first commit

.gitattributes

@@ -0,0 +1,59 @@
+checkpoint-1000/model.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/model.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/model.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-2500/model.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-2500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-3000/model.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-3000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-3500/model.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-3500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-4000/model.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-4000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-4500/model.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-4500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/model.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/model.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-5268/model.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-5268/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/rng_state.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/scheduler.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/training_args.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/rng_state.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/scheduler.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/training_args.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/rng_state.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/scheduler.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/training_args.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-2500/rng_state.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-2500/scheduler.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-2500/training_args.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-3000/rng_state.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-3000/scheduler.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-3000/training_args.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-3500/rng_state.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-3500/scheduler.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-3500/training_args.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-4000/rng_state.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-4000/scheduler.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-4000/training_args.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-4500/rng_state.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-4500/scheduler.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-4500/training_args.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/rng_state.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/scheduler.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/training_args.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/rng_state.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/scheduler.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/training_args.bin filter=lfs diff=lfs merge=lfs -text
+checkpoint-5268/rng_state.pth filter=lfs diff=lfs merge=lfs -text
+checkpoint-5268/scheduler.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-5268/training_args.bin filter=lfs diff=lfs merge=lfs -text
+runs/May26_06-25-40_c3c1060e04ec/events.out.tfevents.1716704756.c3c1060e04ec.954.0 filter=lfs diff=lfs merge=lfs -text
+runs/May26_06-25-40_c3c1060e04ec/events.out.tfevents.1716705623.c3c1060e04ec.954.1 filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,87 @@
+---
+license: apache-2.0
+base_model: google-bert/bert-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- conll2003
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: test-ner
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: conll2003
+      type: conll2003
+      config: conll2003
+      split: validation
+      args: conll2003
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.946619812583668
+    - name: Recall
+      type: recall
+      value: 0.9520363513968361
+    - name: F1
+      type: f1
+      value: 0.9493203557643899
+    - name: Accuracy
+      type: accuracy
+      value: 0.9896226782446167
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# test-ner
+
+This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the conll2003 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0498
+- Precision: 0.9466
+- Recall: 0.9520
+- F1: 0.9493
+- Accuracy: 0.9896
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.42.0.dev0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9896226782446167,
+    "eval_f1": 0.9493203557643899,
+    "eval_loss": 0.049828801304101944,
+    "eval_precision": 0.946619812583668,
+    "eval_recall": 0.9520363513968361,
+    "eval_runtime": 9.7904,
+    "eval_samples": 3250,
+    "eval_samples_per_second": 331.959,
+    "eval_steps_per_second": 41.572,
+    "total_flos": 891900038010780.0,
+    "train_loss": 0.043606681179258075,
+    "train_runtime": 849.8761,
+    "train_samples": 14041,
+    "train_samples_per_second": 49.564,
+    "train_steps_per_second": 6.199
+}

checkpoint-1000/config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "ner",
+  "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-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "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": "4.42.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8859eb08391d9ad2839d519001d76ed4b6684e26917957403a396f2251732083
+size 435617620

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e4065bc1fa53ddd0ef1d3246f28c9b4cf22a2623a11209bfbfd708a1bfe744
+size 871354938

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5486c9208386957d0c7174ac934979fe9d0d54ef0b04812efba089959b0af408
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa1c6be8c6e2d2dce7c70d0ae5c8f169db7ad1685d7af44aec127ca89e7d771
+size 1064

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "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]"
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5694760820045558,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2847380410022779,
+      "grad_norm": 2.7607381343841553,
+      "learning_rate": 4.525436598329537e-05,
+      "loss": 0.1616,
+      "step": 500
+    },
+    {
+      "epoch": 0.5694760820045558,
+      "grad_norm": 0.94535231590271,
+      "learning_rate": 4.050873196659074e-05,
+      "loss": 0.0728,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5268,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 168934961106000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63dfd2bc31481e060350e0c03d646ab35537d1667c980cc381c38e729511fc7a
+size 5112

checkpoint-1500/config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "ner",
+  "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-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "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": "4.42.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dddbe9ac00db89de4092c47817c6b86a8fa82a7c2ab9a5383cf4cc4afa33ce0f
+size 435617620

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2caa95c452f6aa92c455286336a1addf23205f13f405561e9410cd06645de3a
+size 871354938

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34bbff53e9b22f9546e02ab21f1515bedcdaf4229641757488ca166068b3504e
+size 14244

