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: 0.799523115158081
+
+f1_macro: 0.4213571908203974
+
+f1_micro: 0.6363636363636364
+
+f1_weighted: 0.5894579459723435
+
+precision_macro: 0.7132756132756133
+
+precision_micro: 0.6363636363636364
+
+precision_weighted: 0.6391250163977437
+
+recall_macro: 0.41007566007566004
+
+recall_micro: 0.6363636363636364
+
+recall_weighted: 0.6363636363636364
+
+accuracy: 0.6363636363636364

checkpoint-132/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 3,
+  "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": "0",
+    "1": "1",
+    "2": "2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2
+  },
+  "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": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-132/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057d57f4585c4c1281a61de6da39e3fd5864cfbe14f90058a86befdaf3cb695f
+size 437961724

checkpoint-132/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b19468ce179fde653207087ea03c1dece061c74dd7fd0c688717777426e21293
+size 876038906

checkpoint-132/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60eda8ba0bce81eec69d5c5104d3e5140f7eb59de40ce34a84ba9fc7e0f59f12
+size 13990

checkpoint-132/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e6ae674d8e9431da0fc9aebc0f06f3a41974a0580b83ac33049745588218c6b
+size 1064

checkpoint-132/trainer_state.json

@@ -0,0 +1,386 @@
+{
+  "best_metric": 0.799523115158081,
+  "best_model_checkpoint": "autotrain-v6j0j-vgrze/checkpoint-132",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 132,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.045454545454545456,
+      "grad_norm": 12.215251922607422,
+      "learning_rate": 7.5e-06,
+      "loss": 1.0564,
+      "step": 3
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 5.544069290161133,
+      "learning_rate": 1.5e-05,
+      "loss": 1.0358,
+      "step": 6
+    },
+    {
+      "epoch": 0.13636363636363635,
+      "grad_norm": 5.212268352508545,
+      "learning_rate": 2.25e-05,
+      "loss": 1.0246,
+      "step": 9
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 7.0390214920043945,
+      "learning_rate": 3e-05,
+      "loss": 1.0396,
+      "step": 12
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "grad_norm": 6.967841148376465,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.9888,
+      "step": 15
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 4.944703102111816,
+      "learning_rate": 4.5e-05,
+      "loss": 0.8724,
+      "step": 18
+    },
+    {
+      "epoch": 0.3181818181818182,
+      "grad_norm": 8.376965522766113,
+      "learning_rate": 4.971910112359551e-05,
+      "loss": 1.0079,
+      "step": 21
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 4.520912170410156,
+      "learning_rate": 4.8876404494382024e-05,
+      "loss": 0.7559,
+      "step": 24
+    },
+    {
+      "epoch": 0.4090909090909091,
+      "grad_norm": 5.39162540435791,
+      "learning_rate": 4.803370786516854e-05,
+      "loss": 0.8449,
+      "step": 27
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 5.5604400634765625,
+      "learning_rate": 4.719101123595506e-05,
+      "loss": 0.7637,
+      "step": 30
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 8.486992835998535,
+      "learning_rate": 4.6348314606741575e-05,
+      "loss": 0.7665,
+      "step": 33
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 7.629758834838867,
+      "learning_rate": 4.550561797752809e-05,
+      "loss": 0.7202,
+      "step": 36
+    },
+    {
+      "epoch": 0.5909090909090909,
+      "grad_norm": 5.846027851104736,
+      "learning_rate": 4.4662921348314605e-05,
+      "loss": 0.9322,
+      "step": 39
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 6.9962944984436035,
+      "learning_rate": 4.3820224719101126e-05,
+      "loss": 0.9569,
+      "step": 42
+    },
+    {
+      "epoch": 0.6818181818181818,
+      "grad_norm": 3.9776809215545654,
+      "learning_rate": 4.297752808988764e-05,
+      "loss": 0.932,
+      "step": 45
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 4.758964538574219,
+      "learning_rate": 4.2134831460674156e-05,
+      "loss": 0.9228,
+      "step": 48
+    },
+    {
+      "epoch": 0.7727272727272727,
+      "grad_norm": 7.231476783752441,
+      "learning_rate": 4.129213483146068e-05,
+      "loss": 0.8918,
+      "step": 51
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 6.340668201446533,
+      "learning_rate": 4.044943820224719e-05,
+      "loss": 0.8245,
+      "step": 54
+    },
+    {
+      "epoch": 0.8636363636363636,
+      "grad_norm": 8.802640914916992,
+      "learning_rate": 3.960674157303371e-05,
+      "loss": 0.8416,
+      "step": 57
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 7.027118682861328,
+      "learning_rate": 3.876404494382023e-05,
+      "loss": 1.0161,
+      "step": 60
+    },
+    {
+      "epoch": 0.9545454545454546,
+      "grad_norm": 4.328710079193115,
+      "learning_rate": 3.792134831460674e-05,
+      "loss": 0.6521,
+      "step": 63
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.209197044372559,
+      "learning_rate": 3.7078651685393264e-05,
+      "loss": 0.6134,
+      "step": 66
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6363636363636364,
