Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+datasets:
+- BBC/autotrain-data
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.11368879675865173
+
+f1_macro: 0.9748328397861948
+
+f1_micro: 0.9752808988764045
+
+f1_weighted: 0.9752071164560256
+
+precision_macro: 0.9752973544608207
+
+precision_micro: 0.9752808988764045
+
+precision_weighted: 0.9756012580457148
+
+recall_macro: 0.9748949579831934
+
+recall_micro: 0.9752808988764045
+
+recall_weighted: 0.9752808988764045
+
+accuracy: 0.9752808988764045

checkpoint-446/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "_num_labels": 5,
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "business",
+    "1": "entertainment",
+    "2": "politics",
+    "3": "sport",
+    "4": "tech"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "business": 0,
+    "entertainment": 1,
+    "politics": 2,
+    "sport": 3,
+    "tech": 4
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "vocab_size": 30522
+}

checkpoint-446/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:110d80fb3802167c70d64541793d13bf32bfda23eb72c672f09103d05eae9f1b
+size 267841796

checkpoint-446/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f556fdc4c51d164731ceda527291415d08635b89b8501f0be6253edb69af122c
+size 535745722

checkpoint-446/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f036c0172f5ca676082a0009be3cef7c15e11f6dc17ff44e82c508c72a1974e2
+size 14244

checkpoint-446/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42000f01e44026506d77b52395293d738ac7c6eef4cb2e00254c1f15522848fa
+size 1064

