adding distilbert uncased model finetuned on wnut17

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b1334ec50c70a86d0e252165dbd364f448ba5691305ae0abcd34a7027520500
+size 531039877

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8453c4da907b148b1aa2e3bbb645de5280a0c613e8bb1e74a9dede29fddff3a
+size 265524901

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:680de79ee84a9c81054a239af3d0262c28542463ff1a3599c32155512e7de1d1
+size 13553

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d62d927152cd93253f7ecff6a9e2d947d55232db9e2911408013c5fc1471ac3
+size 627

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": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,232 @@
+{
+  "best_metric": 0.2353149950504303,
+  "best_model_checkpoint": "C:/Users/avanjavakam/OneDrive - Moulton Niguel Water/Documents/R_Home/distilbert_ner\\checkpoint-660",
+  "epoch": 3.6956521739130435,
+  "global_step": 1020,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22,
+      "eval_accuracy": 0.910820401008935,
+      "eval_f1": 0.008086253369272238,
+      "eval_loss": 1.8291836977005005,
+      "eval_precision": 0.014814814814814815,
+      "eval_recall": 0.005560704355885079,
+      "eval_runtime": 101.8258,
+      "eval_samples_per_second": 12.639,
+      "eval_steps_per_second": 0.206,
+      "step": 60
+    },
+    {
+      "epoch": 0.43,
+      "eval_accuracy": 0.9256124150314223,
+      "eval_f1": 0.0,
+      "eval_loss": 0.458038866519928,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 111.7945,
+      "eval_samples_per_second": 11.512,
+      "eval_steps_per_second": 0.188,
+      "step": 120
+    },
+    {
+      "epoch": 0.65,
+      "eval_accuracy": 0.9256124150314223,
+      "eval_f1": 0.0,
+      "eval_loss": 0.3688420057296753,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 108.5973,
+      "eval_samples_per_second": 11.851,
+      "eval_steps_per_second": 0.193,
+      "step": 180
+    },
+    {
+      "epoch": 0.87,
+      "eval_accuracy": 0.9325809071865248,
+      "eval_f1": 0.18012866333095068,
+      "eval_loss": 0.31115037202835083,
+      "eval_precision": 0.39375,
+      "eval_recall": 0.11677479147358666,
+      "eval_runtime": 105.4344,
+      "eval_samples_per_second": 12.207,
+      "eval_steps_per_second": 0.199,
+      "step": 240
+    },
+    {
+      "epoch": 1.09,
+      "eval_accuracy": 0.9368133042623231,
+      "eval_f1": 0.29143214509068166,
+      "eval_loss": 0.2867625951766968,
+      "eval_precision": 0.4480769230769231,
+      "eval_recall": 0.2159406858202039,
+      "eval_runtime": 107.3207,
+      "eval_samples_per_second": 11.992,
+      "eval_steps_per_second": 0.196,
+      "step": 300
+    },
+    {
+      "epoch": 1.3,
+      "eval_accuracy": 0.9385661151725022,
+      "eval_f1": 0.35040431266846367,
+      "eval_loss": 0.2620603144168854,
+      "eval_precision": 0.41881443298969073,
+      "eval_recall": 0.30120481927710846,
+      "eval_runtime": 108.3989,
+      "eval_samples_per_second": 11.873,
+      "eval_steps_per_second": 0.194,
+      "step": 360
+    },
+    {
+      "epoch": 1.52,
+      "eval_accuracy": 0.9431832756188278,
+      "eval_f1": 0.4271523178807947,
+      "eval_loss": 0.2517760097980499,
+      "eval_precision": 0.5279672578444747,
+      "eval_recall": 0.3586654309545876,
+      "eval_runtime": 122.2843,
+      "eval_samples_per_second": 10.525,
+      "eval_steps_per_second": 0.172,
+      "step": 420
+    },
+    {
+      "epoch": 1.74,
+      "eval_accuracy": 0.9421144884784747,
+      "eval_f1": 0.43276036400404455,
+      "eval_loss": 0.24010969698429108,
+      "eval_precision": 0.4760845383759733,
+      "eval_recall": 0.39666357738646896,
+      "eval_runtime": 94.176,
+      "eval_samples_per_second": 13.666,
+      "eval_steps_per_second": 0.223,
+      "step": 480
