Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3f8bc86473dc6e49e5578f4589f64cd37bb4dfca4e3d40dd3405de2a852912d
+oid sha256:de9d4e6af8c11cd29e69c392ec14d9364b5fc0b427d4a2da5ebbe57218e19cc2
 size 409103316

run-2/checkpoint-1066/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-2/checkpoint-1066/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:646bf64f2d7588bc518e6f45e4153810e63b161c8d62988b9688bcf154da9d40
+size 409103316

run-2/checkpoint-1066/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbcfcffbbed7e27fc89e35841a8260e7db4f5de1c56df37bea02732b92a433cf
+size 818327802

run-2/checkpoint-1066/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e93670da55318d823f1e4c03808b51663a5b6c2853342674abb539144107925
+size 14244

run-2/checkpoint-1066/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9447444aa7c89c55e6d4117866cbaeb3c3393fad8adc5cb2275d3443f1381bc0
+size 1064

run-2/checkpoint-1066/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-2/checkpoint-1066/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-2/checkpoint-1066/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.6080508828163147,
+  "best_model_checkpoint": "BERT-WMM/run-2/checkpoint-533",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1066,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.94,
+      "grad_norm": 9.333391189575195,
+      "learning_rate": 1.2018217372024236e-05,
+      "loss": 0.7056,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7427230046948357,
+      "eval_loss": 0.6080508828163147,
+      "eval_runtime": 1.9882,
+      "eval_samples_per_second": 1071.329,
+      "eval_steps_per_second": 67.398,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 10.452563285827637,
+      "learning_rate": 9.790971750818855e-06,
+      "loss": 0.4566,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7647887323943662,
+      "eval_loss": 0.6108278632164001,
+      "eval_runtime": 2.0426,
+      "eval_samples_per_second": 1042.799,
+      "eval_steps_per_second": 65.603,
+      "step": 1066
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3198,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 338261076519408.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4245462993229616e-05,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.002285356379677195
+  }
+}

run-2/checkpoint-1066/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a522d40064169dd451f5c63d95d053409f9056cc8f37d6ef08fd626cff2d294
+size 4856

run-2/checkpoint-1599/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-2/checkpoint-1599/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:423fd0a8c6263e8c2d7b12bb899ce6b42430747b90dea9c8dbaf7138c4959529
+size 409103316

run-2/checkpoint-1599/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa231502f99c5628f628a6bc8a1b2723ff93692bb148192c6f7c3f169afdd47c
+size 818327802

run-2/checkpoint-1599/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a0297d8a44379421fcc37b5cd89b37859cf20f999ea1e0c6d33126202fb0483
+size 14244

run-2/checkpoint-1599/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abc0f1b7e77e27c09ef04236a0848487a399bf089fa6c70bbf2124a69abd62a8
+size 1064

run-2/checkpoint-1599/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-2/checkpoint-1599/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-2/checkpoint-1599/trainer_state.json

@@ -0,0 +1,74 @@
+{
+  "best_metric": 0.6080508828163147,
+  "best_model_checkpoint": "BERT-WMM/run-2/checkpoint-533",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1599,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.94,
+      "grad_norm": 9.333391189575195,
+      "learning_rate": 1.2018217372024236e-05,
+      "loss": 0.7056,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7427230046948357,
+      "eval_loss": 0.6080508828163147,
+      "eval_runtime": 1.9882,
+      "eval_samples_per_second": 1071.329,
+      "eval_steps_per_second": 67.398,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 10.452563285827637,
+      "learning_rate": 9.790971750818855e-06,
+      "loss": 0.4566,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7647887323943662,
+      "eval_loss": 0.6108278632164001,
+      "eval_runtime": 2.0426,
+      "eval_samples_per_second": 1042.799,
+      "eval_steps_per_second": 65.603,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 15.208818435668945,
+      "learning_rate": 7.563726129613473e-06,
+      "loss": 0.2952,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7723004694835681,
+      "eval_loss": 0.7061524391174316,
+      "eval_runtime": 2.0864,
+      "eval_samples_per_second": 1020.91,
+      "eval_steps_per_second": 64.226,
+      "step": 1599
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3198,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 507646505902536.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4245462993229616e-05,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.002285356379677195
+  }
+}

run-2/checkpoint-1599/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a522d40064169dd451f5c63d95d053409f9056cc8f37d6ef08fd626cff2d294
+size 4856

