Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d8280328f4d43f1f2d7581b787c926962295e203f4d9ea1bfa8935f254377b1
+oid sha256:86109271700a6566dac67fce11e384e138d7e3ec29af851a59f573daec7c09e1
 size 437958648

run-4/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-4/checkpoint-156/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0521c192539076d612f8aadc1d320ece097574f32d7dc8f670fa9132602b3e6
+size 437958648

run-4/checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b09cca208c8eb308a7b9e0c919e714b6c4ee8f22642b8c89bde22667f61e404
+size 876038394

run-4/checkpoint-156/rng_state.pth

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

run-4/checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f33a7becb27217a0f6f272d1a17a66d314a69e7a2c1e024cd642fbe2c666d556
+size 1064

run-4/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-4/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-4/checkpoint-156/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.49097472924187724,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-4/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": 0.4620938628158845,
+      "eval_loss": 0.7019249200820923,
+      "eval_runtime": 0.7457,
+      "eval_samples_per_second": 371.487,
+      "eval_steps_per_second": 12.07,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.49097472924187724,
+      "eval_loss": 0.6936511993408203,
+      "eval_runtime": 0.7239,
+      "eval_samples_per_second": 382.649,
+      "eval_steps_per_second": 12.433,
+      "step": 156
+    }
+  ],
+  "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": 0.30108518728143985,
+    "learning_rate": 3.148408599279401e-06,
+    "max_seq_length": 32,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32
+  }
+}

run-4/checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd6a22d1663472e27c1914e551020d7e8fa7404f4c9888164cdfe945cc8b090
+size 5240

run-4/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-4/checkpoint-234/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140f45efabf348741698b52ac1c870bde9f999ea855d0c0b41b22d5925703f7f
+size 437958648

run-4/checkpoint-234/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:612b0575643c625137169a0ac056d5ecad3fdd2a52b4d8addee555e0fe167506
+size 876038394

run-4/checkpoint-234/rng_state.pth

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

run-4/checkpoint-234/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e62293677106093a7047433fac55e264d8bc93548455e5de77a76614e4b1dca8
+size 1064

run-4/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-4/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-4/checkpoint-234/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.49458483754512633,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-4/checkpoint-234",
+  "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": 0.4620938628158845,
+      "eval_loss": 0.7019249200820923,
+      "eval_runtime": 0.7457,
+      "eval_samples_per_second": 371.487,
+      "eval_steps_per_second": 12.07,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.49097472924187724,
+      "eval_loss": 0.6936511993408203,
+      "eval_runtime": 0.7239,
+      "eval_samples_per_second": 382.649,
+      "eval_steps_per_second": 12.433,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.49458483754512633,
+      "eval_loss": 0.6922197937965393,
+      "eval_runtime": 0.7344,
+      "eval_samples_per_second": 377.176,
+      "eval_steps_per_second": 12.255,
+      "step": 234
+    }
+  ],
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.30108518728143985,
+    "learning_rate": 3.148408599279401e-06,
+    "max_seq_length": 32,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32
+  }
+}

run-4/checkpoint-234/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd6a22d1663472e27c1914e551020d7e8fa7404f4c9888164cdfe945cc8b090
+size 5240

run-5/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22370544c306edc6510d82821b177a0cf03b6bd3187aee93d03fcb30d9ae77c2
+oid sha256:86109271700a6566dac67fce11e384e138d7e3ec29af851a59f573daec7c09e1
 size 437958648

run-5/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89f119ebd665f2822950d608bed6f89fdcbd5f9edab3e4bb1554bd76b322cc8d
+oid sha256:f374d082dcb68901fb2cc25ceadd44f5aac5a60c778f3f0b874c342c803a28cb
 size 876038394

run-5/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37130ce86432e86a6540ec21a58656c951f8daf1bc2e8d9d71ea344d79d0134b
+oid sha256:8653b340d09b7fdd796da649a76a5d10fb315783ad3d6b1fee9a8035e86bfa33
 size 1064

run-5/checkpoint-78/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5270758122743683,
+  "best_metric": 0.4729241877256318,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-5/checkpoint-78",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,18 +10,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6914958357810974,
-      "eval_runtime": 0.6672,
-      "eval_samples_per_second": 415.152,
-      "eval_steps_per_second": 13.489,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.706026017665863,
+      "eval_runtime": 0.7117,
+      "eval_samples_per_second": 389.212,
+      "eval_steps_per_second": 12.646,
       "step": 78
     }
   ],
   "logging_steps": 500,
-  "max_steps": 234,
+  "max_steps": 78,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -30,7 +30,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
@@ -39,10 +39,10 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.18477489177290296,
-    "learning_rate": 9.403239275856386e-05,
-    "max_seq_length": 128,
-    "num_train_epochs": 3,
+    "dropout_rate": 0.1851032629932426,
+    "learning_rate": 4.486498608182886e-06,
+    "max_seq_length": 32,
+    "num_train_epochs": 1,
     "per_device_train_batch_size": 32
   }
 }

run-5/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61b5a8c2f4c5528cbbda8daae81db05b04be07eb3f2cf93cc5023a85269a938c
+oid sha256:9ad6acdcbd930141ff6c9ddf315e98b847208cb57102c5b40f8230c5988f9790
 size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cd6a22d1663472e27c1914e551020d7e8fa7404f4c9888164cdfe945cc8b090
+oid sha256:9ad6acdcbd930141ff6c9ddf315e98b847208cb57102c5b40f8230c5988f9790
 size 5240