Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1dbce98f3d950879926c2d466908ef43f449be641f52614ec113ba49b10d447
+oid sha256:7a36d3c7e5e28355d4818a4c05cb010abeb9fb8aebd147ae1dab52df1b364ace
 size 437958648

run-7/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-7/checkpoint-156/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a2bdb39300049b03abb324ef2c9c5c87ce65800a07e97612112381ac00c923f
+size 437958648

run-7/checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75f4ee0e4d7ad8945764c3e68c526e8952bea76505b04c011b86fe6894242fad
+size 876038394

run-7/checkpoint-156/rng_state.pth

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

run-7/checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741030cb2d4b2e2f41e23a6d5817bf1c33f0dadb5de2fa6e5c2f23ea7716fad2
+size 1064

run-7/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-7/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-7/checkpoint-156/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.6859205776173285,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-7/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": 0.628158844765343,
+      "eval_loss": 0.631028950214386,
+      "eval_runtime": 0.66,
+      "eval_samples_per_second": 419.684,
+      "eval_steps_per_second": 13.636,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6859205776173285,
+      "eval_loss": 0.6369927525520325,
+      "eval_runtime": 0.6697,
+      "eval_samples_per_second": 413.634,
+      "eval_steps_per_second": 13.439,
+      "step": 156
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 546,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 0.11155873989069165,
+    "learning_rate": 4.329363431290077e-05,
+    "max_seq_length": 128,
+    "num_train_epochs": 7,
+    "per_device_train_batch_size": 32
+  }
+}

run-7/checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a6e0f4b89f8339b44d2921a368ac3573d7d5e11448a30b11f432a00dea58d23
+size 5240

run-7/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-7/checkpoint-234/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acdbc4b35dbfaa60befc01bf5809a6e59ece63b0d61dcce5edab3f5ce72e69dc
+size 437958648

run-7/checkpoint-234/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcdf5c5d7dfa02d02470b7273ce7c64a4d83f2ce75c234c5f336c7f75677a0c6
+size 876038394

run-7/checkpoint-234/rng_state.pth

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

run-7/checkpoint-234/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:215a738ce09207d2474ec5de1404ff5799ba4bbb09d34debcd8a222473821f86
+size 1064

run-7/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-7/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-7/checkpoint-234/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.6859205776173285,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-7/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": 0.628158844765343,
+      "eval_loss": 0.631028950214386,
+      "eval_runtime": 0.66,
+      "eval_samples_per_second": 419.684,
+      "eval_steps_per_second": 13.636,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6859205776173285,
+      "eval_loss": 0.6369927525520325,
+      "eval_runtime": 0.6697,
+      "eval_samples_per_second": 413.634,
+      "eval_steps_per_second": 13.439,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6678700361010831,
+      "eval_loss": 0.9578478336334229,
+      "eval_runtime": 0.6799,
+      "eval_samples_per_second": 407.431,
+      "eval_steps_per_second": 13.238,
+      "step": 234
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 546,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 0.11155873989069165,
+    "learning_rate": 4.329363431290077e-05,
+    "max_seq_length": 128,
+    "num_train_epochs": 7,
+    "per_device_train_batch_size": 32
+  }
+}

run-7/checkpoint-234/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a6e0f4b89f8339b44d2921a368ac3573d7d5e11448a30b11f432a00dea58d23
+size 5240

run-7/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-7/checkpoint-312/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5d2a358d59b3c7b597a43608175b9f07de7fe59ddbd085af55e0d2d31eb80f4
+size 437958648

run-7/checkpoint-312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:558cd84b1312d5534161602c1bd592ae6efb30a69022dd7749ed675798f1fb7d
+size 876038394

run-7/checkpoint-312/rng_state.pth

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

run-7/checkpoint-312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b0ba67afbc69a73513d4675e04c386d2bf0445851edd56839e42e450a4ab56a
+size 1064

