Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5e1af7b274ce0ecc534f29961f764063838cf0a2282ac3b59981b8468e1218e
+oid sha256:68ef9bbcdf0b9c43a5560584a060131419ec777c3ea8a2100314604bffe200d5
 size 437958648

run-12/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-12/checkpoint-78/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c1d6390e451db6a0bcd6eed9b524d9b9ce70ea4a1a65fc81629b37b52daa621
+size 437958648

run-12/checkpoint-78/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:427c3524dff174d39b3e1b9143f63bfd8e33073e60cdc952d1483b8447750a6c
+size 876038394

run-12/checkpoint-78/rng_state.pth

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

run-12/checkpoint-78/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5baeff20d261ff413cafb0b4300e58433cd114f666b2292e5533528759f0c874
+size 1064

run-12/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-12/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-12/checkpoint-78/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_global_step": 39,
+  "best_metric": 0.516245487364621,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-12/checkpoint-39",
+  "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": 0.516245487364621,
+      "eval_loss": 0.6923897862434387,
+      "eval_runtime": 2.0674,
+      "eval_samples_per_second": 133.985,
+      "eval_steps_per_second": 2.419,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.516245487364621,
+      "eval_loss": 0.6917006373405457,
+      "eval_runtime": 2.0364,
+      "eval_samples_per_second": 136.027,
+      "eval_steps_per_second": 2.455,
+      "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": 0.49849590770434266,
+    "learning_rate": 9.8774316117782e-06,
+    "max_seq_length": 128,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64
+  }
+}

run-12/checkpoint-78/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1ca0a005bc785872b17db2ffc23c9314750d805d832a90b96cf4d868c36631
+size 5432

run-13/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-13/checkpoint-39/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd2b05ed7546ad8d82965769b505144cf9c0f5df037226c181609e8250ebe27
+size 437958648

run-13/checkpoint-39/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feba683a55f30daaf944f65293e3f82fc4e26551625896390f9895a0768e4503
+size 876038394

run-13/checkpoint-39/rng_state.pth

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

run-13/checkpoint-39/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa2651d640534ff43c2f19afe5403f33fb68052099e1c50e39d7e3007844f08
+size 1064

run-13/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-13/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-13/checkpoint-39/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_global_step": 39,
+  "best_metric": 0.516245487364621,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-13/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": 0.516245487364621,
+      "eval_loss": 0.6924027800559998,
+      "eval_runtime": 2.1203,
+      "eval_samples_per_second": 130.645,
+      "eval_steps_per_second": 2.358,
+      "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": 0.49872333407822034,
+    "learning_rate": 9.8114993656155e-06,
+    "max_seq_length": 128,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64
+  }
+}

run-13/checkpoint-39/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab18d5ea3c91daf153d055cfc44c13eaaa2507bf308ef5075ac810d80ffc2e7
+size 5432

run-13/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-13/checkpoint-78/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e4cba8378d9f9e0f08ce5684bf811ce609d5e83e7ef1d34984870c3f030978
+size 437958648

run-13/checkpoint-78/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83b7d6ec5a24dd2b73d140829e3d412b7e9e645c32b0fcab824f839f167d914b
+size 876038394

run-13/checkpoint-78/rng_state.pth

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

run-13/checkpoint-78/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c68867cbaf88d5e5731e23d1cf9a6e62d8204184505f521919f81bcc3cd9d55f
+size 1064

run-13/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-13/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-13/checkpoint-78/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_global_step": 39,
+  "best_metric": 0.516245487364621,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-13/checkpoint-39",
+  "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": 0.516245487364621,
+      "eval_loss": 0.6924027800559998,
+      "eval_runtime": 2.1203,
+      "eval_samples_per_second": 130.645,
+      "eval_steps_per_second": 2.358,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5090252707581228,
+      "eval_loss": 0.6917282342910767,
+      "eval_runtime": 2.1557,
+      "eval_samples_per_second": 128.497,
+      "eval_steps_per_second": 2.319,
+      "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": 0.49872333407822034,
+    "learning_rate": 9.8114993656155e-06,
+    "max_seq_length": 128,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64
+  }
+}

run-13/checkpoint-78/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab18d5ea3c91daf153d055cfc44c13eaaa2507bf308ef5075ac810d80ffc2e7
+size 5432

run-14/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-14/checkpoint-39/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ef9bbcdf0b9c43a5560584a060131419ec777c3ea8a2100314604bffe200d5
+size 437958648

run-14/checkpoint-39/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e1067118524dda8e1e2d4f328369b64f9a5903a4da9f2939e6a3073ca08369
+size 876038394

run-14/checkpoint-39/rng_state.pth

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

run-14/checkpoint-39/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ae905efaffe03aeb8da1964aa75681dc7de5901489e35b94cbee280a8a29e4
+size 1064

run-14/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-14/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-14/checkpoint-39/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_global_step": 39,
+  "best_metric": 0.51985559566787,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-14/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": 0.51985559566787,
+      "eval_loss": 0.6934137940406799,
+      "eval_runtime": 2.0528,
+      "eval_samples_per_second": 134.938,
+      "eval_steps_per_second": 2.436,
+      "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": 0.4393287952671322,
+    "learning_rate": 7.152156305086729e-06,
+    "max_seq_length": 128,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64
+  }
+}

run-14/checkpoint-39/training_args.bin

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b1ca0a005bc785872b17db2ffc23c9314750d805d832a90b96cf4d868c36631
+oid sha256:e275261fbf5af4f76416c04e56b1bddc966df7d60fc8547a702c5123da3e39ab
 size 5432