Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ae846d2f187ec9718ac1ce58764f432f9176fcdf04dd707fbe779006b4b498d
+oid sha256:5485c9ad6d7a0e0145e9efaf078870b8d3216fb4e1b687ec2ab951c1dc27c384
 size 52772220

run-3/checkpoint-858/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-3/checkpoint-858/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5485c9ad6d7a0e0145e9efaf078870b8d3216fb4e1b687ec2ab951c1dc27c384
+size 52772220

run-3/checkpoint-858/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a881aa9904d0dc50b53097be3af62577619ba918c2726e9cc313b39c04eb99
+size 105559821

run-3/checkpoint-858/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:101d5cdb9f43e4eea15e6416826afd3918362bf071850bf66455d34c9af03b88
+size 14054

run-3/checkpoint-858/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba50a3ddacd570c9fa550e785128e397556f8f001ee056e4a5c0eca0a92425b7
+size 1064

run-3/checkpoint-858/special_tokens_map.json

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

run-3/checkpoint-858/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-3/checkpoint-858/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": 0.7652740828226702,
+  "best_model_checkpoint": "test-klue/ynat/run-3/checkpoint-858",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 858,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7057208740529263,
+      "eval_f1": 0.7142845530992349,
+      "eval_loss": 0.9159356355667114,
+      "eval_precision": 0.7358209847704137,
+      "eval_recall": 0.7133444688783136,
+      "eval_runtime": 20.4174,
+      "eval_samples_per_second": 446.042,
+      "eval_steps_per_second": 3.526,
+      "step": 286
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 3.536801066291284e-05,
+      "loss": 0.9808,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.740968485780169,
+      "eval_f1": 0.7305367323564163,
+      "eval_loss": 0.7676587104797363,
+      "eval_precision": 0.7005156297297628,
+      "eval_recall": 0.782295308770156,
+      "eval_runtime": 20.2382,
+      "eval_samples_per_second": 449.992,
+      "eval_steps_per_second": 3.558,
+      "step": 572
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7696277588668058,
+      "eval_f1": 0.7652740828226702,
+      "eval_loss": 0.6998419165611267,
+      "eval_precision": 0.7396963225825584,
+      "eval_recall": 0.7990267428994405,
+      "eval_runtime": 18.9919,
+      "eval_samples_per_second": 479.521,
+      "eval_steps_per_second": 3.791,
+      "step": 858
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 858,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 7769601142800.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.476467359994194e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 21
+  }
+}

run-3/checkpoint-858/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:287b4fef327ce95a1f0b49d4c324f403ad768a69004ab3f0d908236462701a2d
+size 4728