Upload 7 files

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "cl-tohoku/bert-base-japanese-v2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "BertJapaneseTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.2",
+  "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 sha256:5bd2b662f0889b90241a1d46c28e36efb7ec0312dd5ace2a98ffc905406abd75
+size 444907637

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 +1,22 @@
+{
+  "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": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "subword_tokenizer_type": "wordpiece",
+  "sudachi_kwargs": null,
+  "tokenizer_class": "BertJapaneseTokenizer",
+  "tokenizer_file": null,
+  "unk_token": "[UNK]",
+  "word_tokenizer_type": "mecab"
+}

trainer_state.json

@@ -0,0 +1,212 @@
+{
+  "best_metric": 0.8479087452471483,
+  "best_model_checkpoint": "./output/model_1\\run-0\\checkpoint-740",
+  "epoch": 14.0,
+  "global_step": 2072,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8060836501901141,
+      "eval_f1": 0.8000895647160824,
+      "eval_loss": 0.46571293473243713,
+      "eval_precision": 0.8103755012570384,
+      "eval_recall": 0.8060836501901141,
+      "eval_runtime": 0.224,
+      "eval_samples_per_second": 1174.099,
+      "eval_steps_per_second": 75.892,
+      "step": 148
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8174904942965779,
+      "eval_f1": 0.8174904942965779,
+      "eval_loss": 0.49181994795799255,
+      "eval_precision": 0.8174904942965779,
+      "eval_recall": 0.8174904942965779,
+      "eval_runtime": 0.2151,
+      "eval_samples_per_second": 1222.875,
+      "eval_steps_per_second": 79.045,
+      "step": 296
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8174904942965779,
+      "eval_f1": 0.8168592417586474,
+      "eval_loss": 0.4677908420562744,
+      "eval_precision": 0.8166185862354719,
+      "eval_recall": 0.8174904942965779,
+      "eval_runtime": 0.212,
+      "eval_samples_per_second": 1240.567,
+      "eval_steps_per_second": 80.189,
+      "step": 444
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 5.031969358167588e-06,
+      "loss": 0.4058,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8403041825095057,
+      "eval_f1": 0.8397518365388166,
+      "eval_loss": 0.4895302653312683,
+      "eval_precision": 0.8396023801788713,
+      "eval_recall": 0.8403041825095057,
+      "eval_runtime": 0.2159,
+      "eval_samples_per_second": 1218.057,
+      "eval_steps_per_second": 78.734,
+      "step": 592
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8479087452471483,
+      "eval_f1": 0.8470891084157254,
+      "eval_loss": 0.5246260762214661,
+      "eval_precision": 0.8471907238947951,
+      "eval_recall": 0.8479087452471483,
+      "eval_runtime": 0.212,
+      "eval_samples_per_second": 1240.567,
+      "eval_steps_per_second": 80.189,
+      "step": 740
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.844106463878327,
+      "eval_f1": 0.842419911092538,
+      "eval_loss": 0.5946373343467712,
+      "eval_precision": 0.8438668765907662,
+      "eval_recall": 0.844106463878327,
+      "eval_runtime": 0.2206,
+      "eval_samples_per_second": 1192.052,
+      "eval_steps_per_second": 77.053,
+      "step": 888
+    },
+    {
+      "epoch": 6.76,
+      "learning_rate": 3.4314701984450724e-06,
+      "loss": 0.2291,
+      "step": 1000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.844106463878327,
+      "eval_f1": 0.8437098422789988,
+      "eval_loss": 0.650194525718689,
+      "eval_precision": 0.8435403587786577,
+      "eval_recall": 0.844106463878327,
+      "eval_runtime": 0.2125,
+      "eval_samples_per_second": 1237.62,
+      "eval_steps_per_second": 79.998,
+      "step": 1036
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8403041825095057,
+      "eval_f1": 0.8391134423962042,
+      "eval_loss": 0.6312099099159241,
+      "eval_precision": 0.8395542107279025,
+      "eval_recall": 0.8403041825095057,
+      "eval_runtime": 0.2165,
+      "eval_samples_per_second": 1214.746,
+      "eval_steps_per_second": 78.52,
+      "step": 1184
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8365019011406845,
+      "eval_f1": 0.8351053157727012,
+      "eval_loss": 0.7456679344177246,
+      "eval_precision": 0.8357697627558571,
+      "eval_recall": 0.8365019011406845,
+      "eval_runtime": 0.2137,
+      "eval_samples_per_second": 1230.687,
+      "eval_steps_per_second": 79.55,
+      "step": 1332
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8403041825095057,
+      "eval_f1": 0.838761109426392,
+      "eval_loss": 0.7921389937400818,
+      "eval_precision": 0.8397848232749173,
+      "eval_recall": 0.8403041825095057,
+      "eval_runtime": 0.2155,
+      "eval_samples_per_second": 1220.389,
+      "eval_steps_per_second": 78.884,
+      "step": 1480
+    },
+    {
+      "epoch": 10.14,
+      "learning_rate": 1.8309710387225575e-06,
+      "loss": 0.1587,
+      "step": 1500
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.8250950570342205,
+      "eval_f1": 0.8256084971375828,
+      "eval_loss": 0.8698846697807312,
+      "eval_precision": 0.8265094169095286,
+      "eval_recall": 0.8250950570342205,
+      "eval_runtime": 0.219,
+      "eval_samples_per_second": 1200.921,
+      "eval_steps_per_second": 77.626,
+      "step": 1628
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.8326996197718631,
+      "eval_f1": 0.831083067018125,
+      "eval_loss": 0.9105260372161865,
+      "eval_precision": 0.832006346665142,
+      "eval_recall": 0.8326996197718631,
+      "eval_runtime": 0.2169,
+      "eval_samples_per_second": 1212.315,
+      "eval_steps_per_second": 78.363,
+      "step": 1776
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.8365019011406845,
+      "eval_f1": 0.8354546196277604,
+      "eval_loss": 0.9163150787353516,
+      "eval_precision": 0.8356459763303871,
+      "eval_recall": 0.8365019011406845,
+      "eval_runtime": 0.2143,
+      "eval_samples_per_second": 1227.36,
+      "eval_steps_per_second": 79.335,
+      "step": 1924
+    },
+    {
+      "epoch": 13.51,
+      "learning_rate": 2.304718790000422e-07,
+      "loss": 0.1181,
+      "step": 2000
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.8326996197718631,
+      "eval_f1": 0.8314521777484043,
+      "eval_loss": 0.931361734867096,
+      "eval_precision": 0.8318193002498804,
+      "eval_recall": 0.8326996197718631,
+      "eval_runtime": 0.2146,
+      "eval_samples_per_second": 1225.552,
+      "eval_steps_per_second": 79.218,
+      "step": 2072
+    }
+  ],
+  "max_steps": 2072,
+  "num_train_epochs": 14,
+  "total_flos": 131021083348800.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.632468517890103e-06,
+    "num_train_epochs": 14,
+    "weight_decay": 0.0028145972556210797
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d8aa7ea9c93e486fe46398005f2b3f7e584730bbf91b05efd7a7f04aa165394
+size 3515