Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: indolem/indobert-base-uncased
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.24004296958446503
+
+f1: 0.912621359223301
+
+precision: 0.94
+
+recall: 0.8867924528301887
+
+auc: 0.9688286163522013
+
+accuracy: 0.9153605015673981

checkpoint-160/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "indolem/indobert-base-uncased",
+  "_num_labels": 2,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_ids": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Relevan",
+    "1": "Tidak Relevan"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Relevan": 0,
+    "Tidak Relevan": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31923
+}

checkpoint-160/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8abc02f49b2c3ad504aa6e5c05cce2946596205fb5707cfafc42c90e597f5164
+size 442262520

checkpoint-160/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e655d27ba82c3b4183c23df563d0ec4da1089694742e8775f11092ff3aa332eb
+size 884646138

checkpoint-160/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d340e0e0954c402b990f22cd5f9a8b683acafd696e9f7e54bba76d106ebb00
+size 14244

checkpoint-160/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dbdadc911e25d2854a46ed369aac3da762f40ea0ab90fb2acda60d72e451a38
+size 1064

checkpoint-160/trainer_state.json

@@ -0,0 +1,209 @@
+{
+  "best_metric": 0.24004296958446503,
+  "best_model_checkpoint": "relevancy-desk-1/checkpoint-160",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04375,
+      "grad_norm": 16.161113739013672,
+      "learning_rate": 5.208333333333334e-06,
+      "loss": 0.7405,
+      "step": 7
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 18.8027400970459,
+      "learning_rate": 1.25e-05,
+      "loss": 0.7231,
+      "step": 14
+    },
+    {
+      "epoch": 0.13125,
+      "grad_norm": 7.321622848510742,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.7016,
+      "step": 21
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 16.223827362060547,
+      "learning_rate": 2.604166666666667e-05,
+      "loss": 0.6902,
+      "step": 28
+    },
+    {
+      "epoch": 0.21875,
+      "grad_norm": 10.89142894744873,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6941,
+      "step": 35
+    },
+    {
+      "epoch": 0.2625,
+      "grad_norm": 11.153426170349121,
+      "learning_rate": 4.0625000000000005e-05,
+      "loss": 0.6313,
+      "step": 42
+    },
+    {
+      "epoch": 0.30625,
+      "grad_norm": 12.487936019897461,
+      "learning_rate": 4.6875e-05,
+      "loss": 0.5933,
+      "step": 49
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 21.75290298461914,
+      "learning_rate": 4.9537037037037035e-05,
+      "loss": 0.5932,
+      "step": 56
+    },
+    {
+      "epoch": 0.39375,
+      "grad_norm": 57.575801849365234,
+      "learning_rate": 4.8726851851851855e-05,
+      "loss": 0.5077,
+      "step": 63
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 23.81184196472168,
+      "learning_rate": 4.791666666666667e-05,
+      "loss": 0.4552,
+      "step": 70
+    },
+    {
+      "epoch": 0.48125,
+      "grad_norm": 19.651561737060547,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 0.8497,
+      "step": 77
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 45.1554069519043,
+      "learning_rate": 4.6412037037037034e-05,
+      "loss": 0.5609,
+      "step": 84
+    },
+    {
+      "epoch": 0.56875,
+      "grad_norm": 124.0260009765625,
+      "learning_rate": 4.5601851851851854e-05,
+      "loss": 0.4622,
+      "step": 91
+    },
+    {
+      "epoch": 0.6125,
+      "grad_norm": 8.57412338256836,
+      "learning_rate": 4.4791666666666673e-05,
+      "loss": 0.3109,
+      "step": 98
+    },
+    {
+      "epoch": 0.65625,
+      "grad_norm": 7.455972194671631,
+      "learning_rate": 4.3981481481481486e-05,
+      "loss": 0.3433,
+      "step": 105
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 23.886850357055664,
+      "learning_rate": 4.31712962962963e-05,
+      "loss": 0.3481,
+      "step": 112
+    },
+    {
+      "epoch": 0.74375,
+      "grad_norm": 15.515789985656738,
+      "learning_rate": 4.236111111111111e-05,
+      "loss": 0.333,
+      "step": 119
+    },
+    {
+      "epoch": 0.7875,
+      "grad_norm": 20.180509567260742,
+      "learning_rate": 4.1550925925925925e-05,
+      "loss": 0.3546,
+      "step": 126
+    },
+    {
+      "epoch": 0.83125,
+      "grad_norm": 39.38922882080078,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 0.1842,
+      "step": 133
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 50.90278244018555,
+      "learning_rate": 3.993055555555556e-05,
+      "loss": 0.2997,
+      "step": 140
+    },
+    {
+      "epoch": 0.91875,
+      "grad_norm": 56.43859100341797,
+      "learning_rate": 3.912037037037037e-05,
+      "loss": 0.4073,
+      "step": 147
+    },
+    {
+      "epoch": 0.9625,
+      "grad_norm": 29.69350814819336,
+      "learning_rate": 3.831018518518519e-05,
+      "loss": 0.2362,
+      "step": 154
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9153605015673981,
+      "eval_auc": 0.9688286163522013,
+      "eval_f1": 0.912621359223301,
+      "eval_loss": 0.24004296958446503,
+      "eval_precision": 0.94,
+      "eval_recall": 0.8867924528301887,
+      "eval_runtime": 0.6665,
+      "eval_samples_per_second": 478.602,
+      "eval_steps_per_second": 30.006,
+      "step": 160
+    }
+  ],
+  "logging_steps": 7,
+  "max_steps": 480,
+  "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": 83735093368320.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-160/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d7fe33abfc87c575e8b8804cbfa3093eed22b554904c0e1695e40196f9bde5
+size 5240

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "indolem/indobert-base-uncased",
+  "_num_labels": 2,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_ids": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Relevan",
+    "1": "Tidak Relevan"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Relevan": 0,
+    "Tidak Relevan": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31923
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8abc02f49b2c3ad504aa6e5c05cce2946596205fb5707cfafc42c90e597f5164
+size 442262520

runs/Aug03_17-14-23_r-apriandito-autotrain-gpu-4douwnbc-306cf-4x08t/events.out.tfevents.1722705264.r-apriandito-autotrain-gpu-4douwnbc-306cf-4x08t.83.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:203c83c4d1d429c174aa36a23728de5e5a1527ea80d561a4406b89df3728f236
-size 5116
+oid sha256:17aa6ef2c9bfa0482657ae3403e7e48e311fa98fc75bb2640eeb29d1c334b27b
+size 21303

runs/Aug03_17-14-23_r-apriandito-autotrain-gpu-4douwnbc-306cf-4x08t/events.out.tfevents.1722705325.r-apriandito-autotrain-gpu-4douwnbc-306cf-4x08t.83.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0357834158d2b66b7cc15c4b697ed0bb4a855923fce6aa799df79dcef2c3520
+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 +1,57 @@
+{
+  "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": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[SEP]",
+      "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,
+  "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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d7fe33abfc87c575e8b8804cbfa3093eed22b554904c0e1695e40196f9bde5
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "relevancy-desk-1/autotrain-data",
+    "model": "indolem/indobert-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": "relevancy-desk-1",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "apriandito",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}