ckpt 3045 second model

config.json

@@ -0,0 +1,94 @@
+{
+  "_name_or_path": "klue/roberta-large",
+  "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": 1024,
+  "id2label": {
+    "0": "no_relation",
+    "1": "org:top_members/employees",
+    "2": "org:members",
+    "3": "org:product",
+    "4": "per:title",
+    "5": "org:alternate_names",
+    "6": "per:employee_of",
+    "7": "org:place_of_headquarters",
+    "8": "per:product",
+    "9": "org:number_of_employees/members",
+    "10": "per:children",
+    "11": "per:place_of_residence",
+    "12": "per:alternate_names",
+    "13": "per:other_family",
+    "14": "per:colleagues",
+    "15": "per:origin",
+    "16": "per:siblings",
+    "17": "per:spouse",
+    "18": "org:founded",
+    "19": "org:political/religious_affiliation",
+    "20": "org:member_of",
+    "21": "per:parents",
+    "22": "org:dissolved",
+    "23": "per:schools_attended",
+    "24": "per:date_of_death",
+    "25": "per:date_of_birth",
+    "26": "per:place_of_birth",
+    "27": "per:place_of_death",
+    "28": "org:founded_by",
+    "29": "per:religion"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "no_relation": 0,
+    "org:alternate_names": 5,
+    "org:dissolved": 22,
+    "org:founded": 18,
+    "org:founded_by": 28,
+    "org:member_of": 20,
+    "org:members": 2,
+    "org:number_of_employees/members": 9,
+    "org:place_of_headquarters": 7,
+    "org:political/religious_affiliation": 19,
+    "org:product": 3,
+    "org:top_members/employees": 1,
+    "per:alternate_names": 12,
+    "per:children": 10,
+    "per:colleagues": 14,
+    "per:date_of_birth": 25,
+    "per:date_of_death": 24,
+    "per:employee_of": 6,
+    "per:origin": 15,
+    "per:other_family": 13,
+    "per:parents": 21,
+    "per:place_of_birth": 26,
+    "per:place_of_death": 27,
+    "per:place_of_residence": 11,
+    "per:product": 8,
+    "per:religion": 29,
+    "per:schools_attended": 23,
+    "per:siblings": 16,
+    "per:spouse": 17,
+    "per:title": 4
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32004
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:764b3cc2c5aa077a07d9360d33326d35290db2a6d5f55ecc95c7427946de2ef9
+size 2693758493

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86120460a7f591e7a20078182a6a0744df37fee53db591d55f2127f7b58456c3
+size 1346929005

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a96fb85137275e672ea5d2094d1bae87433c5af7e7c546fb068350232a2bd7b1
+size 14503

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eccc082304cdb1b781a00d1171288ffa36d40ca690860809f81bcac4e20adae
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e553aa5fa51ec1952575ddea35537c8bb77156c52c8bceb39b8c524e28fb18b
+size 623

trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 3045,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.4532019704433497e-05,
+      "loss": 1.6412,
+      "step": 500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.522167487684729e-05,
+      "loss": 0.7311,
+      "step": 1000
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.9064039408866997e-05,
+      "loss": 0.5043,
+      "step": 1500
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.2918719211822661e-05,
+      "loss": 0.4708,
+      "step": 2000
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 6.7610837438423645e-06,
+      "loss": 0.2924,
+      "step": 2500
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 6.03448275862069e-07,
+      "loss": 0.2632,
+      "step": 3000
+    }
+  ],
+  "max_steps": 3045,
+  "num_train_epochs": 3,
+  "total_flos": 2.303221952809243e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c1f6c94ed8e11dc43a347869cd0365a29db82fb1e485737d390bca1b93cb67
+size 2863