Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e590568e759b254d8d68e6b275bf92d5a77fc1a3153443d7ccf006d8aef4902a
+oid sha256:b3cbdfac140fdffbf6eee776475fe9201ff75b6a9a8d8a4c835033ec1e46f8a3
 size 437977104

run-1/checkpoint-250/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-1/checkpoint-250/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3cbdfac140fdffbf6eee776475fe9201ff75b6a9a8d8a4c835033ec1e46f8a3
+size 437977104

run-1/checkpoint-250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c69e199b16ae9f85ea96e32e3af97c2b3c764c95eb1c2ab15d16df36906017f7
+size 876075258

run-1/checkpoint-250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a63e39490720f9e5149f22ea1c9305a9eb986e42d172cfe5b25c344828e2a4c
+size 14244

run-1/checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76dd6c433ac448f704da2d7ed46a689a347bff77d439102faf66692bcadb189e
+size 1064

run-1/checkpoint-250/special_tokens_map.json

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

run-1/checkpoint-250/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-1/checkpoint-250/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.7203186750411987,
+  "best_model_checkpoint": "satriadata/run-1/checkpoint-250",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.996,
+      "eval_f1": 0.34139582972404187,
+      "eval_loss": 1.5640060901641846,
+      "eval_runtime": 15.1373,
+      "eval_samples_per_second": 66.062,
+      "eval_steps_per_second": 4.162,
+      "step": 83
+    },
+    {
+      "epoch": 1.992,
+      "eval_f1": 0.6408845370670369,
+      "eval_loss": 1.0041351318359375,
+      "eval_runtime": 15.1161,
+      "eval_samples_per_second": 66.155,
+      "eval_steps_per_second": 4.168,
+      "step": 166
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.7652394340421227,
+      "eval_loss": 0.7203186750411987,
+      "eval_runtime": 15.1504,
+      "eval_samples_per_second": 66.005,
+      "eval_steps_per_second": 4.158,
+      "step": 250
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 415,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "gradient_accumulation_steps": 3,
+    "learning_rate": 8.484535826382634e-05,
+    "optimizer": "sgd",
+    "per_device_train_batch_size": 16,
+    "warmup_ratio": 0.3,
+    "weight_decay": 0.01
+  }
+}

run-1/checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:108227d95b08c5e3d95c9d4f4c5b66777995656dac6ed7edd37b99b02be46fed
+size 5112

runs/Jun18_14-34-24_8081f73fda98/events.out.tfevents.1718722224.8081f73fda98.3906.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:978bbdbbcf94f4c48357a9272a364af3d0bc085baa29cf333891fef30fc09ee7
-size 5852
+oid sha256:575fd30f4636f95292917b8b1bb747de6af2dd6d9a556b877c32b8dd1eee15ef
+size 6169