Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:971a3ddf817b712dc07195c844772ef5d1ec4a8fd2faa3cfc511b714130228d0
+oid sha256:3a945d947e49e86e546787bb669f7b65c020565b63a4511277f9d6d829957c53
 size 409103316

run-18/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-18/checkpoint-534/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2c26a4990298c617435add4fef099a107381df4b5d4dd2ceb1932c28c743541
+size 409103316

run-18/checkpoint-534/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7c82d05f4ce26f22c9acaa7998473a49f5f6cbfcd52e5fa856d9f347b60ad8c
+size 818327802

run-18/checkpoint-534/rng_state.pth

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

run-18/checkpoint-534/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dda5eab8086c3361f01b6da1d0d501e5d7ffcc15041db5c9a3384c00b843300f
+size 1064

run-18/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-18/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-18/checkpoint-534/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": 0.5817901492118835,
+  "best_model_checkpoint": "BERT-WMM/run-18/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": 0.7563380281690141,
+      "eval_loss": 0.6019130349159241,
+      "eval_runtime": 2.4196,
+      "eval_samples_per_second": 880.318,
+      "eval_steps_per_second": 55.381,
+      "step": 267
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 9.674468994140625,
+      "learning_rate": 5.7987153604787005e-06,
+      "loss": 0.6061,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7619718309859155,
+      "eval_loss": 0.5817901492118835,
+      "eval_runtime": 2.455,
+      "eval_samples_per_second": 867.605,
+      "eval_steps_per_second": 54.582,
+      "step": 534
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 801,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 349221394826640.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "per_device_train_batch_size": 32
+  }
+}

run-18/checkpoint-534/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
+size 4856

run-18/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-18/checkpoint-801/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d7f234a18b08d68556eb791d0055c0b179dd8190747f6d104dae29ea9eda1d
+size 409103316

run-18/checkpoint-801/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb41a29b069558e60295633a1200ae5a46374d86a3d3f48077ca97f9aa46387
+size 818327802

run-18/checkpoint-801/rng_state.pth

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

run-18/checkpoint-801/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cbdc9fc2ef477673574bd96dbcbae5c7987ba9b5b853636ae08a8f9164bbb32
+size 1064

run-18/checkpoint-801/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-18/checkpoint-801/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-18/checkpoint-801/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.5817901492118835,
+  "best_model_checkpoint": "BERT-WMM/run-18/checkpoint-534",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 801,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7563380281690141,
+      "eval_loss": 0.6019130349159241,
+      "eval_runtime": 2.4196,
+      "eval_samples_per_second": 880.318,
+      "eval_steps_per_second": 55.381,
+      "step": 267
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 9.674468994140625,
+      "learning_rate": 5.7987153604787005e-06,
+      "loss": 0.6061,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7619718309859155,
+      "eval_loss": 0.5817901492118835,
+      "eval_runtime": 2.455,
+      "eval_samples_per_second": 867.605,
+      "eval_steps_per_second": 54.582,
+      "step": 534
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7582159624413145,
+      "eval_loss": 0.6465383768081665,
+      "eval_runtime": 2.4569,
+      "eval_samples_per_second": 866.932,
+      "eval_steps_per_second": 54.539,
+      "step": 801
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 801,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 349221394826640.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "per_device_train_batch_size": 32
+  }
+}

run-18/checkpoint-801/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
+size 4856

run-19/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-19/checkpoint-533/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a945d947e49e86e546787bb669f7b65c020565b63a4511277f9d6d829957c53
+size 409103316

run-19/checkpoint-533/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e69f0b7d99f34f2e81422584ee7b6f8d6d5951fc530dceb4c4dabf03e73df7f
+size 818327802

run-19/checkpoint-533/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4808b2c3875b1e10fbc84d9c9db1c6be6492311d42fc011bb566cb647c74695b
+size 14244

run-19/checkpoint-533/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d6e84cec3f6682da5e6ce3adbec8136f9cd24a430311733c1ab27f15ac4fc1
+size 1064

run-19/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-19/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-19/checkpoint-533/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 0.603524923324585,
+  "best_model_checkpoint": "BERT-WMM/run-19/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": 11.3766508102417,
+      "learning_rate": 1.0605888092670128e-05,
+      "loss": 0.7117,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7568075117370892,
+      "eval_loss": 0.603524923324585,
+      "eval_runtime": 2.4106,
+      "eval_samples_per_second": 883.611,
+      "eval_steps_per_second": 55.589,
+      "step": 533
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1599,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 169371040368096.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "per_device_train_batch_size": 16
+  }
+}

run-19/checkpoint-533/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebedef9b751bedd4e796367e1472df25f06ffc187165c1b123fac9f3e7ae22ec
+size 4856

runs/Apr19_07-31-51_21d31c708e60/events.out.tfevents.1713515237.21d31c708e60.946.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3304e3b8bf2471510baec68865079d99572c4d5fbf1db86916152db8bd5e4457
+size 6850

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
+oid sha256:ebedef9b751bedd4e796367e1472df25f06ffc187165c1b123fac9f3e7ae22ec
 size 4856