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: 0.29163089394569397
+
+f1_macro: 0.7727998858935957
+
+f1_micro: 0.92
+
+f1_weighted: 0.9113598630723149
+
+precision_macro: 0.7648809523809524
+
+precision_micro: 0.92
+
+precision_weighted: 0.9053571428571427
+
+recall_macro: 0.7833333333333332
+
+recall_micro: 0.92
+
+recall_weighted: 0.92
+
+accuracy: 0.92

checkpoint-150/config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 6,
+  "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": "Entertainment",
+    "1": "Food",
+    "2": "Housing",
+    "3": "Medical",
+    "4": "Miscellaneous",
+    "5": "Travel"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Entertainment": 0,
+    "Food": 1,
+    "Housing": 2,
+    "Medical": 3,
+    "Miscellaneous": 4,
+    "Travel": 5
+  },
+  "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": "4.44.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-150/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b80cf61dc51924bcde8910ef314f709a88811306928475cdb9bd6776ade1bb5
+size 437970952

checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10ae67a1886ffd443673f84a6a2a2451203609691ed283ec25e8586c1a7a9f8f
+size 876057338

checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b53c99a2ea19505de0d4e18f71e3b435e94fad506b2f76c61e4575c00e2ea2ca
+size 13990

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1edb25f446c7d2fc8a07e3635e302199dbca58668ddad584ef7fbc0b6b5406b6
+size 1064

checkpoint-150/trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_metric": 0.29163089394569397,
+  "best_model_checkpoint": "autotrain-2p12r-cw2s6/checkpoint-150",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 13.35822582244873,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 1.8569,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 10.923691749572754,
+      "learning_rate": 2.8888888888888888e-05,
+      "loss": 1.6203,
+      "step": 20
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 6.453679084777832,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 1.2797,
+      "step": 30
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 10.624079704284668,
+      "learning_rate": 2.4444444444444445e-05,
+      "loss": 1.1935,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 10.568455696105957,
+      "learning_rate": 2.222222222222222e-05,
+      "loss": 0.9807,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.82,
+      "eval_f1_macro": 0.6733605498937164,
+      "eval_f1_micro": 0.82,
+      "eval_f1_weighted": 0.789679718695989,
+      "eval_loss": 0.8373663425445557,
+      "eval_precision_macro": 0.6934624017957352,
+      "eval_precision_micro": 0.82,
+      "eval_precision_weighted": 0.8152104377104377,
+      "eval_recall_macro": 0.7000000000000001,
+      "eval_recall_micro": 0.82,
+      "eval_recall_weighted": 0.82,
+      "eval_runtime": 19.5504,
+      "eval_samples_per_second": 5.115,
+      "eval_steps_per_second": 1.279,
+      "step": 50
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 6.850324630737305,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 0.8111,
+      "step": 60
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 6.868027210235596,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.721,
+      "step": 70
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.674863815307617,
+      "learning_rate": 1.5555555555555555e-05,
+      "loss": 0.5653,
+      "step": 80
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.8254852294921875,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.5168,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 9.87863826751709,
+      "learning_rate": 1.111111111111111e-05,
+      "loss": 0.4505,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.92,
+      "eval_f1_macro": 0.7727998858935957,
+      "eval_f1_micro": 0.92,
+      "eval_f1_weighted": 0.9113598630723149,
+      "eval_loss": 0.3886770009994507,
+      "eval_precision_macro": 0.7648809523809524,
+      "eval_precision_micro": 0.92,
+      "eval_precision_weighted": 0.9053571428571427,
+      "eval_recall_macro": 0.7833333333333332,
+      "eval_recall_micro": 0.92,
+      "eval_recall_weighted": 0.92,
+      "eval_runtime": 20.1168,
+      "eval_samples_per_second": 4.971,
+      "eval_steps_per_second": 1.243,
+      "step": 100
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 2.6550135612487793,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.347,
+      "step": 110
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 5.567917346954346,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.3921,
+      "step": 120
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 11.323433876037598,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.3246,
+      "step": 130
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 5.023998260498047,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.3217,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.515089750289917,
+      "learning_rate": 0.0,
+      "loss": 0.2423,
+      "step": 150
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.92,
+      "eval_f1_macro": 0.7727998858935957,
+      "eval_f1_micro": 0.92,
+      "eval_f1_weighted": 0.9113598630723149,
+      "eval_loss": 0.29163089394569397,
+      "eval_precision_macro": 0.7648809523809524,
+      "eval_precision_micro": 0.92,
+      "eval_precision_weighted": 0.9053571428571427,
+      "eval_recall_macro": 0.7833333333333332,
+      "eval_recall_micro": 0.92,
+      "eval_recall_weighted": 0.92,
+      "eval_runtime": 19.9884,
+      "eval_samples_per_second": 5.003,
+      "eval_steps_per_second": 1.251,
+      "step": 150
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 150,
+  "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": 78936151449600.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b52150b188249c22f02c127cccbcc0d9ad437b777179e20f20bc5f13869936d9
+size 5240

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 6,
+  "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": "Entertainment",
+    "1": "Food",
+    "2": "Housing",
+    "3": "Medical",
+    "4": "Miscellaneous",
+    "5": "Travel"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Entertainment": 0,
+    "Food": 1,
+    "Housing": 2,
+    "Medical": 3,
+    "Miscellaneous": 4,
+    "Travel": 5
+  },
+  "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": "4.44.0",
+  "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 sha256:8b80cf61dc51924bcde8910ef314f709a88811306928475cdb9bd6776ade1bb5
+size 437970952

runs/Aug18_21-09-43_r-vpingale07-phi-3-transaction-categories-9a0vqm8c-18b68-bg15o/events.out.tfevents.1724015384.r-vpingale07-phi-3-transaction-categories-9a0vqm8c-18b68-bg15o.183.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60027e4ebcc330e5f7dca9a994a2ca775334235d8a1ce0ff37f8ef378c31ccaf
-size 8977
+oid sha256:c25563fe8d0375a2bb7e7b6239ad6376706d6ff82c656a42716ba24a35fe9d63
+size 11211

runs/Aug18_21-09-43_r-vpingale07-phi-3-transaction-categories-9a0vqm8c-18b68-bg15o/events.out.tfevents.1724016371.r-vpingale07-phi-3-transaction-categories-9a0vqm8c-18b68-bg15o.183.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3d7f803ccb28a9a18c7d5d92acc896cd63404a2933942bb2068a39d5801f755
+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:b52150b188249c22f02c127cccbcc0d9ad437b777179e20f20bc5f13869936d9
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-2p12r-cw2s6/autotrain-data",
+    "model": "google-bert/bert-base-uncased",
+    "lr": 3e-05,
+    "epochs": 3,
+    "max_seq_length": 128,
+    "batch_size": 2,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 4,
+    "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-2p12r-cw2s6",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "vpingale07",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}