Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07cb66408e84749abcb73a31aed63d6592983c68fcaf326ff9fa389496230d2e
+oid sha256:c639803864668b00e1fb9129c2f13d6b653c444bcfd0e96b0cd8f093e038f0ef
 size 442505820

run-4/checkpoint-346/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "klue/roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

run-4/checkpoint-346/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c639803864668b00e1fb9129c2f13d6b653c444bcfd0e96b0cd8f093e038f0ef
+size 442505820

run-4/checkpoint-346/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44d9b045663d7f371a96700edbe3a06d92a7b4660dd1bea00d934c51e2121393
+size 885131514

run-4/checkpoint-346/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c63f257a5b3bcad721bc5bf3eb7de36d0539eccfe8a69a53b1cfcc24e811997
+size 14244

run-4/checkpoint-346/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b9729b30039f17489d4701cb6804d23b25b93102379d714611208724a66de3c
+size 1064

run-4/checkpoint-346/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-4/checkpoint-346/tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "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
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-4/checkpoint-346/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.6349053963006231,
+  "best_model_checkpoint": "test-klue/ynat/run-4/checkpoint-346",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 346,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.6349053963006231,
+      "eval_loss": 0.8050844669342041,
+      "eval_runtime": 9.4523,
+      "eval_samples_per_second": 250.626,
+      "eval_steps_per_second": 2.01,
+      "step": 346
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1384,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.402778145515359e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 12
+  }
+}

run-4/checkpoint-346/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c1f7acf9dfb60e3287c48b224e7f5c73404535f43b5b6b6065999408ced52a
+size 4728

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca42cd1860a77f1891a7e2e57b0da97d27de86e1595fa73d5b8296b68537abb3
+oid sha256:46c1f7acf9dfb60e3287c48b224e7f5c73404535f43b5b6b6065999408ced52a
 size 4728