run-2/checkpoint-2132/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-2/checkpoint-2132/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e04580019f1be160be56bfd94d6ed944f031434fc142d84476684b6e3d2d8df4
+size 409103316

run-2/checkpoint-2132/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a41f17960f4622d12a3631c1ccb112d7f696aae57d93caa2f76bcf5fca6520e7
+size 818327802

run-2/checkpoint-2132/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9212a4c80ce2e7f833fdf27e3a5305a7db427c39eec6b6799a8511d4e96931a
+size 14244

run-2/checkpoint-2132/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc21b66aa88fc6c8f9e92c05f7808b278ed1c3252bb9059a9e8e9730825265c
+size 1064

run-2/checkpoint-2132/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-2/checkpoint-2132/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-2/checkpoint-2132/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": 0.6080508828163147,
+  "best_model_checkpoint": "BERT-WMM/run-2/checkpoint-533",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2132,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.94,
+      "grad_norm": 9.333391189575195,
+      "learning_rate": 1.2018217372024236e-05,
+      "loss": 0.7056,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7427230046948357,
+      "eval_loss": 0.6080508828163147,
+      "eval_runtime": 1.9882,
+      "eval_samples_per_second": 1071.329,
+      "eval_steps_per_second": 67.398,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 10.452563285827637,
+      "learning_rate": 9.790971750818855e-06,
+      "loss": 0.4566,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7647887323943662,
+      "eval_loss": 0.6108278632164001,
+      "eval_runtime": 2.0426,
+      "eval_samples_per_second": 1042.799,
+      "eval_steps_per_second": 65.603,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 15.208818435668945,
+      "learning_rate": 7.563726129613473e-06,
+      "loss": 0.2952,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7723004694835681,
+      "eval_loss": 0.7061524391174316,
+      "eval_runtime": 2.0864,
+      "eval_samples_per_second": 1020.91,
+      "eval_steps_per_second": 64.226,
+      "step": 1599
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 71.34471893310547,
+      "learning_rate": 5.3364805084080925e-06,
+      "loss": 0.1924,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7746478873239436,
+      "eval_loss": 0.9748370051383972,
+      "eval_runtime": 1.9954,
+      "eval_samples_per_second": 1067.453,
+      "eval_steps_per_second": 67.154,
+      "step": 2132
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3198,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 676890100708920.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4245462993229616e-05,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.002285356379677195
+  }
+}

run-2/checkpoint-2132/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a522d40064169dd451f5c63d95d053409f9056cc8f37d6ef08fd626cff2d294
+size 4856

run-2/checkpoint-2665/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-2/checkpoint-2665/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3b3cce302106a5fc7115dc6e151116a600deecd48660d13d223ddd7314defa
+size 409103316

run-2/checkpoint-2665/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a5e2a63adb63082d75e800134a6683804d2d11a638ba71baab8fcdb50deafd1
+size 818327802

run-2/checkpoint-2665/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:277661c82c9726484f7bfc2d9b00236317d8d79e0d579345b033a66996ef18e2
+size 14244

run-2/checkpoint-2665/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:078c79dee1ef8bfeeb701582a1e7fe1db6f2d99250c9bb5b60d3b0e2720ae8e1
+size 1064

run-2/checkpoint-2665/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-2/checkpoint-2665/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-2/checkpoint-2665/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.6080508828163147,
+  "best_model_checkpoint": "BERT-WMM/run-2/checkpoint-533",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2665,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.94,
+      "grad_norm": 9.333391189575195,
+      "learning_rate": 1.2018217372024236e-05,
+      "loss": 0.7056,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7427230046948357,
+      "eval_loss": 0.6080508828163147,
+      "eval_runtime": 1.9882,
+      "eval_samples_per_second": 1071.329,
+      "eval_steps_per_second": 67.398,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 10.452563285827637,
+      "learning_rate": 9.790971750818855e-06,
+      "loss": 0.4566,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7647887323943662,
+      "eval_loss": 0.6108278632164001,
+      "eval_runtime": 2.0426,
+      "eval_samples_per_second": 1042.799,
+      "eval_steps_per_second": 65.603,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 15.208818435668945,
+      "learning_rate": 7.563726129613473e-06,
+      "loss": 0.2952,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7723004694835681,
+      "eval_loss": 0.7061524391174316,
+      "eval_runtime": 2.0864,
+      "eval_samples_per_second": 1020.91,
+      "eval_steps_per_second": 64.226,
+      "step": 1599
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 71.34471893310547,
+      "learning_rate": 5.3364805084080925e-06,
+      "loss": 0.1924,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7746478873239436,
+      "eval_loss": 0.9748370051383972,
+      "eval_runtime": 1.9954,
+      "eval_samples_per_second": 1067.453,
+      "eval_steps_per_second": 67.154,
+      "step": 2132
+    },
+    {
+      "epoch": 4.69,
+      "grad_norm": 0.35381996631622314,
+      "learning_rate": 3.1092348872027118e-06,
+      "loss": 0.1118,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7718309859154929,
+      "eval_loss": 1.1978907585144043,
+      "eval_runtime": 2.0749,
+      "eval_samples_per_second": 1026.553,
+      "eval_steps_per_second": 64.581,
+      "step": 2665
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3198,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 846139862236032.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4245462993229616e-05,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.002285356379677195
+  }
+}

