Upload 11 files

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "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": 4096,
+  "label2id": {
+    "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,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81e60002e133897c4024a2dc8515b343843d994db18bf2cc78965f7d9cf5511c
+size 2673072357

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89867acad0de4ecc45896e74fb6aab16c2ca6b6f758df173f7e41d48b7c2b1b9
+size 1336557745

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74390ceb0548fc77a41fab0d84e03929f2835125c156040f32a4081e84d195e0
+size 17563

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c2522d9deea9ff7150a1554c735edc63b6ff8849453f55081ce2d93c2b680a
+size 623

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 +1,15 @@
+
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-large-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,340 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 25.0,
+  "global_step": 2125,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8444531864673486,
+      "eval_f1": 0.5546590729314982,
+      "eval_loss": 0.5102574229240417,
+      "eval_precision": 0.5133235724743778,
+      "eval_recall": 0.6032346868547832,
+      "eval_runtime": 19.295,
+      "eval_samples_per_second": 140.451,
+      "eval_steps_per_second": 1.14,
+      "step": 85
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8653029110936271,
+      "eval_f1": 0.6414725525329859,
+      "eval_loss": 0.43876737356185913,
+      "eval_precision": 0.6090318589545314,
+      "eval_recall": 0.6775636613902272,
+      "eval_runtime": 19.3861,
+      "eval_samples_per_second": 139.791,
+      "eval_steps_per_second": 1.135,
+      "step": 170
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8793863099921322,
+      "eval_f1": 0.6583135794107687,
+      "eval_loss": 0.3875023424625397,
+      "eval_precision": 0.648,
+      "eval_recall": 0.6689607708189952,
+      "eval_runtime": 19.4498,
+      "eval_samples_per_second": 139.333,
+      "eval_steps_per_second": 1.131,
+      "step": 255
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8793076317859952,
+      "eval_f1": 0.6649093904448106,
+      "eval_loss": 0.42981019616127014,
+      "eval_precision": 0.6378002528445006,
+      "eval_recall": 0.6944253269098417,
+      "eval_runtime": 19.1858,
+      "eval_samples_per_second": 141.25,
+      "eval_steps_per_second": 1.147,
+      "step": 340
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8806845003933911,
+      "eval_f1": 0.6834983498349835,
+      "eval_loss": 0.4551577568054199,
+      "eval_precision": 0.6566265060240963,
+      "eval_recall": 0.7126634549208534,
+      "eval_runtime": 19.2293,
+      "eval_samples_per_second": 140.93,
+      "eval_steps_per_second": 1.144,
+      "step": 425
+    },
+    {
+      "epoch": 5.88,
+      "learning_rate": 2.526771764705882e-05,
+      "loss": 0.3534,
+      "step": 500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8738788355625492,
+      "eval_f1": 0.6940358816874092,
+      "eval_loss": 0.5596204996109009,
+      "eval_precision": 0.6543736665650717,
+      "eval_recall": 0.7388162422573985,
+      "eval_runtime": 19.5147,
+      "eval_samples_per_second": 138.87,
+      "eval_steps_per_second": 1.127,
+      "step": 510
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8817073170731707,
+      "eval_f1": 0.6971866156151157,
+      "eval_loss": 0.5754502415657043,
+      "eval_precision": 0.6752660432118671,
+      "eval_recall": 0.7205781142463867,
+      "eval_runtime": 19.1934,
+      "eval_samples_per_second": 141.194,
+      "eval_steps_per_second": 1.146,
