Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+
+---
+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: 0.3905062973499298
+
+f1: 0.7820443482963764
+
+precision: 0.8042269187986651
+
+recall: 0.7610526315789473
+
+auc: 0.8991059238053292
+
+accuracy: 0.8309563758389261

checkpoint-596/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": "4.46.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-596/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36af391fcc6cf6d329ee4ce2450747716314197bf08ef5ddb03cad6e64800d26
+size 437958648

checkpoint-596/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d14b9c1788831f5e8315e6401b1c0eb16f6d7e18cb8da9d06699735f74f034ff
+size 876038394

checkpoint-596/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5effc8cb10520f16c246d7aa6747f0ba8a28b202a2fb5f88b9fc927aba8dfdb
+size 14244

checkpoint-596/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d4c0c15d45202015bf15b799f7c66f2467eb409595ee5167644ebc7bbae2af5
+size 1064

checkpoint-596/trainer_state.json

@@ -0,0 +1,362 @@
+{
+  "best_metric": 0.3905062973499298,
+  "best_model_checkpoint": "olid-stylebkd-p10-bert-uncased/checkpoint-596",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 596,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04697986577181208,
+      "grad_norm": 2.8473196029663086,
+      "learning_rate": 3.1111111111111116e-06,
+      "loss": 0.7023,
+      "step": 14
+    },
+    {
+      "epoch": 0.09395973154362416,
+      "grad_norm": 2.5279300212860107,
+      "learning_rate": 6.222222222222223e-06,
+      "loss": 0.6861,
+      "step": 28
+    },
+    {
+      "epoch": 0.14093959731543623,
+      "grad_norm": 2.878610134124756,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.6529,
+      "step": 42
+    },
+    {
+      "epoch": 0.18791946308724833,
+      "grad_norm": 2.704759359359741,
+      "learning_rate": 1.2444444444444446e-05,
+      "loss": 0.6374,
+      "step": 56
+    },
+    {
+      "epoch": 0.2348993288590604,
+      "grad_norm": 2.618530750274658,
+      "learning_rate": 1.5333333333333334e-05,
+      "loss": 0.5798,
+      "step": 70
+    },
+    {
+      "epoch": 0.28187919463087246,
+      "grad_norm": 3.5130767822265625,
+      "learning_rate": 1.8444444444444448e-05,
+      "loss": 0.5442,
+      "step": 84
+    },
+    {
+      "epoch": 0.3288590604026846,
+      "grad_norm": 6.02633810043335,
+      "learning_rate": 1.982587064676617e-05,
+      "loss": 0.5442,
+      "step": 98
+    },
+    {
+      "epoch": 0.37583892617449666,
+      "grad_norm": 6.7346673011779785,
+      "learning_rate": 1.947761194029851e-05,
+      "loss": 0.538,
+      "step": 112
+    },
+    {
+      "epoch": 0.4228187919463087,
+      "grad_norm": 4.506645202636719,
+      "learning_rate": 1.9129353233830846e-05,
+      "loss": 0.4524,
+      "step": 126
+    },
+    {
+      "epoch": 0.4697986577181208,
+      "grad_norm": 16.355239868164062,
+      "learning_rate": 1.8781094527363186e-05,
+      "loss": 0.4682,
+      "step": 140
+    },
+    {
+      "epoch": 0.5167785234899329,
+      "grad_norm": 4.144381046295166,
+      "learning_rate": 1.8432835820895526e-05,
+      "loss": 0.491,
+      "step": 154
+    },
+    {
+      "epoch": 0.5637583892617449,
+      "grad_norm": 4.07854700088501,
+      "learning_rate": 1.8084577114427863e-05,
+      "loss": 0.474,
+      "step": 168
+    },
+    {
+      "epoch": 0.610738255033557,
+      "grad_norm": 8.74126148223877,
+      "learning_rate": 1.77363184079602e-05,
+      "loss": 0.4303,
+      "step": 182
+    },
+    {
+      "epoch": 0.6577181208053692,
+      "grad_norm": 4.1934285163879395,
+      "learning_rate": 1.7412935323383088e-05,
+      "loss": 0.4545,
+      "step": 196
+    },
+    {
+      "epoch": 0.7046979865771812,
+      "grad_norm": 4.430333137512207,
+      "learning_rate": 1.7064676616915424e-05,
+      "loss": 0.4735,
+      "step": 210
+    },
+    {
+      "epoch": 0.7516778523489933,
+      "grad_norm": 3.5821316242218018,
+      "learning_rate": 1.671641791044776e-05,
+      "loss": 0.4115,
+      "step": 224
+    },
+    {
+      "epoch": 0.7986577181208053,
+      "grad_norm": 2.470816135406494,
+      "learning_rate": 1.63681592039801e-05,
+      "loss": 0.4395,
+      "step": 238
+    },
+    {
+      "epoch": 0.8456375838926175,
+      "grad_norm": 3.9837400913238525,
+      "learning_rate": 1.601990049751244e-05,
+      "loss": 0.4232,
+      "step": 252
+    },
+    {
+      "epoch": 0.8926174496644296,
+      "grad_norm": 5.207034111022949,
+      "learning_rate": 1.5671641791044777e-05,
+      "loss": 0.394,
+      "step": 266
+    },
+    {
+      "epoch": 0.9395973154362416,
+      "grad_norm": 3.6829946041107178,
+      "learning_rate": 1.5323383084577114e-05,
+      "loss": 0.4827,
+      "step": 280
+    },
+    {
+      "epoch": 0.9865771812080537,
+      "grad_norm": 3.973491668701172,
+      "learning_rate": 1.4975124378109454e-05,
+      "loss": 0.4326,
+      "step": 294
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8217281879194631,