+      "eval_f1_macro": 0.25925925925925924,
+      "eval_f1_micro": 0.6363636363636364,
+      "eval_f1_weighted": 0.4949494949494949,
+      "eval_loss": 0.9124495983123779,
+      "eval_precision_macro": 0.21212121212121213,
+      "eval_precision_micro": 0.6363636363636364,
+      "eval_precision_weighted": 0.4049586776859504,
+      "eval_recall_macro": 0.3333333333333333,
+      "eval_recall_micro": 0.6363636363636364,
+      "eval_recall_weighted": 0.6363636363636364,
+      "eval_runtime": 21.8205,
+      "eval_samples_per_second": 6.049,
+      "eval_steps_per_second": 0.412,
+      "step": 66
+    },
+    {
+      "epoch": 1.0454545454545454,
+      "grad_norm": 11.193312644958496,
+      "learning_rate": 3.623595505617978e-05,
+      "loss": 1.0391,
+      "step": 69
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 7.203339576721191,
+      "learning_rate": 3.5393258426966294e-05,
+      "loss": 0.8899,
+      "step": 72
+    },
+    {
+      "epoch": 1.1363636363636362,
+      "grad_norm": 7.495086669921875,
+      "learning_rate": 3.455056179775281e-05,
+      "loss": 0.8276,
+      "step": 75
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 6.776193141937256,
+      "learning_rate": 3.370786516853933e-05,
+      "loss": 0.5918,
+      "step": 78
+    },
+    {
+      "epoch": 1.2272727272727273,
+      "grad_norm": 5.164544105529785,
+      "learning_rate": 3.2865168539325845e-05,
+      "loss": 0.4893,
+      "step": 81
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 9.09774398803711,
+      "learning_rate": 3.202247191011236e-05,
+      "loss": 0.7136,
+      "step": 84
+    },
+    {
+      "epoch": 1.3181818181818181,
+      "grad_norm": 10.055578231811523,
+      "learning_rate": 3.1179775280898874e-05,
+      "loss": 0.7248,
+      "step": 87
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 15.217818260192871,
+      "learning_rate": 3.0337078651685396e-05,
+      "loss": 0.621,
+      "step": 90
+    },
+    {
+      "epoch": 1.4090909090909092,
+      "grad_norm": 5.431407451629639,
+      "learning_rate": 2.949438202247191e-05,
+      "loss": 0.5777,
+      "step": 93
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 8.047085762023926,
+      "learning_rate": 2.8651685393258425e-05,
+      "loss": 0.5288,
+      "step": 96
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 9.707415580749512,
+      "learning_rate": 2.7808988764044946e-05,
+      "loss": 0.8544,
+      "step": 99
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 10.858566284179688,
+      "learning_rate": 2.696629213483146e-05,
+      "loss": 0.7871,
+      "step": 102
+    },
+    {
+      "epoch": 1.5909090909090908,
+      "grad_norm": 11.408150672912598,
+      "learning_rate": 2.6123595505617983e-05,
+      "loss": 0.9048,
+      "step": 105
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 8.766745567321777,
+      "learning_rate": 2.5280898876404497e-05,
+      "loss": 0.664,
+      "step": 108
+    },
+    {
+      "epoch": 1.6818181818181817,
+      "grad_norm": 6.080604076385498,
+      "learning_rate": 2.4438202247191012e-05,
+      "loss": 0.6889,
+      "step": 111
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 9.023200988769531,
+      "learning_rate": 2.359550561797753e-05,
+      "loss": 0.6637,
+      "step": 114
+    },
+    {
+      "epoch": 1.7727272727272727,
+      "grad_norm": 21.281618118286133,
+      "learning_rate": 2.2752808988764045e-05,
+      "loss": 0.993,
+      "step": 117
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 9.379054069519043,
+      "learning_rate": 2.1910112359550563e-05,
+      "loss": 0.641,
+      "step": 120
+    },
+    {
+      "epoch": 1.8636363636363638,
+      "grad_norm": 8.74691104888916,
+      "learning_rate": 2.1067415730337078e-05,
+      "loss": 0.9741,
+      "step": 123
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 8.757966041564941,
+      "learning_rate": 2.0224719101123596e-05,
+      "loss": 0.7756,
+      "step": 126
+    },
+    {
+      "epoch": 1.9545454545454546,
+      "grad_norm": 9.220254898071289,
+      "learning_rate": 1.9382022471910114e-05,
+      "loss": 0.5357,
+      "step": 129
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.899024963378906,
+      "learning_rate": 1.8539325842696632e-05,
+      "loss": 0.4709,
+      "step": 132
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6363636363636364,
+      "eval_f1_macro": 0.4213571908203974,
+      "eval_f1_micro": 0.6363636363636364,
+      "eval_f1_weighted": 0.5894579459723435,
+      "eval_loss": 0.799523115158081,
+      "eval_precision_macro": 0.7132756132756133,
+      "eval_precision_micro": 0.6363636363636364,
+      "eval_precision_weighted": 0.6391250163977437,
+      "eval_recall_macro": 0.41007566007566004,
+      "eval_recall_micro": 0.6363636363636364,
+      "eval_recall_weighted": 0.6363636363636364,
+      "eval_runtime": 22.9495,
+      "eval_samples_per_second": 5.752,
+      "eval_steps_per_second": 0.392,
+      "step": 132
+    }
+  ],
+  "logging_steps": 3,
+  "max_steps": 198,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 69330385571328.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-132/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27aa73565d96fdaa634518a4591b859251b1d16e6afcf363961834e22baf3406
+size 5368

