Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36b7e4fc98acda9f90920138010d077334ebbed430ed326fe0b225e07bfe0f3a
+oid sha256:95c6b5c16a01995c4a176cacf2b2f180be394dc24a28dba58642bfa40a26cefc
 size 52772220

run-1/checkpoint-144/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-1/checkpoint-144/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95c6b5c16a01995c4a176cacf2b2f180be394dc24a28dba58642bfa40a26cefc
+size 52772220

run-1/checkpoint-144/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df776d54df7c249ae6943e2d22706261cdfb16f1ae0499e0cb0f2b287ab5feb5
+size 105559821

run-1/checkpoint-144/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d497dc5be2c1578e10f7f7839faaf259d290a7d1df105558ccf22d7e5d269be8
+size 13990

run-1/checkpoint-144/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21f8103881ef488e07a309054a922ed39b6dd8749565406cdc085ce30285ac3a
+size 1064

run-1/checkpoint-144/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-144/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-1/checkpoint-144/trainer_state.json

@@ -0,0 +1,74 @@
+{
+  "best_metric": 0.7997338685041598,
+  "best_model_checkpoint": "test-klue/ynat/run-1/checkpoint-144",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 144,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7029757329526738,
+      "eval_f1": 0.7260405944382302,
+      "eval_loss": 0.8381879925727844,
+      "eval_precision": 0.7229631912540809,
+      "eval_recall": 0.7649001321251355,
+      "eval_runtime": 23.3561,
+      "eval_samples_per_second": 389.92,
+      "eval_steps_per_second": 3.083,
+      "step": 36
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7735807620511694,
+      "eval_f1": 0.7735521742935774,
+      "eval_loss": 0.6680657267570496,
+      "eval_precision": 0.7454609971772899,
+      "eval_recall": 0.8148292509282873,
+      "eval_runtime": 18.9647,
+      "eval_samples_per_second": 480.207,
+      "eval_steps_per_second": 3.797,
+      "step": 72
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7890633578565939,
+      "eval_f1": 0.7889339303702111,
+      "eval_loss": 0.6286096572875977,
+      "eval_precision": 0.7655079819774946,
+      "eval_recall": 0.8242769336671684,
+      "eval_runtime": 17.2672,
+      "eval_samples_per_second": 527.418,
+      "eval_steps_per_second": 4.17,
+      "step": 108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8031184802898869,
+      "eval_f1": 0.7997338685041598,
+      "eval_loss": 0.5752761960029602,
+      "eval_precision": 0.7861545602008605,
+      "eval_recall": 0.8171411207462347,
+      "eval_runtime": 19.8875,
+      "eval_samples_per_second": 457.926,
+      "eval_steps_per_second": 3.62,
+      "step": 144
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 144,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.210676903396925e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 28
+  }
+}

run-1/checkpoint-144/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8439f2cfb18bdcd79bd0897337ef0ffccaff64712b363ad7a4c9eb11753e0749
+size 4728