Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4899587d098a4fe93c64c694a1e17c8c5488c4d7e7698f0aa681528692de7eb0
+oid sha256:f6ac2c1ec716da94c884cbba4a5fd1dc4d9d686e8a30f993c8d2cd4edda50637
 size 437958648

run-1/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-1/checkpoint-390/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e1b697007cc3f9b6af93a88da4bbf87c401ec39951aa8b7ee0ee9b61b40ed3
+size 437958648

run-1/checkpoint-390/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99201520102ea3deb72ef400fc6883ecbadf53230be9c022c49f9ec3f93f441f
+size 876038394

run-1/checkpoint-390/rng_state.pth

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

run-1/checkpoint-390/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe660754a2f2d811653614355d928f761a5c894c58e3c49da7d80bb97760a91
+size 1064

run-1/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-1/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-1/checkpoint-390/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": 0.6353790613718412,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-78",
+  "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": 0.6353790613718412,
+      "eval_loss": 0.6770245432853699,
+      "eval_runtime": 0.6647,
+      "eval_samples_per_second": 416.704,
+      "eval_steps_per_second": 13.539,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5992779783393501,
+      "eval_loss": 0.6672807335853577,
+      "eval_runtime": 0.6754,
+      "eval_samples_per_second": 410.102,
+      "eval_steps_per_second": 13.325,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6245487364620939,
+      "eval_loss": 0.9171745181083679,
+      "eval_runtime": 0.6735,
+      "eval_samples_per_second": 411.293,
+      "eval_steps_per_second": 13.363,
+      "step": 234
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6209386281588448,
+      "eval_loss": 0.9220866560935974,
+      "eval_runtime": 0.6833,
+      "eval_samples_per_second": 405.376,
+      "eval_steps_per_second": 13.171,
+      "step": 312
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.628158844765343,
+      "eval_loss": 1.6059069633483887,
+      "eval_runtime": 0.7073,
+      "eval_samples_per_second": 391.627,
+      "eval_steps_per_second": 12.724,
+      "step": 390
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 390,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.4335800030221564,
+    "learning_rate": 9.436810464836678e-05,
+    "max_seq_length": 64,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32
+  }
+}

run-1/checkpoint-390/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22c503059a814a22403e32be9aff627d9f6a3b6f2b72fd17968d6d5fa444258
+size 5240

run-2/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-2/checkpoint-78/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ac2c1ec716da94c884cbba4a5fd1dc4d9d686e8a30f993c8d2cd4edda50637
+size 437958648

run-2/checkpoint-78/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8717ae482a6e01000b2ece674bde4e1f1b0f9887fcb8371ec67ca54938b799
+size 876038394

run-2/checkpoint-78/rng_state.pth

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

run-2/checkpoint-78/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e59833b7e34c457c7b60ce82d4ad7fd06ffffd8003ab50080930ee3229d356
+size 1064

run-2/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-2/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-2/checkpoint-78/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": 0.5379061371841155,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-2/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": 0.5379061371841155,
+      "eval_loss": 0.6875276565551758,
+      "eval_runtime": 0.6682,
+      "eval_samples_per_second": 414.568,
+      "eval_steps_per_second": 13.47,
+      "step": 78
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 234,
+  "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": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.3814095642771822,
+    "learning_rate": 1.583371021730821e-05,
+    "max_seq_length": 128,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32
+  }
+}

run-2/checkpoint-78/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3732bb3c272cd2bb4d4158830cc02b5495f820272eff843f24a2f9a3f896652a
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c22c503059a814a22403e32be9aff627d9f6a3b6f2b72fd17968d6d5fa444258
+oid sha256:3732bb3c272cd2bb4d4158830cc02b5495f820272eff843f24a2f9a3f896652a
 size 5240