upload unixcoder inference results

graphcodebert-base-lowLR-highBatchSize/checkpoint-300/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.3,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.3,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.3,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.56.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-300/config_hyperparams.json

@@ -0,0 +1,53 @@
+{
+  "train_config": {
+    "model_name": "microsoft/graphcodebert-base",
+    "num_epochs": 1,
+    "batch_size": 256,
+    "learning_rate": 1e-06,
+    "max_length": 512,
+    "num_labels": 2,
+    "loss_type": "r-drop",
+    "focal_alpha": 1.0,
+    "focal_gamma": 2.0,
+    "r_drop_alpha": 10.0,
+    "infonce_temperature": 0.07,
+    "infonce_weight": 0.5,
+    "label_smoothing": 0.5,
+    "adversarial_epsilon": 0.5,
+    "use_swa": false,
+    "swa_start_epoch": 0,
+    "swa_lr": 1e-05,
+    "data_augmentation": true,
+    "aug_rename_prob": 0.8,
+    "aug_format_prob": 0.8,
+    "freeze_base": true,
+    "seed": 42,
+    "use_wandb": true,
+    "mixup_alpha": 1.0,
+    "low_pass_keep_ratio": 0.5,
+    "freq_consistency_weight": 0.5
+  },
+  "training_arguments": {
+    "output_dir": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/",
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 256,
+    "per_device_eval_batch_size": 512,
+    "learning_rate": 1e-06,
+    "warmup_steps": 204,
+    "weight_decay": 0.1,
+    "logging_steps": 10,
+    "eval_steps": 1000,
+    "save_steps": 50,
+    "metric_for_best_model": "macro_f1",
+    "greater_is_better": true,
+    "save_total_limit": 4,
+    "fp16": true,
+    "seed": 42
+  },
+  "training_state": {
+    "global_step": 300,
+    "epoch": 0.29354207436399216,
+    "best_metric": null,
+    "best_model_checkpoint": null
+  }
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-300/hyperparams.json

@@ -0,0 +1,35 @@
+{
+    "model_name": "microsoft/graphcodebert-base",
+    "output_dir": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/",
+    "num_epochs": 1,
+    "max_steps": -1,
+    "batch_size": 256,
+    "learning_rate": 1e-06,
+    "max_length": 512,
+    "num_labels": 2,
+    "use_wandb": true,
+    "freeze_base": true,
+    "loss_type": "r-drop",
+    "focal_alpha": 1.0,
+    "focal_gamma": 2.0,
+    "r_drop_alpha": 10.0,
+    "infonce_temperature": 0.07,
+    "infonce_weight": 0.5,
+    "seed": 42,
+    "resume_from_checkpoint": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-150",
+    "label_smoothing": 0.5,
+    "adversarial_epsilon": 0.5,
+    "use_swa": false,
+    "swa_start_epoch": 0,
+    "swa_lr": 1e-05,
+    "data_augmentation": true,
+    "aug_rename_prob": 0.8,
+    "aug_format_prob": 0.8,
+    "mixup_alpha": 1.0,
+    "low_pass_keep_ratio": 0.5,
+    "freq_consistency_weight": 0.5,
+    "hidden_dropout_prob": 0.3,
+    "attention_probs_dropout_prob": 0.3,
+    "classifier_dropout": 0.3,
+    "device": "cuda"
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:887ddaff8ed9f2847ee48b07006fe44accd881ddff639ed716d714b0d8cbba1e
+size 498612824

graphcodebert-base-lowLR-highBatchSize/checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ce20a7bc55b277f0f55837d91399a4e5305d0f417f998203c53020e9d7ba4c
+size 4741859

graphcodebert-base-lowLR-highBatchSize/checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73aab9139f3cab35bd545916faa6eb789a3dd6684c13a4cd2232a51854fa7d3a
+size 14645

graphcodebert-base-lowLR-highBatchSize/checkpoint-300/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21c5349d5e7d02de630ebc1cb53ade1d9c6079eeb8594d223bb786011a0428b
+size 1383

graphcodebert-base-lowLR-highBatchSize/checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e499376c1bcdb063e8e402152e4b725b246196c6753599ee18b8ce21bb2784
+size 1465

graphcodebert-base-lowLR-highBatchSize/checkpoint-300/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-300/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-300/trainer_state.json

