Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:017c7fd8cdfc40d05e660a28f8fdb8f78171b64c8062416c21332a818b8614b2
+oid sha256:7e38fd0bac0ea3630404563ae715c928ba270b92070c4c8aa5761218bacece08
 size 409103316

run-10/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-10/checkpoint-1066/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:890cdf9f2ce1aa280345f68de01ee0de889f481f7a20bd13dbb37e3559fe4a8d
+size 409103316

run-10/checkpoint-1066/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:969806d6a37bba6414bab60d05fae22b419c8139d2f6180c350d841c321b7123
+size 818327802

run-10/checkpoint-1066/rng_state.pth

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

run-10/checkpoint-1066/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c59425be3f5afb35e6615a9e8cd8870125d490b1d6c3cd6b727317f3a0894b9d
+size 1064

run-10/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-10/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-10/checkpoint-1066/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.6108968257904053,
+  "best_model_checkpoint": "BERT-WMM/run-10/checkpoint-1066",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1066,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.94,
+      "grad_norm": 11.003177642822266,
+      "learning_rate": 3.5116101047118276e-06,
+      "loss": 0.7883,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7370892018779343,
+      "eval_loss": 0.6418591737747192,
+      "eval_runtime": 2.0865,
+      "eval_samples_per_second": 1020.838,
+      "eval_steps_per_second": 64.222,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 22.481332778930664,
+      "learning_rate": 2.8608298777452175e-06,
+      "loss": 0.5687,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6108968257904053,
+      "eval_runtime": 2.0305,
+      "eval_samples_per_second": 1049.022,
+      "eval_steps_per_second": 65.995,
+      "step": 1066
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3198,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 528381076563648.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.162390331678438e-06,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.000561727996440909
+  }
+}

run-10/checkpoint-1066/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:463ccff4ed8095e86330c3c3432b5d925d66b9d6c0bdc70b6bd557b17c7bd922
+size 4856

run-10/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-10/checkpoint-1599/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8ad2900acc9b2e7d7656dd871ac1b2f923928c5923ed4dfed93c31c74648d42
+size 409103316

run-10/checkpoint-1599/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da28dd23ad9143b16345684cae8b02eab9701293f682949d93f3cc8ca60e85af
+size 818327802

run-10/checkpoint-1599/rng_state.pth

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

run-10/checkpoint-1599/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bf38f97dd35a69957e98c4770fedb90096ecd795b869e9101695cfe1340a04e
+size 1064

run-10/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-10/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-10/checkpoint-1599/trainer_state.json

@@ -0,0 +1,74 @@
+{
+  "best_metric": 0.6108968257904053,
+  "best_model_checkpoint": "BERT-WMM/run-10/checkpoint-1066",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1599,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.94,
+      "grad_norm": 11.003177642822266,
+      "learning_rate": 3.5116101047118276e-06,
+      "loss": 0.7883,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7370892018779343,
+      "eval_loss": 0.6418591737747192,
+      "eval_runtime": 2.0865,
+      "eval_samples_per_second": 1020.838,
+      "eval_steps_per_second": 64.222,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 22.481332778930664,
+      "learning_rate": 2.8608298777452175e-06,
+      "loss": 0.5687,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6108968257904053,
+      "eval_runtime": 2.0305,
+      "eval_samples_per_second": 1049.022,
+      "eval_steps_per_second": 65.995,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 32.06578063964844,
+      "learning_rate": 2.2100496507786074e-06,
+      "loss": 0.4792,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7553990610328638,
+      "eval_loss": 0.6331790089607239,
+      "eval_runtime": 2.1296,
+      "eval_samples_per_second": 1000.171,
+      "eval_steps_per_second": 62.922,
+      "step": 1599
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3198,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 697766505946776.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.162390331678438e-06,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.000561727996440909
+  }
+}

run-10/checkpoint-1599/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:463ccff4ed8095e86330c3c3432b5d925d66b9d6c0bdc70b6bd557b17c7bd922
+size 4856

run-10/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-10/checkpoint-2132/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057131df376899e13f1f8ff4a83a7090358fa502e2c85e40845a62812e5143d8
+size 409103316

run-10/checkpoint-2132/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0844a302ce0716086e8172b538bca70d96a77faef2369ac19727a983a59ff3b
+size 818327802

run-10/checkpoint-2132/rng_state.pth

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

run-10/checkpoint-2132/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6ed4763468bb4be5abdb6086a6d19d6466135003206edc4fc184390fb97dcf
+size 1064

