Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08b2691a9b0ec7dacd6a5cfd13c6c8581e7f46d1fd925b4cb84e4fd88c97a627
+oid sha256:a63d61dd1dbef133a4a54ab1f2f18adfbb803f4221d5942217c0b43ae7213cff
 size 409103316

run-15/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-15/checkpoint-1066/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:746867eae69fb83aa68c6163b89e0b87ef7f3b118cbe30b06eb0185ebf3976be
+size 409103316

run-15/checkpoint-1066/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b629125fe587fa0b975104ac357d18484e54e64e57c9d6e99550aee0467ad9b6
+size 818327802

run-15/checkpoint-1066/rng_state.pth

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

run-15/checkpoint-1066/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10df953eb1db8fca3e516f2843ba88d9a2681c9b41b7a7ecc94d5a2be8a735a6
+size 1064

run-15/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-15/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-15/checkpoint-1066/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.6102677583694458,
+  "best_model_checkpoint": "BERT-WMM/run-15/checkpoint-1066",
+  "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": 8.692239761352539,
+      "learning_rate": 1.3731493717417162e-05,
+      "loss": 0.7076,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7530516431924883,
+      "eval_loss": 0.6211019158363342,
+      "eval_runtime": 1.9926,
+      "eval_samples_per_second": 1068.944,
+      "eval_steps_per_second": 67.248,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 11.677574157714844,
+      "learning_rate": 1.0560248055196108e-05,
+      "loss": 0.4535,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7680751173708921,
+      "eval_loss": 0.6102677583694458,
+      "eval_runtime": 2.2362,
+      "eval_samples_per_second": 952.498,
+      "eval_steps_per_second": 59.922,
+      "step": 1066
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2665,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 348929503378848.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6902739379638215e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.019154977870537472
+  }
+}

run-15/checkpoint-1066/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47578a34c3d9ba21ee4e0ec6e9de13d7e68fe8c675092633f464cbfc506864f8
+size 4856

run-15/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-15/checkpoint-1599/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0e503f244389e83898d3b9889494d01f6b2ae2f04061ce061be1aa6184d200
+size 409103316

run-15/checkpoint-1599/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d712910f4b7e3b73e0c069951ba805c4df3161d6ad6405cd76e5d49edc5a1ba
+size 818327802

run-15/checkpoint-1599/rng_state.pth

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

run-15/checkpoint-1599/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91fac61783411f9fa7b9246bf650fa38d12b534bfcebd623035b4d5245e7829d
+size 1064

run-15/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-15/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-15/checkpoint-1599/trainer_state.json

@@ -0,0 +1,74 @@
+{
+  "best_metric": 0.6102677583694458,
+  "best_model_checkpoint": "BERT-WMM/run-15/checkpoint-1066",
+  "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": 8.692239761352539,
+      "learning_rate": 1.3731493717417162e-05,
+      "loss": 0.7076,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7530516431924883,
+      "eval_loss": 0.6211019158363342,
+      "eval_runtime": 1.9926,
+      "eval_samples_per_second": 1068.944,
+      "eval_steps_per_second": 67.248,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 11.677574157714844,
+      "learning_rate": 1.0560248055196108e-05,
+      "loss": 0.4535,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7680751173708921,
+      "eval_loss": 0.6102677583694458,
+      "eval_runtime": 2.2362,
+      "eval_samples_per_second": 952.498,
+      "eval_steps_per_second": 59.922,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 33.26390838623047,
+      "learning_rate": 7.3890023929750545e-06,
+      "loss": 0.2958,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7751173708920188,
+      "eval_loss": 0.7481958866119385,
+      "eval_runtime": 2.135,
+      "eval_samples_per_second": 997.66,
+      "eval_steps_per_second": 62.764,
+      "step": 1599
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2665,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 518314932761976.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6902739379638215e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.019154977870537472
+  }
+}

run-15/checkpoint-1599/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47578a34c3d9ba21ee4e0ec6e9de13d7e68fe8c675092633f464cbfc506864f8
+size 4856

run-15/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-15/checkpoint-2132/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f497a2fbd92b6f952a26cfd1a0d7d6d00ea3a2401f90d179a16c35b8e7e4e2
+size 409103316

run-15/checkpoint-2132/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194efa14696884f36ad581471940c11f9d261132cb9821d2006f7d84b87611cb
+size 818327802

run-15/checkpoint-2132/rng_state.pth

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

run-15/checkpoint-2132/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b687d46ca313c0198bce3aa79f4897fb4b9c9f87e22a239623a5929be8d803e4
+size 1064

