Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:357fab3c69616ae4165c13b5e9b873054c56d95bfa1b859d9259b9d0ffc1092c
+oid sha256:c335f0d1b7b4570edf9167d1e74331925b690140d9a29633fd105d6a64976cc2
 size 52772220

run-0/checkpoint-429/config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "kykim/albert-kor-base",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "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,
+  "inner_group_num": 1,
+  "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": 256,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.1",
+  "type_vocab_size": 2,
+  "vocab_size": 42000
+}

run-0/checkpoint-429/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c335f0d1b7b4570edf9167d1e74331925b690140d9a29633fd105d6a64976cc2
+size 52772220

run-0/checkpoint-429/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a9e5e63c0dc446a9e8af8869f881339bd8d68f2abeec1fe5690d26e77fbf161
+size 105559821

run-0/checkpoint-429/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e901c9bc070fff22b2c0a90792639c2037b97c721a29a9dbdf0144bdfac548
+size 14054

run-0/checkpoint-429/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6ffad9935ac3d763d2275029f614ea3b4d7d84b8ade3f1d39d29ecbe87a8121
+size 1064

run-0/checkpoint-429/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-429/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": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-429/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": 0.8017785824493558,
+  "best_model_checkpoint": "test-klue/ynat/run-0/checkpoint-429",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 429,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7130778522016031,
+      "eval_f1": 0.7216637589070471,
+      "eval_loss": 0.8219035267829895,
+      "eval_precision": 0.6988998691169065,
+      "eval_recall": 0.7983424589771914,
+      "eval_runtime": 18.6199,
+      "eval_samples_per_second": 489.101,
+      "eval_steps_per_second": 3.867,
+      "step": 143
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7694081475787855,
+      "eval_f1": 0.763100045705191,
+      "eval_loss": 0.6672208309173584,
+      "eval_precision": 0.7528849355070684,
+      "eval_recall": 0.7957912629407226,
+      "eval_runtime": 23.2725,
+      "eval_samples_per_second": 391.321,
+      "eval_steps_per_second": 3.094,
+      "step": 286
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8103656527945536,
+      "eval_f1": 0.8017785824493558,
+      "eval_loss": 0.5746214985847473,
+      "eval_precision": 0.7919124644854595,
+      "eval_recall": 0.8127142807005272,
+      "eval_runtime": 15.6285,
+      "eval_samples_per_second": 582.718,
+      "eval_steps_per_second": 4.607,
+      "step": 429
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 429,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.169673645274978e-05,
+    "warmup_steps": 0.6,
+    "weight_decay": 0.015222201256475635
+  }
+}

run-0/checkpoint-429/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:476a245d2ca35111c33f3c518f6042908b6839662da097e130c6bc629afc07fb
+size 4728