indobert-large-p2_preprocessing_tuning

README.md

@@ -0,0 +1,74 @@
+---
+library_name: transformers
+license: mit
+base_model: indobenchmark/indobert-large-p2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: results_indobert-large-p2_preprocessing_tuning
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# results_indobert-large-p2_preprocessing_tuning
+
+This model is a fine-tuned version of [indobenchmark/indobert-large-p2](https://huggingface.co/indobenchmark/indobert-large-p2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4637
+- Accuracy: 0.4545
+- Precision: 0.5084
+- Recall: 0.4353
+- F1: 0.4145
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3.5225350314211635e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use adafactor and the args are:
+No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 1.6552        | 1.0   | 111  | 1.5541          | 0.2545   | 0.1575    | 0.2126 | 0.1676 |
+| 1.5877        | 2.0   | 222  | 1.5239          | 0.2977   | 0.4944    | 0.2590 | 0.2152 |
+| 1.561         | 3.0   | 333  | 1.4980          | 0.3773   | 0.4931    | 0.3403 | 0.3261 |
+| 1.5361        | 4.0   | 444  | 1.4807          | 0.4227   | 0.4950    | 0.3978 | 0.3865 |
+| 1.5163        | 5.0   | 555  | 1.4637          | 0.4545   | 0.5084    | 0.4353 | 0.4145 |
+| 1.496         | 6.0   | 666  | 1.4509          | 0.4295   | 0.5107    | 0.4127 | 0.3970 |
+| 1.4931        | 7.0   | 777  | 1.4354          | 0.4273   | 0.4916    | 0.4026 | 0.3910 |
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.2

config.json

@@ -0,0 +1,47 @@
+{
+  "_num_labels": 5,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.3,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.3,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

final_model/config.json

@@ -0,0 +1,47 @@
+{
+  "_num_labels": 5,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.3,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.3,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

final_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba173bde194fff86c760183d06fa99427ba4233698b8f0bcfe3bf00c7f05d678
+size 1340635060

final_model/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

final_model/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

final_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ecc0710fe0575728761988d31e5efdffcb03d899093b12918b430b4bca7f18
+size 5240

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba173bde194fff86c760183d06fa99427ba4233698b8f0bcfe3bf00c7f05d678
+size 1340635060

run-0/checkpoint-555/config.json

@@ -0,0 +1,47 @@
+{
+  "_num_labels": 5,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.3,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.3,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-555/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b67d7099022362981a4d208a0350dab8b4a28c51f922d40964ff39788523e3f
+size 1340635060

run-0/checkpoint-555/trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_global_step": 555,
+  "best_metric": 0.34545454545454546,
+  "best_model_checkpoint": "./results_indobert-large-p2_preprocessing_tuning/run-0/checkpoint-555",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 555,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 26.157533645629883,
+      "learning_rate": 1.906084574220028e-05,
+      "loss": 1.6713,
+      "step": 111
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.23863636363636365,
+      "eval_f1": 0.15186499337267767,
+      "eval_loss": 1.5738822221755981,
+      "eval_precision": 0.21780234279986876,
+      "eval_recall": 0.19921385803738745,
+      "eval_runtime": 5.6808,
+      "eval_samples_per_second": 77.454,
+      "eval_steps_per_second": 2.464,
+      "step": 111
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 28.891916275024414,
+      "learning_rate": 1.805811878609401e-05,
+      "loss": 1.6117,
+      "step": 222
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.2727272727272727,
+      "eval_f1": 0.17833531793284116,
+      "eval_loss": 1.5519375801086426,
+      "eval_precision": 0.16588746858953346,
+      "eval_recall": 0.23229946524064174,
+      "eval_runtime": 5.646,
+      "eval_samples_per_second": 77.931,
+      "eval_steps_per_second": 2.48,
+      "step": 222
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 18.7272891998291,
+      "learning_rate": 1.705539182998774e-05,
+      "loss": 1.5958,
+      "step": 333
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.2909090909090909,
+      "eval_f1": 0.19304355849445587,
+      "eval_loss": 1.5347687005996704,
+      "eval_precision": 0.3811392256485068,
+      "eval_recall": 0.24720105466428993,
+      "eval_runtime": 5.6444,
+      "eval_samples_per_second": 77.954,
+      "eval_steps_per_second": 2.48,
+      "step": 333
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 27.44182014465332,
+      "learning_rate": 1.6052664873881467e-05,
+      "loss": 1.5792,
+      "step": 444
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.3159090909090909,
+      "eval_f1": 0.22223201929048866,
+      "eval_loss": 1.521448016166687,
+      "eval_precision": 0.5018285105627551,
+      "eval_recall": 0.2726780817221994,
+      "eval_runtime": 5.6387,
+      "eval_samples_per_second": 78.033,
+      "eval_steps_per_second": 2.483,
+      "step": 444
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 27.527873992919922,
+      "learning_rate": 1.5049937917775197e-05,
+      "loss": 1.5623,
+      "step": 555
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.34545454545454546,
+      "eval_f1": 0.28947961232328573,
+      "eval_loss": 1.5095351934432983,
+      "eval_precision": 0.46474527630134865,
+      "eval_recall": 0.31175859271447504,
+      "eval_runtime": 5.6345,
+      "eval_samples_per_second": 78.09,
+      "eval_steps_per_second": 2.485,
+      "step": 555
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2220,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "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": 4165793621453100.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout": 0.3,
+    "learning_rate": 2.0054539122125413e-05,
+    "optim": "adamw_torch"
+  }
+}

