Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:345ba3b3e3059be5005dafcd41ea927043dd992fd62503e4ce9da39781a36aed
+oid sha256:0b52062f3037426970464c61dfcde2b194f8899c5d100d225d4b24967e773db6
 size 52772220

run-4/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-4/checkpoint-429/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b52062f3037426970464c61dfcde2b194f8899c5d100d225d4b24967e773db6
+size 52772220

run-4/checkpoint-429/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2d3cb4bc67c2bf2dd4ee34d8414856ff9948775e1bb2657db58c1df12429ef8
+size 105559821

run-4/checkpoint-429/rng_state.pth

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

run-4/checkpoint-429/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92fc24ae7d3264eba89182e1bcff36161f7aa0c4d706cee33f98e014ef097c51
+size 1064

run-4/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-4/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-4/checkpoint-429/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.7905352528130531,
+  "best_model_checkpoint": "test-klue/ynat/run-4/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": 0.7115405731854617,
+      "eval_f1": 0.7217522534644514,
+      "eval_loss": 0.8200628757476807,
+      "eval_precision": 0.7080392402733132,
+      "eval_recall": 0.7808268271389747,
+      "eval_runtime": 16.0025,
+      "eval_samples_per_second": 569.099,
+      "eval_steps_per_second": 4.499,
+      "step": 143
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7560118590095531,
+      "eval_f1": 0.7546528982928414,
+      "eval_loss": 0.7018700838088989,
+      "eval_precision": 0.7345285866654627,
+      "eval_recall": 0.7964413469510949,
+      "eval_runtime": 15.5287,
+      "eval_samples_per_second": 586.461,
+      "eval_steps_per_second": 4.637,
+      "step": 286
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7976281980893818,
+      "eval_f1": 0.7905352528130531,
+      "eval_loss": 0.6035104990005493,
+      "eval_precision": 0.7765781217099276,
+      "eval_recall": 0.8076675637884033,
+      "eval_runtime": 15.8094,
+      "eval_samples_per_second": 576.051,
+      "eval_steps_per_second": 4.554,
+      "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": 9.063996284126319e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 17
+  }
+}

run-4/checkpoint-429/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d3d832cf0b37c281bf57e260c91691e1670006fa5c5eed3e4e3de355449c98f
+size 4728