Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a99842767b4825888ae72c25473ac4a6c645db5024cf2febb1d9eaf04aef0239
+oid sha256:0f92be76bebee09b8c7e6f895bb9889ee28341f5d48e4cc52cfd4a2fea7ed967
 size 52772220

run-2/checkpoint-715/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-2/checkpoint-715/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f92be76bebee09b8c7e6f895bb9889ee28341f5d48e4cc52cfd4a2fea7ed967
+size 52772220

run-2/checkpoint-715/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de11555ec173ea8ad459fe7a83c58078c96e01447d50be46117c8a0c03c508f1
+size 105559821

run-2/checkpoint-715/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d6de7157a7c2e61603d526bcb8e417836150701c1aa75ab8ce1dfab34835053
+size 13990

run-2/checkpoint-715/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f10f8cb4a7e15533bf0dd905980367cb40ad354422ae39c2f17edad38aafe0c0
+size 1064

run-2/checkpoint-715/special_tokens_map.json

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

run-2/checkpoint-715/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-2/checkpoint-715/trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_metric": 0.791127304270381,
+  "best_model_checkpoint": "test-klue/ynat/run-2/checkpoint-715",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 715,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7035247611727243,
+      "eval_f1": 0.6938799976841935,
+      "eval_loss": 0.8926264047622681,
+      "eval_precision": 0.6688239815221149,
+      "eval_recall": 0.7620565166942291,
+      "eval_runtime": 18.6832,
+      "eval_samples_per_second": 487.443,
+      "eval_steps_per_second": 3.854,
+      "step": 143
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.755902053365543,
+      "eval_f1": 0.7536895626419333,
+      "eval_loss": 0.7279911637306213,
+      "eval_precision": 0.7340941474653776,
+      "eval_recall": 0.7939069222006351,
+      "eval_runtime": 17.4159,
+      "eval_samples_per_second": 522.912,
+      "eval_steps_per_second": 4.134,
+      "step": 286
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7767651257274624,
+      "eval_f1": 0.7771467127148758,
+      "eval_loss": 0.6603606343269348,
+      "eval_precision": 0.759213360027576,
+      "eval_recall": 0.8070797728859608,
+      "eval_runtime": 19.2366,
+      "eval_samples_per_second": 473.42,
+      "eval_steps_per_second": 3.743,
+      "step": 429
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 4.602084255402649e-06,
+      "loss": 0.6698,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7829142417920281,
+      "eval_f1": 0.781298573051462,
+      "eval_loss": 0.6532090306282043,
+      "eval_precision": 0.7553680307563156,
+      "eval_recall": 0.8167451711250023,
+      "eval_runtime": 19.083,
+      "eval_samples_per_second": 477.232,
+      "eval_steps_per_second": 3.773,
+      "step": 572
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7964203360052706,
+      "eval_f1": 0.791127304270381,
+      "eval_loss": 0.6175519227981567,
+      "eval_precision": 0.7744163690108637,
+      "eval_recall": 0.8125045179978068,
+      "eval_runtime": 18.6355,
+      "eval_samples_per_second": 488.691,
+      "eval_steps_per_second": 3.864,
+      "step": 715
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 715,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 16378290816000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.5304605779594857e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 35
+  }
+}

run-2/checkpoint-715/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc2d7691e050a10d0f183318c4f4d3acfe833d36cdf02525ba7257bbd5ec2ec
+size 4728