Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6115a480a3556deabc06ba3a4a9d328a4f5a7290a47014ca45b7455a400e6d93
+oid sha256:e68abf3d631fbb4906ee054df81e1193e2655201640c808c9162781d865bdfb7
 size 409103316

run-6/checkpoint-134/config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "hfl/chinese-bert-wwm-ext",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE",
+    "2": "NEUTRAL"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NEGATIVE": 0,
+    "NEUTRAL": 2,
+    "POSITIVE": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

run-6/checkpoint-134/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b651dab3a8678a4d9b5545123c1d060726d783aa28c09e90e1dad4ecf3386eae
+size 409103316

run-6/checkpoint-134/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bdf27fb37fed3acc6881cc922902993a520a9fdd7b2a25e559655cacfb0dbd8
+size 818327802

run-6/checkpoint-134/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4942a00faeddfc94e42d2a294bdfa76898722e11695841daac4e4e6ccf109842
+size 14244

run-6/checkpoint-134/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07df6db8cd831883dd666fee5812b0f3a8445023ec615d7d1d929ee0a9963558
+size 1064

run-6/checkpoint-134/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-6/checkpoint-134/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-6/checkpoint-134/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.6478816270828247,
+  "best_model_checkpoint": "BERT-WMM/run-6/checkpoint-134",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 134,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7352112676056338,
+      "eval_loss": 0.6478816270828247,
+      "eval_runtime": 2.0455,
+      "eval_samples_per_second": 1041.294,
+      "eval_steps_per_second": 65.509,
+      "step": 134
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 536,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9530733406603648e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "weight_decay": 0.01257257791736148
+  }
+}

run-6/checkpoint-134/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4215a0d171c998e861cecce9e6a8128f9e991e45dd727f00231bb96a25c0a48c
+size 4856

run-6/checkpoint-268/config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "hfl/chinese-bert-wwm-ext",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE",
+    "2": "NEUTRAL"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NEGATIVE": 0,
+    "NEUTRAL": 2,
+    "POSITIVE": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

run-6/checkpoint-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6d574a36fcfe395623be261483d8968db3d9eaa30cee53ddb279851d0135516
+size 409103316

run-6/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc886334f8e18961cbbd38a99594f8afb231f0a1e9282fe9af97c6d987850b95
+size 818327802

run-6/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3710a75654d913cd9587a7637c761de20056b7c11c92135a182c6da49fe818d9
+size 14244

run-6/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b7aa6928f83b336353ae7c751862ff7a17666a5e495e411175cbb1afb04245
+size 1064

run-6/checkpoint-268/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-6/checkpoint-268/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-6/checkpoint-268/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.598778486251831,
+  "best_model_checkpoint": "BERT-WMM/run-6/checkpoint-268",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 268,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7352112676056338,
+      "eval_loss": 0.6478816270828247,
+      "eval_runtime": 2.0455,
+      "eval_samples_per_second": 1041.294,
+      "eval_steps_per_second": 65.509,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7568075117370892,
+      "eval_loss": 0.598778486251831,
+      "eval_runtime": 2.5526,
+      "eval_samples_per_second": 834.457,
+      "eval_steps_per_second": 52.496,
+      "step": 268
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 536,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9530733406603648e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "weight_decay": 0.01257257791736148
+  }
+}

run-6/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4215a0d171c998e861cecce9e6a8128f9e991e45dd727f00231bb96a25c0a48c
+size 4856

run-6/checkpoint-402/config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "hfl/chinese-bert-wwm-ext",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE",
+    "2": "NEUTRAL"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NEGATIVE": 0,
+    "NEUTRAL": 2,
+    "POSITIVE": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

run-6/checkpoint-402/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cdcf0a7e94a8c4cdf817a058f24e6558b7867504f40a79ce4c7f5759d74e04b
+size 409103316

run-6/checkpoint-402/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f3726694e443d3f2771d1f3e90a399fa28fe3ac2b75c7c149f7babc86498e1
+size 818327802

run-6/checkpoint-402/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fdcda6ce4f391ebd88ccae6650ee532b64877e7fcf08ae7e7f256cfe508f341
+size 14244

