Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f96f85563f3fde390d8269aac1c929c62e068a8a95f52591af730edd3ee9dc6
+oid sha256:e6523cf5a7f71f0458d816d421835b58b455e55bb3b5d1c9476c52cd6ef0bba2
 size 442514444

run-0/checkpoint-4568/config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "klue/bert-base",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "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": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

run-0/checkpoint-4568/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6523cf5a7f71f0458d816d421835b58b455e55bb3b5d1c9476c52cd6ef0bba2
+size 442514444

run-0/checkpoint-4568/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc4bb6049d129f126254d3edab9507945c822209a9aed6ffc6308867801a491
+size 885149946

run-0/checkpoint-4568/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baa65a7fb13d355e9f2b0867495ca451524f1d24f4314ba6309f4eb06ebfcd40
+size 14244

run-0/checkpoint-4568/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54acb4e0358920a1b1dd0c31b4ef5d0bb3138999c467b1c30c6215ba9f1f5863
+size 1064

run-0/checkpoint-4568/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-0/checkpoint-4568/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": "[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": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-4568/trainer_state.json

@@ -0,0 +1,116 @@
+{
+  "best_metric": 0.8502932169961132,
+  "best_model_checkpoint": "test-klue/ynat-hps/run-0/checkpoint-4568",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4568,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.5575177105745416e-05,
+      "loss": 0.7213,
+      "step": 500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.4080438419973303e-05,
+      "loss": 0.5522,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.8362527412907268,
+      "eval_loss": 0.6280386447906494,
+      "eval_runtime": 12.2023,
+      "eval_samples_per_second": 746.334,
+      "eval_steps_per_second": 2.95,
+      "step": 1142
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.258569973420119e-05,
+      "loss": 0.4071,
+      "step": 1500
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.1090961048429078e-05,
+      "loss": 0.4276,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.8415413879849883,
+      "eval_loss": 0.7244753241539001,
+      "eval_runtime": 12.1177,
+      "eval_samples_per_second": 751.545,
+      "eval_steps_per_second": 2.971,
+      "step": 2284
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 9.596222362656965e-06,
+      "loss": 0.337,
+      "step": 2500
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 8.101483676884852e-06,
+      "loss": 0.2512,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.8449137319112024,
+      "eval_loss": 0.8435599207878113,
+      "eval_runtime": 12.1493,
+      "eval_samples_per_second": 749.593,
+      "eval_steps_per_second": 2.963,
+      "step": 3426
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 6.606744991112739e-06,
+      "loss": 0.184,
+      "step": 3500
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 5.112006305340626e-06,
+      "loss": 0.1224,
+      "step": 4000
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 3.6172676195685133e-06,
+      "loss": 0.114,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.8502932169961132,
+      "eval_loss": 0.9528796672821045,
+      "eval_runtime": 12.1904,
+      "eval_samples_per_second": 747.06,
+      "eval_steps_per_second": 2.953,
+      "step": 4568
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5710,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 171806898397200.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.706991579151753e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 2
+  }
+}

run-0/checkpoint-4568/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:185884df1614b0552795213155dd59621bd6ecbfd58643aadc676456a6f4c005
+size 4728