@@ -0,0 +1,253 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.29354207436399216,
+  "eval_steps": 1000,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009784735812133072,
+      "grad_norm": 165951.1875,
+      "learning_rate": 4.411764705882353e-08,
+      "loss": 0.8416,
+      "step": 10
+    },
+    {
+      "epoch": 0.019569471624266144,
+      "grad_norm": 206132.796875,
+      "learning_rate": 9.313725490196079e-08,
+      "loss": 0.8378,
+      "step": 20
+    },
+    {
+      "epoch": 0.029354207436399216,
+      "grad_norm": 171197.53125,
+      "learning_rate": 1.4215686274509803e-07,
+      "loss": 0.8388,
+      "step": 30
+    },
+    {
+      "epoch": 0.03913894324853229,
+      "grad_norm": 206661.828125,
+      "learning_rate": 1.9117647058823527e-07,
+      "loss": 0.847,
+      "step": 40
+    },
+    {
+      "epoch": 0.04892367906066536,
+      "grad_norm": 230268.96875,
+      "learning_rate": 2.4019607843137255e-07,
+      "loss": 0.8411,
+      "step": 50
+    },
+    {
+      "epoch": 0.05870841487279843,
+      "grad_norm": 133248.28125,
+      "learning_rate": 2.8921568627450984e-07,
+      "loss": 0.8412,
+      "step": 60
+    },
+    {
+      "epoch": 0.0684931506849315,
+      "grad_norm": 147768.828125,
+      "learning_rate": 3.3823529411764707e-07,
+      "loss": 0.8431,
+      "step": 70
+    },
+    {
+      "epoch": 0.07827788649706457,
+      "grad_norm": 167327.53125,
+      "learning_rate": 3.872549019607843e-07,
+      "loss": 0.8431,
+      "step": 80
+    },
+    {
+      "epoch": 0.08806262230919765,
+      "grad_norm": 151943.75,
+      "learning_rate": 4.3627450980392154e-07,
+      "loss": 0.8311,
+      "step": 90
+    },
+    {
+      "epoch": 0.09784735812133072,
+      "grad_norm": 149971.59375,
+      "learning_rate": 4.852941176470588e-07,
+      "loss": 0.8412,
+      "step": 100
+    },
+    {
+      "epoch": 0.10763209393346379,
+      "grad_norm": 162329.40625,
+      "learning_rate": 5.34313725490196e-07,
+      "loss": 0.8356,
+      "step": 110
+    },
+    {
+      "epoch": 0.11741682974559686,
+      "grad_norm": 158769.765625,
+      "learning_rate": 5.833333333333334e-07,
+      "loss": 0.8351,
+      "step": 120
+    },
+    {
+      "epoch": 0.12720156555772993,
+      "grad_norm": 157725.59375,
+      "learning_rate": 6.323529411764706e-07,
+      "loss": 0.8331,
+      "step": 130
+    },
+    {
+      "epoch": 0.136986301369863,
+      "grad_norm": 205733.0,
+      "learning_rate": 6.813725490196079e-07,
+      "loss": 0.8366,
+      "step": 140
+    },
+    {
+      "epoch": 0.14677103718199608,
+      "grad_norm": 172581.328125,
+      "learning_rate": 7.30392156862745e-07,
+      "loss": 0.831,
+      "step": 150
+    },
+    {
+      "epoch": 0.15655577299412915,
+      "grad_norm": 137428.0,
+      "learning_rate": 7.794117647058823e-07,
+      "loss": 0.8326,
+      "step": 160
+    },
+    {
+      "epoch": 0.16634050880626222,
+      "grad_norm": 151189.203125,
+      "learning_rate": 8.284313725490196e-07,
+      "loss": 0.8281,
+      "step": 170
+    },
+    {
+      "epoch": 0.1761252446183953,
+      "grad_norm": 145620.625,
+      "learning_rate": 8.774509803921568e-07,
+      "loss": 0.8252,
+      "step": 180
+    },
+    {
+      "epoch": 0.18590998043052837,
+      "grad_norm": 169938.84375,
+      "learning_rate": 9.264705882352941e-07,
+      "loss": 0.8308,
+      "step": 190
+    },
+    {
+      "epoch": 0.19569471624266144,
+      "grad_norm": 138760.015625,
+      "learning_rate": 9.754901960784313e-07,
+      "loss": 0.824,
+      "step": 200
+    },
+    {
+      "epoch": 0.2054794520547945,
+      "grad_norm": 107872.125,
+      "learning_rate": 9.99631294374483e-07,
+      "loss": 0.8254,
+      "step": 210
+    },
+    {
+      "epoch": 0.21526418786692758,
+      "grad_norm": 113610.8359375,
+      "learning_rate": 9.966849112204936e-07,
+      "loss": 0.8267,
+      "step": 220
+    },
+    {
+      "epoch": 0.22504892367906065,
+      "grad_norm": 172441.515625,
+      "learning_rate": 9.908095200725339e-07,
+      "loss": 0.8198,
+      "step": 230
+    },
+    {
+      "epoch": 0.23483365949119372,
+      "grad_norm": 128079.9140625,
+      "learning_rate": 9.82039768787326e-07,
+      "loss": 0.8143,
+      "step": 240
+    },
+    {
+      "epoch": 0.2446183953033268,
+      "grad_norm": 98149.8984375,
+      "learning_rate": 9.70427373595903e-07,
+      "loss": 0.8191,
+      "step": 250
+    },
+    {
+      "epoch": 0.25440313111545987,
+      "grad_norm": 147377.4375,
+      "learning_rate": 9.560408141270531e-07,
+      "loss": 0.8178,
+      "step": 260
+    },
+    {
+      "epoch": 0.26418786692759294,
+      "grad_norm": 156439.40625,
+      "learning_rate": 9.389649295750781e-07,
+      "loss": 0.8085,
+      "step": 270
+    },
+    {
+      "epoch": 0.273972602739726,
+      "grad_norm": 131892.015625,
+      "learning_rate": 9.193004183933174e-07,
+      "loss": 0.8172,
+      "step": 280
+    },
+    {
+      "epoch": 0.2837573385518591,
+      "grad_norm": 132474.5,
+      "learning_rate": 8.971632444637971e-07,
+      "loss": 0.8136,
+      "step": 290
+    },
+    {
+      "epoch": 0.29354207436399216,
+      "grad_norm": 112619.109375,
+      "learning_rate": 8.726839532448928e-07,
+      "loss": 0.8065,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1022,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.0413858103296e+16,
+  "train_batch_size": 512,
+  "trial_name": null,
+  "trial_params": null
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d0ce832e6223863ce0cb8edb6365c4f89eeb0b5c285c88ed750e293e5ffbe9
+size 5905

