Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:513f3e552e64976184f65148662ba5bd0a5a386a843b2678c6b9bf430d8067c4
+oid sha256:5669a9e347b456a864f46fd26cdb0be1392fe9128429eb17a111096a4855b114
 size 409103316

run-0/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-0/checkpoint-1066/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7755e65b6162f8636a9241f6923420b193ca30b3a5dca7418b51a2bcc380f86d
+size 409103316

run-0/checkpoint-1066/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63d963cf3cbd7391c62eb322b08595cc0bd5b707c4533beeae4a064153966de0
+size 818327802

run-0/checkpoint-1066/rng_state.pth

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

run-0/checkpoint-1066/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbf55a5bf069992fe6cfbfae4a696b1cd7d93685a9743ad6546c3030830f638
+size 1064

run-0/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-0/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-0/checkpoint-1066/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.6369415521621704,
+  "best_model_checkpoint": "BERT-WMM/run-0/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": 11.681629180908203,
+      "learning_rate": 2.5842410540171958e-05,
+      "loss": 0.7181,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7525821596244131,
+      "eval_loss": 0.6369415521621704,
+      "eval_runtime": 1.9836,
+      "eval_samples_per_second": 1073.792,
+      "eval_steps_per_second": 67.553,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 6.492458820343018,
+      "learning_rate": 2.1053231418568556e-05,
+      "loss": 0.4571,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7497652582159624,
+      "eval_loss": 0.6769182682037354,
+      "eval_runtime": 2.0259,
+      "eval_samples_per_second": 1051.385,
+      "eval_steps_per_second": 66.144,
+      "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": 3.063158966177536e-05,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 2.6426532465921284e-05
+  }
+}

run-0/checkpoint-1066/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48c24530a27c9d1e90a961cc0645745786b44285899342b0769165200ee8a2b1
+size 4856

run-0/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-0/checkpoint-1599/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e29b5f49710d0d17c6aee07e8cc1bc4edaa86a3c66b73d52d1ef1136d10f23
+size 409103316

run-0/checkpoint-1599/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b04eae6a685408364150ca5d02a35737876cace088d1b38561f5da6ab19d7a30
+size 818327802

run-0/checkpoint-1599/rng_state.pth

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

run-0/checkpoint-1599/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a7f77912cd35b35f45f50fd2c3bbb7b15cbe8d92a9601be01ae387622324a8
+size 1064

run-0/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-0/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-0/checkpoint-1599/trainer_state.json

@@ -0,0 +1,74 @@
+{
+  "best_metric": 0.6369415521621704,
+  "best_model_checkpoint": "BERT-WMM/run-0/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": 11.681629180908203,
+      "learning_rate": 2.5842410540171958e-05,
+      "loss": 0.7181,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7525821596244131,
+      "eval_loss": 0.6369415521621704,
+      "eval_runtime": 1.9836,
+      "eval_samples_per_second": 1073.792,
+      "eval_steps_per_second": 67.553,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 6.492458820343018,
+      "learning_rate": 2.1053231418568556e-05,
+      "loss": 0.4571,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7497652582159624,
+      "eval_loss": 0.6769182682037354,
+      "eval_runtime": 2.0259,
+      "eval_samples_per_second": 1051.385,
+      "eval_steps_per_second": 66.144,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 13.743987083435059,
+      "learning_rate": 1.626405229696515e-05,
+      "loss": 0.2889,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7596244131455399,
+      "eval_loss": 0.8726277351379395,
+      "eval_runtime": 2.0636,
+      "eval_samples_per_second": 1032.174,
+      "eval_steps_per_second": 64.935,
+      "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": 3.063158966177536e-05,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 2.6426532465921284e-05
+  }
+}

run-0/checkpoint-1599/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48c24530a27c9d1e90a961cc0645745786b44285899342b0769165200ee8a2b1
+size 4856

run-0/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-0/checkpoint-2132/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9279f69393a8e46b14e7123d3a8ee47397fdee79745b2de35fe04c017cb26f
+size 409103316

