Training in progress, epoch 1

run-12/checkpoint-267/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:971a3ddf817b712dc07195c844772ef5d1ec4a8fd2faa3cfc511b714130228d0
+oid sha256:709e0174af7e7bfc36b2ca42177cb07663d435c4830e3ef2fd95156cc7684138
 size 409103316

run-12/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc8b54fc5e8c9423b8eb78032472c72dce9ff03db39846d1622f31a3d6911c46
+oid sha256:52ef4431d2c45c5021200b1e749d9a863141163026b276944e492c1db9ee3f59
 size 818327802

run-12/checkpoint-267/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d605219d0cdfe1356d19dfc261c4f045664dbc44ddf04517d0b2ebd1dab264c7
+oid sha256:44c8fc955f6ab66538b705aa40f6ebb08474ec445464a7a19ca29971b9fc42d4
 size 1064

run-12/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6019130349159241,
+  "best_metric": 0.6081846952438354,
   "best_model_checkpoint": "BERT-WMM/run-12/checkpoint-267",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,23 +10,23 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7563380281690141,
-      "eval_loss": 0.6019130349159241,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6081846952438354,
       "eval_runtime": 2.4539,
-      "eval_samples_per_second": 868.022,
-      "eval_steps_per_second": 54.608,
+      "eval_samples_per_second": 868.011,
+      "eval_steps_per_second": 54.607,
       "step": 267
     }
   ],
   "logging_steps": 500,
-  "max_steps": 801,
+  "max_steps": 1335,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "per_device_train_batch_size": 32
+    "num_train_epochs": 5
   }
 }

run-12/checkpoint-267/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
+oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
 size 4856

run-12/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2c26a4990298c617435add4fef099a107381df4b5d4dd2ceb1932c28c743541
+oid sha256:976557a36bef1a4a492485f3f6cb8948205b7b3a9ea05ce8ce0eb8982fcc1d9e
 size 409103316

run-12/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7c82d05f4ce26f22c9acaa7998473a49f5f6cbfcd52e5fa856d9f347b60ad8c
+oid sha256:890b6f5cc14af75c85002de6e2745609f1bf02f4a33a71cd0af847d31243fe8a
 size 818327802

run-12/checkpoint-534/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda5eab8086c3361f01b6da1d0d501e5d7ffcc15041db5c9a3384c00b843300f
+oid sha256:5e2aa06609570d504e0cfaf6c3bd801e1681706921a7512c6ccb9eded784901f
 size 1064

run-12/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5817901492118835,
+  "best_metric": 0.5776590704917908,
   "best_model_checkpoint": "BERT-WMM/run-12/checkpoint-534",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,39 +10,39 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7563380281690141,
-      "eval_loss": 0.6019130349159241,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6081846952438354,
       "eval_runtime": 2.4539,
-      "eval_samples_per_second": 868.022,
-      "eval_steps_per_second": 54.608,
+      "eval_samples_per_second": 868.011,
+      "eval_steps_per_second": 54.607,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.674468994140625,
-      "learning_rate": 5.7987153604787005e-06,
-      "loss": 0.6061,
+      "grad_norm": 9.532360076904297,
+      "learning_rate": 9.65168237740807e-06,
+      "loss": 0.6057,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7619718309859155,
-      "eval_loss": 0.5817901492118835,
-      "eval_runtime": 2.4912,
-      "eval_samples_per_second": 855.006,
-      "eval_steps_per_second": 53.789,
+      "eval_accuracy": 0.7657276995305164,
+      "eval_loss": 0.5776590704917908,
+      "eval_runtime": 2.4958,
+      "eval_samples_per_second": 853.421,
+      "eval_steps_per_second": 53.689,
       "step": 534
     }
   ],
   "logging_steps": 500,
-  "max_steps": 801,
+  "max_steps": 1335,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 539341394870880.0,
+  "total_flos": 907987959990720.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "per_device_train_batch_size": 32
+    "num_train_epochs": 5
   }
 }

run-12/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
+oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
 size 4856

run-12/checkpoint-801/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26d7f234a18b08d68556eb791d0055c0b179dd8190747f6d104dae29ea9eda1d
+oid sha256:22b99fd8821bb6a7a58373b3e00909c671d6605dea0dd95a2c9cb3761b3b7f4e
 size 409103316

run-12/checkpoint-801/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cb41a29b069558e60295633a1200ae5a46374d86a3d3f48077ca97f9aa46387
+oid sha256:62a624295ad87feed2451e9981cc71ab700084e2468c6ef4e3d6a128b0f68b6c
 size 818327802