graphcodebert-base-lowLR-highBatchSize/checkpoint-350/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.3,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.3,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.3,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.56.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-350/config_hyperparams.json

@@ -0,0 +1,53 @@
+{
+  "train_config": {
+    "model_name": "microsoft/graphcodebert-base",
+    "num_epochs": 1,
+    "batch_size": 256,
+    "learning_rate": 1e-06,
+    "max_length": 512,
+    "num_labels": 2,
+    "loss_type": "r-drop",
+    "focal_alpha": 1.0,
+    "focal_gamma": 2.0,
+    "r_drop_alpha": 10.0,
+    "infonce_temperature": 0.07,
+    "infonce_weight": 0.5,
+    "label_smoothing": 0.5,
+    "adversarial_epsilon": 0.5,
+    "use_swa": false,
+    "swa_start_epoch": 0,
+    "swa_lr": 1e-05,
+    "data_augmentation": true,
+    "aug_rename_prob": 0.8,
+    "aug_format_prob": 0.8,
+    "freeze_base": true,
+    "seed": 42,
+    "use_wandb": true,
+    "mixup_alpha": 1.0,
+    "low_pass_keep_ratio": 0.5,
+    "freq_consistency_weight": 0.5
+  },
+  "training_arguments": {
+    "output_dir": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/",
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 256,
+    "per_device_eval_batch_size": 512,
+    "learning_rate": 1e-06,
+    "warmup_steps": 204,
+    "weight_decay": 0.1,
+    "logging_steps": 10,
+    "eval_steps": 1000,
+    "save_steps": 50,
+    "metric_for_best_model": "macro_f1",
+    "greater_is_better": true,
+    "save_total_limit": 4,
+    "fp16": true,
+    "seed": 42
+  },
+  "training_state": {
+    "global_step": 350,
+    "epoch": 0.3424657534246575,
+    "best_metric": null,
+    "best_model_checkpoint": null
+  }
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-350/hyperparams.json