run-0/checkpoint-555/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2718cfa04c9d7664e92a9d3fe2c105da6e2410abefc860ef4614a2042f5296e
+size 5304

run-1/checkpoint-1998/config.json

@@ -0,0 +1,47 @@
+{
+  "_num_labels": 5,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-1998/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07e15fc676b2b34404c59af505ebedb4042e66cec064ff3815003599148b501d
+size 1340635060

run-1/checkpoint-1998/trainer_state.json

@@ -0,0 +1,389 @@
+{
+  "best_global_step": 1998,
+  "best_metric": 0.5340909090909091,
+  "best_model_checkpoint": "./results_indobert-large-p2_preprocessing_tuning/run-1/checkpoint-1998",
+  "epoch": 18.0,
+  "eval_steps": 500,
+  "global_step": 1998,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 28.307113647460938,
+      "learning_rate": 3.347995007341736e-05,
+      "loss": 1.6047,
+      "step": 111
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.2545454545454545,
+      "eval_f1": 0.17276828110161443,
+      "eval_loss": 1.5445789098739624,
+      "eval_precision": 0.15013455356645924,
+      "eval_recall": 0.2126797385620915,
+      "eval_runtime": 5.6508,
+      "eval_samples_per_second": 77.865,
+      "eval_steps_per_second": 2.478,
+      "step": 111
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 26.515804290771484,
+      "learning_rate": 3.171868255770678e-05,
+      "loss": 1.5395,
+      "step": 222
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.3386363636363636,
+      "eval_f1": 0.25941876303739597,
+      "eval_loss": 1.509023904800415,
+      "eval_precision": 0.4118648391560013,
+      "eval_recall": 0.2931060606060606,
+      "eval_runtime": 5.6362,
+      "eval_samples_per_second": 78.067,
+      "eval_steps_per_second": 2.484,
+      "step": 222
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 17.496076583862305,
+      "learning_rate": 2.9957415041996202e-05,
+      "loss": 1.5068,
+      "step": 333
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.39090909090909093,
+      "eval_f1": 0.31160041861619076,
+      "eval_loss": 1.4787184000015259,
+      "eval_precision": 0.46941073658516264,
+      "eval_recall": 0.3394613556378262,
+      "eval_runtime": 5.6351,
+      "eval_samples_per_second": 78.082,
+      "eval_steps_per_second": 2.484,
+      "step": 333
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 19.426055908203125,
+      "learning_rate": 2.819614752628562e-05,
+      "loss": 1.4708,
+      "step": 444
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.425,
+      "eval_f1": 0.35879524661207,
+      "eval_loss": 1.4531804323196411,
+      "eval_precision": 0.5943328601223339,
+      "eval_recall": 0.37929201517436806,
+      "eval_runtime": 5.6373,
+      "eval_samples_per_second": 78.052,
+      "eval_steps_per_second": 2.483,
+      "step": 444
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 24.8659610748291,
+      "learning_rate": 2.643488001057504e-05,
+      "loss": 1.4514,
+      "step": 555
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.44772727272727275,
+      "eval_f1": 0.3811685823691032,
+      "eval_loss": 1.4312589168548584,
+      "eval_precision": 0.40861740753373244,
+      "eval_recall": 0.401798871063577,
+      "eval_runtime": 5.634,
+      "eval_samples_per_second": 78.097,
+      "eval_steps_per_second": 2.485,
+      "step": 555
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 20.785106658935547,
+      "learning_rate": 2.4673612494864454e-05,
+      "loss": 1.4318,
+      "step": 666
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4727272727272727,
+      "eval_f1": 0.42115625735603157,
+      "eval_loss": 1.4126225709915161,
+      "eval_precision": 0.6314769518811494,
+      "eval_recall": 0.4340944513003337,
+      "eval_runtime": 5.6323,
+      "eval_samples_per_second": 78.121,
+      "eval_steps_per_second": 2.486,
+      "step": 666
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 21.870254516601562,
+      "learning_rate": 2.2912344979153876e-05,
+      "loss": 1.4118,
+      "step": 777
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.4636363636363636,
+      "eval_f1": 0.4063186285023795,
+      "eval_loss": 1.395840048789978,
+      "eval_precision": 0.6317628654319302,
+      "eval_recall": 0.4194442730472142,
+      "eval_runtime": 5.646,
+      "eval_samples_per_second": 77.931,
+      "eval_steps_per_second": 2.48,
+      "step": 777
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 25.146141052246094,
+      "learning_rate": 2.115107746344329e-05,
+      "loss": 1.3992,
+      "step": 888
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.4818181818181818,
+      "eval_f1": 0.4368896891233544,
+      "eval_loss": 1.382132649421692,
+      "eval_precision": 0.6322711381096474,
+      "eval_recall": 0.445048876776818,
+      "eval_runtime": 5.6417,
+      "eval_samples_per_second": 77.991,
+      "eval_steps_per_second": 2.482,
+      "step": 888
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 19.100143432617188,
+      "learning_rate": 1.9389809947732713e-05,
+      "loss": 1.3817,
+      "step": 999
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.48863636363636365,
+      "eval_f1": 0.44047740781253586,
+      "eval_loss": 1.369884729385376,
+      "eval_precision": 0.6328607028095519,
