Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: google-bert/bert-base-uncased
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.20468038320541382
+
+f1_macro: 0.5346970986126391
+
+f1_micro: 0.9440559440559441
+
+f1_weighted: 0.9410445215583293
+
+precision_macro: 0.5573908674461452
+
+precision_micro: 0.9440559440559441
+
+precision_weighted: 0.9419302500177272
+
+recall_macro: 0.5198802592658838
+
+recall_micro: 0.9440559440559441
+
+recall_weighted: 0.9440559440559441
+
+accuracy: 0.9440559440559441

checkpoint-753/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 5,
+  "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": "16",
+    "1": "nan",
+    "2": "negative",
+    "3": "neutral",
+    "4": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "16": 0,
+    "nan": 1,
+    "negative": 2,
+    "neutral": 3,
+    "positive": 4
+  },
+  "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": "4.45.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-753/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2622cb6fce647d749ff91990e9991b1c1da9144960f862c78806a41b63423213
+size 437967876

checkpoint-753/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11325d35e504142f3a380bd2221068c512ceddfab9cb5b8243152f8ec55ebd0f
+size 876051194

checkpoint-753/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66866a018df1097dc9ce6063814a9951f38a2f59f78f8c285acd273c4467b5f
+size 13990

checkpoint-753/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b6f2b87db404cfebc70e7cab2d10769b0e1d9d8dc10a01cf280626b95d54b1b
+size 1064