@@ -0,0 +1,35 @@
+{
+    "model_name": "microsoft/graphcodebert-base",
+    "output_dir": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/",
+    "num_epochs": 1,
+    "max_steps": -1,
+    "batch_size": 256,
+    "learning_rate": 1e-06,
+    "max_length": 512,
+    "num_labels": 2,
+    "use_wandb": true,
+    "freeze_base": true,
+    "loss_type": "r-drop",
+    "focal_alpha": 1.0,
+    "focal_gamma": 2.0,
+    "r_drop_alpha": 10.0,
+    "infonce_temperature": 0.07,
+    "infonce_weight": 0.5,
+    "seed": 42,
+    "resume_from_checkpoint": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-150",
+    "label_smoothing": 0.5,
+    "adversarial_epsilon": 0.5,
+    "use_swa": false,
+    "swa_start_epoch": 0,
+    "swa_lr": 1e-05,
+    "data_augmentation": true,
+    "aug_rename_prob": 0.8,
+    "aug_format_prob": 0.8,
+    "mixup_alpha": 1.0,
+    "low_pass_keep_ratio": 0.5,
+    "freq_consistency_weight": 0.5,
+    "hidden_dropout_prob": 0.3,
+    "attention_probs_dropout_prob": 0.3,
+    "classifier_dropout": 0.3,
+    "device": "cuda"
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-350/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fef80ac3319fc044bd5ed974ce634130ad50dd3891109eedb8d138f19c9ac974
+size 498612824

graphcodebert-base-lowLR-highBatchSize/checkpoint-350/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc46c104c26de9b07a90c7a38f083f5e2a8d00cb7be0e639f6f74084fd942547
+size 4741859

graphcodebert-base-lowLR-highBatchSize/checkpoint-350/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef2287c5d715c4c2b1f2475cc59ae767683b80b8c74ca678c03ca174ce5f0e2f
+size 14645

graphcodebert-base-lowLR-highBatchSize/checkpoint-350/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21c5349d5e7d02de630ebc1cb53ade1d9c6079eeb8594d223bb786011a0428b
+size 1383

graphcodebert-base-lowLR-highBatchSize/checkpoint-350/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:928190fa1d3edd4ba374db3d04217b214d87bc7124232d8888e8b2ae2eb12f68
+size 1465

graphcodebert-base-lowLR-highBatchSize/checkpoint-350/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-350/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-350/trainer_state.json

