Initial commit of bert-uncased news classifier model

config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "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": "U.S. NEWS",
+    "1": "COMEDY",
+    "10": "ENVIRONMENT",
+    "11": "EDUCATION",
+    "12": "CRIME",
+    "13": "SCIENCE",
+    "14": "WELLNESS",
+    "15": "BUSINESS",
+    "16": "STYLE & BEAUTY",
+    "17": "FOOD & DRINK",
+    "18": "MEDIA",
+    "19": "QUEER VOICES",
+    "2": "PARENTING",
+    "20": "HOME & LIVING",
+    "21": "WOMEN",
+    "22": "BLACK VOICES",
+    "23": "TRAVEL",
+    "24": "MONEY",
+    "25": "RELIGION",
+    "26": "LATINO VOICES",
+    "27": "IMPACT",
+    "28": "WEDDINGS",
+    "29": "COLLEGE",
+    "3": "WORLD NEWS",
+    "30": "PARENTS",
+    "31": "ARTS & CULTURE",
+    "32": "STYLE",
+    "33": "GREEN",
+    "34": "TASTE",
+    "35": "HEALTHY LIVING",
+    "36": "THE WORLDPOST",
+    "37": "GOOD NEWS",
+    "38": "WORLDPOST",
+    "39": "FIFTY",
+    "4": "CULTURE & ARTS",
+    "40": "ARTS",
+    "41": "DIVORCE",
+    "5": "TECH",
+    "6": "SPORTS",
+    "7": "ENTERTAINMENT",
+    "8": "POLITICS",
+    "9": "WEIRD NEWS"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ARTS": "40",
+    "ARTS & CULTURE": "31",
+    "BLACK VOICES": "22",
+    "BUSINESS": "15",
+    "COLLEGE": "29",
+    "COMEDY": "1",
+    "CRIME": "12",
+    "CULTURE & ARTS": "4",
+    "DIVORCE": "41",
+    "EDUCATION": "11",
+    "ENTERTAINMENT": "7",
+    "ENVIRONMENT": "10",
+    "FIFTY": "39",
+    "FOOD & DRINK": "17",
+    "GOOD NEWS": "37",
+    "GREEN": "33",
+    "HEALTHY LIVING": "35",
+    "HOME & LIVING": "20",
+    "IMPACT": "27",
+    "LATINO VOICES": "26",
+    "MEDIA": "18",
+    "MONEY": "24",
+    "PARENTING": "2",
+    "PARENTS": "30",
+    "POLITICS": "8",
+    "QUEER VOICES": "19",
+    "RELIGION": "25",
+    "SCIENCE": "13",
+    "SPORTS": "6",
+    "STYLE": "32",
+    "STYLE & BEAUTY": "16",
+    "TASTE": "34",
+    "TECH": "5",
+    "THE WORLDPOST": "36",
+    "TRAVEL": "23",
+    "U.S. NEWS": "0",
+    "WEDDINGS": "28",
+    "WEIRD NEWS": "9",
+    "WELLNESS": "14",
+    "WOMEN": "21",
+    "WORLD NEWS": "3",
+    "WORLDPOST": "38"
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa6be0aaac658b4e79fab7e42f7f9d4d32c08425baa21ac4fde8e4022dd7384b
+size 438081688

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3555de87341a2dcc8ec06724994441973550924e20a21e3f59d4534a16b5f82
+size 876287627

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:466050a5d97bb23ab888aaec723ecc1ca4313d5bb3cdff24cbf1d438a836b6bd
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3513ac14236a591f848e8f70b3bc13614b16e138e093f56d78106ac22054847
+size 1465

