Upload folder using huggingface_hub

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "cl-tohoku/bert-base-japanese-whole-word-masking",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7
+  },
+  "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": "multi_label_classification",
+  "tokenizer_class": "BertJapaneseTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:116f003f832ef84febb581b079a7d1757460f3370cc85d56c72fbafc33a285c7
+size 442517520

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab1ab3d561307654c400503c862c7e41a6a36fd1ae37926c3a0e437b7300f52
+size 885156090

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19f6d3f23e6561cb9a4532984efd506c31da0160a96a778f92c03b4307b58adb
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfbccebeeff5d49f34e4f578ad7a01db80617e774deed447b8ec8ff3c13157bd
+size 1064

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 +1,61 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "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
+    }
+  },
+  "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": null,
+  "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 +1,151 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 200,
+  "global_step": 2138,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09354536950420954,
+      "eval_accuracy": 0.5728155339805825,
+      "eval_loss": 0.26913607120513916,
+      "eval_runtime": 16.2852,
+      "eval_samples_per_second": 69.572,
+      "eval_steps_per_second": 8.72,
+      "step": 200
+    },
+    {
+      "epoch": 0.18709073900841908,
+      "eval_accuracy": 0.6425419240953222,
+      "eval_loss": 0.25252005457878113,
+      "eval_runtime": 19.5477,
+      "eval_samples_per_second": 57.961,
+      "eval_steps_per_second": 7.264,
+      "step": 400
+    },
+    {
+      "epoch": 0.23386342376052385,
+      "grad_norm": 1.209536075592041,
+      "learning_rate": 3.8306828811973814e-05,
+      "loss": 0.3012,
+      "step": 500
+    },
+    {
+      "epoch": 0.2806361085126286,
+      "eval_accuracy": 0.6857899382171226,
+      "eval_loss": 0.237541064620018,
+      "eval_runtime": 18.6594,
+      "eval_samples_per_second": 60.72,
+      "eval_steps_per_second": 7.61,
+      "step": 600
+    },
+    {
+      "epoch": 0.37418147801683815,
+      "eval_accuracy": 0.7007943512797882,
+      "eval_loss": 0.2300291657447815,
+      "eval_runtime": 17.2054,
+      "eval_samples_per_second": 65.852,
+      "eval_steps_per_second": 8.253,
+      "step": 800
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 1.29645836353302,
+      "learning_rate": 2.6613657623947615e-05,
+      "loss": 0.2615,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "eval_accuracy": 0.7193292144748455,
+      "eval_loss": 0.2208750993013382,
+      "eval_runtime": 16.5003,
+      "eval_samples_per_second": 68.665,
+      "eval_steps_per_second": 8.606,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5612722170252572,
+      "eval_accuracy": 0.7131509267431597,
+      "eval_loss": 0.21556398272514343,
+      "eval_runtime": 16.4369,
+      "eval_samples_per_second": 68.93,
+      "eval_steps_per_second": 8.639,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6548175865294668,
+      "eval_accuracy": 0.7422771403353927,
+      "eval_loss": 0.21151377260684967,
+      "eval_runtime": 16.5068,
+      "eval_samples_per_second": 68.638,
+      "eval_steps_per_second": 8.603,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7015902712815716,
+      "grad_norm": 1.2882506847381592,
+      "learning_rate": 1.492048643592142e-05,
+      "loss": 0.2496,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7483629560336763,
+      "eval_accuracy": 0.7502206531332745,
+      "eval_loss": 0.2063572257757187,
+      "eval_runtime": 18.4271,
+      "eval_samples_per_second": 61.486,
+      "eval_steps_per_second": 7.706,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8419083255378859,
+      "eval_accuracy": 0.7546337157987644,
+      "eval_loss": 0.2039937973022461,
+      "eval_runtime": 17.4715,
+      "eval_samples_per_second": 64.848,
+      "eval_steps_per_second": 8.128,
+      "step": 1800
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 1.526292324066162,
+      "learning_rate": 3.2273152478952295e-06,
+      "loss": 0.2373,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "eval_accuracy": 0.7405119152691968,
+      "eval_loss": 0.20458175241947174,
+      "eval_runtime": 17.1202,
+      "eval_samples_per_second": 66.179,
+      "eval_steps_per_second": 8.294,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4500493926531072.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d720fb19cb26c7e16da2e5a996677b9b6e6d1b0d8ca25d9a9c69814848b37d3b
+size 5176