@@ -0,0 +1,288 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3424657534246575,
+  "eval_steps": 1000,
+  "global_step": 350,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009784735812133072,
+      "grad_norm": 165951.1875,
+      "learning_rate": 4.411764705882353e-08,
+      "loss": 0.8416,
+      "step": 10
+    },
+    {
+      "epoch": 0.019569471624266144,
+      "grad_norm": 206132.796875,
+      "learning_rate": 9.313725490196079e-08,
+      "loss": 0.8378,
+      "step": 20
+    },
+    {
+      "epoch": 0.029354207436399216,
+      "grad_norm": 171197.53125,
+      "learning_rate": 1.4215686274509803e-07,
+      "loss": 0.8388,
+      "step": 30
+    },
+    {
+      "epoch": 0.03913894324853229,
+      "grad_norm": 206661.828125,
+      "learning_rate": 1.9117647058823527e-07,
+      "loss": 0.847,
+      "step": 40
+    },
+    {
+      "epoch": 0.04892367906066536,
+      "grad_norm": 230268.96875,
+      "learning_rate": 2.4019607843137255e-07,
+      "loss": 0.8411,
+      "step": 50
+    },
+    {
+      "epoch": 0.05870841487279843,
+      "grad_norm": 133248.28125,
+      "learning_rate": 2.8921568627450984e-07,
+      "loss": 0.8412,
+      "step": 60
+    },
+    {
+      "epoch": 0.0684931506849315,
+      "grad_norm": 147768.828125,
+      "learning_rate": 3.3823529411764707e-07,
+      "loss": 0.8431,
+      "step": 70
+    },
+    {
+      "epoch": 0.07827788649706457,
+      "grad_norm": 167327.53125,
+      "learning_rate": 3.872549019607843e-07,
+      "loss": 0.8431,
+      "step": 80
+    },
+    {
+      "epoch": 0.08806262230919765,
+      "grad_norm": 151943.75,
+      "learning_rate": 4.3627450980392154e-07,
+      "loss": 0.8311,
+      "step": 90
+    },
+    {
+      "epoch": 0.09784735812133072,
+      "grad_norm": 149971.59375,
+      "learning_rate": 4.852941176470588e-07,
+      "loss": 0.8412,
+      "step": 100
+    },
+    {
+      "epoch": 0.10763209393346379,
+      "grad_norm": 162329.40625,
+      "learning_rate": 5.34313725490196e-07,
+      "loss": 0.8356,
+      "step": 110
+    },
+    {
+      "epoch": 0.11741682974559686,
+      "grad_norm": 158769.765625,
+      "learning_rate": 5.833333333333334e-07,
+      "loss": 0.8351,
+      "step": 120
+    },
+    {
+      "epoch": 0.12720156555772993,
+      "grad_norm": 157725.59375,
+      "learning_rate": 6.323529411764706e-07,
+      "loss": 0.8331,
+      "step": 130
+    },
+    {
+      "epoch": 0.136986301369863,
+      "grad_norm": 205733.0,
+      "learning_rate": 6.813725490196079e-07,
+      "loss": 0.8366,
+      "step": 140
+    },
+    {
+      "epoch": 0.14677103718199608,
+      "grad_norm": 172581.328125,
+      "learning_rate": 7.30392156862745e-07,
+      "loss": 0.831,
+      "step": 150
+    },
+    {
+      "epoch": 0.15655577299412915,
+      "grad_norm": 137428.0,
+      "learning_rate": 7.794117647058823e-07,
+      "loss": 0.8326,
+      "step": 160
+    },
+    {
+      "epoch": 0.16634050880626222,
+      "grad_norm": 151189.203125,
+      "learning_rate": 8.284313725490196e-07,
+      "loss": 0.8281,
+      "step": 170
+    },
+    {
+      "epoch": 0.1761252446183953,
+      "grad_norm": 145620.625,
+      "learning_rate": 8.774509803921568e-07,
+      "loss": 0.8252,
+      "step": 180
+    },
+    {
+      "epoch": 0.18590998043052837,
+      "grad_norm": 169938.84375,
+      "learning_rate": 9.264705882352941e-07,
+      "loss": 0.8308,
+      "step": 190
+    },
+    {
+      "epoch": 0.19569471624266144,
+      "grad_norm": 138760.015625,
+      "learning_rate": 9.754901960784313e-07,
+      "loss": 0.824,
+      "step": 200
+    },
+    {
+      "epoch": 0.2054794520547945,
+      "grad_norm": 107872.125,
+      "learning_rate": 9.99631294374483e-07,
+      "loss": 0.8254,
+      "step": 210
+    },
+    {
+      "epoch": 0.21526418786692758,
+      "grad_norm": 113610.8359375,
+      "learning_rate": 9.966849112204936e-07,
+      "loss": 0.8267,
+      "step": 220
+    },
+    {
+      "epoch": 0.22504892367906065,
+      "grad_norm": 172441.515625,
+      "learning_rate": 9.908095200725339e-07,
+      "loss": 0.8198,
+      "step": 230
+    },
+    {
+      "epoch": 0.23483365949119372,
+      "grad_norm": 128079.9140625,
+      "learning_rate": 9.82039768787326e-07,
+      "loss": 0.8143,
+      "step": 240
+    },
+    {
+      "epoch": 0.2446183953033268,
+      "grad_norm": 98149.8984375,
+      "learning_rate": 9.70427373595903e-07,
+      "loss": 0.8191,
+      "step": 250
+    },
+    {
+      "epoch": 0.25440313111545987,
+      "grad_norm": 147377.4375,
+      "learning_rate": 9.560408141270531e-07,
+      "loss": 0.8178,
+      "step": 260
+    },
+    {
+      "epoch": 0.26418786692759294,
+      "grad_norm": 156439.40625,
+      "learning_rate": 9.389649295750781e-07,
+      "loss": 0.8085,
+      "step": 270
+    },
+    {
+      "epoch": 0.273972602739726,
+      "grad_norm": 131892.015625,
+      "learning_rate": 9.193004183933174e-07,
+      "loss": 0.8172,
+      "step": 280
+    },
+    {
+      "epoch": 0.2837573385518591,
+      "grad_norm": 132474.5,
+      "learning_rate": 8.971632444637971e-07,
+      "loss": 0.8136,
+      "step": 290
+    },
+    {
+      "epoch": 0.29354207436399216,
+      "grad_norm": 112619.109375,
+      "learning_rate": 8.726839532448928e-07,
+      "loss": 0.8065,
+      "step": 300
+    },
+    {
+      "epoch": 0.30332681017612523,
+      "grad_norm": 94225.5703125,
+      "learning_rate": 8.460069019297606e-07,
+      "loss": 0.813,
+      "step": 310
+    },
+    {
+      "epoch": 0.3131115459882583,
+      "grad_norm": 117812.8203125,
+      "learning_rate": 8.172894081553822e-07,
+      "loss": 0.8022,
+      "step": 320
+    },
+    {
+      "epoch": 0.32289628180039137,
+      "grad_norm": 143287.125,
+      "learning_rate": 7.86700822282382e-07,
+      "loss": 0.8061,
+      "step": 330
+    },
+    {
+      "epoch": 0.33268101761252444,
+      "grad_norm": 107456.25,
+      "learning_rate": 7.544215287164917e-07,
+      "loss": 0.8006,
+      "step": 340
+    },
+    {
+      "epoch": 0.3424657534246575,
+      "grad_norm": 101521.171875,
+      "learning_rate": 7.206418821609812e-07,
+      "loss": 0.8055,
+      "step": 350
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1022,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.7149501120512e+16,
+  "train_batch_size": 512,
+  "trial_name": null,
+  "trial_params": null
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-350/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d0ce832e6223863ce0cb8edb6365c4f89eeb0b5c285c88ed750e293e5ffbe9
+size 5905