+      "eval_recall": 0.4521078717034599,
+      "eval_runtime": 5.6338,
+      "eval_samples_per_second": 78.101,
+      "eval_steps_per_second": 2.485,
+      "step": 999
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 27.9638671875,
+      "learning_rate": 1.762854243202213e-05,
+      "loss": 1.3738,
+      "step": 1110
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.4863636363636364,
+      "eval_f1": 0.4383040341201726,
+      "eval_loss": 1.3581469058990479,
+      "eval_precision": 0.6375822435542926,
+      "eval_recall": 0.44977869760957995,
+      "eval_runtime": 5.6419,
+      "eval_samples_per_second": 77.987,
+      "eval_steps_per_second": 2.481,
+      "step": 1110
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 21.18199920654297,
+      "learning_rate": 1.5867274916311547e-05,
+      "loss": 1.3676,
+      "step": 1221
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.4954545454545455,
+      "eval_f1": 0.4464058678860118,
+      "eval_loss": 1.3483368158340454,
+      "eval_precision": 0.6465497076023392,
+      "eval_recall": 0.4576812525709585,
+      "eval_runtime": 5.6322,
+      "eval_samples_per_second": 78.122,
+      "eval_steps_per_second": 2.486,
+      "step": 1221
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 20.461551666259766,
+      "learning_rate": 1.4106007400600966e-05,
+      "loss": 1.3456,
+      "step": 1332
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.49772727272727274,
+      "eval_f1": 0.45309114799612626,
+      "eval_loss": 1.3403079509735107,
+      "eval_precision": 0.6216789934702979,
+      "eval_recall": 0.4615172654143242,
+      "eval_runtime": 5.6417,
+      "eval_samples_per_second": 77.99,
+      "eval_steps_per_second": 2.482,
+      "step": 1332
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 22.989744186401367,
+      "learning_rate": 1.2344739884890382e-05,
+      "loss": 1.3461,
+      "step": 1443
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.4954545454545455,
+      "eval_f1": 0.45083981073459956,
+      "eval_loss": 1.3333238363265991,
+      "eval_precision": 0.6414684410584339,
+      "eval_recall": 0.4573236608163079,
+      "eval_runtime": 5.6425,
+      "eval_samples_per_second": 77.98,
+      "eval_steps_per_second": 2.481,
+      "step": 1443
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 25.141088485717773,
+      "learning_rate": 1.0583472369179801e-05,
+      "loss": 1.3328,
+      "step": 1554
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.5045454545454545,
+      "eval_f1": 0.4703906523958635,
+      "eval_loss": 1.3271719217300415,
+      "eval_precision": 0.6402919474918446,
+      "eval_recall": 0.4697626148361443,
+      "eval_runtime": 5.6452,
+      "eval_samples_per_second": 77.943,
+      "eval_steps_per_second": 2.48,
+      "step": 1554
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 25.32221031188965,
+      "learning_rate": 8.82220485346922e-06,
+      "loss": 1.3318,
+      "step": 1665
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.5227272727272727,
+      "eval_f1": 0.4880063307593935,
+      "eval_loss": 1.3223538398742676,
+      "eval_precision": 0.63281290138433,
+      "eval_recall": 0.4929561451620275,
+      "eval_runtime": 5.6478,
+      "eval_samples_per_second": 77.906,
+      "eval_steps_per_second": 2.479,
+      "step": 1665
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 22.660276412963867,
+      "learning_rate": 7.060937337758639e-06,
+      "loss": 1.3283,
+      "step": 1776
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.5227272727272727,
+      "eval_f1": 0.4891241086551116,
+      "eval_loss": 1.3183715343475342,
+      "eval_precision": 0.6357144636301626,
+      "eval_recall": 0.49185134718222956,
+      "eval_runtime": 5.6328,
+      "eval_samples_per_second": 78.114,
+      "eval_steps_per_second": 2.485,
+      "step": 1776
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 23.627805709838867,
+      "learning_rate": 5.299669822048057e-06,
+      "loss": 1.3244,
+      "step": 1887
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.5318181818181819,
+      "eval_f1": 0.49959033811814146,
+      "eval_loss": 1.3156731128692627,
+      "eval_precision": 0.6414611620564796,
+      "eval_recall": 0.5044939496777732,
+      "eval_runtime": 5.6491,
+      "eval_samples_per_second": 77.888,
+      "eval_steps_per_second": 2.478,
+      "step": 1887
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 21.08611488342285,
+      "learning_rate": 3.5384023063374753e-06,
+      "loss": 1.3202,
+      "step": 1998
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.5340909090909091,
+      "eval_f1": 0.50148050227307,
+      "eval_loss": 1.3135546445846558,
+      "eval_precision": 0.6410177133655395,
+      "eval_recall": 0.5074763471822296,
+      "eval_runtime": 5.6436,
+      "eval_samples_per_second": 77.964,
+      "eval_steps_per_second": 2.481,
+      "step": 1998
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2220,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "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": 1.499685703723116e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout": 0.1,
+    "learning_rate": 3.5225350314211635e-05,
+    "optim": "adafactor"
+  }
+}

