval_DIS": {
+        "f1": 0.6575342465753424,
+        "number": 1518,
+        "precision": 0.5229571984435798,
+        "recall": 0.8853754940711462
+      },
+      "eval_EVE": {
+        "f1": 0.958100558659218,
+        "number": 704,
+        "precision": 0.9423076923076923,
+        "recall": 0.9744318181818182
+      },
+      "eval_FOOD": {
+        "f1": 0.53125,
+        "number": 1132,
+        "precision": 0.38825448613376834,
+        "recall": 0.8409893992932862
+      },
+      "eval_INST": {
+        "f1": 0.5454545454545454,
+        "number": 24,
+        "precision": 0.42857142857142855,
+        "recall": 0.75
+      },
+      "eval_LOC": {
+        "f1": 0.9938849369774116,
+        "number": 24048,
+        "precision": 0.9942571785268415,
+        "recall": 0.9935129740518962
+      },
+      "eval_MEDIA": {
+        "f1": 0.9480381760339343,
+        "number": 916,
+        "precision": 0.9216494845360824,
+        "recall": 0.9759825327510917
+      },
+      "eval_MYTH": {
+        "f1": 0.6987951807228915,
+        "number": 64,
+        "precision": 0.5686274509803921,
+        "recall": 0.90625
+      },
+      "eval_ORG": {
+        "f1": 0.9804511278195489,
+        "number": 6618,
+        "precision": 0.9757557617479796,
+        "recall": 0.9851919008763977
+      },
+      "eval_PER": {
+        "f1": 0.9935385784872672,
+        "number": 10530,
+        "precision": 0.9941053432211447,
+        "recall": 0.9929724596391263
+      },
+      "eval_PLANT": {
+        "f1": 0.56656346749226,
+        "number": 1788,
+        "precision": 0.4331360946745562,
+        "recall": 0.8187919463087249
+      },
+      "eval_TIME": {
+        "f1": 0.7452830188679245,
+        "number": 578,
+        "precision": 0.6829971181556196,
+        "recall": 0.8200692041522492
+      },
+      "eval_VEHI": {
+        "f1": 0.8571428571428572,
+        "number": 64,
+        "precision": 0.7894736842105263,
+        "recall": 0.9375
+      },
+      "eval_loss": 0.09848607331514359,
+      "eval_overall_accuracy": 0.9839002953677689,
+      "eval_overall_f1": 0.9165482757984463,
+      "eval_overall_precision": 0.8698606149751348,
+      "eval_overall_recall": 0.9685318775589784,
+      "eval_runtime": 95.1985,
+      "eval_samples_per_second": 345.678,
+      "eval_steps_per_second": 7.206,
+      "step": 5470
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.574040219378429e-06,
+      "loss": 0.0791,
+      "step": 6250
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 6.288848263254113e-06,
+      "loss": 0.0668,
+      "step": 7500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.003656307129799e-06,
+      "loss": 0.0584,
+      "step": 8750
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.7184643510054846e-06,
+      "loss": 0.0526,
+      "step": 10000
+    },
+    {
+      "epoch": 2.0,
+      "eval_ANIM": {
+        "f1": 0.7314670813893208,
+        "number": 3208,
+        "precision": 0.6259982253771074,
+        "recall": 0.8796758104738155
+      },
+      "eval_BIO": {
+        "f1": 0.6363636363636364,
+        "number": 16,
+        "precision": 0.5,
+        "recall": 0.875
+      },
+      "eval_CEL": {
+        "f1": 0.7835051546391752,
+        "number": 82,
+        "precision": 0.6785714285714286,
+        "recall": 0.926829268292683
+      },
+      "eval_DIS": {
+        "f1": 0.6950578338590956,
+        "number": 1518,
+        "precision": 0.5783027121609798,
+        "recall": 0.8708827404479579
+      },
+      "eval_EVE": {
+        "f1": 0.9678321678321677,
+        "number": 704,
+        "precision": 0.953168044077135,
+        "recall": 0.9829545454545454
+      },
+      "eval_FOOD": {
+        "f1": 0.5880893300248139,
+        "number": 1132,
+        "precision": 0.45315487571701724,
+        "recall": 0.8374558303886925
+      },
+      "eval_INST": {
+        "f1": 0.5625000000000001,
+        "number": 24,
+        "precision": 0.45,
+        "recall": 0.75
+      },
+      "eval_LOC": {
+        "f1": 0.9941398944349777,
+        "number": 24048,
+        "precision": 0.9936030572401762,
+        "recall": 0.9946773120425815
+      },
+      "eval_MEDIA": {
+        "f1": 0.9540106951871657,
+        "number": 916,
+        "precision": 0.9350104821802935,
+        "recall": 0.9737991266375546
+      },
+      "eval_MYTH": {
+        "f1": 0.8055555555555555,
+        "number": 64,
+        "precision": 0.725,
+        "recall": 0.90625
+      },
+      "eval_ORG": {
+        "f1": 0.9806938159879336,
+        "number": 6618,
+        "precision": 0.9789220114423366,
+        "recall": 0.9824720459353279
+      },
+      "eval_PER": {
+        "f1": 0.9945915172217479,
+        "number": 10530,
+        "precision": 0.9937428896473265,
+        "recall": 0.9954415954415955
+      },
+      "eval_PLANT": {
+        "f1": 0.6153232242617718,
+        "number": 1788,
+        "precision": 0.478287841191067,
+        "recall": 0.8624161073825504
+      },
+      "eval_TIME": {
+        "f1": 0.7310030395136778,
+        "number": 578,
+        "precision": 0.6517615176151762,
+        "recall": 0.8321799307958477
+      },
+      "eval_VEHI": {
+        "f1": 0.8571428571428572,
+        "number": 64,
+        "precision": 0.7894736842105263,
+        "recall": 0.9375
+      },
+      "eval_loss": 0.11049605160951614,
+      "eval_overall_accuracy": 0.9861263597723507,
+      "eval_overall_f1": 0.9277588486101026,
+      "eval_overall_precision": 0.8877743728620296,
+      "eval_overall_recall": 0.9715149151881458,
+      "eval_runtime": 94.1134,
+      "eval_samples_per_second": 349.663,
+      "eval_steps_per_second": 7.289,
+      "step": 10940
+    },
+    {
+      "epoch": 2.0,
+      "step": 10940,
+      "total_flos": 1.929975843125117e+16,
+      "train_loss": 0.1132796828881914,
+      "train_runtime": 2485.5568,
+      "train_samples_per_second": 211.269,
+      "train_steps_per_second": 4.401
+    }
+  ],
+  "logging_steps": 1250,
+  "max_steps": 10940,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1.929975843125117e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c703d30f4b92af3adbd1285ac8dc67f3529f8939696ac473deb440cfcb72f8de
+size 4207