run-10/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-10/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-10/checkpoint-2132/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": 0.6108968257904053,
+  "best_model_checkpoint": "BERT-WMM/run-10/checkpoint-1066",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2132,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.94,
+      "grad_norm": 11.003177642822266,
+      "learning_rate": 3.5116101047118276e-06,
+      "loss": 0.7883,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7370892018779343,
+      "eval_loss": 0.6418591737747192,
+      "eval_runtime": 2.0865,
+      "eval_samples_per_second": 1020.838,
+      "eval_steps_per_second": 64.222,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 22.481332778930664,
+      "learning_rate": 2.8608298777452175e-06,
+      "loss": 0.5687,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6108968257904053,
+      "eval_runtime": 2.0305,
+      "eval_samples_per_second": 1049.022,
+      "eval_steps_per_second": 65.995,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 32.06578063964844,
+      "learning_rate": 2.2100496507786074e-06,
+      "loss": 0.4792,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7553990610328638,
+      "eval_loss": 0.6331790089607239,
+      "eval_runtime": 2.1296,
+      "eval_samples_per_second": 1000.171,
+      "eval_steps_per_second": 62.922,
+      "step": 1599
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 21.596628189086914,
+      "learning_rate": 1.5592694238119975e-06,
+      "loss": 0.4182,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7530516431924883,
+      "eval_loss": 0.6648078560829163,
+      "eval_runtime": 2.7647,
+      "eval_samples_per_second": 770.434,
+      "eval_steps_per_second": 48.469,
+      "step": 2132
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3198,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 867010100753160.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.162390331678438e-06,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.000561727996440909
+  }
+}

run-10/checkpoint-2132/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:463ccff4ed8095e86330c3c3432b5d925d66b9d6c0bdc70b6bd557b17c7bd922
+size 4856

run-10/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-10/checkpoint-2665/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e38fd0bac0ea3630404563ae715c928ba270b92070c4c8aa5761218bacece08
+size 409103316

run-10/checkpoint-2665/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ba9a6dfc6147fdbc1025ba0735d981d512fa56781762e4b016958733814c59
+size 818327802

run-10/checkpoint-2665/rng_state.pth

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

run-10/checkpoint-2665/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0492c389979f18a29298be128837fe55b3844fae4a11a6be164099863ed17a8
+size 1064

run-10/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-10/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-10/checkpoint-2665/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.6108968257904053,
+  "best_model_checkpoint": "BERT-WMM/run-10/checkpoint-1066",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2665,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.94,
+      "grad_norm": 11.003177642822266,
+      "learning_rate": 3.5116101047118276e-06,
+      "loss": 0.7883,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7370892018779343,
+      "eval_loss": 0.6418591737747192,
+      "eval_runtime": 2.0865,
+      "eval_samples_per_second": 1020.838,
+      "eval_steps_per_second": 64.222,
+      "step": 533
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 22.481332778930664,
+      "learning_rate": 2.8608298777452175e-06,
+      "loss": 0.5687,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6108968257904053,
+      "eval_runtime": 2.0305,
+      "eval_samples_per_second": 1049.022,
+      "eval_steps_per_second": 65.995,
+      "step": 1066
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 32.06578063964844,
+      "learning_rate": 2.2100496507786074e-06,
+      "loss": 0.4792,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7553990610328638,
+      "eval_loss": 0.6331790089607239,
+      "eval_runtime": 2.1296,
+      "eval_samples_per_second": 1000.171,
+      "eval_steps_per_second": 62.922,
+      "step": 1599
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 21.596628189086914,
+      "learning_rate": 1.5592694238119975e-06,
+      "loss": 0.4182,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7530516431924883,
+      "eval_loss": 0.6648078560829163,
+      "eval_runtime": 2.7647,
+      "eval_samples_per_second": 770.434,
+      "eval_steps_per_second": 48.469,
+      "step": 2132
+    },
+    {
+      "epoch": 4.69,
+      "grad_norm": 17.562744140625,
+      "learning_rate": 9.084891968453876e-07,
+      "loss": 0.3558,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7586854460093897,
+      "eval_loss": 0.6886456608772278,
+      "eval_runtime": 2.0657,
+      "eval_samples_per_second": 1031.129,
+      "eval_steps_per_second": 64.869,
+      "step": 2665
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3198,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 1036259862280272.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.162390331678438e-06,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 16,
+    "weight_decay": 0.000561727996440909
+  }
+}

run-10/checkpoint-2665/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:463ccff4ed8095e86330c3c3432b5d925d66b9d6c0bdc70b6bd557b17c7bd922
+size 4856

runs/Apr18_08-35-19_da5e8340a418/events.out.tfevents.1713430578.da5e8340a418.15241.10

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c567eeba67064e635441525cc2e02d6c8d8e3c052ec3400c7f25ce23f763cc2
-size 6722
+oid sha256:11a37feb95e90ca6d42e26ca105450e6b2243184b6aa37abafe792b308150927
+size 8467