+      "step": 595
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.879897718332022,
+      "eval_f1": 0.7010550996483003,
+      "eval_loss": 0.6235392093658447,
+      "eval_precision": 0.6828711256117456,
+      "eval_recall": 0.7202339986235375,
+      "eval_runtime": 19.2793,
+      "eval_samples_per_second": 140.565,
+      "eval_steps_per_second": 1.141,
+      "step": 680
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8861132966168371,
+      "eval_f1": 0.7035076108537393,
+      "eval_loss": 0.6701436638832092,
+      "eval_precision": 0.6775015933715742,
+      "eval_recall": 0.7315898141775636,
+      "eval_runtime": 19.3944,
+      "eval_samples_per_second": 139.731,
+      "eval_steps_per_second": 1.134,
+      "step": 765
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8706530291109362,
+      "eval_f1": 0.6894660429101467,
+      "eval_loss": 0.7287982106208801,
+      "eval_precision": 0.6489523231096265,
+      "eval_recall": 0.7353750860289057,
+      "eval_runtime": 19.3186,
+      "eval_samples_per_second": 140.279,
+      "eval_steps_per_second": 1.139,
+      "step": 850
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.877537372147915,
+      "eval_f1": 0.6930596285434995,
+      "eval_loss": 0.7054932713508606,
+      "eval_precision": 0.6581064356435643,
+      "eval_recall": 0.7319339298004129,
+      "eval_runtime": 19.2233,
+      "eval_samples_per_second": 140.975,
+      "eval_steps_per_second": 1.144,
+      "step": 935
+    },
+    {
+      "epoch": 11.76,
+      "learning_rate": 1.7493035294117648e-05,
+      "loss": 0.0425,
+      "step": 1000
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.8837529504327302,
+      "eval_f1": 0.7010959814015278,
+      "eval_loss": 0.7131127119064331,
+      "eval_precision": 0.6774711168164314,
+      "eval_recall": 0.7264280798348245,
+      "eval_runtime": 19.4321,
+      "eval_samples_per_second": 139.46,
+      "eval_steps_per_second": 1.132,
+      "step": 1020
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.8865460267505901,
+      "eval_f1": 0.71240632805995,
+      "eval_loss": 0.7414566278457642,
+      "eval_precision": 0.6902226524685382,
+      "eval_recall": 0.7360633172746043,
+      "eval_runtime": 19.4932,
+      "eval_samples_per_second": 139.023,
+      "eval_steps_per_second": 1.129,
+      "step": 1105
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.8769079464988199,
+      "eval_f1": 0.7031301482701812,
+      "eval_loss": 0.820663332939148,
+      "eval_precision": 0.6744627054361567,
+      "eval_recall": 0.7343427391603579,
+      "eval_runtime": 19.2777,
+      "eval_samples_per_second": 140.577,
+      "eval_steps_per_second": 1.141,
+      "step": 1190
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.8817859952793077,
+      "eval_f1": 0.7152581769882118,
+      "eval_loss": 0.8483569622039795,
+      "eval_precision": 0.6910490856592878,
+      "eval_recall": 0.7412250516173434,
+      "eval_runtime": 19.4808,
+      "eval_samples_per_second": 139.112,
+      "eval_steps_per_second": 1.129,
+      "step": 1275
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.8836349331235248,
+      "eval_f1": 0.7072444591465431,
+      "eval_loss": 0.8380259275436401,
+      "eval_precision": 0.6808917197452229,
+      "eval_recall": 0.735719201651755,
+      "eval_runtime": 19.2903,
+      "eval_samples_per_second": 140.485,
+      "eval_steps_per_second": 1.14,
+      "step": 1360
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.8843430369787569,
+      "eval_f1": 0.7132094424912104,
+      "eval_loss": 0.8519468307495117,
+      "eval_precision": 0.6944897293772416,