run-1/checkpoint-1998/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed8145004f2ca45b2da65c4909138f82df15e15928e4fb3105a0807198eb5bd8
+size 5304

run-2/checkpoint-888/config.json

@@ -0,0 +1,47 @@
+{
+  "_num_labels": 5,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-888/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d719a532d71aa147139a87755a12cb0d04bdcc096420991de6dd1c085f60349
+size 1340635060

run-2/checkpoint-888/trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_global_step": 888,
+  "best_metric": 0.5068181818181818,
+  "best_model_checkpoint": "./results_indobert-large-p2_preprocessing_tuning/run-2/checkpoint-888",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 888,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 27.982898712158203,
+      "learning_rate": 4.155146788213293e-05,
+      "loss": 1.5977,
+      "step": 111
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.2636363636363636,
+      "eval_f1": 0.1799745107509752,
+      "eval_loss": 1.5375301837921143,
+      "eval_precision": 0.25754679410593384,
+      "eval_recall": 0.2207596325243384,
+      "eval_runtime": 5.6549,
+      "eval_samples_per_second": 77.809,
+      "eval_steps_per_second": 2.476,
+      "step": 111
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 26.399566650390625,
+      "learning_rate": 3.9365584974589446e-05,
+      "loss": 1.53,
+      "step": 222
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.3568181818181818,
+      "eval_f1": 0.2808285329868572,
+      "eval_loss": 1.4986050128936768,
+      "eval_precision": 0.4284489841672241,
+      "eval_recall": 0.31234477124183,
+      "eval_runtime": 5.6438,
+      "eval_samples_per_second": 77.962,
+      "eval_steps_per_second": 2.481,
+      "step": 222
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 17.31713104248047,
+      "learning_rate": 3.7179702067045956e-05,
+      "loss": 1.4936,
+      "step": 333
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3886363636363636,
+      "eval_f1": 0.32744459189481273,
+      "eval_loss": 1.4661439657211304,
+      "eval_precision": 0.45449121759466593,
+      "eval_recall": 0.3438792620777915,
+      "eval_runtime": 5.642,
+      "eval_samples_per_second": 77.987,
+      "eval_steps_per_second": 2.481,
+      "step": 333
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 18.687728881835938,
+      "learning_rate": 3.499381915950247e-05,
+      "loss": 1.4543,
+      "step": 444
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4431818181818182,
+      "eval_f1": 0.38349095423479923,
+      "eval_loss": 1.4361019134521484,
+      "eval_precision": 0.6067617470249049,
+      "eval_recall": 0.39622406188582654,
+      "eval_runtime": 5.6469,
+      "eval_samples_per_second": 77.919,
+      "eval_steps_per_second": 2.479,
+      "step": 444
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 24.65712547302246,
+      "learning_rate": 3.280793625195898e-05,
+      "loss": 1.432,
+      "step": 555
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4727272727272727,
+      "eval_f1": 0.4139282607939324,
+      "eval_loss": 1.411230206489563,
+      "eval_precision": 0.43078144078144087,
+      "eval_recall": 0.43161207664884127,
+      "eval_runtime": 5.6457,
+      "eval_samples_per_second": 77.935,
+      "eval_steps_per_second": 2.48,
+      "step": 555
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 20.577791213989258,
+      "learning_rate": 3.06220533444155e-05,
+      "loss": 1.4101,
+      "step": 666
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.48409090909090907,
+      "eval_f1": 0.4338799158412677,
+      "eval_loss": 1.390539288520813,
+      "eval_precision": 0.6315770552471583,
+      "eval_recall": 0.44571526920791626,
+      "eval_runtime": 5.639,
+      "eval_samples_per_second": 78.028,
+      "eval_steps_per_second": 2.483,
+      "step": 666
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 21.280122756958008,
+      "learning_rate": 2.8436170436872013e-05,
+      "loss": 1.3888,
+      "step": 777
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.4727272727272727,
+      "eval_f1": 0.424862819641019,
+      "eval_loss": 1.37294602394104,
+      "eval_precision": 0.6410874819887262,
+      "eval_recall": 0.4338800047991224,
+      "eval_runtime": 5.6393,
+      "eval_samples_per_second": 78.023,
+      "eval_steps_per_second": 2.483,
+      "step": 777
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 24.84048843383789,
+      "learning_rate": 2.6250287529328527e-05,
+      "loss": 1.3743,
+      "step": 888
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5068181818181818,
+      "eval_f1": 0.4797829051866942,
+      "eval_loss": 1.3590517044067383,
+      "eval_precision": 0.6435987454921921,
+      "eval_recall": 0.47469299899446965,
+      "eval_runtime": 5.6444,
+      "eval_samples_per_second": 77.953,
+      "eval_steps_per_second": 2.48,
+      "step": 888
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2220,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "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": 6665269794324960.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout": 0.1,
+    "learning_rate": 4.3717658150869716e-05,
+    "optim": "adamw_torch"
+  }
+}