checkpoint-753/trainer_state.json

@@ -0,0 +1,306 @@
+{
+  "best_metric": 0.20468038320541382,
+  "best_model_checkpoint": "autotrain-o5mxr-bsop6/checkpoint-753",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 753,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.099601593625498,
+      "grad_norm": 5.523846626281738,
+      "learning_rate": 1.6447368421052635e-05,
+      "loss": 1.3608,
+      "step": 25
+    },
+    {
+      "epoch": 0.199203187250996,
+      "grad_norm": 4.111423969268799,
+      "learning_rate": 3.289473684210527e-05,
+      "loss": 1.0428,
+      "step": 50
+    },
+    {
+      "epoch": 0.29880478087649404,
+      "grad_norm": 5.932701110839844,
+      "learning_rate": 4.9342105263157894e-05,
+      "loss": 0.824,
+      "step": 75
+    },
+    {
+      "epoch": 0.398406374501992,
+      "grad_norm": 14.16284465789795,
+      "learning_rate": 4.82274741506647e-05,
+      "loss": 0.8565,
+      "step": 100
+    },
+    {
+      "epoch": 0.49800796812749004,
+      "grad_norm": 7.437353610992432,
+      "learning_rate": 4.638109305760709e-05,
+      "loss": 0.7849,
+      "step": 125
+    },
+    {
+      "epoch": 0.5976095617529881,
+      "grad_norm": 14.002378463745117,
+      "learning_rate": 4.453471196454949e-05,
+      "loss": 0.6819,
+      "step": 150
+    },
+    {
+      "epoch": 0.6972111553784861,
+      "grad_norm": 7.128929138183594,
+      "learning_rate": 4.2688330871491875e-05,
+      "loss": 0.9145,
+      "step": 175
+    },
+    {
+      "epoch": 0.796812749003984,
+      "grad_norm": 7.11976432800293,
+      "learning_rate": 4.084194977843427e-05,
+      "loss": 0.7596,
+      "step": 200
+    },
+    {
+      "epoch": 0.896414342629482,
+      "grad_norm": 10.390266418457031,
+      "learning_rate": 3.8995568685376664e-05,
+      "loss": 0.704,
+      "step": 225
+    },
+    {
+      "epoch": 0.9960159362549801,
+      "grad_norm": 8.346457481384277,
+      "learning_rate": 3.714918759231906e-05,
+      "loss": 0.6437,
+      "step": 250
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8041958041958042,
+      "eval_f1_macro": 0.36845586105500655,
+      "eval_f1_micro": 0.8041958041958042,
+      "eval_f1_weighted": 0.7771738216042354,
+      "eval_loss": 0.5281614065170288,
+      "eval_precision_macro": 0.4761472822311331,
+      "eval_precision_micro": 0.8041958041958042,
+      "eval_precision_weighted": 0.80077693322795,
+      "eval_recall_macro": 0.36810085833863637,
+      "eval_recall_micro": 0.8041958041958042,
+      "eval_recall_weighted": 0.8041958041958042,
+      "eval_runtime": 359.8505,
+      "eval_samples_per_second": 5.563,
+      "eval_steps_per_second": 0.35,
+      "step": 251
+    },
+    {
+      "epoch": 1.095617529880478,
+      "grad_norm": 4.572272300720215,
+      "learning_rate": 3.5302806499261446e-05,
+      "loss": 0.6044,
+      "step": 275
+    },
+    {
+      "epoch": 1.1952191235059761,
+      "grad_norm": 3.9493234157562256,
+      "learning_rate": 3.345642540620384e-05,
+      "loss": 0.6022,
+      "step": 300
+    },
+    {
+      "epoch": 1.294820717131474,
+      "grad_norm": 6.116109848022461,
+      "learning_rate": 3.1610044313146235e-05,
+      "loss": 0.494,
+      "step": 325
+    },
+    {
+      "epoch": 1.3944223107569722,
+      "grad_norm": 11.72847843170166,
+      "learning_rate": 2.976366322008863e-05,
+      "loss": 0.5509,
+      "step": 350
+    },
+    {
+      "epoch": 1.4940239043824701,
+      "grad_norm": 6.265529632568359,
+      "learning_rate": 2.791728212703102e-05,
+      "loss": 0.5268,
+      "step": 375
+    },
+    {
+      "epoch": 1.593625498007968,
+      "grad_norm": 5.475246906280518,
+      "learning_rate": 2.6070901033973415e-05,
+      "loss": 0.6499,
+      "step": 400
+    },
+    {
+      "epoch": 1.6932270916334662,
+      "grad_norm": 5.1211256980896,
+      "learning_rate": 2.4224519940915806e-05,
+      "loss": 0.5373,
+      "step": 425
+    },
+    {
+      "epoch": 1.792828685258964,
+      "grad_norm": 2.6638262271881104,
+      "learning_rate": 2.23781388478582e-05,
+      "loss": 0.4476,
+      "step": 450
+    },
+    {
+      "epoch": 1.8924302788844622,
+      "grad_norm": 45.47649383544922,
+      "learning_rate": 2.053175775480059e-05,
+      "loss": 0.5096,
+      "step": 475
+    },
+    {
+      "epoch": 1.9920318725099602,
+      "grad_norm": 6.048641204833984,
+      "learning_rate": 1.8685376661742986e-05,
+      "loss": 0.424,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9100899100899101,
+      "eval_f1_macro": 0.4902522309112827,
+      "eval_f1_micro": 0.9100899100899101,
+      "eval_f1_weighted": 0.9024494723879539,
+      "eval_loss": 0.2924034893512726,
+      "eval_precision_macro": 0.5296504253394911,
+      "eval_precision_micro": 0.9100899100899101,
+      "eval_precision_weighted": 0.9052689915360643,
+      "eval_recall_macro": 0.4726016384805666,
+      "eval_recall_micro": 0.9100899100899101,
+      "eval_recall_weighted": 0.9100899100899101,
+      "eval_runtime": 365.8456,
+      "eval_samples_per_second": 5.472,
+      "eval_steps_per_second": 0.344,
+      "step": 502
+    },
+    {
+      "epoch": 2.091633466135458,
+      "grad_norm": 2.1055290699005127,
+      "learning_rate": 1.6838995568685377e-05,
+      "loss": 0.4131,
+      "step": 525
+    },
+    {
+      "epoch": 2.191235059760956,
+      "grad_norm": 22.558122634887695,
+      "learning_rate": 1.499261447562777e-05,
+      "loss": 0.3949,
+      "step": 550
+    },
+    {
+      "epoch": 2.2908366533864544,
+      "grad_norm": 9.2990083694458,
+      "learning_rate": 1.3146233382570164e-05,
+      "loss": 0.2408,
+      "step": 575
+    },
+    {
+      "epoch": 2.3904382470119523,
+      "grad_norm": 23.017541885375977,
+      "learning_rate": 1.1299852289512555e-05,
+      "loss": 0.2457,
+      "step": 600
+    },
+    {
+      "epoch": 2.49003984063745,
+      "grad_norm": 0.9120715260505676,
+      "learning_rate": 9.45347119645495e-06,
+      "loss": 0.3485,
+      "step": 625
+    },
+    {
+      "epoch": 2.589641434262948,
+      "grad_norm": 2.4525136947631836,
+      "learning_rate": 7.607090103397342e-06,
+      "loss": 0.2528,
+      "step": 650
+    },
+    {
+      "epoch": 2.6892430278884465,
+      "grad_norm": 10.707359313964844,
+      "learning_rate": 5.760709010339734e-06,
+      "loss": 0.298,
+      "step": 675
+    },
+    {
+      "epoch": 2.7888446215139444,
+      "grad_norm": 24.448265075683594,
+      "learning_rate": 3.914327917282127e-06,
+      "loss": 0.2448,
+      "step": 700
+    },
+    {
+      "epoch": 2.8884462151394423,
+      "grad_norm": 1.235875129699707,
+      "learning_rate": 2.06794682422452e-06,
+      "loss": 0.4039,
+      "step": 725
+    },
+    {
+      "epoch": 2.9880478087649402,
+      "grad_norm": 9.670615196228027,
+      "learning_rate": 2.215657311669129e-07,
+      "loss": 0.3307,
+      "step": 750
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9440559440559441,
+      "eval_f1_macro": 0.5346970986126391,
+      "eval_f1_micro": 0.9440559440559441,
+      "eval_f1_weighted": 0.9410445215583293,
+      "eval_loss": 0.20468038320541382,
+      "eval_precision_macro": 0.5573908674461452,
+      "eval_precision_micro": 0.9440559440559441,
+      "eval_precision_weighted": 0.9419302500177272,
+      "eval_recall_macro": 0.5198802592658838,
+      "eval_recall_micro": 0.9440559440559441,
+      "eval_recall_weighted": 0.9440559440559441,
+      "eval_runtime": 338.5361,
+      "eval_samples_per_second": 5.914,
+      "eval_steps_per_second": 0.372,
+      "step": 753
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 753,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 395071890909696.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-753/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aba5126c6dd21967b1fec570187dd4d4aadfe22f8a695a65d708bcdfc7229c37
+size 5240

