Upload folder using huggingface_hub

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,92 @@
+---
+license: apache-2.0
+base_model: bert-base-cased
+tags:
+- generated_from_trainer
+datasets:
+- conll2003
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: bert-finetuned-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: 0.936092715231788
+    - name: Recall
+      type: recall
+      value: 0.9515314708852238
+    - name: F1
+      type: f1
+      value: 0.9437489567684861
+    - name: Accuracy
+      type: accuracy
+      value: 0.986504385706717
+---
+
+<!-- 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. -->
+
+# bert-finetuned-ner
+
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0597
+- Precision: 0.9361
+- Recall: 0.9515
+- F1: 0.9437
+- Accuracy: 0.9865
+
+## 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: 2e-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
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0794        | 1.0   | 1756 | 0.0703          | 0.9143    | 0.9317 | 0.9229 | 0.9808   |
+| 0.0346        | 2.0   | 3512 | 0.0573          | 0.9331    | 0.9490 | 0.9410 | 0.9861   |
+| 0.0191        | 3.0   | 5268 | 0.0597          | 0.9361    | 0.9515 | 0.9437 | 0.9865   |
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.0
+- Tokenizers 0.13.3

checkpoint-1756/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": "4.31.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

checkpoint-1756/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5b13cf849e37881a22023d827c8092f51450d3a37d121086ed138af6e4db77c
+size 861923909

checkpoint-1756/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c94abb0332ded24735b71a95bc6be31c1f784ffece54b9fb1cee31eb7e7337b
+size 430971305

checkpoint-1756/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2ec4b738d10fd57571de452ec625272641d74315bae317f926453e29fe0c76
+size 13553

checkpoint-1756/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d2673b41ff200e34ce1428ea0f6aa519740c87ece8f446df9868ddb7b08813
+size 627

checkpoint-1756/special_tokens_map.json

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

checkpoint-1756/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "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-1756/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 1756,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.810174639331815e-05,
+      "loss": 0.2574,
+      "step": 500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6203492786636296e-05,
+      "loss": 0.1076,
+      "step": 1000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.4305239179954442e-05,
+      "loss": 0.0794,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9808382881026667,
+      "eval_f1": 0.9228973910144204,
+      "eval_loss": 0.07026076316833496,
+      "eval_precision": 0.9142857142857143,
+      "eval_recall": 0.9316728374284753,
+      "eval_runtime": 490.5826,
+      "eval_samples_per_second": 6.625,
+      "eval_steps_per_second": 0.83,
+      "step": 1756
+    }
+  ],
+  "max_steps": 5268,
+  "num_train_epochs": 3,
+  "total_flos": 307479492426330.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1756/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a6e01967aba4e23de7904e8698e4b29526f7afd0798abe580d5932307236aa
+size 3963

checkpoint-3512/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": "4.31.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

checkpoint-3512/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74be4753c0abe380ff48bd7a1f94f240fc5a6dc1ddc7a32df725731df27f70ba
+size 861923909

checkpoint-3512/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b512d291ed8a17f1d620391c29484181db7450f72774974a242fed36f48d0216
+size 430971305

checkpoint-3512/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ec8bebfd85f39912455c3ddb2b58830364f9c8005441a2a685311f046b302f
+size 13553

checkpoint-3512/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32761276cf4965bc59816e8d72b145013cb6520efc0f0045aeb7a64bd47ff3c0
+size 627

