Upload folder using huggingface_hub

README.md

@@ -0,0 +1,27 @@
+
+---
+library_name: transformers
+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: 0.45051154494285583
+
+f1: 0.8405797101449275
+
+precision: 0.8130841121495327
+
+recall: 0.87
+
+auc: 0.9207
+
+accuracy: 0.835

checkpoint-200/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 2,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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": "4.48.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fedaaa8d4091562fba151cdd69ffbed30fc1407e32d490854dd676decb2fd61
+size 437958648

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b76e116ac2fd6df9e037c210a3c9b747f09c79238daeed5bc1775d67fba702e
+size 876032762

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389098f0a4f5b6a3f82a933850ce68fc377babbec4c4f5484f8638c7dfe004f6
+size 13990

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aec29ec06ea312431cbd371fa4978409da48afde177f8cffaadff377958ca85
+size 1064

checkpoint-200/trainer_state.json

@@ -0,0 +1,348 @@
+{
+  "best_metric": 0.45051154494285583,
+  "best_model_checkpoint": "BERT-AI-Vacancy/checkpoint-200",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 8.434496879577637,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.6593,
+      "step": 5
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 7.955150127410889,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.7268,
+      "step": 10
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 8.903063774108887,
+      "learning_rate": 2.5e-05,
+      "loss": 0.6602,
+      "step": 15
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 12.550924301147461,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.5844,
+      "step": 20
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 8.15670108795166,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.5748,
+      "step": 25
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.381443500518799,
+      "learning_rate": 5e-05,
+      "loss": 0.4641,
+      "step": 30
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 5.676944255828857,
+      "learning_rate": 4.9074074074074075e-05,
+      "loss": 0.7415,
+      "step": 35
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 9.691534996032715,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 0.5794,
+      "step": 40
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 15.755120277404785,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 0.5693,
+      "step": 45
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 10.331628799438477,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 0.5301,
+      "step": 50
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 4.5462141036987305,
+      "learning_rate": 4.5370370370370374e-05,
+      "loss": 0.3862,
+      "step": 55
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.572924613952637,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.6586,
+      "step": 60
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 6.483484745025635,
+      "learning_rate": 4.351851851851852e-05,
+      "loss": 0.5363,
+      "step": 65
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 7.233407974243164,
+      "learning_rate": 4.259259259259259e-05,
+      "loss": 0.4871,
+      "step": 70
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.731393814086914,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.4605,
+      "step": 75
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.989573001861572,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 0.4152,
+      "step": 80
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 24.533870697021484,
+      "learning_rate": 3.981481481481482e-05,
+      "loss": 0.4753,
+      "step": 85
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.738238573074341,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.5456,
+      "step": 90
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 15.251642227172852,
+      "learning_rate": 3.7962962962962964e-05,
+      "loss": 0.3913,
+      "step": 95
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 11.198273658752441,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.5346,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.815,
+      "eval_auc": 0.9108999999999999,
+      "eval_f1": 0.8310502283105022,
+      "eval_loss": 0.4921284019947052,
+      "eval_precision": 0.7647058823529411,
+      "eval_recall": 0.91,
+      "eval_runtime": 29.8706,
+      "eval_samples_per_second": 6.696,
+      "eval_steps_per_second": 0.435,
+      "step": 100
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 5.278227806091309,
+      "learning_rate": 3.611111111111111e-05,
+      "loss": 0.4063,
+      "step": 105
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 8.036142349243164,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.4221,
+      "step": 110
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 9.602019309997559,
+      "learning_rate": 3.425925925925926e-05,
+      "loss": 0.495,
+      "step": 115
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 8.248969078063965,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.2828,
+      "step": 120
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 4.021635055541992,
+      "learning_rate": 3.240740740740741e-05,
+      "loss": 0.131,
+      "step": 125
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 10.284868240356445,
+      "learning_rate": 3.148148148148148e-05,
+      "loss": 0.5376,
+      "step": 130
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 11.141060829162598,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.7297,
+      "step": 135
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 14.501387596130371,
+      "learning_rate": 2.962962962962963e-05,
+      "loss": 0.2696,
+      "step": 140
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 9.892600059509277,
+      "learning_rate": 2.8703703703703706e-05,
+      "loss": 0.3433,
+      "step": 145
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 4.6811137199401855,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.5032,
+      "step": 150
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 1.6397993564605713,
+      "learning_rate": 2.6851851851851855e-05,
+      "loss": 0.2801,
+      "step": 155
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.426936149597168,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 0.5105,
+      "step": 160
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 2.963355779647827,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5286,
+      "step": 165
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 6.488004684448242,
+      "learning_rate": 2.4074074074074074e-05,
+      "loss": 0.674,
+      "step": 170
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 11.268607139587402,
+      "learning_rate": 2.314814814814815e-05,
+      "loss": 0.6404,
+      "step": 175
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 5.970183849334717,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.4052,
+      "step": 180
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 6.261168003082275,
+      "learning_rate": 2.1296296296296296e-05,
+      "loss": 0.4296,
+      "step": 185
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 4.376778602600098,
+      "learning_rate": 2.037037037037037e-05,
+      "loss": 0.203,
+      "step": 190
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 4.808477878570557,
+      "learning_rate": 1.9444444444444445e-05,
+      "loss": 0.2788,
+      "step": 195
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.679661512374878,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.1991,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.835,
+      "eval_auc": 0.9207,
+      "eval_f1": 0.8405797101449275,
+      "eval_loss": 0.45051154494285583,
+      "eval_precision": 0.8130841121495327,
+      "eval_recall": 0.87,
+      "eval_runtime": 30.0166,
+      "eval_samples_per_second": 6.663,
+      "eval_steps_per_second": 0.433,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 300,
+  "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": 105244422144000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff48d136d5bb44c6fe2438a32f64f302fae05c74544f165114b9ad2f3163755
+size 5368

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 2,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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": "4.48.0",
+  "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 sha256:6fedaaa8d4091562fba151cdd69ffbed30fc1407e32d490854dd676decb2fd61
+size 437958648

runs/Dec18_05-48-57_r-mralexgov-autotrain-advanced-ejrqtbux-928f4-g2xwb/events.out.tfevents.1766036939.r-mralexgov-autotrain-advanced-ejrqtbux-928f4-g2xwb.66.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8216e78b43a004890a9db1490f3d490ecd9625f1305637ca32b15d41b71c40
-size 16456
+oid sha256:868d14103e13d76522222dfc8ac63f771992156de5aeae510106da9dd0b06c36
+size 19650

runs/Dec18_05-48-57_r-mralexgov-autotrain-advanced-ejrqtbux-928f4-g2xwb/events.out.tfevents.1766038475.r-mralexgov-autotrain-advanced-ejrqtbux-928f4-g2xwb.66.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b360870a1314684def2706c3fbca74e3775655b7bf1689ff93e6556e03cf56c4
+size 607

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 sha256:5ff48d136d5bb44c6fe2438a32f64f302fae05c74544f165114b9ad2f3163755
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "BERT-AI-Vacancy/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": "BERT-AI-Vacancy",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "MrAlexGov",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}