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 5,
+  "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": "16",
+    "1": "nan",
+    "2": "negative",
+    "3": "neutral",
+    "4": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "16": 0,
+    "nan": 1,
+    "negative": 2,
+    "neutral": 3,
+    "positive": 4
+  },
+  "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": "4.45.0",
+  "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 sha256:2622cb6fce647d749ff91990e9991b1c1da9144960f862c78806a41b63423213
+size 437967876

runs/Oct07_13-14-30_r-kafikani-autotrain-advanced-v2-rj0fn53v-b61c9-bn01w/events.out.tfevents.1728306878.r-kafikani-autotrain-advanced-v2-rj0fn53v-b61c9-bn01w.125.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51c864b866e61c8f707ebc546ecdfc2b6ab0ebb956e61a925b575cf53dd24ba1
-size 12145
+oid sha256:634e311ae809a6412732353986f5304ecfdb13901e8844161b97a50ea4e4e0e3
+size 14387

runs/Oct07_13-14-30_r-kafikani-autotrain-advanced-v2-rj0fn53v-b61c9-bn01w/events.out.tfevents.1728312304.r-kafikani-autotrain-advanced-v2-rj0fn53v-b61c9-bn01w.125.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a61d05ab50b9dc18adf4b7e4f7d0cebc2efc9bd58f3644032e9d1e47ae3f9f3
+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": 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:aba5126c6dd21967b1fec570187dd4d4aadfe22f8a695a65d708bcdfc7229c37
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-o5mxr-bsop6/autotrain-data",
+    "model": "google-bert/bert-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": "autotrain-o5mxr-bsop6",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "kafikani",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}