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1585352b864844478d94c858a87708af4c03469d44e8907d83c669b453b5654
+size 1064

checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "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]"
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8542141230068337,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2847380410022779,
+      "grad_norm": 2.7607381343841553,
+      "learning_rate": 4.525436598329537e-05,
+      "loss": 0.1616,
+      "step": 500
+    },
+    {
+      "epoch": 0.5694760820045558,
+      "grad_norm": 0.94535231590271,
+      "learning_rate": 4.050873196659074e-05,
+      "loss": 0.0728,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8542141230068337,
+      "grad_norm": 2.5376665592193604,
+      "learning_rate": 3.5763097949886106e-05,
+      "loss": 0.063,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5268,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 253845449351568.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63dfd2bc31481e060350e0c03d646ab35537d1667c980cc381c38e729511fc7a
+size 5112

checkpoint-2000/config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "ner",
+  "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-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "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": "4.42.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:181a539611492bddef2493ae28041701978557110d8a1db609157b8209117b34
+size 435617620

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bcf8db07e0a7c4dc767877db851f12444ee5c96b481d3fd50222cf5c4702164
+size 871354938

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35815f9cf8e7a0d3914a589a0d9bbcc907b37f2cc88601ab0c2117bab2340fb8
+size 14244

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c9d598d8830ba0028be8296b6d503e067e8d4e490df6001932e48104c4d9029
+size 1064

checkpoint-2000/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "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]"
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.1389521640091116,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2847380410022779,
+      "grad_norm": 2.7607381343841553,
+      "learning_rate": 4.525436598329537e-05,
+      "loss": 0.1616,
+      "step": 500
+    },
+    {
+      "epoch": 0.5694760820045558,
+      "grad_norm": 0.94535231590271,
+      "learning_rate": 4.050873196659074e-05,
+      "loss": 0.0728,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8542141230068337,
+      "grad_norm": 2.5376665592193604,
+      "learning_rate": 3.5763097949886106e-05,
+      "loss": 0.063,
+      "step": 1500
+    },
+    {
+      "epoch": 1.1389521640091116,
+      "grad_norm": 1.2084846496582031,
+      "learning_rate": 3.1017463933181475e-05,
+      "loss": 0.0425,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5268,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 339051956562216.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63dfd2bc31481e060350e0c03d646ab35537d1667c980cc381c38e729511fc7a
+size 5112

checkpoint-2500/config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "ner",
+  "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-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "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": "4.42.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08e75305c3713d4f0ca32d70a139dcd4d263a12565737643e4b4751a884f0e3f
+size 435617620

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44ed3b7b70a1d855f9ec6baef66d7f950003750c55ac8b8149445d4bee597b0
+size 871354938

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc5936524aaca82b4b7c78f0b94793f2239e75063af0ce6a1226295512a42cb
+size 14244

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53d07b70aee919d41805e8d2b1fbb2b2a58eb6bcf1c92c65db4f753386ace213
+size 1064

checkpoint-2500/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-2500/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "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]"
+}

checkpoint-2500/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4236902050113895,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2847380410022779,
+      "grad_norm": 2.7607381343841553,
+      "learning_rate": 4.525436598329537e-05,
+      "loss": 0.1616,
+      "step": 500
+    },
+    {
+      "epoch": 0.5694760820045558,
+      "grad_norm": 0.94535231590271,
+      "learning_rate": 4.050873196659074e-05,
+      "loss": 0.0728,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8542141230068337,
+      "grad_norm": 2.5376665592193604,
+      "learning_rate": 3.5763097949886106e-05,
+      "loss": 0.063,
+      "step": 1500
+    },
+    {
+      "epoch": 1.1389521640091116,
+      "grad_norm": 1.2084846496582031,
+      "learning_rate": 3.1017463933181475e-05,
+      "loss": 0.0425,
+      "step": 2000
+    },
+    {
+      "epoch": 1.4236902050113895,
+      "grad_norm": 0.5610941648483276,
+      "learning_rate": 2.6271829916476843e-05,
+      "loss": 0.0298,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5268,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 422500723573320.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63dfd2bc31481e060350e0c03d646ab35537d1667c980cc381c38e729511fc7a
+size 5112

checkpoint-3000/config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "ner",
+  "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-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "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": "4.42.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-3000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:587aa9eab668557375b4539eed73274856418beacf970fcd5440f68fe5421bdf
+size 435617620

checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d4cc3ba9a368c14b65feffd150ee7aa16aac5c35e61bd0d704f7353de3473ce
+size 871354938