checkpoint-446/trainer_state.json

@@ -0,0 +1,337 @@
+{
+  "best_metric": 0.11368879675865173,
+  "best_model_checkpoint": "BBC/checkpoint-446",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 446,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04932735426008968,
+      "grad_norm": 2.2345685958862305,
+      "learning_rate": 8.208955223880597e-06,
+      "loss": 1.6224,
+      "step": 11
+    },
+    {
+      "epoch": 0.09865470852017937,
+      "grad_norm": 3.739938974380493,
+      "learning_rate": 1.6417910447761194e-05,
+      "loss": 1.5896,
+      "step": 22
+    },
+    {
+      "epoch": 0.14798206278026907,
+      "grad_norm": 2.8613524436950684,
+      "learning_rate": 2.4626865671641793e-05,
+      "loss": 1.4769,
+      "step": 33
+    },
+    {
+      "epoch": 0.19730941704035873,
+      "grad_norm": 4.428678035736084,
+      "learning_rate": 3.283582089552239e-05,
+      "loss": 1.2341,
+      "step": 44
+    },
+    {
+      "epoch": 0.24663677130044842,
+      "grad_norm": 2.953808069229126,
+      "learning_rate": 4.104477611940299e-05,
+      "loss": 0.9053,
+      "step": 55
+    },
+    {
+      "epoch": 0.29596412556053814,
+      "grad_norm": 4.068609237670898,
+      "learning_rate": 4.850746268656717e-05,
+      "loss": 0.5467,
+      "step": 66
+    },
+    {
+      "epoch": 0.3452914798206278,
+      "grad_norm": Infinity,
+      "learning_rate": 4.933554817275748e-05,
+      "loss": 0.4172,
+      "step": 77
+    },
+    {
+      "epoch": 0.39461883408071746,
+      "grad_norm": 17.124122619628906,
+      "learning_rate": 4.8421926910299006e-05,
+      "loss": 0.2072,
+      "step": 88
+    },
+    {
+      "epoch": 0.4439461883408072,
+      "grad_norm": 4.019614219665527,
+      "learning_rate": 4.750830564784053e-05,
+      "loss": 0.2032,
+      "step": 99
+    },
+    {
+      "epoch": 0.49327354260089684,
+      "grad_norm": 16.75712776184082,
+      "learning_rate": 4.659468438538207e-05,
+      "loss": 0.2285,
+      "step": 110
+    },
+    {
+      "epoch": 0.5426008968609866,
+      "grad_norm": 0.29395201802253723,
+      "learning_rate": 4.568106312292359e-05,
+      "loss": 0.1339,
+      "step": 121
+    },
+    {
+      "epoch": 0.5919282511210763,
+      "grad_norm": 0.19628354907035828,
+      "learning_rate": 4.476744186046512e-05,
+      "loss": 0.2383,
+      "step": 132
+    },
+    {
+      "epoch": 0.6412556053811659,
+      "grad_norm": 11.740421295166016,
+      "learning_rate": 4.385382059800665e-05,
+      "loss": 0.1953,
+      "step": 143
+    },
+    {
+      "epoch": 0.6905829596412556,
+      "grad_norm": 11.316059112548828,
+      "learning_rate": 4.2940199335548175e-05,
+      "loss": 0.1348,
+      "step": 154
+    },
+    {
+      "epoch": 0.7399103139013453,
+      "grad_norm": 0.13278043270111084,
+      "learning_rate": 4.20265780730897e-05,
+      "loss": 0.0165,
+      "step": 165
+    },
+    {
+      "epoch": 0.7892376681614349,
+      "grad_norm": 0.08719899505376816,
+      "learning_rate": 4.111295681063123e-05,
+      "loss": 0.0113,
+      "step": 176
+    },
+    {
+      "epoch": 0.8385650224215246,
+      "grad_norm": 0.10285717248916626,
+      "learning_rate": 4.019933554817276e-05,
+      "loss": 0.0562,
+      "step": 187
+    },
+    {
+      "epoch": 0.8878923766816144,
+      "grad_norm": 0.17199571430683136,
+      "learning_rate": 3.928571428571429e-05,
+      "loss": 0.1757,
+      "step": 198
+    },
+    {
+      "epoch": 0.9372197309417041,
+      "grad_norm": 4.296013832092285,
+      "learning_rate": 3.837209302325582e-05,
+      "loss": 0.1623,
+      "step": 209
+    },
+    {
+      "epoch": 0.9865470852017937,
+      "grad_norm": 0.0789671242237091,
+      "learning_rate": 3.7458471760797344e-05,
+      "loss": 0.1756,
+      "step": 220
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9415730337078652,
+      "eval_f1_macro": 0.9405622158426933,
+      "eval_f1_micro": 0.9415730337078652,
+      "eval_f1_weighted": 0.9410207995888995,
+      "eval_loss": 0.2357553094625473,
+      "eval_precision_macro": 0.9403873157660169,
+      "eval_precision_micro": 0.9415730337078652,
+      "eval_precision_weighted": 0.945045999282218,
+      "eval_recall_macro": 0.9449872676343263,
+      "eval_recall_micro": 0.9415730337078652,
+      "eval_recall_weighted": 0.9415730337078652,
+      "eval_runtime": 1.1567,
+      "eval_samples_per_second": 384.701,
+      "eval_steps_per_second": 24.206,
+      "step": 223
+    },
+    {
+      "epoch": 1.0358744394618835,
+      "grad_norm": 36.847206115722656,
+      "learning_rate": 3.662790697674418e-05,
+      "loss": 0.2338,
+      "step": 231
+    },
+    {
+      "epoch": 1.0852017937219731,
+      "grad_norm": 0.21538594365119934,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.034,
+      "step": 242
+    },
+    {
+      "epoch": 1.1345291479820627,
+      "grad_norm": 0.09186477214097977,
+      "learning_rate": 3.4800664451827244e-05,
+      "loss": 0.0824,
+      "step": 253
+    },
+    {
+      "epoch": 1.1838565022421526,
+      "grad_norm": 0.10708645731210709,
+      "learning_rate": 3.397009966777408e-05,
+      "loss": 0.0314,
+      "step": 264
+    },
+    {
+      "epoch": 1.2331838565022422,
+      "grad_norm": 0.061287783086299896,
+      "learning_rate": 3.305647840531562e-05,
+      "loss": 0.0139,
+      "step": 275
+    },
+    {
+      "epoch": 1.2825112107623318,
+      "grad_norm": 26.10398292541504,
+      "learning_rate": 3.2142857142857144e-05,
+      "loss": 0.1447,
+      "step": 286
+    },
+    {
+      "epoch": 1.3318385650224216,
+      "grad_norm": 0.06678097695112228,
+      "learning_rate": 3.122923588039867e-05,
+      "loss": 0.0048,
+      "step": 297
+    },
+    {
+      "epoch": 1.3811659192825112,
+      "grad_norm": 0.03612040355801582,
+      "learning_rate": 3.03156146179402e-05,
+      "loss": 0.0365,
+      "step": 308
+    },
+    {
+      "epoch": 1.4304932735426008,
+      "grad_norm": 0.05210395157337189,
+      "learning_rate": 2.940199335548173e-05,
+      "loss": 0.1038,
+      "step": 319
+    },
+    {
+      "epoch": 1.4798206278026906,
+      "grad_norm": 0.04557207226753235,
+      "learning_rate": 2.848837209302326e-05,
+      "loss": 0.0745,
+      "step": 330
+    },
+    {
+      "epoch": 1.5291479820627802,
+      "grad_norm": 0.09987442195415497,
+      "learning_rate": 2.7574750830564782e-05,
+      "loss": 0.1806,
+      "step": 341
+    },
+    {
+      "epoch": 1.57847533632287,
+      "grad_norm": 0.0828678086400032,
+      "learning_rate": 2.6661129568106313e-05,
+      "loss": 0.0048,
+      "step": 352
+    },
+    {
+      "epoch": 1.6278026905829597,
+      "grad_norm": 0.05174608528614044,
+      "learning_rate": 2.5747508305647843e-05,
+      "loss": 0.136,
+      "step": 363
+    },
+    {
+      "epoch": 1.6771300448430493,
+      "grad_norm": 0.05517464876174927,
+      "learning_rate": 2.483388704318937e-05,
+      "loss": 0.1924,
+      "step": 374
+    },
+    {
+      "epoch": 1.726457399103139,
+      "grad_norm": 0.0699392706155777,
+      "learning_rate": 2.39202657807309e-05,
+      "loss": 0.0129,
+      "step": 385
+    },
+    {
+      "epoch": 1.7757847533632287,
+      "grad_norm": 0.04404047504067421,
+      "learning_rate": 2.3006644518272428e-05,
+      "loss": 0.0032,
+      "step": 396
+    },
+    {
+      "epoch": 1.8251121076233185,
+      "grad_norm": 0.048387836664915085,
+      "learning_rate": 2.2093023255813955e-05,
+      "loss": 0.0437,
+      "step": 407
+    },
+    {
+      "epoch": 1.8744394618834082,
+      "grad_norm": 0.06495353579521179,
+      "learning_rate": 2.1179401993355482e-05,
+      "loss": 0.0095,
+      "step": 418
+    },
+    {
+      "epoch": 1.9237668161434978,
+      "grad_norm": 1.6995466947555542,
+      "learning_rate": 2.026578073089701e-05,
+      "loss": 0.0047,
+      "step": 429
+    },
+    {
+      "epoch": 1.9730941704035874,
+      "grad_norm": 0.02669903263449669,
+      "learning_rate": 1.935215946843854e-05,
+      "loss": 0.0239,
+      "step": 440
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9752808988764045,
+      "eval_f1_macro": 0.9748328397861948,
+      "eval_f1_micro": 0.9752808988764045,
+      "eval_f1_weighted": 0.9752071164560256,
+      "eval_loss": 0.11368879675865173,
+      "eval_precision_macro": 0.9752973544608207,
+      "eval_precision_micro": 0.9752808988764045,
+      "eval_precision_weighted": 0.9756012580457148,
+      "eval_recall_macro": 0.9748949579831934,
+      "eval_recall_micro": 0.9752808988764045,
+      "eval_recall_weighted": 0.9752808988764045,
+      "eval_runtime": 1.1607,
+      "eval_samples_per_second": 383.394,
+      "eval_steps_per_second": 24.124,
+      "step": 446
+    }
+  ],
+  "logging_steps": 11,
+  "max_steps": 669,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 117902292326400.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-446/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cd4891a5678c56ffc974de8b6d91bfc9dd816ddf5efd9f5dc2ee0b42609adb
+size 4984