run-0/checkpoint-2132/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc6238eedd54c4d633fe717b8feb6d58816a48ead9efdbb67187c24c0e4dbfd6
+size 818327802

run-0/checkpoint-2132/rng_state.pth

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

run-0/checkpoint-2132/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:500bde988124b2d60b4de5a2dc0252924803e8cf00c78786716576aab7a696e0
+size 1064

run-0/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-0/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-0/checkpoint-2132/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": 0.6369415521621704,
+  "best_model_checkpoint": "BERT-WMM/run-0/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": 11.681629180908203,
+      "learning_rate": 2.5842410540171958e-05,
+      "loss": 0.7181,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7525821596244131,
+      "eval_loss": 0.6369415521621704,
+      "eval_runtime": 1.9836,
+      "eval_samples_per_second": 1073.792,
+      "eval_steps_per_second": 67.553,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 6.492458820343018,
+      "learning_rate": 2.1053231418568556e-05,
+      "loss": 0.4571,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7497652582159624,
+      "eval_loss": 0.6769182682037354,
+      "eval_runtime": 2.0259,
+      "eval_samples_per_second": 1051.385,
+      "eval_steps_per_second": 66.144,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 13.743987083435059,
+      "learning_rate": 1.626405229696515e-05,
+      "loss": 0.2889,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7596244131455399,
+      "eval_loss": 0.8726277351379395,
+      "eval_runtime": 2.0636,
+      "eval_samples_per_second": 1032.174,
+      "eval_steps_per_second": 64.935,
+      "step": 1599
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 31.317466735839844,
+      "learning_rate": 1.147487317536175e-05,
+      "loss": 0.1815,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7572769953051643,
+      "eval_loss": 1.311642050743103,
+      "eval_runtime": 2.081,
+      "eval_samples_per_second": 1023.549,
+      "eval_steps_per_second": 64.392,
+      "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": 3.063158966177536e-05,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 2.6426532465921284e-05
+  }
+}

run-0/checkpoint-2132/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48c24530a27c9d1e90a961cc0645745786b44285899342b0769165200ee8a2b1
+size 4856

run-0/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-0/checkpoint-2665/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7da5cff29fa27aada8dfa6d678eea4c6f60d4d60f17642f989ce89dd34f757c
+size 409103316

run-0/checkpoint-2665/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d3a689128acf808762df7a3e08d8fc4dc686b6bba654695b0adf95fdb31184
+size 818327802

run-0/checkpoint-2665/rng_state.pth

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

run-0/checkpoint-2665/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7a79124861e7453a45dcfd5e8716f0b9cc4a0e961601bc3ef48e9884cc8df9
+size 1064

run-0/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-0/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-0/checkpoint-2665/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.6369415521621704,
+  "best_model_checkpoint": "BERT-WMM/run-0/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": 11.681629180908203,
+      "learning_rate": 2.5842410540171958e-05,
+      "loss": 0.7181,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7525821596244131,
+      "eval_loss": 0.6369415521621704,
+      "eval_runtime": 1.9836,
+      "eval_samples_per_second": 1073.792,
+      "eval_steps_per_second": 67.553,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 6.492458820343018,
+      "learning_rate": 2.1053231418568556e-05,
+      "loss": 0.4571,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7497652582159624,
+      "eval_loss": 0.6769182682037354,
+      "eval_runtime": 2.0259,
+      "eval_samples_per_second": 1051.385,
+      "eval_steps_per_second": 66.144,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 13.743987083435059,
+      "learning_rate": 1.626405229696515e-05,
+      "loss": 0.2889,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7596244131455399,
+      "eval_loss": 0.8726277351379395,
+      "eval_runtime": 2.0636,
+      "eval_samples_per_second": 1032.174,
+      "eval_steps_per_second": 64.935,
+      "step": 1599
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 31.317466735839844,
+      "learning_rate": 1.147487317536175e-05,
+      "loss": 0.1815,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7572769953051643,
+      "eval_loss": 1.311642050743103,
+      "eval_runtime": 2.081,
+      "eval_samples_per_second": 1023.549,
+      "eval_steps_per_second": 64.392,
+      "step": 2132
+    },
+    {
+      "epoch": 4.69,
+      "grad_norm": 0.05295910686254501,
+      "learning_rate": 6.685694053758349e-06,
+      "loss": 0.1073,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7610328638497652,
+      "eval_loss": 1.4908134937286377,
+      "eval_runtime": 2.0562,
+      "eval_samples_per_second": 1035.88,
+      "eval_steps_per_second": 65.168,
+      "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": 3.063158966177536e-05,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 2.6426532465921284e-05
+  }
+}

