model added

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "bert-base-multilingual-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 105879
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f5cdcbd9be9bf03764936528c700daee3b1d49c523c27c5d86dc484591e27f6
+size 667173367

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-multilingual-uncased"}

trainer_state.json

@@ -0,0 +1,96 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.8,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 0.5178,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.946119307248236,
+      "eval_f1": 0.9269931515699703,
+      "eval_loss": 0.20892712473869324,
+      "eval_precision": 0.9278323848939473,
+      "eval_recall": 0.9261554350632585,
+      "eval_runtime": 2.7187,
+      "eval_samples_per_second": 367.826,
+      "step": 625
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.3600000000000002e-05,
+      "loss": 0.2064,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9685695958948044,
+      "eval_f1": 0.9600723607701254,
+      "eval_loss": 0.1718911975622177,
+      "eval_precision": 0.9609415416451113,
+      "eval_recall": 0.9592047508391428,
+      "eval_runtime": 2.6825,
+      "eval_samples_per_second": 372.791,
+      "step": 1250
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.04e-05,
+      "loss": 0.1378,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9693713919178961,
+      "eval_f1": 0.961869302863012,
+      "eval_loss": 0.16582955420017242,
+      "eval_precision": 0.95658835546476,
+      "eval_recall": 0.9672088820036148,
+      "eval_runtime": 2.6697,
+      "eval_samples_per_second": 374.576,
+      "step": 1875
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.0884,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0616,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9757857601026299,
+      "eval_f1": 0.9698453608247423,
+      "eval_loss": 0.1476062387228012,
+      "eval_precision": 0.9680987908412657,
+      "eval_recall": 0.9715982442550994,
+      "eval_runtime": 4.3214,
+      "eval_samples_per_second": 231.405,
+      "step": 2500
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 0.0426,
+      "step": 3000
+    }
+  ],
+  "max_steps": 3125,
+  "num_train_epochs": 5,
+  "total_flos": 228175031247744.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e067d6e545a7da36bbbb792e004d1b4d68eac0bc82cc3bb3be58fe8e589dce65
+size 2415