run-2/checkpoint-888/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc729469000a177aefc94e34e3e6a799b7a60083f5d6c40f2adb23cc599545f9
+size 5304

run-3/checkpoint-999/config.json

@@ -0,0 +1,47 @@
+{
+  "_num_labels": 5,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-3/checkpoint-999/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93607dc340a2d1d7ea3d3b721bc9018aba30b267ad48dab2f3f2ce46766c82ad
+size 1340635060

run-3/checkpoint-999/trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_global_step": 999,
+  "best_metric": 0.4954545454545455,
+  "best_model_checkpoint": "./results_indobert-large-p2_preprocessing_tuning/run-3/checkpoint-999",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 999,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 28.07038688659668,
+      "learning_rate": 3.3016175944992974e-05,
+      "loss": 1.6052,
+      "step": 111
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.25681818181818183,
+      "eval_f1": 0.17675619592464678,
+      "eval_loss": 1.5476956367492676,
+      "eval_precision": 0.22089947089947087,
+      "eval_recall": 0.21530508706979296,
+      "eval_runtime": 5.6509,
+      "eval_samples_per_second": 77.863,
+      "eval_steps_per_second": 2.477,
+      "step": 111
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 26.43117332458496,
+      "learning_rate": 3.127930602561183e-05,
+      "loss": 1.543,
+      "step": 222
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.32727272727272727,
+      "eval_f1": 0.2417304318204673,
+      "eval_loss": 1.5140272378921509,
+      "eval_precision": 0.41058006919572254,
+      "eval_recall": 0.282364081996435,
+      "eval_runtime": 5.6439,
+      "eval_samples_per_second": 77.961,
+      "eval_steps_per_second": 2.481,
+      "step": 222
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 17.558069229125977,
+      "learning_rate": 2.9542436106230683e-05,
+      "loss": 1.5127,
+      "step": 333
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.35909090909090907,
+      "eval_f1": 0.2703941838976566,
+      "eval_loss": 1.4859756231307983,
+      "eval_precision": 0.4807188323597861,
+      "eval_recall": 0.30677121897710136,
+      "eval_runtime": 5.6443,
+      "eval_samples_per_second": 77.955,
+      "eval_steps_per_second": 2.48,
+      "step": 333
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 19.551990509033203,
+      "learning_rate": 2.7805566186849536e-05,
+      "loss": 1.4782,
+      "step": 444
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.41818181818181815,
+      "eval_f1": 0.3384192026632338,
+      "eval_loss": 1.4601621627807617,
+      "eval_precision": 0.49135958882110203,
+      "eval_recall": 0.36583056241144474,
+      "eval_runtime": 5.6426,
+      "eval_samples_per_second": 77.979,
+      "eval_steps_per_second": 2.481,
+      "step": 444
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 24.336103439331055,
+      "learning_rate": 2.606869626746839e-05,
+      "loss": 1.4585,
+      "step": 555
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.43863636363636366,
+      "eval_f1": 0.3715119915434134,
+      "eval_loss": 1.4385919570922852,
+      "eval_precision": 0.41001389914433395,
+      "eval_recall": 0.39180555555555563,
+      "eval_runtime": 5.6421,
+      "eval_samples_per_second": 77.985,
+      "eval_steps_per_second": 2.481,
+      "step": 555
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 20.89763069152832,
+      "learning_rate": 2.433182634808724e-05,
+      "loss": 1.4404,
+      "step": 666
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.45,
+      "eval_f1": 0.3827180550754695,
+      "eval_loss": 1.4205297231674194,
+      "eval_precision": 0.4161682321743297,
+      "eval_recall": 0.40269050802139034,
+      "eval_runtime": 5.6514,
+      "eval_samples_per_second": 77.857,
+      "eval_steps_per_second": 2.477,
+      "step": 666
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 21.438804626464844,
+      "learning_rate": 2.2594956428706095e-05,
+      "loss": 1.4209,
+      "step": 777
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.46136363636363636,
+      "eval_f1": 0.4025527449318057,
+      "eval_loss": 1.4050540924072266,
+      "eval_precision": 0.6351323893652621,
+      "eval_recall": 0.41623608825814706,
+      "eval_runtime": 5.6367,
+      "eval_samples_per_second": 78.06,
+      "eval_steps_per_second": 2.484,
+      "step": 777
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 25.60862922668457,
+      "learning_rate": 2.0858086509324948e-05,
+      "loss": 1.4091,
+      "step": 888
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.4818181818181818,
+      "eval_f1": 0.44363701601041755,
+      "eval_loss": 1.392228603363037,
+      "eval_precision": 0.6408069190319805,
+      "eval_recall": 0.44583264774441245,
+      "eval_runtime": 5.642,
+      "eval_samples_per_second": 77.986,
+      "eval_steps_per_second": 2.481,
+      "step": 888
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 19.344066619873047,
+      "learning_rate": 1.91212165899438e-05,
+      "loss": 1.3911,
+      "step": 999
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.4954545454545455,
+      "eval_f1": 0.44896411578531625,
+      "eval_loss": 1.3796334266662598,
+      "eval_precision": 0.6507260296673966,
+      "eval_recall": 0.4559108048813931,
+      "eval_runtime": 5.64,
+      "eval_samples_per_second": 78.015,
+      "eval_steps_per_second": 2.482,
+      "step": 999
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2220,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "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": 7498428518615580.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout": 0.1,
+    "learning_rate": 3.473739838762294e-05,
+    "optim": "adamw_torch"
+  }
+}

run-3/checkpoint-999/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab9278cb3dc0f63bca53110e0d1c7cb99427159cac07769457f10c95cc61aa2
+size 5304

run-4/checkpoint-2220/config.json

@@ -0,0 +1,47 @@
+{
+  "_num_labels": 5,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-4/checkpoint-2220/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd62eaa9fe39b422eb3bfc2f8945cd7b2fc3bcf161dbd67d9647c4061a6f17d8
+size 1340635060