run-0/checkpoint-2665/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48c24530a27c9d1e90a961cc0645745786b44285899342b0769165200ee8a2b1
+size 4856

run-0/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-0/checkpoint-3198/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1a12716375b855a6e80bf87c969b99e6b8e0fcc209ea581692dd6bba5ce4bd5
+size 409103316

run-0/checkpoint-3198/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f9f9979f170da366b678421fcc0e7f8b23c817926b3b614ea7f5c45bd0f41a
+size 818327802

run-0/checkpoint-3198/rng_state.pth

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

run-0/checkpoint-3198/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b0ae7009afc3087434a15b2496b4ac47bc555753b034670a0538647bab095b
+size 1064

run-0/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-0/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-0/checkpoint-3198/trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": 0.6369415521621704,
+  "best_model_checkpoint": "BERT-WMM/run-0/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": 11.681629180908203,
+      "learning_rate": 2.5842410540171958e-05,
+      "loss": 0.7181,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7525821596244131,
+      "eval_loss": 0.6369415521621704,
+      "eval_runtime": 1.9836,
+      "eval_samples_per_second": 1073.792,
+      "eval_steps_per_second": 67.553,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 6.492458820343018,
+      "learning_rate": 2.1053231418568556e-05,
+      "loss": 0.4571,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7497652582159624,
+      "eval_loss": 0.6769182682037354,
+      "eval_runtime": 2.0259,
+      "eval_samples_per_second": 1051.385,
+      "eval_steps_per_second": 66.144,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 13.743987083435059,
+      "learning_rate": 1.626405229696515e-05,
+      "loss": 0.2889,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7596244131455399,
+      "eval_loss": 0.8726277351379395,
+      "eval_runtime": 2.0636,
+      "eval_samples_per_second": 1032.174,
+      "eval_steps_per_second": 64.935,
+      "step": 1599
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 31.317466735839844,
+      "learning_rate": 1.147487317536175e-05,
+      "loss": 0.1815,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7572769953051643,
+      "eval_loss": 1.311642050743103,
+      "eval_runtime": 2.081,
+      "eval_samples_per_second": 1023.549,
+      "eval_steps_per_second": 64.392,
+      "step": 2132
+    },
+    {
+      "epoch": 4.69,
+      "grad_norm": 0.05295910686254501,
+      "learning_rate": 6.685694053758349e-06,
+      "loss": 0.1073,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7610328638497652,
+      "eval_loss": 1.4908134937286377,
+      "eval_runtime": 2.0562,
+      "eval_samples_per_second": 1035.88,
+      "eval_steps_per_second": 65.168,
+      "step": 2665
+    },
+    {
+      "epoch": 5.63,
+      "grad_norm": 0.06595510989427567,
+      "learning_rate": 1.896514932154947e-06,
+      "loss": 0.045,
+      "step": 3000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7591549295774648,
+      "eval_loss": 1.5977472066879272,
+      "eval_runtime": 2.0716,
+      "eval_samples_per_second": 1028.204,
+      "eval_steps_per_second": 64.685,
+      "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": 3.063158966177536e-05,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 2.6426532465921284e-05
+  }
+}

run-0/checkpoint-3198/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48c24530a27c9d1e90a961cc0645745786b44285899342b0769165200ee8a2b1
+size 4856