graphcodebert-base-lowLR-highBatchSize/checkpoint-400/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.3,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.3,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.3,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.56.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-400/config_hyperparams.json

@@ -0,0 +1,53 @@
+{
+  "train_config": {
+    "model_name": "microsoft/graphcodebert-base",
+    "num_epochs": 1,
+    "batch_size": 256,
+    "learning_rate": 1e-06,
+    "max_length": 512,
+    "num_labels": 2,
+    "loss_type": "r-drop",
+    "focal_alpha": 1.0,
+    "focal_gamma": 2.0,
+    "r_drop_alpha": 10.0,
+    "infonce_temperature": 0.07,
+    "infonce_weight": 0.5,
+    "label_smoothing": 0.5,
+    "adversarial_epsilon": 0.5,
+    "use_swa": false,
+    "swa_start_epoch": 0,
+    "swa_lr": 1e-05,
+    "data_augmentation": true,
+    "aug_rename_prob": 0.8,
+    "aug_format_prob": 0.8,
+    "freeze_base": true,
+    "seed": 42,
+    "use_wandb": true,
+    "mixup_alpha": 1.0,
+    "low_pass_keep_ratio": 0.5,
+    "freq_consistency_weight": 0.5
+  },
+  "training_arguments": {
+    "output_dir": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/",
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 256,
+    "per_device_eval_batch_size": 512,
+    "learning_rate": 1e-06,
+    "warmup_steps": 204,
+    "weight_decay": 0.1,
+    "logging_steps": 10,
+    "eval_steps": 1000,
+    "save_steps": 50,
+    "metric_for_best_model": "macro_f1",
+    "greater_is_better": true,
+    "save_total_limit": 4,
+    "fp16": true,
+    "seed": 42
+  },
+  "training_state": {
+    "global_step": 400,
+    "epoch": 0.3913894324853229,
+    "best_metric": null,
+    "best_model_checkpoint": null
+  }
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-400/hyperparams.json

@@ -0,0 +1,35 @@
+{
+    "model_name": "microsoft/graphcodebert-base",
+    "output_dir": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/",
+    "num_epochs": 1,
+    "max_steps": -1,
+    "batch_size": 256,
+    "learning_rate": 1e-06,
+    "max_length": 512,
+    "num_labels": 2,
+    "use_wandb": true,
+    "freeze_base": true,
+    "loss_type": "r-drop",
+    "focal_alpha": 1.0,
+    "focal_gamma": 2.0,
+    "r_drop_alpha": 10.0,
+    "infonce_temperature": 0.07,
+    "infonce_weight": 0.5,
+    "seed": 42,
+    "resume_from_checkpoint": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-150",
+    "label_smoothing": 0.5,
+    "adversarial_epsilon": 0.5,
+    "use_swa": false,
+    "swa_start_epoch": 0,
+    "swa_lr": 1e-05,
+    "data_augmentation": true,
+    "aug_rename_prob": 0.8,
+    "aug_format_prob": 0.8,
+    "mixup_alpha": 1.0,
+    "low_pass_keep_ratio": 0.5,
+    "freq_consistency_weight": 0.5,
+    "hidden_dropout_prob": 0.3,
+    "attention_probs_dropout_prob": 0.3,
+    "classifier_dropout": 0.3,
+    "device": "cuda"
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-400/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee10a85c7345f840ced5553e4c296702832c3b8bc1ad78d1524d2e1e0581559
+size 498612824