run-12/checkpoint-801/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cbdc9fc2ef477673574bd96dbcbae5c7987ba9b5b853636ae08a8f9164bbb32
+oid sha256:6d4fd24f628450570301e96568f256a50cad9a43cd0a510b6a50e86be9f9a3a5
 size 1064

run-12/checkpoint-801/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5817901492118835,
+  "best_metric": 0.5776590704917908,
   "best_model_checkpoint": "BERT-WMM/run-12/checkpoint-534",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,48 +10,48 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7563380281690141,
-      "eval_loss": 0.6019130349159241,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6081846952438354,
       "eval_runtime": 2.4539,
-      "eval_samples_per_second": 868.022,
-      "eval_steps_per_second": 54.608,
+      "eval_samples_per_second": 868.011,
+      "eval_steps_per_second": 54.607,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.674468994140625,
-      "learning_rate": 5.7987153604787005e-06,
-      "loss": 0.6061,
+      "grad_norm": 9.532360076904297,
+      "learning_rate": 9.65168237740807e-06,
+      "loss": 0.6057,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7619718309859155,
-      "eval_loss": 0.5817901492118835,
-      "eval_runtime": 2.4912,
-      "eval_samples_per_second": 855.006,
-      "eval_steps_per_second": 53.789,
+      "eval_accuracy": 0.7657276995305164,
+      "eval_loss": 0.5776590704917908,
+      "eval_runtime": 2.4958,
+      "eval_samples_per_second": 853.421,
+      "eval_steps_per_second": 53.689,
       "step": 534
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7582159624413145,
-      "eval_loss": 0.6465383768081665,
-      "eval_runtime": 2.4805,
-      "eval_samples_per_second": 858.714,
-      "eval_steps_per_second": 54.022,
+      "eval_accuracy": 0.7690140845070422,
+      "eval_loss": 0.6647635102272034,
+      "eval_runtime": 2.4905,
+      "eval_samples_per_second": 855.253,
+      "eval_steps_per_second": 53.805,
       "step": 801
     }
   ],
   "logging_steps": 500,
-  "max_steps": 801,
+  "max_steps": 1335,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 539341394870880.0,
+  "total_flos": 907987959990720.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "per_device_train_batch_size": 32
+    "num_train_epochs": 5
   }
 }

run-12/checkpoint-801/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
+oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
 size 4856

run-8/checkpoint-1068/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-8/checkpoint-1068/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be86a3545123e440e90e40dcbfd3e25b7c607d03543cf59dbfbcfd5ab4c3b45f
+size 409103316

run-8/checkpoint-1068/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e1166e00c810b5e1aece2aa8579986f54f02a7ac182283da9312b97e3dc9e8
+size 818327802

run-8/checkpoint-1068/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88efce74fbb2721dc5ac34e297a693ee9d8b613381cc20bc06917c3f551f452b
+size 14244

run-8/checkpoint-1068/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99710eaca949f554ced3febb88242f5791546c4a3874f3ce0ec9086db0a0ce0b
+size 1064

run-8/checkpoint-1068/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-8/checkpoint-1068/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-8/checkpoint-1068/trainer_state.json

@@ -0,0 +1,73 @@
+{
+  "best_metric": 0.5776590704917908,
+  "best_model_checkpoint": "BERT-WMM/run-8/checkpoint-534",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1068,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6081846952438354,
+      "eval_runtime": 2.4296,
+      "eval_samples_per_second": 876.671,
+      "eval_steps_per_second": 55.152,
+      "step": 267
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 9.532360076904297,
+      "learning_rate": 9.65168237740807e-06,
+      "loss": 0.6057,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7657276995305164,
+      "eval_loss": 0.5776590704917908,
+      "eval_runtime": 2.4625,
+      "eval_samples_per_second": 864.981,
+      "eval_steps_per_second": 54.417,
+      "step": 534
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7690140845070422,
+      "eval_loss": 0.6647635102272034,
+      "eval_runtime": 2.4715,
+      "eval_samples_per_second": 861.81,
+      "eval_steps_per_second": 54.217,
+      "step": 801
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 26.327552795410156,
+      "learning_rate": 3.872231852014017e-06,
+      "loss": 0.2807,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7615023474178404,
+      "eval_loss": 0.758091151714325,
+      "eval_runtime": 2.4677,
+      "eval_samples_per_second": 863.139,
+      "eval_steps_per_second": 54.301,
+      "step": 1068
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1335,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 883767136544712.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "num_train_epochs": 5
+  }
+}

run-8/checkpoint-1068/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
+size 4856

