Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7725531aff7ea684b5ce01d879615089faaec01188ac2b4be3aae2c5097dc6cb
+oid sha256:c053fa33e6c4d90609a6b1b91d5c3feb37ca677b4ae4db8ba190f7229f6fc8ec
 size 437958648

run-3/checkpoint-273/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-3/checkpoint-273/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d3767a72724c2c58b2c81e0562d8413e9d4f5caeb1b9fdaa27df4b7e0d75f7a
+size 437958648

run-3/checkpoint-273/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad788d04fc311e9ddc6d828189aa0f2432c22fa5b9d27ce3d4aadd81ea99bc12
+size 876038394

run-3/checkpoint-273/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e8cce1ef4c90f8213d96cc748629114d15c258c4382451d6e5f2b05e004b38
+size 14244

run-3/checkpoint-273/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:054928b15a24e6e260d45f8d13f6cc96f46307deb52269e62b6f2d485ad3bdec
+size 1064

run-3/checkpoint-273/special_tokens_map.json

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

run-3/checkpoint-273/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-3/checkpoint-273/trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_global_step": 117,
+  "best_metric": 0.5270758122743683,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-3/checkpoint-117",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 273,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7352272868156433,
+      "eval_runtime": 3.9598,
+      "eval_samples_per_second": 69.952,
+      "eval_steps_per_second": 1.263,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.705345869064331,
+      "eval_runtime": 3.922,
+      "eval_samples_per_second": 70.627,
+      "eval_steps_per_second": 1.275,
+      "step": 78
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.7159296870231628,
+      "eval_runtime": 3.871,
+      "eval_samples_per_second": 71.558,
+      "eval_steps_per_second": 1.292,
+      "step": 117
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7200120091438293,
+      "eval_runtime": 4.0328,
+      "eval_samples_per_second": 68.686,
+      "eval_steps_per_second": 1.24,
+      "step": 156
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6923828721046448,
+      "eval_runtime": 3.9431,
+      "eval_samples_per_second": 70.249,
+      "eval_steps_per_second": 1.268,
+      "step": 195
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.703078031539917,
+      "eval_runtime": 3.8951,
+      "eval_samples_per_second": 71.114,
+      "eval_steps_per_second": 1.284,
+      "step": 234
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6917700171470642,
+      "eval_runtime": 3.943,
+      "eval_samples_per_second": 70.251,
+      "eval_steps_per_second": 1.268,
+      "step": 273
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "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": {
+    "learning_rate": 0.00034808787914393757,
+    "num_train_epochs": 8,
+    "per_device_train_batch_size": 64
+  }
+}

run-3/checkpoint-273/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5644c7f94f0e1545e85b4f41ff61b79163592688c536fd858ee23f77dc3e81ff
+size 5432

run-3/checkpoint-312/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-3/checkpoint-312/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1cece9be192bf4dcb99bd866ac9a4ceb6887ea9d9cdb796a4ffc485e715775
+size 437958648

run-3/checkpoint-312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da789c9414d1dbccbf70723a556b01a9793b82621cf1a51ab782151d43e0bb2
+size 876038394

run-3/checkpoint-312/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041e5d2bdc96990e0f8434bff7eca89d140a37db560a1650bb86e91bcb8ea319
+size 14244

run-3/checkpoint-312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a34cbbda5e5162d089d2fb7675179b31f7d3194dcc05a0257443365dd225366a
+size 1064

run-3/checkpoint-312/special_tokens_map.json

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

run-3/checkpoint-312/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-3/checkpoint-312/trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_global_step": 117,
+  "best_metric": 0.5270758122743683,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-3/checkpoint-117",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 312,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7352272868156433,
+      "eval_runtime": 3.9598,
+      "eval_samples_per_second": 69.952,
+      "eval_steps_per_second": 1.263,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.705345869064331,
+      "eval_runtime": 3.922,
+      "eval_samples_per_second": 70.627,
+      "eval_steps_per_second": 1.275,
+      "step": 78
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.7159296870231628,
+      "eval_runtime": 3.871,
+      "eval_samples_per_second": 71.558,
+      "eval_steps_per_second": 1.292,
+      "step": 117
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.7200120091438293,
+      "eval_runtime": 4.0328,
+      "eval_samples_per_second": 68.686,
+      "eval_steps_per_second": 1.24,
+      "step": 156
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6923828721046448,
+      "eval_runtime": 3.9431,
+      "eval_samples_per_second": 70.249,
+      "eval_steps_per_second": 1.268,
+      "step": 195
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.703078031539917,
+      "eval_runtime": 3.8951,
+      "eval_samples_per_second": 71.114,
+      "eval_steps_per_second": 1.284,
+      "step": 234
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6917700171470642,
+      "eval_runtime": 3.943,
+      "eval_samples_per_second": 70.251,
+      "eval_steps_per_second": 1.268,
+      "step": 273
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6957749724388123,
+      "eval_runtime": 3.8397,
+      "eval_samples_per_second": 72.142,
+      "eval_steps_per_second": 1.302,
+      "step": 312
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "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": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 0.00034808787914393757,
+    "num_train_epochs": 8,
+    "per_device_train_batch_size": 64
+  }
+}

run-3/checkpoint-312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5644c7f94f0e1545e85b4f41ff61b79163592688c536fd858ee23f77dc3e81ff
+size 5432

run-4/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-4/checkpoint-39/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c053fa33e6c4d90609a6b1b91d5c3feb37ca677b4ae4db8ba190f7229f6fc8ec
+size 437958648

run-4/checkpoint-39/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c6a84c592c14e38bd89dbae99b5b5a2790b85e9d93072ea33f7e4d55de95a6
+size 876038394

run-4/checkpoint-39/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afca84cca3e41f31adc342431bd2ff157dddd1608dfba762abc0e1c205d7595e
+size 14244

run-4/checkpoint-39/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97730fa92ba3d5dcb3eab7c7d1f37ef74c58e43183c7c17f46e6460f5dcd931d
+size 1064

run-4/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-4/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-4/checkpoint-39/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_global_step": 39,
+  "best_metric": 0.5270758122743683,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-4/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": 0.5270758122743683,
+      "eval_loss": 0.688007116317749,
+      "eval_runtime": 4.062,
+      "eval_samples_per_second": 68.193,
+      "eval_steps_per_second": 1.231,
+      "step": 39
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 390,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": {
+    "learning_rate": 1.2006381357099625e-05,
+    "num_train_epochs": 10,
+    "per_device_train_batch_size": 64
+  }
+}

run-4/checkpoint-39/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b540180ff0b98848a471f26357611814f20b9156c28d0318e00c76cc1e5426
+size 5432

runs/Apr10_11-55-59_972d5d989ccb/events.out.tfevents.1744289575.972d5d989ccb.224.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a6ed46340a88aba66c78800f9e2373a1b258b3f6b722d3e538d2c686075bf2
+size 6054

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5644c7f94f0e1545e85b4f41ff61b79163592688c536fd858ee23f77dc3e81ff
+oid sha256:08b540180ff0b98848a471f26357611814f20b9156c28d0318e00c76cc1e5426
 size 5432