add: kobigbird base finetuned klue mrc

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "kobigbird-bert-base",
+  "architectures": [
+    "BigBirdForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_type": "block_sparse",
+  "block_size": 64,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 4096,
+  "model_type": "big_bird",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_random_blocks": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "rescale_embeddings": false,
+  "sep_token_id": 3,
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "type_vocab_size": 2,
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 32500
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d946f814a6bea1629b6a0d62d29b2441fb4d2c438bb03edc02f986ff854d9400
+size 943229005

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed7187bf84878cf112b7bfaff9723b53860b0817e5880a919a1e3cfa76dac4a
+size 471656101

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be0e07c11052fb02f83565b65528591acdb94f191f708a1a79e562178ea28455
+size 21579

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0765fe20bbb4aa8153e862dc2d95a7cd2e02d95c74927d339bc5e0169433a39
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:762ef643c14e421cf1936823cf0ad0e6f603c1ab5e29c83e49d59fbc4f98a9da
+size 623

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "eos_token": "</s>",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "mask_token": "[MASK]",
+  "model_max_length": 4096,
+  "name_or_path": "kobigbird-bert-base",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "kobigbird-bert-base/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.989090909090909,
+  "global_step": 340,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.99,
+      "learning_rate": 4e-05,
+      "loss": 2.8431,
+      "step": 68
+    },
+    {
+      "epoch": 0.99,
+      "eval_runtime": 196.4833,
+      "eval_samples_per_second": 29.728,
+      "eval_steps_per_second": 0.468,
+      "step": 68
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 3e-05,
+      "loss": 1.1753,
+      "step": 136
+    },
+    {
+      "epoch": 1.99,
+      "eval_runtime": 196.6946,
+      "eval_samples_per_second": 29.696,
+      "eval_steps_per_second": 0.468,
+      "step": 136
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 2e-05,
+      "loss": 0.7899,
+      "step": 204
+    },
+    {
+      "epoch": 2.99,
+      "eval_runtime": 197.3831,
+      "eval_samples_per_second": 29.592,
+      "eval_steps_per_second": 0.466,
+      "step": 204
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 1e-05,
+      "loss": 0.5618,
+      "step": 272
+    },
+    {
+      "epoch": 3.99,
+      "eval_runtime": 200.0691,
+      "eval_samples_per_second": 29.195,
+      "eval_steps_per_second": 0.46,
+      "step": 272
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 0.0,
+      "loss": 0.4302,
+      "step": 340
+    },
+    {
+      "epoch": 4.99,
+      "eval_runtime": 198.1115,
+      "eval_samples_per_second": 29.483,
+      "eval_steps_per_second": 0.464,
+      "step": 340
+    }
+  ],
+  "max_steps": 340,
+  "num_train_epochs": 5,
+  "total_flos": 1.9333975281854054e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b31c3098880f0ec9d7e564dfd2163c3bc02c5249e67874278f9010bf45a3938b
+size 3247