+      "eval_recall": 0.7329662766689607,
+      "eval_runtime": 19.2344,
+      "eval_samples_per_second": 140.893,
+      "eval_steps_per_second": 1.144,
+      "step": 1445
+    },
+    {
+      "epoch": 17.65,
+      "learning_rate": 9.71835294117647e-06,
+      "loss": 0.0084,
+      "step": 1500
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.8830841856805665,
+      "eval_f1": 0.7116891779222945,
+      "eval_loss": 0.8689035773277283,
+      "eval_precision": 0.6903914590747331,
+      "eval_recall": 0.7343427391603579,
+      "eval_runtime": 19.4385,
+      "eval_samples_per_second": 139.414,
+      "eval_steps_per_second": 1.132,
+      "step": 1530
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.8835562549173879,
+      "eval_f1": 0.7146202743392439,
+      "eval_loss": 0.8715231418609619,
+      "eval_precision": 0.6953125,
+      "eval_recall": 0.7350309704060565,
+      "eval_runtime": 19.2513,
+      "eval_samples_per_second": 140.77,
+      "eval_steps_per_second": 1.143,
+      "step": 1615
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.885483870967742,
+      "eval_f1": 0.7111858704793944,
+      "eval_loss": 0.8707020282745361,
+      "eval_precision": 0.6956235603817045,
+      "eval_recall": 0.7274604267033723,
+      "eval_runtime": 19.2021,
+      "eval_samples_per_second": 141.13,
+      "eval_steps_per_second": 1.146,
+      "step": 1700
+    },
+    {
+      "epoch": 21.0,
+      "eval_accuracy": 0.8852478363493312,
+      "eval_f1": 0.7130956347884039,
+      "eval_loss": 0.8659564256668091,
+      "eval_precision": 0.6912144702842378,
+      "eval_recall": 0.7364074328974536,
+      "eval_runtime": 19.3453,
+      "eval_samples_per_second": 140.086,
+      "eval_steps_per_second": 1.137,
+      "step": 1785
+    },
+    {
+      "epoch": 22.0,
+      "eval_accuracy": 0.8861132966168371,
+      "eval_f1": 0.7195429339606789,
+      "eval_loss": 0.8910586833953857,
+      "eval_precision": 0.7031198686371101,
+      "eval_recall": 0.7367515485203028,
+      "eval_runtime": 19.253,
+      "eval_samples_per_second": 140.757,
+      "eval_steps_per_second": 1.143,
+      "step": 1870
+    },
+    {
+      "epoch": 23.0,
+      "eval_accuracy": 0.8848544453186468,
+      "eval_f1": 0.7184726176519846,
+      "eval_loss": 0.9158034920692444,
+      "eval_precision": 0.6998368678629691,
+      "eval_recall": 0.7381280110116999,
+      "eval_runtime": 19.2359,
+      "eval_samples_per_second": 140.882,
+      "eval_steps_per_second": 1.144,
+      "step": 1955
+    },
+    {
+      "epoch": 23.53,
+      "learning_rate": 1.943670588235294e-06,
+      "loss": 0.0026,
+      "step": 2000
+    },
+    {
+      "epoch": 24.0,
+      "eval_accuracy": 0.8862706530291109,
+      "eval_f1": 0.7187237615449201,
+      "eval_loss": 0.9025561809539795,
+      "eval_precision": 0.7018694653984913,
+      "eval_recall": 0.7364074328974536,
+      "eval_runtime": 19.4156,
+      "eval_samples_per_second": 139.578,
+      "eval_steps_per_second": 1.133,
+      "step": 2040
+    },
+    {
+      "epoch": 25.0,
+      "eval_accuracy": 0.8865066876475216,
+      "eval_f1": 0.718912569223024,
+      "eval_loss": 0.9014936089515686,
+      "eval_precision": 0.7016049787094661,
+      "eval_recall": 0.7370956641431521,
+      "eval_runtime": 19.2209,
+      "eval_samples_per_second": 140.992,
+      "eval_steps_per_second": 1.145,
+      "step": 2125
+    }
+  ],
+  "max_steps": 2125,
+  "num_train_epochs": 25,
+  "total_flos": 1.5762129485609082e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe7cdcd926dae7c2318f04bcf681a1ab9fa3c0d3736d6d2968248c5934cfc06
+size 3375