Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58c816109f599405e710163b5c6e4a35a540644dd43051c351004ea8dbba0c22
+oid sha256:1036b0e130873abffbdebd8d5d578898371e33ac172389ec55bfbdc9aa024367
 size 437977104

run-0/checkpoint-1250/config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "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": "Ideologi",
+    "1": "Politik",
+    "2": "Sumber Daya Alam",
+    "3": "Sosial Budaya",
+    "4": "Demografi",
+    "5": "Geografi",
+    "6": "Ekonomi",
+    "7": "Pertahanan dan Keamanan"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Demografi": 4,
+    "Ekonomi": 6,
+    "Geografi": 5,
+    "Ideologi": 0,
+    "Pertahanan dan Keamanan": 7,
+    "Politik": 1,
+    "Sosial Budaya": 3,
+    "Sumber Daya Alam": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-1250/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1036b0e130873abffbdebd8d5d578898371e33ac172389ec55bfbdc9aa024367
+size 437977104

run-0/checkpoint-1250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e02977fee8c9a14824a4edfdb65ec786751efff1edced2df0cc7c7478f0fb2db
+size 876075258

run-0/checkpoint-1250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d469c4e9e4895ad5e67ec676deb78499c563451c903341bf616cb9958db90b
+size 14244

run-0/checkpoint-1250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f914720d416c69554e3b949218fb408e071df64476b3e35955929757df072d3d
+size 1064

run-0/checkpoint-1250/special_tokens_map.json

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

run-0/checkpoint-1250/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": true,
+  "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]"
+}

run-0/checkpoint-1250/trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_metric": 0.5731388926506042,
+  "best_model_checkpoint": "satriadata/run-0/checkpoint-1250",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1250,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.520844900048434,
+      "eval_loss": 1.3270556926727295,
+      "eval_runtime": 15.2159,
+      "eval_samples_per_second": 65.721,
+      "eval_steps_per_second": 4.14,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.648948669433594,
+      "learning_rate": 5.086297130534548e-05,
+      "loss": 1.4798,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.7148278885110101,
+      "eval_loss": 0.8877580165863037,
+      "eval_runtime": 15.0754,
+      "eval_samples_per_second": 66.333,
+      "eval_steps_per_second": 4.179,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.8147606395143462,
+      "eval_loss": 0.6009902358055115,
+      "eval_runtime": 15.0542,
+      "eval_samples_per_second": 66.427,
+      "eval_steps_per_second": 4.185,
+      "step": 750
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 12.858877182006836,
+      "learning_rate": 1.6954323768448494e-05,
+      "loss": 0.4927,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.8354816202915758,
+      "eval_loss": 0.5939759612083435,
+      "eval_runtime": 15.0559,
+      "eval_samples_per_second": 66.419,
+      "eval_steps_per_second": 4.184,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.849511756667626,
+      "eval_loss": 0.5731388926506042,
+      "eval_runtime": 15.0566,
+      "eval_samples_per_second": 66.416,
+      "eval_steps_per_second": 4.184,
+      "step": 1250
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4210003673088000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "gradient_accumulation_steps": 1,
+    "learning_rate": 6.781729507379398e-05,
+    "optimizer": "adamw",
+    "per_device_train_batch_size": 16,
+    "warmup_ratio": 0.2,
+    "weight_decay": 0.01
+  }
+}

run-0/checkpoint-1250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4abaae79bebab84d41f2cc797ca65537defd0aa0551a2db6488e1d56e27f56e5
+size 5112

runs/Jun18_14-34-24_8081f73fda98/events.out.tfevents.1718721268.8081f73fda98.3906.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d51cb7670cdd71b106f1ca6c324ce49c130348ef06d71d9f3a1931d45823def
-size 6914
+oid sha256:0761f675cee7ef1ccd79d6cfea2a9f39447913b50f94397bf7de5fa9ec275072
+size 7585