run-2/checkpoint-2665/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a522d40064169dd451f5c63d95d053409f9056cc8f37d6ef08fd626cff2d294
+size 4856

run-2/checkpoint-3198/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-2/checkpoint-3198/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26fb9c2a232d942264061a85eabef420b9ecd7722f3e0417c6ef6c303d54a20e
+size 409103316

run-2/checkpoint-3198/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3876e303cd8a9111cb138776be9161ed76c9ff5eaf1640f7554d3d92ea459e6b
+size 818327802

run-2/checkpoint-3198/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22bf02b30277d45e8a05d66b020d674535c6c4e043dedd2496b55e484a23858d
+size 14244

run-2/checkpoint-3198/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a362f162b993e5ed5f386f34c90fd59ccaf3d8b3d4d8f4f1e62d26637fb40755
+size 1064

run-2/checkpoint-3198/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-2/checkpoint-3198/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-2/checkpoint-3198/trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": 0.6080508828163147,
+  "best_model_checkpoint": "BERT-WMM/run-2/checkpoint-533",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 3198,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.94,
+      "grad_norm": 9.333391189575195,
+      "learning_rate": 1.2018217372024236e-05,
+      "loss": 0.7056,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7427230046948357,
+      "eval_loss": 0.6080508828163147,
+      "eval_runtime": 1.9882,
+      "eval_samples_per_second": 1071.329,
+      "eval_steps_per_second": 67.398,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 10.452563285827637,
+      "learning_rate": 9.790971750818855e-06,
+      "loss": 0.4566,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7647887323943662,
+      "eval_loss": 0.6108278632164001,
+      "eval_runtime": 2.0426,
+      "eval_samples_per_second": 1042.799,
+      "eval_steps_per_second": 65.603,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 15.208818435668945,
+      "learning_rate": 7.563726129613473e-06,
+      "loss": 0.2952,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7723004694835681,
+      "eval_loss": 0.7061524391174316,
+      "eval_runtime": 2.0864,
+      "eval_samples_per_second": 1020.91,
+      "eval_steps_per_second": 64.226,
+      "step": 1599
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 71.34471893310547,
+      "learning_rate": 5.3364805084080925e-06,
+      "loss": 0.1924,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7746478873239436,
+      "eval_loss": 0.9748370051383972,
+      "eval_runtime": 1.9954,
+      "eval_samples_per_second": 1067.453,
+      "eval_steps_per_second": 67.154,
+      "step": 2132
+    },
+    {
+      "epoch": 4.69,
+      "grad_norm": 0.35381996631622314,
+      "learning_rate": 3.1092348872027118e-06,
+      "loss": 0.1118,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7718309859154929,
+      "eval_loss": 1.1978907585144043,
+      "eval_runtime": 2.0749,
+      "eval_samples_per_second": 1026.553,
+      "eval_steps_per_second": 64.581,
+      "step": 2665
+    },
+    {
+      "epoch": 5.63,
+      "grad_norm": 0.07311483472585678,
+      "learning_rate": 8.819892659973308e-07,
+      "loss": 0.0745,
+      "step": 3000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7704225352112676,
+      "eval_loss": 1.2845892906188965,
+      "eval_runtime": 2.0235,
+      "eval_samples_per_second": 1052.612,
+      "eval_steps_per_second": 66.221,
+      "step": 3198
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3198,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 1014949731017880.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4245462993229616e-05,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.002285356379677195
+  }
+}

run-2/checkpoint-3198/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a522d40064169dd451f5c63d95d053409f9056cc8f37d6ef08fd626cff2d294
+size 4856