graphcodebert-base-lowLR-highBatchSize/checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098d03c86fe53a3089a267670691e3962e4c472851441ae635a00cc4591c4859
+size 4741859

graphcodebert-base-lowLR-highBatchSize/checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a71ce2adaa088d39a621c53df9b35a02f7ea78037e7f34b85f7d46bbafa926
+size 14645

graphcodebert-base-lowLR-highBatchSize/checkpoint-400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21c5349d5e7d02de630ebc1cb53ade1d9c6079eeb8594d223bb786011a0428b
+size 1383

graphcodebert-base-lowLR-highBatchSize/checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:751709a16f55bce9f670805512a4ac28a4b3f402b1eecc52a1097cfeac6fb5d7
+size 1465

graphcodebert-base-lowLR-highBatchSize/checkpoint-400/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-400/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-400/trainer_state.json

@@ -0,0 +1,323 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3913894324853229,
+  "eval_steps": 1000,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009784735812133072,
+      "grad_norm": 165951.1875,
+      "learning_rate": 4.411764705882353e-08,
+      "loss": 0.8416,
+      "step": 10
+    },
+    {
+      "epoch": 0.019569471624266144,
+      "grad_norm": 206132.796875,
+      "learning_rate": 9.313725490196079e-08,
+      "loss": 0.8378,
+      "step": 20
+    },
+    {
+      "epoch": 0.029354207436399216,
+      "grad_norm": 171197.53125,
+      "learning_rate": 1.4215686274509803e-07,
+      "loss": 0.8388,
+      "step": 30
+    },
+    {
+      "epoch": 0.03913894324853229,
+      "grad_norm": 206661.828125,
+      "learning_rate": 1.9117647058823527e-07,
+      "loss": 0.847,
+      "step": 40
+    },
+    {
+      "epoch": 0.04892367906066536,
+      "grad_norm": 230268.96875,
+      "learning_rate": 2.4019607843137255e-07,
+      "loss": 0.8411,
+      "step": 50
+    },
+    {
+      "epoch": 0.05870841487279843,
+      "grad_norm": 133248.28125,
+      "learning_rate": 2.8921568627450984e-07,
+      "loss": 0.8412,
+      "step": 60
+    },
+    {
+      "epoch": 0.0684931506849315,
+      "grad_norm": 147768.828125,
+      "learning_rate": 3.3823529411764707e-07,
+      "loss": 0.8431,
+      "step": 70
+    },
+    {
+      "epoch": 0.07827788649706457,
+      "grad_norm": 167327.53125,
+      "learning_rate": 3.872549019607843e-07,
+      "loss": 0.8431,
+      "step": 80
+    },
+    {
+      "epoch": 0.08806262230919765,
+      "grad_norm": 151943.75,
+      "learning_rate": 4.3627450980392154e-07,
+      "loss": 0.8311,
+      "step": 90
+    },
+    {
+      "epoch": 0.09784735812133072,
+      "grad_norm": 149971.59375,
+      "learning_rate": 4.852941176470588e-07,
+      "loss": 0.8412,
+      "step": 100
+    },
+    {
+      "epoch": 0.10763209393346379,
+      "grad_norm": 162329.40625,
+      "learning_rate": 5.34313725490196e-07,
+      "loss": 0.8356,
+      "step": 110
+    },
+    {
+      "epoch": 0.11741682974559686,
+      "grad_norm": 158769.765625,
+      "learning_rate": 5.833333333333334e-07,
+      "loss": 0.8351,
+      "step": 120
+    },
+    {
+      "epoch": 0.12720156555772993,
+      "grad_norm": 157725.59375,
+      "learning_rate": 6.323529411764706e-07,
+      "loss": 0.8331,
+      "step": 130
+    },
+    {
+      "epoch": 0.136986301369863,
+      "grad_norm": 205733.0,
+      "learning_rate": 6.813725490196079e-07,
+      "loss": 0.8366,
+      "step": 140
+    },
+    {
+      "epoch": 0.14677103718199608,
+      "grad_norm": 172581.328125,
+      "learning_rate": 7.30392156862745e-07,