checkpoint-3512/special_tokens_map.json

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

checkpoint-3512/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "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-3512/trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 3512,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.810174639331815e-05,
+      "loss": 0.2574,
+      "step": 500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6203492786636296e-05,
+      "loss": 0.1076,
+      "step": 1000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.4305239179954442e-05,
+      "loss": 0.0794,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9808382881026667,
+      "eval_f1": 0.9228973910144204,
+      "eval_loss": 0.07026076316833496,
+      "eval_precision": 0.9142857142857143,
+      "eval_recall": 0.9316728374284753,
+      "eval_runtime": 490.5826,
+      "eval_samples_per_second": 6.625,
+      "eval_steps_per_second": 0.83,
+      "step": 1756
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.240698557327259e-05,
+      "loss": 0.0588,
+      "step": 2000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.0508731966590738e-05,
+      "loss": 0.0419,
+      "step": 2500
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.610478359908885e-06,
+      "loss": 0.0437,
+      "step": 3000
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 6.712224753227031e-06,
+      "loss": 0.0346,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9861217401542356,
+      "eval_f1": 0.9410095953274927,
+      "eval_loss": 0.057285286486148834,
+      "eval_precision": 0.9331457885156379,
+      "eval_recall": 0.9490070683271625,
+      "eval_runtime": 491.5796,
+      "eval_samples_per_second": 6.611,
+      "eval_steps_per_second": 0.828,
+      "step": 3512
+    }
+  ],
+  "max_steps": 5268,
+  "num_train_epochs": 3,
+  "total_flos": 614577222463212.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3512/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a6e01967aba4e23de7904e8698e4b29526f7afd0798abe580d5932307236aa
+size 3963

checkpoint-5268/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": "4.31.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

checkpoint-5268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0918dd98ecfa7474e24451ca0c4d5ce54c02a5344bbf0e8c877def62f76d0fb7
+size 861923909

checkpoint-5268/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4569917fea8ff4835e7315149882a7a9ad673048923e3e318930ef4c49c53e
+size 430971305

checkpoint-5268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f369fbf294ac3edca8b203a13127bbf96ca15c4cbb92e91753942fcc41c42b7
+size 13553

checkpoint-5268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e7e8bd6502b144a381aeadde8571b5afaf3b9e9ee062ae653aa6a5305180ba
+size 627

checkpoint-5268/special_tokens_map.json

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

checkpoint-5268/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "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-5268/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 5268,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.810174639331815e-05,
+      "loss": 0.2574,
+      "step": 500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6203492786636296e-05,
+      "loss": 0.1076,
+      "step": 1000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.4305239179954442e-05,
+      "loss": 0.0794,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9808382881026667,
+      "eval_f1": 0.9228973910144204,
+      "eval_loss": 0.07026076316833496,
+      "eval_precision": 0.9142857142857143,
+      "eval_recall": 0.9316728374284753,
+      "eval_runtime": 490.5826,
+      "eval_samples_per_second": 6.625,
+      "eval_steps_per_second": 0.83,
+      "step": 1756
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.240698557327259e-05,
+      "loss": 0.0588,
+      "step": 2000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.0508731966590738e-05,
+      "loss": 0.0419,
+      "step": 2500
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.610478359908885e-06,
+      "loss": 0.0437,
+      "step": 3000
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 6.712224753227031e-06,
+      "loss": 0.0346,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9861217401542356,
+      "eval_f1": 0.9410095953274927,
+      "eval_loss": 0.057285286486148834,
+      "eval_precision": 0.9331457885156379,
+      "eval_recall": 0.9490070683271625,
+      "eval_runtime": 491.5796,
+      "eval_samples_per_second": 6.611,
+      "eval_steps_per_second": 0.828,
+      "step": 3512
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 4.8139711465451785e-06,
+      "loss": 0.0258,
+      "step": 4000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 2.9157175398633257e-06,
+      "loss": 0.0191,
+      "step": 4500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.0174639331814731e-06,
+      "loss": 0.0191,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.986504385706717,
+      "eval_f1": 0.9437489567684861,
+      "eval_loss": 0.05966141074895859,
+      "eval_precision": 0.936092715231788,
+      "eval_recall": 0.9515314708852238,
+      "eval_runtime": 487.1838,
+      "eval_samples_per_second": 6.671,
+      "eval_steps_per_second": 0.835,
+      "step": 5268
+    }
+  ],
+  "max_steps": 5268,
+  "num_train_epochs": 3,
+  "total_flos": 923635312577460.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a6e01967aba4e23de7904e8698e4b29526f7afd0798abe580d5932307236aa
+size 3963

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": "4.31.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4569917fea8ff4835e7315149882a7a9ad673048923e3e318930ef4c49c53e
+size 430971305

runs/Jul25_22-08-45_055f00759d15/events.out.tfevents.1690323088.055f00759d15.489.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:380759545d88f40fbf0e1a2f4c2f907f02da2307541677fbe7be1acd797e3a00
+size 7722

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 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a6e01967aba4e23de7904e8698e4b29526f7afd0798abe580d5932307236aa
+size 3963