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 2e-05,
+      "loss": 0.5257,
+      "step": 500
+    },
+    {
+      "epoch": 1.96,
+      "eval_accuracy": 0.9433542815612842,
+      "eval_f1": 0.44863731656184486,
+      "eval_loss": 0.24359002709388733,
+      "eval_precision": 0.5162846803377563,
+      "eval_recall": 0.39666357738646896,
+      "eval_runtime": 82.8193,
+      "eval_samples_per_second": 15.54,
+      "eval_steps_per_second": 0.254,
+      "step": 540
+    },
+    {
+      "epoch": 2.17,
+      "eval_accuracy": 0.9458766192125176,
+      "eval_f1": 0.45366379310344823,
+      "eval_loss": 0.2503388226032257,
+      "eval_precision": 0.5418275418275418,
+      "eval_recall": 0.3901760889712697,
+      "eval_runtime": 83.163,
+      "eval_samples_per_second": 15.476,
+      "eval_steps_per_second": 0.253,
+      "step": 600
+    },
+    {
+      "epoch": 2.39,
+      "eval_accuracy": 0.9451498439570775,
+      "eval_f1": 0.45833333333333337,
+      "eval_loss": 0.2353149950504303,
+      "eval_precision": 0.46853823814133594,
+      "eval_recall": 0.448563484708063,
+      "eval_runtime": 82.081,
+      "eval_samples_per_second": 15.68,
+      "eval_steps_per_second": 0.256,
+      "step": 660
+    },
+    {
+      "epoch": 2.61,
+      "eval_accuracy": 0.9475866786370827,
+      "eval_f1": 0.4585847504114098,
+      "eval_loss": 0.24050550162792206,
+      "eval_precision": 0.5618279569892473,
+      "eval_recall": 0.3873957367933272,
+      "eval_runtime": 86.6375,
+      "eval_samples_per_second": 14.855,
+      "eval_steps_per_second": 0.242,
+      "step": 720
+    },
+    {
+      "epoch": 2.83,
+      "eval_accuracy": 0.9481424479500663,
+      "eval_f1": 0.46777777777777774,
+      "eval_loss": 0.23974569141864777,
+      "eval_precision": 0.5839112343966713,
+      "eval_recall": 0.3901760889712697,
+      "eval_runtime": 86.3845,
+      "eval_samples_per_second": 14.899,
+      "eval_steps_per_second": 0.243,
+      "step": 780
+    },
+    {
+      "epoch": 3.04,
+      "eval_accuracy": 0.948398956863751,
+      "eval_f1": 0.48290598290598286,
+      "eval_loss": 0.245252326130867,
+      "eval_precision": 0.5699873896595208,
+      "eval_recall": 0.41890639481000924,
+      "eval_runtime": 83.9294,
+      "eval_samples_per_second": 15.334,
+      "eval_steps_per_second": 0.25,
+      "step": 840
+    },
+    {
+      "epoch": 3.26,
+      "eval_accuracy": 0.9486982172630499,
+      "eval_f1": 0.4776902887139107,
+      "eval_loss": 0.2514230012893677,
+      "eval_precision": 0.5508474576271186,
+      "eval_recall": 0.42168674698795183,
+      "eval_runtime": 81.402,
+      "eval_samples_per_second": 15.81,
+      "eval_steps_per_second": 0.258,
+      "step": 900
+    },
+    {
+      "epoch": 3.48,
+      "eval_accuracy": 0.9491257321191912,
+      "eval_f1": 0.47783783783783784,
+      "eval_loss": 0.26181262731552124,
+      "eval_precision": 0.5732814526588845,
+      "eval_recall": 0.40963855421686746,
+      "eval_runtime": 85.1954,
+      "eval_samples_per_second": 15.106,
+      "eval_steps_per_second": 0.246,
+      "step": 960
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 8.636363636363637e-06,
+      "loss": 0.0843,
+      "step": 1000
+    },
+    {
+      "epoch": 3.7,
+      "eval_accuracy": 0.9493394895472618,
+      "eval_f1": 0.48801742919389973,
+      "eval_loss": 0.2565685510635376,
+      "eval_precision": 0.5918097754293263,
+      "eval_recall": 0.4151992585727525,
+      "eval_runtime": 92.7674,
+      "eval_samples_per_second": 13.873,
+      "eval_steps_per_second": 0.226,
+      "step": 1020
+    }
+  ],
+  "max_steps": 1380,
+  "num_train_epochs": 5,
+  "total_flos": 216292519441470.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eacee13e77155bd35bd397be9ff18e665ccb9a6abe2d93bd2a63f8306be2e271
+size 3707