run-6/checkpoint-402/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2200d787e718198abd7bd2f30e5f54fd16beebcae6f6b9e3e538b3867896610f
+size 1064

run-6/checkpoint-402/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-6/checkpoint-402/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-6/checkpoint-402/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.598778486251831,
+  "best_model_checkpoint": "BERT-WMM/run-6/checkpoint-268",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 402,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7352112676056338,
+      "eval_loss": 0.6478816270828247,
+      "eval_runtime": 2.0455,
+      "eval_samples_per_second": 1041.294,
+      "eval_steps_per_second": 65.509,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7568075117370892,
+      "eval_loss": 0.598778486251831,
+      "eval_runtime": 2.5526,
+      "eval_samples_per_second": 834.457,
+      "eval_steps_per_second": 52.496,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7582159624413145,
+      "eval_loss": 0.6211540102958679,
+      "eval_runtime": 2.1567,
+      "eval_samples_per_second": 987.64,
+      "eval_steps_per_second": 62.133,
+      "step": 402
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 536,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9530733406603648e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "weight_decay": 0.01257257791736148
+  }
+}

run-6/checkpoint-402/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4215a0d171c998e861cecce9e6a8128f9e991e45dd727f00231bb96a25c0a48c
+size 4856

run-6/checkpoint-536/config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "hfl/chinese-bert-wwm-ext",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE",
+    "2": "NEUTRAL"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NEGATIVE": 0,
+    "NEUTRAL": 2,
+    "POSITIVE": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

run-6/checkpoint-536/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e68abf3d631fbb4906ee054df81e1193e2655201640c808c9162781d865bdfb7
+size 409103316

run-6/checkpoint-536/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a984887c7aa7694dad309b277dc6f85af427cc5f90c35f28c1aa5b783384d078
+size 818327802

run-6/checkpoint-536/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68fc68a5a2897f6cb39e3e2ec857ff1fc3fd2c96caa5464a844d2408e486abe7
+size 14244

run-6/checkpoint-536/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174c507a518c9b343a60bb5387ba7d192944a4fc65e9eba7bb37e8980fe3e0c8
+size 1064

run-6/checkpoint-536/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-6/checkpoint-536/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-6/checkpoint-536/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": 0.598778486251831,
+  "best_model_checkpoint": "BERT-WMM/run-6/checkpoint-268",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 536,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7352112676056338,
+      "eval_loss": 0.6478816270828247,
+      "eval_runtime": 2.0455,
+      "eval_samples_per_second": 1041.294,
+      "eval_steps_per_second": 65.509,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7568075117370892,
+      "eval_loss": 0.598778486251831,
+      "eval_runtime": 2.5526,
+      "eval_samples_per_second": 834.457,
+      "eval_steps_per_second": 52.496,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7582159624413145,
+      "eval_loss": 0.6211540102958679,
+      "eval_runtime": 2.1567,
+      "eval_samples_per_second": 987.64,
+      "eval_steps_per_second": 62.133,
+      "step": 402
+    },
+    {
+      "epoch": 3.73,
+      "grad_norm": 9.620325088500977,
+      "learning_rate": 1.3117656765629316e-06,
+      "loss": 0.5199,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7633802816901408,
+      "eval_loss": 0.6602327227592468,
+      "eval_runtime": 2.0894,
+      "eval_samples_per_second": 1019.414,
+      "eval_steps_per_second": 64.132,
+      "step": 536
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 536,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 732330975627216.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9530733406603648e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "weight_decay": 0.01257257791736148
+  }
+}

run-6/checkpoint-536/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4215a0d171c998e861cecce9e6a8128f9e991e45dd727f00231bb96a25c0a48c
+size 4856

runs/Apr18_08-35-19_da5e8340a418/events.out.tfevents.1713430033.da5e8340a418.15241.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942adf5316bc0f35a7c6b412160b85f61141d72f9f1a951219a92a668aa0b436
+size 6766

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d11893aa7531a00a798ff2c74d6b44e7248ec089d85163d6ee787b4e26991cd
+oid sha256:4215a0d171c998e861cecce9e6a8128f9e991e45dd727f00231bb96a25c0a48c
 size 4856