run-4/checkpoint-2220/trainer_state.json

@@ -0,0 +1,427 @@
+{
+  "best_global_step": 2220,
+  "best_metric": 0.48409090909090907,
+  "best_model_checkpoint": "./results_indobert-large-p2_preprocessing_tuning/run-4/checkpoint-2220",
+  "epoch": 20.0,
+  "eval_steps": 500,
+  "global_step": 2220,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 28.173372268676758,
+      "learning_rate": 2.061757049019103e-05,
+      "loss": 1.6195,
+      "step": 111
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.22727272727272727,
+      "eval_f1": 0.16707363603285513,
+      "eval_loss": 1.5637433528900146,
+      "eval_precision": 0.1896742471557858,
+      "eval_recall": 0.19347410759175462,
+      "eval_runtime": 5.6498,
+      "eval_samples_per_second": 77.879,
+      "eval_steps_per_second": 2.478,
+      "step": 111
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 26.51243019104004,
+      "learning_rate": 1.9532949483361077e-05,
+      "loss": 1.5637,
+      "step": 222
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.2840909090909091,
+      "eval_f1": 0.20335907891998062,
+      "eval_loss": 1.5392452478408813,
+      "eval_precision": 0.24167936991869915,
+      "eval_recall": 0.24468174390968506,
+      "eval_runtime": 5.6407,
+      "eval_samples_per_second": 78.005,
+      "eval_steps_per_second": 2.482,
+      "step": 222
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 18.05230712890625,
+      "learning_rate": 1.844832847653112e-05,
+      "loss": 1.5436,
+      "step": 333
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3159090909090909,
+      "eval_f1": 0.222951366983383,
+      "eval_loss": 1.518822431564331,
+      "eval_precision": 0.4947492546611489,
+      "eval_recall": 0.2669387026372321,
+      "eval_runtime": 5.6405,
+      "eval_samples_per_second": 78.007,
+      "eval_steps_per_second": 2.482,
+      "step": 333
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 21.303878784179688,
+      "learning_rate": 1.7363707469701166e-05,
+      "loss": 1.5177,
+      "step": 444
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.35454545454545455,
+      "eval_f1": 0.2592289550384887,
+      "eval_loss": 1.5000191926956177,
+      "eval_precision": 0.5177054197359525,
+      "eval_recall": 0.30301713400978103,
+      "eval_runtime": 5.6399,
+      "eval_samples_per_second": 78.016,
+      "eval_steps_per_second": 2.482,
+      "step": 444
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 23.725130081176758,
+      "learning_rate": 1.627908646287121e-05,
+      "loss": 1.5018,
+      "step": 555
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.38636363636363635,
+      "eval_f1": 0.28658706487641944,
+      "eval_loss": 1.4842791557312012,
+      "eval_precision": 0.3875367377720319,
+      "eval_recall": 0.3301949643493761,
+      "eval_runtime": 5.6473,
+      "eval_samples_per_second": 77.913,
+      "eval_steps_per_second": 2.479,
+      "step": 555
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 21.390344619750977,
+      "learning_rate": 1.5194465456041256e-05,
+      "loss": 1.4906,
+      "step": 666
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.3840909090909091,
+      "eval_f1": 0.2939072926084069,
+      "eval_loss": 1.4709296226501465,
+      "eval_precision": 0.4050465432146414,
+      "eval_recall": 0.33076463161021985,
+      "eval_runtime": 5.6511,
+      "eval_samples_per_second": 77.861,
+      "eval_steps_per_second": 2.477,
+      "step": 666
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 21.77083396911621,
+      "learning_rate": 1.4109844449211303e-05,
+      "loss": 1.4748,
+      "step": 777
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.4,
+      "eval_f1": 0.31341312575745073,
+      "eval_loss": 1.4593591690063477,
+      "eval_precision": 0.4112193362193362,