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 3,
+  "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": "0",
+    "1": "1",
+    "2": "2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2
+  },
+  "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": "4.47.1",
+  "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 sha256:057d57f4585c4c1281a61de6da39e3fd5864cfbe14f90058a86befdaf3cb695f
+size 437961724

runs/Jan08_15-14-57_r-zkava01-updatedtone-821a8nhg-29aa1-l3ncu/events.out.tfevents.1736349299.r-zkava01-updatedtone-821a8nhg-29aa1-l3ncu.104.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3abf9fe50e52b4fca71fbdf84ec4b2e1a56ce71bf7f980e8abd712e8db941b90
-size 13908
+oid sha256:272c2333f1b387885240a5a218654e2a87feab3c0ac0e356f5578d16e8182b76
+size 21820

runs/Jan08_15-14-57_r-zkava01-updatedtone-821a8nhg-29aa1-l3ncu/events.out.tfevents.1736350403.r-zkava01-updatedtone-821a8nhg-29aa1-l3ncu.104.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363d18fd229484f62d57daaf1a6e4b47ca35bd1e04dba1c5290c9dc7bf078021
+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 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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 sha256:27aa73565d96fdaa634518a4591b859251b1d16e6afcf363961834e22baf3406
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-v6j0j-vgrze/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-v6j0j-vgrze",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "zkava01",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}