Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dad4f20bb8325cf712a4ac7b165422962fb687c7bafd94e36372eba8e246812
+oid sha256:c94dd733e20fd5254b49d4ff885429ad3d9e35e34689bc8ea052bb57c2869ede
 size 437958648

run-4/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-4/checkpoint-468/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b9d727d32513dc9f7a9bb1d23baaf2fea33cc77080ab06b88b41bfad318004e
+size 437958648

run-4/checkpoint-468/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6af6a8b149a8193eed223785751b83759eb8f3bc9557be7c99c77c676027975
+size 876038394

run-4/checkpoint-468/rng_state.pth

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

run-4/checkpoint-468/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30c58396c6f5aaed5a1739daec3a15e620f96477b79d7cbf13bc8026a42d4559
+size 1064

run-4/checkpoint-468/special_tokens_map.json

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

run-4/checkpoint-468/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-4/checkpoint-468/trainer_state.json

@@ -0,0 +1,93 @@
+{
+  "best_metric": 0.6209386281588448,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-4/checkpoint-156",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 468,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.48736462093862815,
+      "eval_loss": 0.6965199708938599,
+      "eval_runtime": 0.6659,
+      "eval_samples_per_second": 416.006,
+      "eval_steps_per_second": 13.516,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6209386281588448,
+      "eval_loss": 0.6646698713302612,
+      "eval_runtime": 0.6767,
+      "eval_samples_per_second": 409.337,
+      "eval_steps_per_second": 13.3,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6028880866425993,
+      "eval_loss": 0.7253009676933289,
+      "eval_runtime": 0.6903,
+      "eval_samples_per_second": 401.276,
+      "eval_steps_per_second": 13.038,
+      "step": 234
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6173285198555957,
+      "eval_loss": 0.8552143573760986,
+      "eval_runtime": 0.6773,
+      "eval_samples_per_second": 408.954,
+      "eval_steps_per_second": 13.287,
+      "step": 312
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6028880866425993,
+      "eval_loss": 1.088321328163147,
+      "eval_runtime": 0.682,
+      "eval_samples_per_second": 406.167,
+      "eval_steps_per_second": 13.197,
+      "step": 390
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6137184115523465,
+      "eval_loss": 1.061012625694275,
+      "eval_runtime": 0.6838,
+      "eval_samples_per_second": 405.118,
+      "eval_steps_per_second": 13.163,
+      "step": 468
+    }
+  ],
+  "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": 0.3106507620625306,
+    "learning_rate": 2.082241947858954e-05,
+    "max_seq_length": 64,
+    "num_train_epochs": 7,
+    "per_device_train_batch_size": 32
+  }
+}

run-4/checkpoint-468/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5be81cb1de8a624ab3bea479cc7b6d48f487d19102523964e97f34738892498c
+size 5240

run-4/checkpoint-546/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-4/checkpoint-546/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36dce385435a29a895507a2af3f8269e3136deeda1fe1e7d2d4ae94766e8edfa
+size 437958648

run-4/checkpoint-546/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49ded9b8eec3e27856eb860ed0f2e80b934d8de28d79cc07d2e8a1e6fc726df5
+size 876038394

run-4/checkpoint-546/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:946be53fbc8e5c6c5072dff7fac4e0ae5b68bd6589561152df2e3ffdbe47d3fe
+size 14244

run-4/checkpoint-546/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80166ffd717ef38a7412d2790128a2801078420949cea3265297ef3430b4eccb
+size 1064

run-4/checkpoint-546/special_tokens_map.json

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

run-4/checkpoint-546/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-4/checkpoint-546/trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": 0.6209386281588448,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-4/checkpoint-156",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 546,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.48736462093862815,
+      "eval_loss": 0.6965199708938599,
+      "eval_runtime": 0.6659,
+      "eval_samples_per_second": 416.006,
+      "eval_steps_per_second": 13.516,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6209386281588448,
+      "eval_loss": 0.6646698713302612,
+      "eval_runtime": 0.6767,
+      "eval_samples_per_second": 409.337,
+      "eval_steps_per_second": 13.3,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6028880866425993,
+      "eval_loss": 0.7253009676933289,
+      "eval_runtime": 0.6903,
+      "eval_samples_per_second": 401.276,
+      "eval_steps_per_second": 13.038,
+      "step": 234
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6173285198555957,
+      "eval_loss": 0.8552143573760986,
+      "eval_runtime": 0.6773,
+      "eval_samples_per_second": 408.954,
+      "eval_steps_per_second": 13.287,
+      "step": 312
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6028880866425993,
+      "eval_loss": 1.088321328163147,
+      "eval_runtime": 0.682,
+      "eval_samples_per_second": 406.167,
+      "eval_steps_per_second": 13.197,
+      "step": 390
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6137184115523465,
+      "eval_loss": 1.061012625694275,
+      "eval_runtime": 0.6838,
+      "eval_samples_per_second": 405.118,
+      "eval_steps_per_second": 13.163,
+      "step": 468
+    },
+    {
+      "epoch": 6.410256410256411,
+      "grad_norm": 7.283018589019775,
+      "learning_rate": 1.7542697729214633e-06,
+      "loss": 0.429,
+      "step": 500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6064981949458483,
+      "eval_loss": 1.1389989852905273,
+      "eval_runtime": 0.698,
+      "eval_samples_per_second": 396.872,
+      "eval_steps_per_second": 12.895,
+      "step": 546
+    }
+  ],
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1050076221941760.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.3106507620625306,
+    "learning_rate": 2.082241947858954e-05,
+    "max_seq_length": 64,
+    "num_train_epochs": 7,
+    "per_device_train_batch_size": 32
+  }
+}

run-4/checkpoint-546/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5be81cb1de8a624ab3bea479cc7b6d48f487d19102523964e97f34738892498c
+size 5240

run-6/checkpoint-78/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-6/checkpoint-78/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c94dd733e20fd5254b49d4ff885429ad3d9e35e34689bc8ea052bb57c2869ede
+size 437958648

run-6/checkpoint-78/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90d20233ed242d4a21ad9a63cfe2ea0b608977abdaa883c21585c6076070be20
+size 876038394

run-6/checkpoint-78/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd53c5c3dd7d411230f105bda2473d2a3923ae5b6e14f965bb99d91f5a28c9b2
+size 14244

run-6/checkpoint-78/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:317950ddaa5d62588a5831d94acaf059c0b5f1c11f77deee13a4fa3c48db44e2
+size 1064

run-6/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-6/checkpoint-78/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-6/checkpoint-78/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": 0.6173285198555957,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-6/checkpoint-78",
+  "epoch": 1.0,
+  "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": 0.6173285198555957,
+      "eval_loss": 0.6599248051643372,
+      "eval_runtime": 0.671,
+      "eval_samples_per_second": 412.835,
+      "eval_steps_per_second": 13.413,
+      "step": 78
+    }
+  ],
+  "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": 0.3770050043353135,
+    "learning_rate": 4.5879078314079037e-05,
+    "max_seq_length": 256,
+    "num_train_epochs": 9,
+    "per_device_train_batch_size": 32
+  }
+}

run-6/checkpoint-78/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8857fa298894494dd4e60cf6903099108d9727ab84eed16d135974865f7eb4
+size 5304

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5be81cb1de8a624ab3bea479cc7b6d48f487d19102523964e97f34738892498c
-size 5240
+oid sha256:8e8857fa298894494dd4e60cf6903099108d9727ab84eed16d135974865f7eb4
+size 5304