initial Commit

Adding files from fine-tuning with bert-base-cased for NER tasks with conll2003.

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": "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"
+  },
+  "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,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "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": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a829dbd1e2459d4c4ac5499e5ce9502b956bf1787ee35a7086f72a465d38274
+size 430929740

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25e3b623f1b0aa28cb18c4db00cf2cf7859daf7a57ecadb435798dcb0f6ccde9
+size 861979194

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:705529cb45a3e77e6c3724513529127e7dc30b7e57e6da885ee385c3d754b03f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8904a3b84c2c1c1a8d603aad8decefcfa37724ed620464005af108446897134c
+size 1064

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 +1,55 @@
+{
+  "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": 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]"
+}

trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2634,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5694760820045558,
+      "grad_norm": 1.2870991230010986,
+      "learning_rate": 1.6203492786636296e-05,
+      "loss": 0.1607,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9892251037546519,
+      "eval_f1": 0.932541011047874,
+      "eval_loss": 0.03849802538752556,
+      "eval_precision": 0.9266467065868264,
+      "eval_recall": 0.938510781671159,
+      "eval_runtime": 24.1011,
+      "eval_samples_per_second": 134.849,
+      "eval_steps_per_second": 8.464,
+      "step": 878
+    },
+    {
+      "epoch": 1.1389521640091116,
+      "grad_norm": 1.1381593942642212,
+      "learning_rate": 1.240698557327259e-05,
+      "loss": 0.0444,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7084282460136673,
+      "grad_norm": 2.2290921211242676,
+      "learning_rate": 8.610478359908885e-06,
+      "loss": 0.0281,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9912320012470043,
+      "eval_f1": 0.9497939618198639,
+      "eval_loss": 0.03679182380437851,
+      "eval_precision": 0.9482787573467675,
+      "eval_recall": 0.9513140161725068,
+      "eval_runtime": 24.0032,
+      "eval_samples_per_second": 135.398,
+      "eval_steps_per_second": 8.499,
+      "step": 1756
+    },
+    {
+      "epoch": 2.277904328018223,
+      "grad_norm": 2.8408632278442383,
+      "learning_rate": 4.8139711465451785e-06,
+      "loss": 0.019,
+      "step": 2000
+    },
+    {
+      "epoch": 2.847380410022779,
+      "grad_norm": 0.38438597321510315,
+      "learning_rate": 1.0174639331814731e-06,
+      "loss": 0.0146,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2634,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2751824963545344.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d217a32840781057884f71d0c6cfc33211f434acf449615892d1990446b4cafd
+size 5112