Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f78425da84e5249ec0347c4d7498fc90a36b20212a0d3708f9a579091f6d3486
+oid sha256:fe0734b04a599386c06794785bd330535293caf1c8b07e37562d45198c2a61c1
 size 437958648

run-12/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-12/checkpoint-156/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81b6235305e69462b2631c3d114d2c2a236398f0bbed3a0998250f37fa3c3f67
+size 437958648

run-12/checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cc0bcb674d42278512b10721943fa1918441e482947847ac896ae809959eea2
+size 876038394

run-12/checkpoint-156/rng_state.pth

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

run-12/checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f20499ab4c7b340d9e9ab76a88345caa4528c1503e0a698554ef06548146e3
+size 1064

run-12/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-12/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-12/checkpoint-156/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.6678700361010831,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_2/run-12/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": 0.6462093862815884,
+      "eval_loss": 0.629618763923645,
+      "eval_runtime": 0.6734,
+      "eval_samples_per_second": 411.318,
+      "eval_steps_per_second": 13.364,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6678700361010831,
+      "eval_loss": 0.6215720176696777,
+      "eval_runtime": 0.7099,
+      "eval_samples_per_second": 390.188,
+      "eval_steps_per_second": 12.678,
+      "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": 0.1011620764963787,
+    "learning_rate": 3.530044593929663e-05,
+    "max_seq_length": 128,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32
+  }
+}

run-12/checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ed4370d780a8380bd6c97eed17f750416994e8b1c51e0ab0faf4f55c3af9cf
+size 5240

run-12/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-12/checkpoint-234/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174272dc14fc839ec8f233af7e54786aba7b9db2cf671e253f95974a86a3c8d8
+size 437958648

run-12/checkpoint-234/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ae1591493425da25c4e3608aedca6541b874588baf5ef98d6acae4a2c3bbce3
+size 876038394

run-12/checkpoint-234/rng_state.pth

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

run-12/checkpoint-234/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd089e93ce62acc1d4d60beaba10bfb9a52d10ca8beb787cab0f5f7b47b7a95f
+size 1064

run-12/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-12/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-12/checkpoint-234/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.6678700361010831,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_2/run-12/checkpoint-156",
+  "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": 0.6462093862815884,
+      "eval_loss": 0.629618763923645,
+      "eval_runtime": 0.6734,
+      "eval_samples_per_second": 411.318,
+      "eval_steps_per_second": 13.364,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6678700361010831,
+      "eval_loss": 0.6215720176696777,
+      "eval_runtime": 0.7099,
+      "eval_samples_per_second": 390.188,
+      "eval_steps_per_second": 12.678,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6678700361010831,
+      "eval_loss": 0.6740977168083191,
+      "eval_runtime": 0.7007,
+      "eval_samples_per_second": 395.322,
+      "eval_steps_per_second": 12.844,
+      "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": 0.1011620764963787,
+    "learning_rate": 3.530044593929663e-05,
+    "max_seq_length": 128,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32
+  }
+}

run-12/checkpoint-234/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ed4370d780a8380bd6c97eed17f750416994e8b1c51e0ab0faf4f55c3af9cf
+size 5240

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe0734b04a599386c06794785bd330535293caf1c8b07e37562d45198c2a61c1
+size 437958648

run-13/checkpoint-78/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73f45088f5ff27069cc3dcb61783175626aed163eac8297d83fecc58bb4f24e4
+size 876038394

run-13/checkpoint-78/rng_state.pth

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

run-13/checkpoint-78/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73c860388dd5e8180583409ac747e1dbf6c04191bb0e8bdd9490260068e3eec3
+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 +1,55 @@
+{
+  "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-13/checkpoint-78/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": 0.6389891696750902,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_2/run-13/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": 0.6389891696750902,
+      "eval_loss": 0.6633024215698242,
+      "eval_runtime": 0.8514,
+      "eval_samples_per_second": 325.359,
+      "eval_steps_per_second": 10.571,
+      "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": 0.10926117742613603,
+    "learning_rate": 4.464498271916028e-05,
+    "max_seq_length": 128,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32
+  }
+}

run-13/checkpoint-78/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4470ec300bf3e2198c1983bac509997338f53208fb6523e6dddf6cb0a0cd51
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97ed4370d780a8380bd6c97eed17f750416994e8b1c51e0ab0faf4f55c3af9cf
+oid sha256:ea4470ec300bf3e2198c1983bac509997338f53208fb6523e6dddf6cb0a0cd51
 size 5240