+      "eval_auc": 0.8938196432503853,
+      "eval_f1": 0.7706422018348624,
+      "eval_loss": 0.3977891504764557,
+      "eval_precision": 0.7906976744186046,
+      "eval_recall": 0.751578947368421,
+      "eval_runtime": 2.28,
+      "eval_samples_per_second": 1045.597,
+      "eval_steps_per_second": 16.666,
+      "step": 298
+    },
+    {
+      "epoch": 1.0335570469798658,
+      "grad_norm": 5.082137107849121,
+      "learning_rate": 1.4626865671641792e-05,
+      "loss": 0.3941,
+      "step": 308
+    },
+    {
+      "epoch": 1.0805369127516777,
+      "grad_norm": 8.384503364562988,
+      "learning_rate": 1.427860696517413e-05,
+      "loss": 0.3692,
+      "step": 322
+    },
+    {
+      "epoch": 1.1275167785234899,
+      "grad_norm": 4.126455783843994,
+      "learning_rate": 1.393034825870647e-05,
+      "loss": 0.3797,
+      "step": 336
+    },
+    {
+      "epoch": 1.174496644295302,
+      "grad_norm": 2.891618013381958,
+      "learning_rate": 1.3582089552238807e-05,
+      "loss": 0.4014,
+      "step": 350
+    },
+    {
+      "epoch": 1.221476510067114,
+      "grad_norm": 6.136148929595947,
+      "learning_rate": 1.3233830845771145e-05,
+      "loss": 0.393,
+      "step": 364
+    },
+    {
+      "epoch": 1.2684563758389262,
+      "grad_norm": 3.083270788192749,
+      "learning_rate": 1.2885572139303483e-05,
+      "loss": 0.3564,
+      "step": 378
+    },
+    {
+      "epoch": 1.3154362416107381,
+      "grad_norm": 2.6372623443603516,
+      "learning_rate": 1.2537313432835823e-05,
+      "loss": 0.3492,
+      "step": 392
+    },
+    {
+      "epoch": 1.3624161073825503,
+      "grad_norm": 4.032045841217041,
+      "learning_rate": 1.218905472636816e-05,
+      "loss": 0.3858,
+      "step": 406
+    },
+    {
+      "epoch": 1.4093959731543624,
+      "grad_norm": 5.014185428619385,
+      "learning_rate": 1.1840796019900498e-05,
+      "loss": 0.3123,
+      "step": 420
+    },
+    {
+      "epoch": 1.4563758389261745,
+      "grad_norm": 5.151511192321777,
+      "learning_rate": 1.1492537313432836e-05,
+      "loss": 0.3717,
+      "step": 434
+    },
+    {
+      "epoch": 1.5033557046979866,
+      "grad_norm": 4.571159839630127,
+      "learning_rate": 1.1144278606965176e-05,
+      "loss": 0.3542,
+      "step": 448
+    },
+    {
+      "epoch": 1.5503355704697985,
+      "grad_norm": 4.309226036071777,
+      "learning_rate": 1.0796019900497514e-05,
+      "loss": 0.348,
+      "step": 462
+    },
+    {
+      "epoch": 1.5973154362416109,
+      "grad_norm": 3.4935061931610107,
+      "learning_rate": 1.0447761194029851e-05,
+      "loss": 0.3742,
+      "step": 476
+    },
+    {
+      "epoch": 1.6442953020134228,
+      "grad_norm": 3.565952777862549,
+      "learning_rate": 1.009950248756219e-05,
+      "loss": 0.3557,
+      "step": 490
+    },
+    {
+      "epoch": 1.691275167785235,
+      "grad_norm": 6.2538065910339355,
+      "learning_rate": 9.751243781094527e-06,
+      "loss": 0.3404,
+      "step": 504
+    },
+    {
+      "epoch": 1.738255033557047,
+      "grad_norm": 3.3098158836364746,
+      "learning_rate": 9.402985074626867e-06,
+      "loss": 0.401,
+      "step": 518
+    },
+    {
+      "epoch": 1.785234899328859,
+      "grad_norm": 5.43450927734375,
+      "learning_rate": 9.054726368159204e-06,
+      "loss": 0.3626,
+      "step": 532
+    },
+    {
+      "epoch": 1.8322147651006713,
+      "grad_norm": 5.279735088348389,
+      "learning_rate": 8.706467661691544e-06,
+      "loss": 0.2923,
+      "step": 546
+    },
+    {
+      "epoch": 1.8791946308724832,
+      "grad_norm": 6.0305328369140625,
+      "learning_rate": 8.35820895522388e-06,
+      "loss": 0.3978,
+      "step": 560
+    },
+    {
+      "epoch": 1.9261744966442953,
+      "grad_norm": 1.9193602800369263,
+      "learning_rate": 8.00995024875622e-06,
+      "loss": 0.3308,
+      "step": 574
+    },
+    {
+      "epoch": 1.9731543624161074,
+      "grad_norm": 4.429193019866943,
+      "learning_rate": 7.661691542288557e-06,
+      "loss": 0.3681,
+      "step": 588
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8309563758389261,
+      "eval_auc": 0.8991059238053292,
+      "eval_f1": 0.7820443482963764,
+      "eval_loss": 0.3905062973499298,
+      "eval_precision": 0.8042269187986651,
+      "eval_recall": 0.7610526315789473,
+      "eval_runtime": 2.2806,
+      "eval_samples_per_second": 1045.317,
+      "eval_steps_per_second": 16.662,
+      "step": 596
+    }
+  ],
+  "logging_steps": 14,
+  "max_steps": 894,
+  "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": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1253987289845760.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-596/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:387e0d0bc1a6e51ea4fb5ca3dfc25ef39457ad0a7f6b5e686c960975c25487cb
+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": "4.46.2",
+  "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 sha256:36af391fcc6cf6d329ee4ce2450747716314197bf08ef5ddb03cad6e64800d26
+size 437958648