run-8/checkpoint-1335/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-8/checkpoint-1335/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87d7df15b3f66abb639f6f827a81d42cb4047051cfbde3665cb2ce2fecb82122
+size 409103316

run-8/checkpoint-1335/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f151333b045123e4862a3a7fab6912fb367a75dc6421cb1df423ce26a10162f0
+size 818327802

run-8/checkpoint-1335/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fe610f625e919d82fdbaa3afd268f77970e25b62afd1b9f3d78dc3d12f69f50
+size 14244

run-8/checkpoint-1335/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9462cebdd70bc492d7b3757b48d821084c9fd9829a619f501a3658a0972c6551
+size 1064

run-8/checkpoint-1335/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-8/checkpoint-1335/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-8/checkpoint-1335/trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_metric": 0.5776590704917908,
+  "best_model_checkpoint": "BERT-WMM/run-8/checkpoint-534",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1335,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6081846952438354,
+      "eval_runtime": 2.4296,
+      "eval_samples_per_second": 876.671,
+      "eval_steps_per_second": 55.152,
+      "step": 267
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 9.532360076904297,
+      "learning_rate": 9.65168237740807e-06,
+      "loss": 0.6057,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7657276995305164,
+      "eval_loss": 0.5776590704917908,
+      "eval_runtime": 2.4625,
+      "eval_samples_per_second": 864.981,
+      "eval_steps_per_second": 54.417,
+      "step": 534
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7690140845070422,
+      "eval_loss": 0.6647635102272034,
+      "eval_runtime": 2.4715,
+      "eval_samples_per_second": 861.81,
+      "eval_steps_per_second": 54.217,
+      "step": 801
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 26.327552795410156,
+      "learning_rate": 3.872231852014017e-06,
+      "loss": 0.2807,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7615023474178404,
+      "eval_loss": 0.758091151714325,
+      "eval_runtime": 2.4677,
+      "eval_samples_per_second": 863.139,
+      "eval_steps_per_second": 54.301,
+      "step": 1068
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7643192488262911,
+      "eval_loss": 0.8205846548080444,
+      "eval_runtime": 2.4814,
+      "eval_samples_per_second": 858.382,
+      "eval_steps_per_second": 54.002,
+      "step": 1335
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1335,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 883767136544712.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "num_train_epochs": 5
+  }
+}

run-8/checkpoint-1335/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
+size 4856

run-8/checkpoint-534/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-8/checkpoint-534/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:976557a36bef1a4a492485f3f6cb8948205b7b3a9ea05ce8ce0eb8982fcc1d9e
+size 409103316

run-8/checkpoint-534/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:890b6f5cc14af75c85002de6e2745609f1bf02f4a33a71cd0af847d31243fe8a
+size 818327802

run-8/checkpoint-534/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50b42ca1a83d9e0487eef7bc4978f59ad97364890e28f585669fc8e766195ed9
+size 14244

run-8/checkpoint-534/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2aa06609570d504e0cfaf6c3bd801e1681706921a7512c6ccb9eded784901f
+size 1064

run-8/checkpoint-534/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-8/checkpoint-534/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-8/checkpoint-534/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": 0.5776590704917908,
+  "best_model_checkpoint": "BERT-WMM/run-8/checkpoint-534",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 534,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6081846952438354,
+      "eval_runtime": 2.4296,
+      "eval_samples_per_second": 876.671,
+      "eval_steps_per_second": 55.152,
+      "step": 267
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 9.532360076904297,
+      "learning_rate": 9.65168237740807e-06,
+      "loss": 0.6057,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7657276995305164,
+      "eval_loss": 0.5776590704917908,
+      "eval_runtime": 2.4625,
+      "eval_samples_per_second": 864.981,
+      "eval_steps_per_second": 54.417,
+      "step": 534
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1335,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 535476916548000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "num_train_epochs": 5
+  }
+}

run-8/checkpoint-534/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
+size 4856

run-8/checkpoint-801/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-8/checkpoint-801/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b99fd8821bb6a7a58373b3e00909c671d6605dea0dd95a2c9cb3761b3b7f4e
+size 409103316

run-8/checkpoint-801/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62a624295ad87feed2451e9981cc71ab700084e2468c6ef4e3d6a128b0f68b6c
+size 818327802

run-8/checkpoint-801/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2e88e818a2ba76e34870352cb30ede96939fd3b25fc6442146490e0caecf29
+size 14244

run-8/checkpoint-801/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4fd24f628450570301e96568f256a50cad9a43cd0a510b6a50e86be9f9a3a5
+size 1064