+      "eval_recall": 0.3468304367201426,
+      "eval_runtime": 5.6465,
+      "eval_samples_per_second": 77.924,
+      "eval_steps_per_second": 2.479,
+      "step": 777
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 26.71363639831543,
+      "learning_rate": 1.3025223442381347e-05,
+      "loss": 1.4683,
+      "step": 888
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.42045454545454547,
+      "eval_f1": 0.359908589559646,
+      "eval_loss": 1.4492100477218628,
+      "eval_precision": 0.6176410063500948,
+      "eval_recall": 0.3752995166598108,
+      "eval_runtime": 5.643,
+      "eval_samples_per_second": 77.973,
+      "eval_steps_per_second": 2.481,
+      "step": 888
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 20.639911651611328,
+      "learning_rate": 1.1940602435551393e-05,
+      "loss": 1.4531,
+      "step": 999
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.4318181818181818,
+      "eval_f1": 0.36729459537697784,
+      "eval_loss": 1.4398030042648315,
+      "eval_precision": 0.6194453783927468,
+      "eval_recall": 0.3847588155308744,
+      "eval_runtime": 5.6431,
+      "eval_samples_per_second": 77.971,
+      "eval_steps_per_second": 2.481,
+      "step": 999
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 28.17357635498047,
+      "learning_rate": 1.0855981428721437e-05,
+      "loss": 1.4491,
+      "step": 1110
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.4318181818181818,
+      "eval_f1": 0.36386279688990475,
+      "eval_loss": 1.4310266971588135,
+      "eval_precision": 0.4143773997162906,
+      "eval_recall": 0.3842602495543672,
+      "eval_runtime": 5.6507,
+      "eval_samples_per_second": 77.866,
+      "eval_steps_per_second": 2.478,
+      "step": 1110
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 21.685190200805664,
+      "learning_rate": 9.771360421891483e-06,
+      "loss": 1.4454,
+      "step": 1221
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.44772727272727275,
+      "eval_f1": 0.38095142005589766,
+      "eval_loss": 1.4234737157821655,
+      "eval_precision": 0.4134604525908873,
+      "eval_recall": 0.40081290849673207,
+      "eval_runtime": 5.6455,
+      "eval_samples_per_second": 77.938,
+      "eval_steps_per_second": 2.48,
+      "step": 1221
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 22.45073890686035,
+      "learning_rate": 8.686739415061529e-06,
+      "loss": 1.4259,
+      "step": 1332
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.4431818181818182,
+      "eval_f1": 0.37841971280585274,
+      "eval_loss": 1.417261004447937,
+      "eval_precision": 0.6213600856072766,
+      "eval_recall": 0.3951208921797157,
+      "eval_runtime": 5.6548,
+      "eval_samples_per_second": 77.81,
+      "eval_steps_per_second": 2.476,
+      "step": 1332
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 22.751588821411133,
+      "learning_rate": 7.602118408231573e-06,
+      "loss": 1.4269,
+      "step": 1443
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.45227272727272727,
+      "eval_f1": 0.38372927204896606,
+      "eval_loss": 1.41156005859375,
+      "eval_precision": 0.6219436130594713,
+      "eval_recall": 0.4022510169568993,
+      "eval_runtime": 5.6568,
+      "eval_samples_per_second": 77.783,
+      "eval_steps_per_second": 2.475,
+      "step": 1443
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 25.058902740478516,
+      "learning_rate": 6.517497401401619e-06,
+      "loss": 1.4149,
+      "step": 1554
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.46136363636363636,
+      "eval_f1": 0.3965849769868146,
+      "eval_loss": 1.406818151473999,
+      "eval_precision": 0.62480495292599,
+      "eval_recall": 0.4135868012706248,
+      "eval_runtime": 5.6396,
+      "eval_samples_per_second": 78.019,
+      "eval_steps_per_second": 2.482,
