Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19cf132e1ec02e0c30d81009a761fc4520c92c64412183f266bf3de7c588a666
+oid sha256:08b2691a9b0ec7dacd6a5cfd13c6c8581e7f46d1fd925b4cb84e4fd88c97a627
 size 409103316

run-13/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-13/checkpoint-1066/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a624b519880d29f6e01cc1e152951460916679ecc61bb3fb4eec84ad3f43d15e
+size 409103316

run-13/checkpoint-1066/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4792fe45a142771e7ee87346abd142a68352eeff4cf57bc824bce3dcf367d0bd
+size 818327802

run-13/checkpoint-1066/rng_state.pth

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

run-13/checkpoint-1066/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:728ef15244fd69fa36ca4f7c48a4f1b189457e4b6bee513261473760fec0501c
+size 1064

run-13/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-13/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-13/checkpoint-1066/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.6162846088409424,
+  "best_model_checkpoint": "BERT-WMM/run-13/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": 12.600181579589844,
+      "learning_rate": 1.4607577277616791e-05,
+      "loss": 0.7148,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6162846088409424,
+      "eval_runtime": 1.9944,
+      "eval_samples_per_second": 1067.994,
+      "eval_steps_per_second": 67.188,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 8.747657775878906,
+      "learning_rate": 1.1234002848605984e-05,
+      "loss": 0.4485,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7624413145539906,
+      "eval_loss": 0.6197112202644348,
+      "eval_runtime": 2.1341,
+      "eval_samples_per_second": 998.1,
+      "eval_steps_per_second": 62.791,
+      "step": 1066
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2665,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 338261076519408.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.7981151706627596e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.009594844383188954
+  }
+}

run-13/checkpoint-1066/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:487692c351886fb721523721f90e7b355b077959171c7e7c7bf47d30d3da6baa
+size 4856

run-13/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-13/checkpoint-1599/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d4485c13a0c1e3c6a12ee9ae447b3c510c7f0cdb5b4267a242ed0232949a50
+size 409103316

run-13/checkpoint-1599/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e35b5fbb40c2fa5733581b76addc00192cf4184b23811becf8aebd0fb2171be5
+size 818327802

run-13/checkpoint-1599/rng_state.pth

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

run-13/checkpoint-1599/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0af5eda80aa1104a16db079eafe26edae83293b6e539871ba6e5d7dcb893a1c
+size 1064

run-13/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-13/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-13/checkpoint-1599/trainer_state.json

@@ -0,0 +1,74 @@
+{
+  "best_metric": 0.6162846088409424,
+  "best_model_checkpoint": "BERT-WMM/run-13/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": 12.600181579589844,
+      "learning_rate": 1.4607577277616791e-05,
+      "loss": 0.7148,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6162846088409424,
+      "eval_runtime": 1.9944,
+      "eval_samples_per_second": 1067.994,
+      "eval_steps_per_second": 67.188,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 8.747657775878906,
+      "learning_rate": 1.1234002848605984e-05,
+      "loss": 0.4485,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7624413145539906,
+      "eval_loss": 0.6197112202644348,
+      "eval_runtime": 2.1341,
+      "eval_samples_per_second": 998.1,
+      "eval_steps_per_second": 62.791,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 34.570838928222656,
+      "learning_rate": 7.860428419595179e-06,
+      "loss": 0.2791,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7661971830985915,
+      "eval_loss": 0.7673255205154419,
+      "eval_runtime": 2.1145,
+      "eval_samples_per_second": 1007.348,
+      "eval_steps_per_second": 63.373,
+      "step": 1599
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2665,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 507646505902536.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.7981151706627596e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.009594844383188954
+  }
+}

run-13/checkpoint-1599/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:487692c351886fb721523721f90e7b355b077959171c7e7c7bf47d30d3da6baa
+size 4856

run-13/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-13/checkpoint-2132/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21fbe61dc116c634a3a850eec23b504b2811b3c1ec4860038d02c0eefbd8b100
+size 409103316

run-13/checkpoint-2132/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0908a403ce1316935da749eedf9ce59bb7f9e73a8b0c5975462ab564696e5723
+size 818327802

run-13/checkpoint-2132/rng_state.pth

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

run-13/checkpoint-2132/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ba88c361984524c710473ce1b20622a9b24f35a93e6fd3bdb4fce4399db0d9a
+size 1064

