Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72165d5df0d1fd587ab1e25a3e24ba9b919b3e3b81140d2d33db356e47e25d20
+oid sha256:5b9a6ffb4850ba563bfc29057df7eca272aea725ec6291a3c6e50375edb16a06
 size 437958648

run-8/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": "4.50.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-8/checkpoint-312/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95787563bbf692ca6c522a112bba14d09cd73cec4ed589bbdea166ce3c0421bf
+size 437958648

run-8/checkpoint-312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd506866583965cee17c9f4e7ee1b1807728dc367e4215b371a180009f3aa99
+size 876038394

run-8/checkpoint-312/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d0d2c188a811beecdcb8d141644a9877cfc40250ce371b521f578d956a42a2f
+size 14244

run-8/checkpoint-312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8d72bf9b9a02bef196d3d7103c77f0b4420bb52052256fcc497fdff00935a8a
+size 1064

run-8/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-8/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-8/checkpoint-312/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_global_step": 312,
+  "best_metric": 0.6425992779783394,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-8/checkpoint-312",
+  "epoch": 2.0,
+  "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": 0.5342960288808665,
+      "eval_loss": 0.689421534538269,
+      "eval_runtime": 1.8851,
+      "eval_samples_per_second": 146.945,
+      "eval_steps_per_second": 4.774,
+      "step": 156
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6425992779783394,
+      "eval_loss": 0.6595048308372498,
+      "eval_runtime": 1.9025,
+      "eval_samples_per_second": 145.597,
+      "eval_steps_per_second": 4.731,
+      "step": 312
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 624,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 16,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_prob": 0.2844968059597932,
+    "learning_rate": 8.569403178386092e-06,
+    "max_length": 512,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16
+  }
+}

run-8/checkpoint-312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5921434ea59283336be21d8ab0a4ae756feae9fa1c43aca804730744bec53113
+size 5432

run-8/checkpoint-468/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": "4.50.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-8/checkpoint-468/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5808db5ffa01d60f2a6f0269c8153c74e508888c2f5ff35f41edcbca472004bd
+size 437958648

run-8/checkpoint-468/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab088be7178ea8a8aa427f22b9a3b4b797d50f493af95e6cbc142cfc54ee317
+size 876038394

run-8/checkpoint-468/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cd25910825ec3ed29de217bb81fddff7f920ee8f10f536071bc7a30e7cb096f
+size 14244

run-8/checkpoint-468/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0abef3800094d0c4b1f78d6601a703236741dabe5924c714af9958c54c20084b
+size 1064

run-8/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-8/checkpoint-468/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-8/checkpoint-468/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_global_step": 312,
+  "best_metric": 0.6425992779783394,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-8/checkpoint-312",
+  "epoch": 3.0,
+  "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": 0.5342960288808665,
+      "eval_loss": 0.689421534538269,
+      "eval_runtime": 1.8851,
+      "eval_samples_per_second": 146.945,
+      "eval_steps_per_second": 4.774,
+      "step": 156
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6425992779783394,
+      "eval_loss": 0.6595048308372498,
+      "eval_runtime": 1.9025,
+      "eval_samples_per_second": 145.597,
+      "eval_steps_per_second": 4.731,
+      "step": 312
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6101083032490975,
+      "eval_loss": 0.701920747756958,
+      "eval_runtime": 1.9131,
+      "eval_samples_per_second": 144.789,
+      "eval_steps_per_second": 4.704,
+      "step": 468
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 624,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 16,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_prob": 0.2844968059597932,
+    "learning_rate": 8.569403178386092e-06,
+    "max_length": 512,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16
+  }
+}

run-8/checkpoint-468/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5921434ea59283336be21d8ab0a4ae756feae9fa1c43aca804730744bec53113
+size 5432

run-8/checkpoint-624/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": "4.50.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-8/checkpoint-624/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dbda4dabf0a3b9afd452b3c56b5a39dffdc2c1e119dc8af2c0156dad5a6a769
+size 437958648

