Upload folder using huggingface_hub

config.json

@@ -0,0 +1,71 @@
+{
+  "apply_position_embeddings": true,
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": 0.0,
+  "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",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20"
+  },
+  "initializer_range": 0.01,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "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": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 4,
+  "position_embedding_type": "relative_key_query",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3976051fe2a7a144773caeaebbe9a707639dd0db2bb3011f119649f893f6165b
+size 498635236

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca9364bc0a1f5786d8ab23f2dbe4b19d995b9c67bc48b265bed0cbe78c24360
+size 994250891

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0fbc0aa227a8d80d5cd52d65d220ef4969e2492bb86392fd91dc52db90f26a1
+size 14645

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57459ee51d4cd9f8537c9eab28b29bea6e317e26245af868facafd63fbdcd384
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9217a3e4c1c197bdc3c269da044b7aa23b5f1c1eeb9f0bc1136873c083247f00
+size 1465

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_global_step": 7000,
+  "best_metric": 0.8717496172154136,
+  "best_model_checkpoint": "banBERT-Base-ner/checkpoint-7000",
+  "epoch": 0.3872538172161983,
+  "eval_steps": 1000,
+  "global_step": 7000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05532197388802833,
+      "grad_norm": 6.376655101776123,
+      "learning_rate": 4.9578094439787654e-05,
+      "loss": 0.4601,
+      "step": 1000
+    },
+    {
+      "epoch": 0.05532197388802833,
+      "eval_f1": 0.8369469378053125,
+      "eval_loss": 0.16556322574615479,
+      "eval_precision": 0.8429710358834732,
+      "eval_recall": 0.8536588983062214,
+      "eval_runtime": 30.8716,
+      "eval_samples_per_second": 252.303,
+      "eval_steps_per_second": 31.55,
+      "step": 1000
+    },
+    {
+      "epoch": 0.11064394777605666,
+      "grad_norm": 5.981681823730469,
+      "learning_rate": 4.864673558722176e-05,
+      "loss": 0.1688,
+      "step": 2000
+    },
+    {
+      "epoch": 0.11064394777605666,
+      "eval_f1": 0.8684155788385287,
+      "eval_loss": 0.15073692798614502,
+      "eval_precision": 0.8786383070318958,
+      "eval_recall": 0.8647918685142635,
+      "eval_runtime": 30.222,
+      "eval_samples_per_second": 257.726,
+      "eval_steps_per_second": 32.228,
+      "step": 2000
+    },
+    {
+      "epoch": 0.16596592166408497,
+      "grad_norm": 8.93840217590332,
+      "learning_rate": 4.771537673465586e-05,
+      "loss": 0.1682,
+      "step": 3000
+    },
+    {
+      "epoch": 0.16596592166408497,
+      "eval_f1": 0.8652855455238344,
+      "eval_loss": 0.14961303770542145,
+      "eval_precision": 0.8529293795796855,
+      "eval_recall": 0.882634319862615,
+      "eval_runtime": 30.5151,
+      "eval_samples_per_second": 255.251,
+      "eval_steps_per_second": 31.919,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2212878955521133,
+      "grad_norm": 11.654342651367188,
+      "learning_rate": 4.678401788208997e-05,
+      "loss": 0.1599,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2212878955521133,
+      "eval_f1": 0.85060492164182,
+      "eval_loss": 0.15266153216362,
+      "eval_precision": 0.8604386440507177,
+      "eval_recall": 0.8517179818649396,
+      "eval_runtime": 30.3777,
+      "eval_samples_per_second": 256.405,
+      "eval_steps_per_second": 32.063,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2766098694401416,
+      "grad_norm": 1.2951234579086304,
+      "learning_rate": 4.5852659029524075e-05,
+      "loss": 0.1473,
+      "step": 5000
+    },
+    {
+      "epoch": 0.2766098694401416,
+      "eval_f1": 0.8576298116414219,
+      "eval_loss": 0.13760635256767273,
+      "eval_precision": 0.8797513822853761,
+      "eval_recall": 0.8550127016283164,
+      "eval_runtime": 30.3473,
+      "eval_samples_per_second": 256.662,
+      "eval_steps_per_second": 32.095,
+      "step": 5000
+    },
+    {
+      "epoch": 0.33193184332816994,
+      "grad_norm": 9.229101181030273,
+      "learning_rate": 4.4921300176958186e-05,
+      "loss": 0.1453,
+      "step": 6000
+    },
+    {
+      "epoch": 0.33193184332816994,
+      "eval_f1": 0.8707701964752692,
+      "eval_loss": 0.14014214277267456,
+      "eval_precision": 0.8700724058976196,
+      "eval_recall": 0.8747071525772437,
+      "eval_runtime": 32.7251,
+      "eval_samples_per_second": 238.013,
+      "eval_steps_per_second": 29.763,
+      "step": 6000
+    },
+    {
+      "epoch": 0.3872538172161983,
+      "grad_norm": 12.196864128112793,
+      "learning_rate": 4.398994132439229e-05,
+      "loss": 0.1526,
+      "step": 7000
+    },
+    {
+      "epoch": 0.3872538172161983,
+      "eval_f1": 0.8717496172154136,
+      "eval_loss": 0.13219104707241058,
+      "eval_precision": 0.8705852927728186,
+      "eval_recall": 0.8764025942697206,
+      "eval_runtime": 31.7642,
+      "eval_samples_per_second": 245.213,
+      "eval_steps_per_second": 30.663,
+      "step": 7000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 54228,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1829391492096000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ecf5fa2c7e60f0b2c3b6bd0ed8092280b60c4ca5812d905c62d12f3f85a8dd
+size 5713