Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b065f683c5313ed15e05dee6db5f2e50dde7ed68627d3ee313a634b1326a304
+oid sha256:e1dbce98f3d950879926c2d466908ef43f449be641f52614ec113ba49b10d447
 size 437958648

run-11/checkpoint-156/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-11/checkpoint-156/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f2beaa212bb6cc8b3d0f77db50d96eee8e8d41b1855a8a596dd2960b04ea94e
+size 437958648

run-11/checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:234e8816edb16062c0fbdd7ca5f2abc1f1302df54b47bf220e7f79458cc883d5
+size 876038394

run-11/checkpoint-156/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b06d22713ab0eccf6163f8b0ec7376abad69fdc0b947461e0b301173cdd320
+size 14244

run-11/checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06cb31602b46ea02d18181e1dcf7ca4b9ce77b7a32b3e1956f969ca0a2ed56cf
+size 1064

run-11/checkpoint-156/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-11/checkpoint-156/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-11/checkpoint-156/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.6642599277978339,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-11/checkpoint-156",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 156,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6498194945848376,
+      "eval_loss": 0.654392421245575,
+      "eval_runtime": 0.6743,
+      "eval_samples_per_second": 410.767,
+      "eval_steps_per_second": 13.346,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6642599277978339,
+      "eval_loss": 0.6084265112876892,
+      "eval_runtime": 0.6873,
+      "eval_samples_per_second": 403.001,
+      "eval_steps_per_second": 13.094,
+      "step": 156
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 702,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.3696170960550694,
+    "learning_rate": 4.078854927314618e-05,
+    "max_seq_length": 256,
+    "num_train_epochs": 9,
+    "per_device_train_batch_size": 32
+  }
+}

run-11/checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86a6fb49832edf5c98c28420cdc451282412f1028f0865d86090d311e06db35
+size 5304

run-11/checkpoint-234/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-11/checkpoint-234/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b404a412c2ddc6dd0bf7de0e30d325381773141d58e8d5bf36326c1f6d688bf8
+size 437958648

run-11/checkpoint-234/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3054f550b0827217e8a5772064cb542e1e7fc8850afeeebe76fab43889c4925
+size 876038394

run-11/checkpoint-234/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5893971a43e53d8cccb69cbc77f5b88d424dd9d85114d1b21fc0c54c6cb446cf
+size 14244

run-11/checkpoint-234/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c14fd2f520f9a2763d8c00d0b399735aa66a0ad0bb68761bf619deb6ecd95c8
+size 1064

run-11/checkpoint-234/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-11/checkpoint-234/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-11/checkpoint-234/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.6642599277978339,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-11/checkpoint-156",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 234,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6498194945848376,
+      "eval_loss": 0.654392421245575,
+      "eval_runtime": 0.6743,
+      "eval_samples_per_second": 410.767,
+      "eval_steps_per_second": 13.346,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6642599277978339,
+      "eval_loss": 0.6084265112876892,
+      "eval_runtime": 0.6873,
+      "eval_samples_per_second": 403.001,
+      "eval_steps_per_second": 13.094,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6606498194945848,
+      "eval_loss": 0.6855643391609192,
+      "eval_runtime": 0.6794,
+      "eval_samples_per_second": 407.709,
+      "eval_steps_per_second": 13.247,
+      "step": 234
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 702,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.3696170960550694,
+    "learning_rate": 4.078854927314618e-05,
+    "max_seq_length": 256,
+    "num_train_epochs": 9,
+    "per_device_train_batch_size": 32
+  }
+}

run-11/checkpoint-234/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86a6fb49832edf5c98c28420cdc451282412f1028f0865d86090d311e06db35
+size 5304

run-11/checkpoint-312/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-11/checkpoint-312/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aee98943808cb5ea19800bdbf206aff473c8a05a490d5eb030ff65cd4c86da2
+size 437958648

run-11/checkpoint-312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:963dd7ac4f43d42a50e4a9ec59ad2b3ad30af63a91c8f188b88e147c59e5dbee
+size 876038394

run-11/checkpoint-312/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1a4990042dba800f8bdd3161c3d4f03f32aec4981e4c59a23be760f07f9773
+size 14244

run-11/checkpoint-312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a2c201efeedfef0f8c896606718047abf81d3dca7112a8a5efed460a37ba39
+size 1064

