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: 0.893719494342804
+
+f1_macro: 0.6365079365079365
+
+f1_micro: 0.7857142857142857
+
+f1_weighted: 0.727437641723356
+
+precision_macro: 0.6166666666666667
+
+precision_micro: 0.7857142857142857
+
+precision_weighted: 0.7047619047619048
+
+recall_macro: 0.6875
+
+recall_micro: 0.7857142857142857
+
+recall_weighted: 0.7857142857142857
+
+accuracy: 0.7857142857142857

checkpoint-21/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 4,
+  "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": "African",
+    "1": "Asian",
+    "2": "Latin American",
+    "3": "Middle Eastern"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "African": 0,
+    "Asian": 1,
+    "Latin American": 2,
+    "Middle Eastern": 3
+  },
+  "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-21/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:349819b45e999562b653ccf22facc7485f3deaca1a7a29e8737414eb82815bf5
+size 437964800

checkpoint-21/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ba8246abc50dcf64524d9a5b7bb4fe54f19708ef7e34fc71810d21d80afba36
+size 876045050

checkpoint-21/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440735e4ca4dbfe96baaf573c3bfc29385388fc2df2057e9217ceddb0b7188f5
+size 13990

checkpoint-21/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920472e7d43331d49f9a5d188a9619ca9d755bde39f75d40a2be1bb62c452a5b
+size 1064

checkpoint-21/trainer_state.json

@@ -0,0 +1,243 @@
+{
+  "best_metric": 0.893719494342804,
+  "best_model_checkpoint": "autotrain-jr45n-23iwd/checkpoint-21",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 21,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 13.014251708984375,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.574,
+      "step": 1
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 6.878973007202148,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.436,
+      "step": 2
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 8.282319068908691,
+      "learning_rate": 5e-05,
+      "loss": 1.5673,
+      "step": 3
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 9.62940502166748,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 1.2444,
+      "step": 4
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 11.141054153442383,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 1.665,
+      "step": 5
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 10.266294479370117,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.3428,
+      "step": 6
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 18.852968215942383,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 1.4157,
+      "step": 7
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7857142857142857,
+      "eval_f1_macro": 0.6375,
+      "eval_f1_micro": 0.7857142857142857,
+      "eval_f1_weighted": 0.7285714285714285,
+      "eval_loss": 1.2462433576583862,
+      "eval_precision_macro": 0.6041666666666666,
+      "eval_precision_micro": 0.7857142857142857,
+      "eval_precision_weighted": 0.6904761904761905,
+      "eval_recall_macro": 0.6875,
+      "eval_recall_micro": 0.7857142857142857,
+      "eval_recall_weighted": 0.7857142857142857,
+      "eval_runtime": 2.3828,
+      "eval_samples_per_second": 5.875,
+      "eval_steps_per_second": 0.42,
+      "step": 7
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 9.181815147399902,
+      "learning_rate": 3.611111111111111e-05,
+      "loss": 1.3051,
+      "step": 8
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 7.824043273925781,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.2258,
+      "step": 9
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 7.767913341522217,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 1.3915,
+      "step": 10
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 10.508928298950195,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 1.1089,
+      "step": 11
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 15.723339080810547,
+      "learning_rate": 2.5e-05,
+      "loss": 1.1304,
+      "step": 12
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 9.557744979858398,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 1.1083,
+      "step": 13
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 20.124605178833008,
+      "learning_rate": 1.9444444444444445e-05,
+      "loss": 1.2587,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6428571428571429,
+      "eval_f1_macro": 0.5038461538461538,
+      "eval_f1_micro": 0.6428571428571429,
+      "eval_f1_weighted": 0.5758241758241758,
+      "eval_loss": 1.00484299659729,
+      "eval_precision_macro": 0.6111111111111112,
+      "eval_precision_micro": 0.6428571428571429,
+      "eval_precision_weighted": 0.6984126984126985,
+      "eval_recall_macro": 0.5625,
+      "eval_recall_micro": 0.6428571428571429,
+      "eval_recall_weighted": 0.6428571428571429,
+      "eval_runtime": 2.4717,
+      "eval_samples_per_second": 5.664,
+      "eval_steps_per_second": 0.405,
+      "step": 14
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 12.81100845336914,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.2278,
+      "step": 15
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 9.036030769348145,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 0.9014,
+      "step": 16
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 11.079411506652832,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.8781,
+      "step": 17
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 8.225976943969727,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.8964,
+      "step": 18
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 11.431103706359863,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 0.9341,
+      "step": 19
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 6.8565449714660645,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 0.9554,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 10.979363441467285,
+      "learning_rate": 0.0,
+      "loss": 1.0157,
+      "step": 21
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7857142857142857,
+      "eval_f1_macro": 0.6365079365079365,
+      "eval_f1_micro": 0.7857142857142857,
+      "eval_f1_weighted": 0.727437641723356,
+      "eval_loss": 0.893719494342804,
+      "eval_precision_macro": 0.6166666666666667,
+      "eval_precision_micro": 0.7857142857142857,
+      "eval_precision_weighted": 0.7047619047619048,
+      "eval_recall_macro": 0.6875,
+      "eval_recall_micro": 0.7857142857142857,
+      "eval_recall_weighted": 0.7857142857142857,
+      "eval_runtime": 2.4283,
+      "eval_samples_per_second": 5.765,
+      "eval_steps_per_second": 0.412,
+      "step": 21
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 21,
+  "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": 11050862764032.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-21/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5940e7fa266adc09465ee1fe02eed1c11d75ea4842c68e67d5b94665bd7d2990
+size 5240

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 4,
+  "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": "African",
+    "1": "Asian",
+    "2": "Latin American",
+    "3": "Middle Eastern"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "African": 0,
+    "Asian": 1,
+    "Latin American": 2,
+    "Middle Eastern": 3
+  },
+  "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 sha256:349819b45e999562b653ccf22facc7485f3deaca1a7a29e8737414eb82815bf5
+size 437964800

runs/Nov04_18-11-30_r-wendys-llc-autotrain-advanced-j37uaf0f-1a7a2-9lyn1/events.out.tfevents.1730743890.r-wendys-llc-autotrain-advanced-j37uaf0f-1a7a2-9lyn1.126.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8cf1d07150caa08c6f1fea2c28b0ab3d27a6fa257cef1626eb14cb2f24a1e3e
-size 5223
+oid sha256:e50dea9a11790ce660b577b6b6e96e4e00e363d5b86d549156071c070236da82
+size 12372

runs/Nov04_18-11-30_r-wendys-llc-autotrain-advanced-j37uaf0f-1a7a2-9lyn1/events.out.tfevents.1730744012.r-wendys-llc-autotrain-advanced-j37uaf0f-1a7a2-9lyn1.126.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e15a1b1585f36abc4e9f1034c6c2eb652bd41e9a1424dfd335b6bc374547c9
+size 906

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 sha256:5940e7fa266adc09465ee1fe02eed1c11d75ea4842c68e67d5b94665bd7d2990
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-jr45n-23iwd/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-jr45n-23iwd",
+    "auto_find_batch_size": false,
+    "mixed_precision": "none",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "wendys-llc",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}