run-7/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-7/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-7/checkpoint-312/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": 0.6859205776173285,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-7/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": 0.628158844765343,
+      "eval_loss": 0.631028950214386,
+      "eval_runtime": 0.66,
+      "eval_samples_per_second": 419.684,
+      "eval_steps_per_second": 13.636,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6859205776173285,
+      "eval_loss": 0.6369927525520325,
+      "eval_runtime": 0.6697,
+      "eval_samples_per_second": 413.634,
+      "eval_steps_per_second": 13.439,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6678700361010831,
+      "eval_loss": 0.9578478336334229,
+      "eval_runtime": 0.6799,
+      "eval_samples_per_second": 407.431,
+      "eval_steps_per_second": 13.238,
+      "step": 234
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6642599277978339,
+      "eval_loss": 1.3767695426940918,
+      "eval_runtime": 0.6798,
+      "eval_samples_per_second": 407.485,
+      "eval_steps_per_second": 13.24,
+      "step": 312
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 546,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 0.11155873989069165,
+    "learning_rate": 4.329363431290077e-05,
+    "max_seq_length": 128,
+    "num_train_epochs": 7,
+    "per_device_train_batch_size": 32
+  }
+}

run-7/checkpoint-312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a6e0f4b89f8339b44d2921a368ac3573d7d5e11448a30b11f432a00dea58d23
+size 5240

run-7/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-7/checkpoint-390/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b046ea9ea7377c68369df6fc3bc921f3a1f8d47760d35b91e721263e6131b51
+size 437958648

run-7/checkpoint-390/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4468ee3acfe22782ed4043e9c3654e46bd5cb5c3414ba641f704a3174fbbd0ff
+size 876038394

run-7/checkpoint-390/rng_state.pth

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

run-7/checkpoint-390/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae204fcf0b4047412582492c46b3b8be7d7544d0fdd0f5d1f87f177e0ab311bb
+size 1064

run-7/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-7/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-7/checkpoint-390/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": 0.6859205776173285,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-7/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": 0.628158844765343,
+      "eval_loss": 0.631028950214386,
+      "eval_runtime": 0.66,
+      "eval_samples_per_second": 419.684,
+      "eval_steps_per_second": 13.636,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6859205776173285,
+      "eval_loss": 0.6369927525520325,
+      "eval_runtime": 0.6697,
+      "eval_samples_per_second": 413.634,
+      "eval_steps_per_second": 13.439,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6678700361010831,
+      "eval_loss": 0.9578478336334229,
+      "eval_runtime": 0.6799,
+      "eval_samples_per_second": 407.431,
+      "eval_steps_per_second": 13.238,
+      "step": 234
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6642599277978339,
+      "eval_loss": 1.3767695426940918,
+      "eval_runtime": 0.6798,
+      "eval_samples_per_second": 407.485,
+      "eval_steps_per_second": 13.24,
+      "step": 312
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6534296028880866,
+      "eval_loss": 1.6084797382354736,
+      "eval_runtime": 0.678,
+      "eval_samples_per_second": 408.534,
+      "eval_steps_per_second": 13.274,
+      "step": 390
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 546,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 0.11155873989069165,
+    "learning_rate": 4.329363431290077e-05,
+    "max_seq_length": 128,
+    "num_train_epochs": 7,
+    "per_device_train_batch_size": 32
+  }
+}

run-7/checkpoint-390/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a6e0f4b89f8339b44d2921a368ac3573d7d5e11448a30b11f432a00dea58d23
+size 5240

run-7/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-7/checkpoint-468/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:406242da2f62c8ddaa77ba4b2bfbacda2c25621302eb3ec2abd2f8da90b9fefe
+size 437958648

run-7/checkpoint-468/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd3caa0b85b704e81d64ef9449a99ec3723ee81cd84072783d87686f1b782b0b
+size 876038394

run-7/checkpoint-468/rng_state.pth

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

run-7/checkpoint-468/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4113dd925e00e3c4df76e44043c8a9caa46a4bae9a15adb27ac4bd7d869609
+size 1064