runs/Dec15_19-48-29_r-dilarayavuz-model-merge-e2munm62-1afa0-gthas/events.out.tfevents.1734292111.r-dilarayavuz-model-merge-e2munm62-1afa0-gthas.204.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8276f80be4bf98795a18165fe733d30dd97a3d6df4cf9c070de870e882ce2e5
-size 5232
+oid sha256:c9a4cda10e361bb2087ab3ee5439da992897df561d378e7de83b478bb15ab32b
+size 20400

runs/Dec15_19-48-29_r-dilarayavuz-model-merge-e2munm62-1afa0-gthas/events.out.tfevents.1734292219.r-dilarayavuz-model-merge-e2munm62-1afa0-gthas.204.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6360fb0dd2677e55d4c117c0e68f9a9fa1ce9be9c8853de862060a5036809e1c
+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 +1,55 @@
+{
+  "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": false,
+  "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 sha256:387e0d0bc1a6e51ea4fb5ca3dfc25ef39457ad0a7f6b5e686c960975c25487cb
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "olid-stylebkd-p10-bert-uncased/autotrain-data",
+    "model": "google-bert/bert-base-uncased",
+    "lr": 2e-05,
+    "epochs": 3,
+    "max_seq_length": 128,
+    "batch_size": 32,
+    "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": "olid-stylebkd-p10-bert-uncased",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "dilarayavuz",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}