trainer_state.json

@@ -0,0 +1,191 @@
+{
+  "best_metric": 0.7803345268228339,
+  "best_model_checkpoint": "../models/bert-uncased-news-classifier/checkpoint-2096",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2096,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09541984732824428,
+      "grad_norm": 5.648463249206543,
+      "learning_rate": 4.9522900763358784e-05,
+      "loss": 2.538,
+      "step": 100
+    },
+    {
+      "epoch": 0.19083969465648856,
+      "grad_norm": 3.8880655765533447,
+      "learning_rate": 4.904580152671756e-05,
+      "loss": 1.6729,
+      "step": 200
+    },
+    {
+      "epoch": 0.2862595419847328,
+      "grad_norm": 5.740947723388672,
+      "learning_rate": 4.856870229007634e-05,
+      "loss": 1.461,
+      "step": 300
+    },
+    {
+      "epoch": 0.3816793893129771,
+      "grad_norm": 3.8042280673980713,
+      "learning_rate": 4.809160305343512e-05,
+      "loss": 1.3513,
+      "step": 400
+    },
+    {
+      "epoch": 0.4770992366412214,
+      "grad_norm": 3.8541226387023926,
+      "learning_rate": 4.7614503816793896e-05,
+      "loss": 1.291,
+      "step": 500
+    },
+    {
+      "epoch": 0.5725190839694656,
+      "grad_norm": 12.443678855895996,
+      "learning_rate": 4.713740458015267e-05,
+      "loss": 1.2381,
+      "step": 600
+    },
+    {
+      "epoch": 0.6679389312977099,
+      "grad_norm": 4.856504917144775,
+      "learning_rate": 4.666030534351145e-05,
+      "loss": 1.1978,
+      "step": 700
+    },
+    {
+      "epoch": 0.7633587786259542,
+      "grad_norm": 4.257474422454834,
+      "learning_rate": 4.618320610687023e-05,
+      "loss": 1.1588,
+      "step": 800
+    },
+    {
+      "epoch": 0.8587786259541985,
+      "grad_norm": 4.104170322418213,
+      "learning_rate": 4.570610687022901e-05,
+      "loss": 1.1497,
+      "step": 900
+    },
+    {
+      "epoch": 0.9541984732824428,
+      "grad_norm": 5.3210039138793945,
+      "learning_rate": 4.522900763358779e-05,
+      "loss": 1.1079,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.7669080563260455,
+      "eval_loss": 1.070055365562439,
+      "eval_runtime": 85.1145,
+      "eval_samples_per_second": 393.881,
+      "eval_steps_per_second": 6.156,
+      "step": 1048
+    },
+    {
+      "epoch": 1.049618320610687,
+      "grad_norm": 4.200919151306152,
+      "learning_rate": 4.475190839694657e-05,
+      "loss": 0.9816,
+      "step": 1100
+    },
+    {
+      "epoch": 1.1450381679389312,
+      "grad_norm": 5.287803649902344,
+      "learning_rate": 4.4274809160305345e-05,
+      "loss": 0.8863,
+      "step": 1200
+    },
+    {
+      "epoch": 1.2404580152671756,
+      "grad_norm": 4.714105606079102,
+      "learning_rate": 4.379770992366413e-05,
+      "loss": 0.8701,
+      "step": 1300
+    },
+    {
+      "epoch": 1.33587786259542,
+      "grad_norm": 4.039190292358398,
+      "learning_rate": 4.332061068702291e-05,
+      "loss": 0.8825,
+      "step": 1400
+    },
+    {
+      "epoch": 1.4312977099236641,
+      "grad_norm": 4.385517120361328,
+      "learning_rate": 4.2843511450381676e-05,
+      "loss": 0.8781,
+      "step": 1500
+    },
+    {
+      "epoch": 1.5267175572519083,
+      "grad_norm": 5.384212493896484,
+      "learning_rate": 4.236641221374046e-05,
+      "loss": 0.8599,
+      "step": 1600
+    },
+    {
+      "epoch": 1.6221374045801527,
+      "grad_norm": 4.302755832672119,
+      "learning_rate": 4.188931297709924e-05,
+      "loss": 0.8789,
+      "step": 1700
+    },
+    {
+      "epoch": 1.717557251908397,
+      "grad_norm": 3.6755897998809814,
+      "learning_rate": 4.1412213740458014e-05,
+      "loss": 0.8725,
+      "step": 1800
+    },
+    {
+      "epoch": 1.8129770992366412,
+      "grad_norm": 5.063183784484863,
+      "learning_rate": 4.0935114503816795e-05,
+      "loss": 0.8711,
+      "step": 1900
+    },
+    {
+      "epoch": 1.9083969465648853,
+      "grad_norm": 5.043242931365967,
+      "learning_rate": 4.0458015267175576e-05,
+      "loss": 0.842,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.7803345268228339,
+      "eval_loss": 1.0013784170150757,
+      "eval_runtime": 86.731,
+      "eval_samples_per_second": 386.54,
+      "eval_steps_per_second": 6.042,
+      "step": 2096
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 10480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 3.529481144352768e+16,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:470cb7c6da2ad69fe3e0b767988b9961419c9788b2b86dd909adb70c6a73be1a
+size 5777