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "_num_labels": 5,
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "business",
+    "1": "entertainment",
+    "2": "politics",
+    "3": "sport",
+    "4": "tech"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "business": 0,
+    "entertainment": 1,
+    "politics": 2,
+    "sport": 3,
+    "tech": 4
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:110d80fb3802167c70d64541793d13bf32bfda23eb72c672f09103d05eae9f1b
+size 267841796

runs/Apr30_07-02-05_r-nawincom-textclass2-7adih043-2b405-4dip5/events.out.tfevents.1714460525.r-nawincom-textclass2-7adih043-2b405-4dip5.62.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bffdd6ad87b42a9704ca1a2f494cec8355d359fd0d50c8b56216e88df18e832f
-size 4806
+oid sha256:f1797c392f5b2686537abe968ab6b2f56abc2331321f5d945348bf26def2fb66
+size 20275

runs/Apr30_07-02-05_r-nawincom-textclass2-7adih043-2b405-4dip5/events.out.tfevents.1714460578.r-nawincom-textclass2-7adih043-2b405-4dip5.62.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea8a3f57b4959972e7eebb3636b204becbe53bbfec7db7dafcee0ca34bc260d2
+size 921

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": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cd4891a5678c56ffc974de8b6d91bfc9dd816ddf5efd9f5dc2ee0b42609adb
+size 4984

training_params.json

@@ -0,0 +1,28 @@
+{
+    "data_path": "BBC/autotrain-data",
+    "model": "distilbert/distilbert-base-uncased",
+    "lr": 5e-05,
+    "epochs": 3,
+    "max_seq_length": 128,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "text_column": "autotrain_text",
+    "target_column": "autotrain_label",
+    "logging_steps": -1,
+    "project_name": "BBC",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "evaluation_strategy": "epoch",
+    "username": "NawinCom",
+    "log": "tensorboard"
+}