+      "step": 1554
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 25.90663719177246,
+      "learning_rate": 5.432876394571665e-06,
+      "loss": 1.4154,
+      "step": 1665
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.4681818181818182,
+      "eval_f1": 0.40920946163765315,
+      "eval_loss": 1.4027258157730103,
+      "eval_precision": 0.6300146138362699,
+      "eval_recall": 0.4239477638374698,
+      "eval_runtime": 5.6499,
+      "eval_samples_per_second": 77.878,
+      "eval_steps_per_second": 2.478,
+      "step": 1665
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 23.27178192138672,
+      "learning_rate": 4.34825538774171e-06,
+      "loss": 1.4127,
+      "step": 1776
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.4681818181818182,
+      "eval_f1": 0.40934331177145705,
+      "eval_loss": 1.3994897603988647,
+      "eval_precision": 0.6302565920883121,
+      "eval_recall": 0.4239477638374698,
+      "eval_runtime": 5.6497,
+      "eval_samples_per_second": 77.88,
+      "eval_steps_per_second": 2.478,
+      "step": 1776
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 24.377626419067383,
+      "learning_rate": 3.2636343809117553e-06,
+      "loss": 1.409,
+      "step": 1887
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.47954545454545455,
+      "eval_f1": 0.4268450750732614,
+      "eval_loss": 1.3972902297973633,
+      "eval_precision": 0.6328140298234569,
+      "eval_recall": 0.438621909136615,
+      "eval_runtime": 5.6515,
+      "eval_samples_per_second": 77.856,
+      "eval_steps_per_second": 2.477,
+      "step": 1887
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 21.303892135620117,
+      "learning_rate": 2.1790133740818008e-06,
+      "loss": 1.4057,
+      "step": 1998
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.4818181818181818,
+      "eval_f1": 0.43042012354512893,
+      "eval_loss": 1.3956239223480225,
+      "eval_precision": 0.6351662548714184,
+      "eval_recall": 0.44174690913661496,
+      "eval_runtime": 5.6444,
+      "eval_samples_per_second": 77.953,
+      "eval_steps_per_second": 2.48,
+      "step": 1998
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 28.218753814697266,
+      "learning_rate": 1.0943923672518462e-06,
+      "loss": 1.4045,
+      "step": 2109
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.4818181818181818,
+      "eval_f1": 0.4310770770506327,
+      "eval_loss": 1.394635796546936,
+      "eval_precision": 0.6376135558831151,
+      "eval_recall": 0.4418063268430915,
+      "eval_runtime": 5.6469,
+      "eval_samples_per_second": 77.919,
+      "eval_steps_per_second": 2.479,
+      "step": 2109
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 22.574962615966797,
+      "learning_rate": 9.771360421891483e-09,
+      "loss": 1.3992,
+      "step": 2220
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.48409090909090907,
+      "eval_f1": 0.43274338861391276,
+      "eval_loss": 1.3942500352859497,
+      "eval_precision": 0.6394552780212288,
+      "eval_recall": 0.44362450866127334,
+      "eval_runtime": 5.6595,
+      "eval_samples_per_second": 77.745,
+      "eval_steps_per_second": 2.474,
+      "step": 2220
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2220,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "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": 1.66631744858124e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout": 0.1,
+    "learning_rate": 2.1692420136599093e-05,
+    "optim": "adamw_torch"
+  }
+}

run-4/checkpoint-2220/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2eaecb8cb5c84ecec84ac208ebeb83d488f70ed7d854a82f441c39d1effd6a5
+size 5304

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ecc0710fe0575728761988d31e5efdffcb03d899093b12918b430b4bca7f18
+size 5240