run-11/checkpoint-312/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-11/checkpoint-312/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-11/checkpoint-312/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": 0.6642599277978339,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-11/checkpoint-156",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 312,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6498194945848376,
+      "eval_loss": 0.654392421245575,
+      "eval_runtime": 0.6743,
+      "eval_samples_per_second": 410.767,
+      "eval_steps_per_second": 13.346,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6642599277978339,
+      "eval_loss": 0.6084265112876892,
+      "eval_runtime": 0.6873,
+      "eval_samples_per_second": 403.001,
+      "eval_steps_per_second": 13.094,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6606498194945848,
+      "eval_loss": 0.6855643391609192,
+      "eval_runtime": 0.6794,
+      "eval_samples_per_second": 407.709,
+      "eval_steps_per_second": 13.247,
+      "step": 234
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.628158844765343,
+      "eval_loss": 1.2223302125930786,
+      "eval_runtime": 0.6764,
+      "eval_samples_per_second": 409.519,
+      "eval_steps_per_second": 13.306,
+      "step": 312
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 702,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.3696170960550694,
+    "learning_rate": 4.078854927314618e-05,
+    "max_seq_length": 256,
+    "num_train_epochs": 9,
+    "per_device_train_batch_size": 32
+  }
+}

run-11/checkpoint-312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86a6fb49832edf5c98c28420cdc451282412f1028f0865d86090d311e06db35
+size 5304

run-11/checkpoint-390/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-11/checkpoint-390/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:589a9fea6cab38938c4dffef9da3b0de0c35aa585a0b5bf49dc3310697b9d99d
+size 437958648

run-11/checkpoint-390/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a819a1a71a7835042dfebb1c931546df0013666561e64c116d70577853b47061
+size 876038394

run-11/checkpoint-390/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab7e7efc6e523fe7096c3409edac8cd4fe85d5a37151e866e2575a2cca2b359
+size 14244

run-11/checkpoint-390/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad44eb7455cbae079082a8eb6e1b4aebec4033013933fa0e314d860bd405f127
+size 1064

run-11/checkpoint-390/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-11/checkpoint-390/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-11/checkpoint-390/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": 0.6642599277978339,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-11/checkpoint-156",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 390,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6498194945848376,
+      "eval_loss": 0.654392421245575,
+      "eval_runtime": 0.6743,
+      "eval_samples_per_second": 410.767,
+      "eval_steps_per_second": 13.346,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6642599277978339,
+      "eval_loss": 0.6084265112876892,
+      "eval_runtime": 0.6873,
+      "eval_samples_per_second": 403.001,
+      "eval_steps_per_second": 13.094,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6606498194945848,
+      "eval_loss": 0.6855643391609192,
+      "eval_runtime": 0.6794,
+      "eval_samples_per_second": 407.709,
+      "eval_steps_per_second": 13.247,
+      "step": 234
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.628158844765343,
+      "eval_loss": 1.2223302125930786,
+      "eval_runtime": 0.6764,
+      "eval_samples_per_second": 409.519,
+      "eval_steps_per_second": 13.306,
+      "step": 312
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6462093862815884,
+      "eval_loss": 1.7422877550125122,
+      "eval_runtime": 0.6787,
+      "eval_samples_per_second": 408.13,
+      "eval_steps_per_second": 13.261,
+      "step": 390
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 702,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.3696170960550694,
+    "learning_rate": 4.078854927314618e-05,
+    "max_seq_length": 256,
+    "num_train_epochs": 9,
+    "per_device_train_batch_size": 32
+  }
+}

run-11/checkpoint-390/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86a6fb49832edf5c98c28420cdc451282412f1028f0865d86090d311e06db35
+size 5304

run-11/checkpoint-468/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-11/checkpoint-468/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8530d6c9a75ff91822dc98740cf29146d265b369e06c89f9ab0b02d254b9766
+size 437958648

run-11/checkpoint-468/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d57f7bb79df2e4c3ac2e9d4a18d6946d38c053e2a060637517016612704cc71
+size 876038394

run-11/checkpoint-468/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fdf0de6d254b055796bfcfbc98ddb20abec09724d2ab84450cc286ba297dd61
+size 14244

run-11/checkpoint-468/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a18e9c470ddbe98f3c8b6720ec47dcceb39ffd2cb0e8ef8dc31688df30efb9
+size 1064