Upload 9 files

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "cl-tohoku/bert-large-japanese-v2",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32768
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db09277b42bf87b3b7b2b88e2450882e4639c87ba55b81a331aa881b159a10fc
+size 1349910133

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e20557c355e3290481e6b6d9dceb69cdf09d0e572c912153010ddae7e235969
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b7e60817c9ffc76417d2ce6b62f56cc326e0925739e2949d055c5a5a47aac3b
+size 627

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "do_subword_tokenize": true,
+  "do_word_tokenize": true,
+  "jumanpp_kwargs": null,
+  "mask_token": "[MASK]",
+  "mecab_kwargs": {
+    "mecab_dic": "unidic_lite"
+  },
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "subword_tokenizer_type": "wordpiece",
+  "sudachi_kwargs": null,
+  "tokenizer_class": "BertJapaneseTokenizer",
+  "unk_token": "[UNK]",
+  "word_tokenizer_type": "mecab"
+}

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 3354,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.105545617173524e-06,
+      "loss": 0.6881,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 8.211091234347049e-06,
+      "loss": 0.4955,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8793565683646113,
+      "eval_f1": 0.8793090346786706,
+      "eval_loss": 0.3616451621055603,
+      "eval_precision": 0.8805569789010309,
+      "eval_recall": 0.8793565683646113,
+      "eval_runtime": 59.9562,
+      "eval_samples_per_second": 18.664,
+      "eval_steps_per_second": 2.335,
+      "step": 1118
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 7.316636851520573e-06,
+      "loss": 0.2764,
+      "step": 1500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 6.422182468694097e-06,
+      "loss": 0.2205,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8766756032171582,
+      "eval_f1": 0.8764664011056418,
+      "eval_loss": 0.4942081570625305,
+      "eval_precision": 0.8772358831944725,
+      "eval_recall": 0.8766756032171582,
+      "eval_runtime": 59.8387,
+      "eval_samples_per_second": 18.7,
+      "eval_steps_per_second": 2.34,
+      "step": 2236
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 5.527728085867621e-06,
+      "loss": 0.1486,
+      "step": 2500
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 4.633273703041145e-06,
+      "loss": 0.0856,
+      "step": 3000
+    }
+  ],
+  "max_steps": 5590,
+  "num_train_epochs": 5,
+  "total_flos": 1.561969933062336e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e2760d0cf9217185fa7d124d2a5676e2933887633add1dda2825d3486458b8
+size 3963