Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e7180d1e19a898f1beb292a73f8386dde07cf28e7b65dcfb30d59b43d88e596
+oid sha256:6115a480a3556deabc06ba3a4a9d328a4f5a7290a47014ca45b7455a400e6d93
 size 409103316

run-4/checkpoint-670/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-4/checkpoint-670/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cd6f3cff498c7d1f3b2a4ce8bf8a719a08e324a27cf249cc519bb4a1d588531
+size 409103316

run-4/checkpoint-670/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3db9f5139b8bc920edd1385ba976de37b2c96059f38765e9e72debd66813588b
+size 818327802

run-4/checkpoint-670/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e32b4e2a76fcfc09520f2d2189948e11758cc8aaa3f650b4d9b0ce21055f60da
+size 14244

run-4/checkpoint-670/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9201c9b194193c2d092122a06002b80a5037a171f125044627ae04049a7a0a5
+size 1064

run-4/checkpoint-670/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-4/checkpoint-670/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-4/checkpoint-670/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": 0.6047325730323792,
+  "best_model_checkpoint": "BERT-WMM/run-4/checkpoint-268",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 670,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7248826291079812,
+      "eval_loss": 0.6610550880432129,
+      "eval_runtime": 2.0768,
+      "eval_samples_per_second": 1025.597,
+      "eval_steps_per_second": 64.521,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.755868544600939,
+      "eval_loss": 0.6047325730323792,
+      "eval_runtime": 2.0636,
+      "eval_samples_per_second": 1032.163,
+      "eval_steps_per_second": 64.934,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7568075117370892,
+      "eval_loss": 0.6309530138969421,
+      "eval_runtime": 2.6635,
+      "eval_samples_per_second": 799.702,
+      "eval_steps_per_second": 50.31,
+      "step": 402
+    },
+    {
+      "epoch": 3.73,
+      "grad_norm": 9.669575691223145,
+      "learning_rate": 4.323409306826513e-06,
+      "loss": 0.5385,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6676124334335327,
+      "eval_runtime": 2.0995,
+      "eval_samples_per_second": 1014.528,
+      "eval_steps_per_second": 63.825,
+      "step": 536
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7530516431924883,
+      "eval_loss": 0.694180965423584,
+      "eval_runtime": 2.1225,
+      "eval_samples_per_second": 1003.547,
+      "eval_steps_per_second": 63.134,
+      "step": 670
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 804,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 709335274032504.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1434279877264858e-05,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 64,
+    "weight_decay": 0.007798418229484321
+  }
+}

run-4/checkpoint-670/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc8ba15acf69ccfa7cad78d9e146e493b9003672aa3b6919156015dfb1a7a16
+size 4856

run-4/checkpoint-804/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-4/checkpoint-804/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:278ef315295d7089f973e9c8357dc120b7c326e619b7c178255b8fb20f4f66e5
+size 409103316

run-4/checkpoint-804/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eae99c65c3199ea13bb9599d18aa00b51f139b33c7b867c5cd87a52fa5e4640
+size 818327802

run-4/checkpoint-804/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ef16036783fc2db3c083c33b168a180c1d506495ec9230e71b0eb1ed47b4b36
+size 14244

run-4/checkpoint-804/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e01cc2a96d1f07350dda40775edf8161e5320519daaf80b925a1a8460a20159
+size 1064

run-4/checkpoint-804/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-4/checkpoint-804/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-4/checkpoint-804/trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": 0.6047325730323792,
+  "best_model_checkpoint": "BERT-WMM/run-4/checkpoint-268",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 804,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7248826291079812,
+      "eval_loss": 0.6610550880432129,
+      "eval_runtime": 2.0768,
+      "eval_samples_per_second": 1025.597,
+      "eval_steps_per_second": 64.521,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.755868544600939,
+      "eval_loss": 0.6047325730323792,
+      "eval_runtime": 2.0636,
+      "eval_samples_per_second": 1032.163,
+      "eval_steps_per_second": 64.934,
+      "step": 268
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7568075117370892,
+      "eval_loss": 0.6309530138969421,
+      "eval_runtime": 2.6635,
+      "eval_samples_per_second": 799.702,
+      "eval_steps_per_second": 50.31,
+      "step": 402
+    },
+    {
+      "epoch": 3.73,
+      "grad_norm": 9.669575691223145,
+      "learning_rate": 4.323409306826513e-06,
+      "loss": 0.5385,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6676124334335327,
+      "eval_runtime": 2.0995,
+      "eval_samples_per_second": 1014.528,
+      "eval_steps_per_second": 63.825,
+      "step": 536
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7530516431924883,
+      "eval_loss": 0.694180965423584,
+      "eval_runtime": 2.1225,
+      "eval_samples_per_second": 1003.547,
+      "eval_steps_per_second": 63.134,
+      "step": 670
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7502347417840376,
+      "eval_loss": 0.7122268676757812,
+      "eval_runtime": 2.0528,
+      "eval_samples_per_second": 1037.598,
+      "eval_steps_per_second": 65.276,
+      "step": 804
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 804,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 709335274032504.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1434279877264858e-05,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 64,
+    "weight_decay": 0.007798418229484321
+  }
+}

run-4/checkpoint-804/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc8ba15acf69ccfa7cad78d9e146e493b9003672aa3b6919156015dfb1a7a16
+size 4856

run-5/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-5/checkpoint-267/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6115a480a3556deabc06ba3a4a9d328a4f5a7290a47014ca45b7455a400e6d93
+size 409103316

run-5/checkpoint-267/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d51262842df1054b632a29ea66bc9fc5d957248ba9bcdca4f3e195d304b6314
+size 818327802

run-5/checkpoint-267/rng_state.pth

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

run-5/checkpoint-267/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab3b17d1969fd0b91ad7d8767d2c65a7afa789e978300157a086606fc39af78
+size 1064

run-5/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-5/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-5/checkpoint-267/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.6466411352157593,
+  "best_model_checkpoint": "BERT-WMM/run-5/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": 0.7338028169014085,
+      "eval_loss": 0.6466411352157593,
+      "eval_runtime": 2.0904,
+      "eval_samples_per_second": 1018.923,
+      "eval_steps_per_second": 64.101,
+      "step": 267
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 534,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.887574420426101e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 32,
+    "weight_decay": 1.6818908255902827e-05
+  }
+}

run-5/checkpoint-267/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d11893aa7531a00a798ff2c74d6b44e7248ec089d85163d6ee787b4e26991cd
+size 4856

runs/Apr18_08-35-19_da5e8340a418/events.out.tfevents.1713429976.da5e8340a418.15241.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d32ad86ec33e27fb821d0223bd2b1ee9420cef74b8c067aa79ba8b68149488
+size 5768

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc8ba15acf69ccfa7cad78d9e146e493b9003672aa3b6919156015dfb1a7a16
+oid sha256:9d11893aa7531a00a798ff2c74d6b44e7248ec089d85163d6ee787b4e26991cd
 size 4856