Upload folder using huggingface_hub

config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_ids": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-PER",
+    "1": "O",
+    "2": "I-PER",
+    "3": "B-LOC",
+    "4": "B-NUM",
+    "5": "B-ORG"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 3,
+    "B-NUM": 4,
+    "B-ORG": 5,
+    "B-PER": 0,
+    "I-PER": 2,
+    "O": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31923
+}

id2label.json

@@ -0,0 +1,8 @@
+{
+  "0": "B-PER",
+  "1": "O",
+  "2": "I-PER",
+  "3": "B-LOC",
+  "4": "B-NUM",
+  "5": "B-ORG"
+}

label2id.json

@@ -0,0 +1,8 @@
+{
+  "B-PER": 0,
+  "O": 1,
+  "I-PER": 2,
+  "B-LOC": 3,
+  "B-NUM": 4,
+  "B-ORG": 5
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30f29ffc7fff3db45d2cbc690fe5527b67ca364f147b60f5cfdeffa4177dbaef
+size 439912264

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 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "ignore_mismatched_sizes": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab4c35021e7ac954af153634ee70597ee8ea3e1c29513d4bc23e54857dedc68f
+size 5240

training_history.json

@@ -0,0 +1,79 @@
+[
+  {
+    "loss": 0.8685,
+    "grad_norm": 3.481233835220337,
+    "learning_rate": 9.900000000000002e-06,
+    "epoch": 0.7092198581560284,
+    "step": 100
+  },
+  {
+    "eval_loss": 0.2325897216796875,
+    "eval_accuracy": 0.9201523930470672,
+    "eval_f1": 0.717974180734856,
+    "eval_runtime": 3.2063,
+    "eval_samples_per_second": 174.345,
+    "eval_steps_per_second": 5.614,
+    "epoch": 1.0,
+    "step": 141
+  },
+  {
+    "loss": 0.2274,
+    "grad_norm": 1.5385990142822266,
+    "learning_rate": 1.9900000000000003e-05,
+    "epoch": 1.4184397163120568,
+    "step": 200
+  },
+  {
+    "eval_loss": 0.14628532528877258,
+    "eval_accuracy": 0.9490435748868958,
+    "eval_f1": 0.8258811152025249,
+    "eval_runtime": 3.1326,
+    "eval_samples_per_second": 178.447,
+    "eval_steps_per_second": 5.746,
+    "epoch": 2.0,
+    "step": 282
+  },
+  {
+    "loss": 0.1409,
+    "grad_norm": 1.131034016609192,
+    "learning_rate": 2.9900000000000002e-05,
+    "epoch": 2.127659574468085,
+    "step": 300
+  },
+  {
+    "loss": 0.1162,
+    "grad_norm": 1.4681241512298584,
+    "learning_rate": 3.99e-05,
+    "epoch": 2.8368794326241136,
+    "step": 400
+  },
+  {
+    "eval_loss": 0.16565711796283722,
+    "eval_accuracy": 0.9450750059528534,
+    "eval_f1": 0.8205513784461153,
+    "eval_runtime": 3.1398,
+    "eval_samples_per_second": 178.04,
+    "eval_steps_per_second": 5.733,
+    "epoch": 3.0,
+    "step": 423
+  },
+  {
+    "train_runtime": 218.6651,
+    "train_samples_per_second": 61.491,
+    "train_steps_per_second": 1.934,
+    "total_flos": 878380812168192.0,
+    "train_loss": 0.3254874164049225,
+    "epoch": 3.0,
+    "step": 423
+  },
+  {
+    "eval_loss": 0.12958413362503052,
+    "eval_accuracy": 0.9540563620836892,
+    "eval_f1": 0.8495117748420448,
+    "eval_runtime": 3.1102,
+    "eval_samples_per_second": 179.087,
+    "eval_steps_per_second": 5.787,
+    "epoch": 3.0,
+    "step": 423
+  }
+]