Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68ef9bbcdf0b9c43a5560584a060131419ec777c3ea8a2100314604bffe200d5
+oid sha256:a7b1ce95cf26f9cf0a81ff3e0a6cfc35703eece360a4200497fa557c1642d043
 size 437958648

run-14/checkpoint-78/config.json

@@ -0,0 +1,26 @@
+{
+  "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": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-14/checkpoint-78/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228f113606458d83d51457fcaead6ba675e11331a4f1979ce592c33c8fac2d0a
+size 437958648

run-14/checkpoint-78/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9681b69d67273778bd89b112493f52c85a993b3c5e7ec239ad49fef7b94ec87
+size 876038394

run-14/checkpoint-78/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2359103b6aecc5a33be9630634e2521d802ca571eca1b4adeac3ec6496c46f19
+size 14244

run-14/checkpoint-78/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc05072d215bec5149531a1ea9f4923a4e3d5ffc5decf0ccbb36303f24c21e0
+size 1064

run-14/checkpoint-78/special_tokens_map.json

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

run-14/checkpoint-78/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-14/checkpoint-78/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_global_step": 78,
+  "best_metric": 0.5234657039711191,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-14/checkpoint-78",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 78,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.51985559566787,
+      "eval_loss": 0.6934137940406799,
+      "eval_runtime": 2.0528,
+      "eval_samples_per_second": 134.938,
+      "eval_steps_per_second": 2.436,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5234657039711191,
+      "eval_loss": 0.6922642588615417,
+      "eval_runtime": 2.1157,
+      "eval_samples_per_second": 130.928,
+      "eval_steps_per_second": 2.363,
+      "step": 78
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 117,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 64,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.4393287952671322,
+    "learning_rate": 7.152156305086729e-06,
+    "max_seq_length": 128,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64
+  }
+}

run-14/checkpoint-78/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e275261fbf5af4f76416c04e56b1bddc966df7d60fc8547a702c5123da3e39ab
+size 5432

run-15/checkpoint-39/config.json

@@ -0,0 +1,26 @@
+{
+  "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": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-15/checkpoint-39/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f5ce2bfdc1595aea38908cab2fb5c83c5e03d5d33e52afabb55eaa7b4432f5a
+size 437958648

run-15/checkpoint-39/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84d875c3c7dd24f92ebd65b288bfb3f0c4a0aab73fbb70e12936d1d5c59b1559
+size 876038394

run-15/checkpoint-39/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb9d75225831e9955fede3b2d004809f8a35dbd2208354c70b53a96923288fdc
+size 14244

run-15/checkpoint-39/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9655534235b2ef552806a0b8f42df42815113a1c45de2eee38916ea953dd1a96
+size 1064

run-15/checkpoint-39/special_tokens_map.json

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

run-15/checkpoint-39/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-15/checkpoint-39/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_global_step": 39,
+  "best_metric": 0.5126353790613718,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-15/checkpoint-39",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 39,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5126353790613718,
+      "eval_loss": 0.6933870315551758,
+      "eval_runtime": 2.0573,
+      "eval_samples_per_second": 134.64,
+      "eval_steps_per_second": 2.43,
+      "step": 39
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 117,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 64,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.4368409139165982,
+    "learning_rate": 7.180479236862086e-06,
+    "max_seq_length": 128,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64
+  }
+}

run-15/checkpoint-39/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74db5e3bcf26cdd26cfccab7a00e044ef65e0673c2cbe11ecbc9efae47e8c832
+size 5432

run-15/checkpoint-78/config.json

@@ -0,0 +1,26 @@
+{
+  "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": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-15/checkpoint-78/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed5eafe82338075354d078ecba1100fd3282e7a9afef245825a583c005ca5a90
+size 437958648

run-15/checkpoint-78/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5150a582fb2133696f8dd95c17a21e3db0e2977726be4ec4e16f04712534a629
+size 876038394

run-15/checkpoint-78/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2359103b6aecc5a33be9630634e2521d802ca571eca1b4adeac3ec6496c46f19
+size 14244

run-15/checkpoint-78/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0997eccd966c1765ebb135f02f09b7a22fd7cba344c18d9d91e9323222260ab2
+size 1064

run-15/checkpoint-78/special_tokens_map.json

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

run-15/checkpoint-78/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-15/checkpoint-78/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_global_step": 78,
+  "best_metric": 0.5234657039711191,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-15/checkpoint-78",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 78,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5126353790613718,
+      "eval_loss": 0.6933870315551758,
+      "eval_runtime": 2.0573,
+      "eval_samples_per_second": 134.64,
+      "eval_steps_per_second": 2.43,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5234657039711191,
+      "eval_loss": 0.6921409368515015,
+      "eval_runtime": 2.1409,
+      "eval_samples_per_second": 129.385,
+      "eval_steps_per_second": 2.335,
+      "step": 78
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 117,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 64,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.4368409139165982,
+    "learning_rate": 7.180479236862086e-06,
+    "max_seq_length": 128,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64
+  }
+}

run-15/checkpoint-78/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74db5e3bcf26cdd26cfccab7a00e044ef65e0673c2cbe11ecbc9efae47e8c832
+size 5432

run-16/checkpoint-39/config.json

@@ -0,0 +1,26 @@
+{
+  "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": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-16/checkpoint-39/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b1ce95cf26f9cf0a81ff3e0a6cfc35703eece360a4200497fa557c1642d043
+size 437958648

run-16/checkpoint-39/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea9a67d005699dcbe00e3220541fe2ee90700ead0bf9812db5836c662a054263
+size 876038394

run-16/checkpoint-39/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb9d75225831e9955fede3b2d004809f8a35dbd2208354c70b53a96923288fdc
+size 14244

run-16/checkpoint-39/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:accfe0e1676f9151f6c5875262ed5c9b368b0785771e3beac15870a4a149d872
+size 1064

run-16/checkpoint-39/special_tokens_map.json

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

run-16/checkpoint-39/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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-16/checkpoint-39/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_global_step": 39,
+  "best_metric": 0.5234657039711191,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-16/checkpoint-39",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 39,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5234657039711191,
+      "eval_loss": 0.6925029754638672,
+      "eval_runtime": 2.039,
+      "eval_samples_per_second": 135.851,
+      "eval_steps_per_second": 2.452,
+      "step": 39
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 117,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 64,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.44098302544765366,
+    "learning_rate": 8.083678512733892e-06,
+    "max_seq_length": 128,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64
+  }
+}

run-16/checkpoint-39/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:146fbdf2834cbef3d85afd15584c2fb23e7839c30f3f8ae9ec29ef0284462cc5
+size 5432

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e275261fbf5af4f76416c04e56b1bddc966df7d60fc8547a702c5123da3e39ab
+oid sha256:146fbdf2834cbef3d85afd15584c2fb23e7839c30f3f8ae9ec29ef0284462cc5
 size 5432