run-8/checkpoint-624/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:598bbb630bb413e8d886658945d6a4de5827ad4ae21f3e42345556c08dbba120
+size 876038394

run-8/checkpoint-624/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36b7b76e4aa4142b7a5681b78e8136bbf89a42f16e69e522c0009f1b9e20aa53
+size 14244

run-8/checkpoint-624/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2239e8580a419f2779161d44ee84fc8d4a8d46fc865ffb47b71687a7d49c8b
+size 1064

run-8/checkpoint-624/special_tokens_map.json

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

run-8/checkpoint-624/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-8/checkpoint-624/trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_global_step": 624,
+  "best_metric": 0.6570397111913358,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-8/checkpoint-624",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 624,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5342960288808665,
+      "eval_loss": 0.689421534538269,
+      "eval_runtime": 1.8851,
+      "eval_samples_per_second": 146.945,
+      "eval_steps_per_second": 4.774,
+      "step": 156
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6425992779783394,
+      "eval_loss": 0.6595048308372498,
+      "eval_runtime": 1.9025,
+      "eval_samples_per_second": 145.597,
+      "eval_steps_per_second": 4.731,
+      "step": 312
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6101083032490975,
+      "eval_loss": 0.701920747756958,
+      "eval_runtime": 1.9131,
+      "eval_samples_per_second": 144.789,
+      "eval_steps_per_second": 4.704,
+      "step": 468
+    },
+    {
+      "epoch": 3.2051282051282053,
+      "grad_norm": 6.512232780456543,
+      "learning_rate": 1.702894221345954e-06,
+      "loss": 0.62,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6570397111913358,
+      "eval_loss": 0.6833600997924805,
+      "eval_runtime": 1.8684,
+      "eval_samples_per_second": 148.252,
+      "eval_steps_per_second": 4.817,
+      "step": 624
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 624,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 675295079132640.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_prob": 0.2844968059597932,
+    "learning_rate": 8.569403178386092e-06,
+    "max_length": 512,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16
+  }
+}

run-8/checkpoint-624/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5921434ea59283336be21d8ab0a4ae756feae9fa1c43aca804730744bec53113
+size 5432

run-9/checkpoint-156/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": "4.50.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-9/checkpoint-156/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b9a6ffb4850ba563bfc29057df7eca272aea725ec6291a3c6e50375edb16a06
+size 437958648

run-9/checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3094b1bdf39bd76595901eb37671ed31501cf9686a39d70300fa8eacfa2f900
+size 876038394

run-9/checkpoint-156/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c08f3ee56cb0c8179e472791dd9c939931284445a70f9f9379b0b3e4b2670bd
+size 14244

run-9/checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3d1109fce6cb08b519485c7b22d483c93f343a96f8d44d3955909d235d4002f
+size 1064

run-9/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-9/checkpoint-156/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-9/checkpoint-156/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_global_step": 156,
+  "best_metric": 0.6101083032490975,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-9/checkpoint-156",
+  "epoch": 1.0,
+  "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": 0.6101083032490975,
+      "eval_loss": 0.653643012046814,
+      "eval_runtime": 1.8408,
+      "eval_samples_per_second": 150.479,
+      "eval_steps_per_second": 4.889,
+      "step": 156
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 780,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_prob": 0.4726254000746759,
+    "learning_rate": 2.224337433152446e-05,
+    "max_length": 128,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16
+  }
+}

run-9/checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a252109aa6ad3ae340fafeb8b0f2eefc98a32ff01a529423eaecebb450d0abe7
+size 5432

runs/Apr03_16-04-20_262bc2ef345e/events.out.tfevents.1743699345.262bc2ef345e.187.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25d2d274d3355fd2afa88a2af6dcb2d272fae5617c1cc5bbaf6390fe9e50f5a9
+size 5747

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5921434ea59283336be21d8ab0a4ae756feae9fa1c43aca804730744bec53113
+oid sha256:a252109aa6ad3ae340fafeb8b0f2eefc98a32ff01a529423eaecebb450d0abe7
 size 5432