run-13/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-13/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-13/checkpoint-2132/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": 0.6162846088409424,
+  "best_model_checkpoint": "BERT-WMM/run-13/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": 12.600181579589844,
+      "learning_rate": 1.4607577277616791e-05,
+      "loss": 0.7148,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6162846088409424,
+      "eval_runtime": 1.9944,
+      "eval_samples_per_second": 1067.994,
+      "eval_steps_per_second": 67.188,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 8.747657775878906,
+      "learning_rate": 1.1234002848605984e-05,
+      "loss": 0.4485,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7624413145539906,
+      "eval_loss": 0.6197112202644348,
+      "eval_runtime": 2.1341,
+      "eval_samples_per_second": 998.1,
+      "eval_steps_per_second": 62.791,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 34.570838928222656,
+      "learning_rate": 7.860428419595179e-06,
+      "loss": 0.2791,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7661971830985915,
+      "eval_loss": 0.7673255205154419,
+      "eval_runtime": 2.1145,
+      "eval_samples_per_second": 1007.348,
+      "eval_steps_per_second": 63.373,
+      "step": 1599
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 25.005464553833008,
+      "learning_rate": 4.486853990584372e-06,
+      "loss": 0.1691,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7680751173708921,
+      "eval_loss": 1.1236116886138916,
+      "eval_runtime": 2.0265,
+      "eval_samples_per_second": 1051.061,
+      "eval_steps_per_second": 66.123,
+      "step": 2132
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2665,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 676890100708920.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.7981151706627596e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.009594844383188954
+  }
+}

run-13/checkpoint-2132/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:487692c351886fb721523721f90e7b355b077959171c7e7c7bf47d30d3da6baa
+size 4856

run-13/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-13/checkpoint-2665/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e37e7b4e9fbb36fcceedf45df897614d2aa1495e0bbe1b2ab32ccfa121fc6759
+size 409103316

run-13/checkpoint-2665/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c79d23719ad956a3e73d651c26ea2f7f36aa9f9eed7fd9f5235d900fc5886c
+size 818327802

run-13/checkpoint-2665/rng_state.pth

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

run-13/checkpoint-2665/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:418cc85c181c7b69a06ed877e0f0aca62a412daf278324761adac98eadc5448a
+size 1064

run-13/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-13/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-13/checkpoint-2665/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.6162846088409424,
+  "best_model_checkpoint": "BERT-WMM/run-13/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": 12.600181579589844,
+      "learning_rate": 1.4607577277616791e-05,
+      "loss": 0.7148,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6162846088409424,
+      "eval_runtime": 1.9944,
+      "eval_samples_per_second": 1067.994,
+      "eval_steps_per_second": 67.188,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 8.747657775878906,
+      "learning_rate": 1.1234002848605984e-05,
+      "loss": 0.4485,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7624413145539906,
+      "eval_loss": 0.6197112202644348,
+      "eval_runtime": 2.1341,
+      "eval_samples_per_second": 998.1,
+      "eval_steps_per_second": 62.791,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 34.570838928222656,
+      "learning_rate": 7.860428419595179e-06,
+      "loss": 0.2791,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7661971830985915,
+      "eval_loss": 0.7673255205154419,
+      "eval_runtime": 2.1145,
+      "eval_samples_per_second": 1007.348,
+      "eval_steps_per_second": 63.373,
+      "step": 1599
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 25.005464553833008,
+      "learning_rate": 4.486853990584372e-06,
+      "loss": 0.1691,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7680751173708921,
+      "eval_loss": 1.1236116886138916,
+      "eval_runtime": 2.0265,
+      "eval_samples_per_second": 1051.061,
+      "eval_steps_per_second": 66.123,
+      "step": 2132
+    },
+    {
+      "epoch": 4.69,
+      "grad_norm": 0.5956600904464722,
+      "learning_rate": 1.113279561573566e-06,
+      "loss": 0.0966,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7690140845070422,
+      "eval_loss": 1.2481839656829834,
+      "eval_runtime": 2.1691,
+      "eval_samples_per_second": 981.987,
+      "eval_steps_per_second": 61.778,
+      "step": 2665
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2665,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 846139862236032.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.7981151706627596e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.009594844383188954
+  }
+}

run-13/checkpoint-2665/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:487692c351886fb721523721f90e7b355b077959171c7e7c7bf47d30d3da6baa
+size 4856

run-15/checkpoint-533/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-533/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b2691a9b0ec7dacd6a5cfd13c6c8581e7f46d1fd925b4cb84e4fd88c97a627
+size 409103316

run-15/checkpoint-533/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f94819f23678c21e67c9defa70cb4c4974bbc4d19ccbc35306204107fea796df
+size 818327802

run-15/checkpoint-533/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cd3c5a8822e67ef4af7188dd571a48877b29db4a131ffc031fd52e683869738
+size 14244

run-15/checkpoint-533/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5a7de0167b5779c0bd435e1bbf2062fea9a76bf2608858d8f82dab568b8a6fe
+size 1064

run-15/checkpoint-533/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-533/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-533/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.6211019158363342,
+  "best_model_checkpoint": "BERT-WMM/run-15/checkpoint-533",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 533,
+  "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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2665,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 180039467227536.0,
+  "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-533/training_args.bin

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