run-15/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-15/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-15/checkpoint-2132/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": 0.6102677583694458,
+  "best_model_checkpoint": "BERT-WMM/run-15/checkpoint-1066",
+  "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": 8.692239761352539,
+      "learning_rate": 1.3731493717417162e-05,
+      "loss": 0.7076,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7530516431924883,
+      "eval_loss": 0.6211019158363342,
+      "eval_runtime": 1.9926,
+      "eval_samples_per_second": 1068.944,
+      "eval_steps_per_second": 67.248,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 11.677574157714844,
+      "learning_rate": 1.0560248055196108e-05,
+      "loss": 0.4535,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7680751173708921,
+      "eval_loss": 0.6102677583694458,
+      "eval_runtime": 2.2362,
+      "eval_samples_per_second": 952.498,
+      "eval_steps_per_second": 59.922,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 33.26390838623047,
+      "learning_rate": 7.3890023929750545e-06,
+      "loss": 0.2958,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7751173708920188,
+      "eval_loss": 0.7481958866119385,
+      "eval_runtime": 2.135,
+      "eval_samples_per_second": 997.66,
+      "eval_steps_per_second": 62.764,
+      "step": 1599
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 14.7713041305542,
+      "learning_rate": 4.217756730754001e-06,
+      "loss": 0.1874,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7708920187793428,
+      "eval_loss": 1.0311119556427002,
+      "eval_runtime": 2.0623,
+      "eval_samples_per_second": 1032.824,
+      "eval_steps_per_second": 64.976,
+      "step": 2132
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2665,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 687558527568360.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6902739379638215e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.019154977870537472
+  }
+}

run-15/checkpoint-2132/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47578a34c3d9ba21ee4e0ec6e9de13d7e68fe8c675092633f464cbfc506864f8
+size 4856

run-15/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-15/checkpoint-2665/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e322892e49d679cfbf59c1cc860f9a44d9f51a054f5fc4777263dd39b03b5421
+size 409103316

run-15/checkpoint-2665/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d6de371f4720de6ca984a22322315d85209706889ba919ee72eacf5f4ffc12
+size 818327802

run-15/checkpoint-2665/rng_state.pth

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

run-15/checkpoint-2665/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6895f2cea5a125b2775353e5b5ca69fe3e246069754b2b141a858d0582f79b35
+size 1064

run-15/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-15/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-15/checkpoint-2665/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.6102677583694458,
+  "best_model_checkpoint": "BERT-WMM/run-15/checkpoint-1066",
+  "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": 8.692239761352539,
+      "learning_rate": 1.3731493717417162e-05,
+      "loss": 0.7076,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7530516431924883,
+      "eval_loss": 0.6211019158363342,
+      "eval_runtime": 1.9926,
+      "eval_samples_per_second": 1068.944,
+      "eval_steps_per_second": 67.248,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 11.677574157714844,
+      "learning_rate": 1.0560248055196108e-05,
+      "loss": 0.4535,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7680751173708921,
+      "eval_loss": 0.6102677583694458,
+      "eval_runtime": 2.2362,
+      "eval_samples_per_second": 952.498,
+      "eval_steps_per_second": 59.922,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 33.26390838623047,
+      "learning_rate": 7.3890023929750545e-06,
+      "loss": 0.2958,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7751173708920188,
+      "eval_loss": 0.7481958866119385,
+      "eval_runtime": 2.135,
+      "eval_samples_per_second": 997.66,
+      "eval_steps_per_second": 62.764,
+      "step": 1599
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 14.7713041305542,
+      "learning_rate": 4.217756730754001e-06,
+      "loss": 0.1874,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7708920187793428,
+      "eval_loss": 1.0311119556427002,
+      "eval_runtime": 2.0623,
+      "eval_samples_per_second": 1032.824,
+      "eval_steps_per_second": 64.976,
+      "step": 2132
+    },
+    {
+      "epoch": 4.69,
+      "grad_norm": 1.1739749908447266,
+      "learning_rate": 1.0465110685329476e-06,
+      "loss": 0.1051,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7727699530516432,
+      "eval_loss": 1.1397253274917603,
+      "eval_runtime": 2.1823,
+      "eval_samples_per_second": 976.021,
+      "eval_steps_per_second": 61.402,
+      "step": 2665
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2665,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 856808289095472.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6902739379638215e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.019154977870537472
+  }
+}

run-15/checkpoint-2665/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47578a34c3d9ba21ee4e0ec6e9de13d7e68fe8c675092633f464cbfc506864f8
+size 4856

run-19/checkpoint-267/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-19/checkpoint-267/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a63d61dd1dbef133a4a54ab1f2f18adfbb803f4221d5942217c0b43ae7213cff
+size 409103316

run-19/checkpoint-267/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6c35c19b3033524502b333f3effce0d2d99fe0651595357c1e9ee00b1bb5471
+size 818327802

run-19/checkpoint-267/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:123e89548a83b33069b1dc6f7e79d621eac970b4e99c56bc48c19b6733a7f692
+size 14244

run-19/checkpoint-267/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3081e0c1671f48c011c79aa776bcc1778551b80f8c0052c7c3a201996bd0303
+size 1064

run-19/checkpoint-267/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-19/checkpoint-267/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-19/checkpoint-267/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.64137202501297,
+  "best_model_checkpoint": "BERT-WMM/run-19/checkpoint-267",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 267,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7361502347417841,
+      "eval_loss": 0.64137202501297,
+      "eval_runtime": 1.9678,
+      "eval_samples_per_second": 1082.453,
+      "eval_steps_per_second": 68.098,
+      "step": 267
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 801,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4384792339701421e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "weight_decay": 0.00035180961962651564
+  }
+}

run-19/checkpoint-267/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bda6d0591379b4005638e47cc567a832be7f1e2ee85c267cf84315e6fce938e6
+size 4856