+      "loss": 0.831,
+      "step": 150
+    },
+    {
+      "epoch": 0.15655577299412915,
+      "grad_norm": 137428.0,
+      "learning_rate": 7.794117647058823e-07,
+      "loss": 0.8326,
+      "step": 160
+    },
+    {
+      "epoch": 0.16634050880626222,
+      "grad_norm": 151189.203125,
+      "learning_rate": 8.284313725490196e-07,
+      "loss": 0.8281,
+      "step": 170
+    },
+    {
+      "epoch": 0.1761252446183953,
+      "grad_norm": 145620.625,
+      "learning_rate": 8.774509803921568e-07,
+      "loss": 0.8252,
+      "step": 180
+    },
+    {
+      "epoch": 0.18590998043052837,
+      "grad_norm": 169938.84375,
+      "learning_rate": 9.264705882352941e-07,
+      "loss": 0.8308,
+      "step": 190
+    },
+    {
+      "epoch": 0.19569471624266144,
+      "grad_norm": 138760.015625,
+      "learning_rate": 9.754901960784313e-07,
+      "loss": 0.824,
+      "step": 200
+    },
+    {
+      "epoch": 0.2054794520547945,
+      "grad_norm": 107872.125,
+      "learning_rate": 9.99631294374483e-07,
+      "loss": 0.8254,
+      "step": 210
+    },
+    {
+      "epoch": 0.21526418786692758,
+      "grad_norm": 113610.8359375,
+      "learning_rate": 9.966849112204936e-07,
+      "loss": 0.8267,
+      "step": 220
+    },
+    {
+      "epoch": 0.22504892367906065,
+      "grad_norm": 172441.515625,
+      "learning_rate": 9.908095200725339e-07,
+      "loss": 0.8198,
+      "step": 230
+    },
+    {
+      "epoch": 0.23483365949119372,
+      "grad_norm": 128079.9140625,
+      "learning_rate": 9.82039768787326e-07,
+      "loss": 0.8143,
+      "step": 240
+    },
+    {
+      "epoch": 0.2446183953033268,
+      "grad_norm": 98149.8984375,
+      "learning_rate": 9.70427373595903e-07,
+      "loss": 0.8191,
+      "step": 250
+    },
+    {
+      "epoch": 0.25440313111545987,
+      "grad_norm": 147377.4375,
+      "learning_rate": 9.560408141270531e-07,
+      "loss": 0.8178,
+      "step": 260
+    },
+    {
+      "epoch": 0.26418786692759294,
+      "grad_norm": 156439.40625,
+      "learning_rate": 9.389649295750781e-07,
+      "loss": 0.8085,
+      "step": 270
+    },
+    {
+      "epoch": 0.273972602739726,
+      "grad_norm": 131892.015625,
+      "learning_rate": 9.193004183933174e-07,
+      "loss": 0.8172,
+      "step": 280
+    },
+    {
+      "epoch": 0.2837573385518591,
+      "grad_norm": 132474.5,
+      "learning_rate": 8.971632444637971e-07,
+      "loss": 0.8136,
+      "step": 290
+    },
+    {
+      "epoch": 0.29354207436399216,
+      "grad_norm": 112619.109375,
+      "learning_rate": 8.726839532448928e-07,
+      "loss": 0.8065,
+      "step": 300
+    },
+    {
+      "epoch": 0.30332681017612523,
+      "grad_norm": 94225.5703125,
+      "learning_rate": 8.460069019297606e-07,
+      "loss": 0.813,
+      "step": 310
+    },
+    {
+      "epoch": 0.3131115459882583,
+      "grad_norm": 117812.8203125,
+      "learning_rate": 8.172894081553822e-07,
+      "loss": 0.8022,
+      "step": 320
+    },
+    {
+      "epoch": 0.32289628180039137,
+      "grad_norm": 143287.125,
+      "learning_rate": 7.86700822282382e-07,
+      "loss": 0.8061,
+      "step": 330
+    },
+    {
+      "epoch": 0.33268101761252444,
+      "grad_norm": 107456.25,
+      "learning_rate": 7.544215287164917e-07,
+      "loss": 0.8006,
+      "step": 340
+    },
+    {
+      "epoch": 0.3424657534246575,
+      "grad_norm": 101521.171875,
+      "learning_rate": 7.206418821609812e-07,
+      "loss": 0.8055,
+      "step": 350
+    },
+    {
+      "epoch": 0.3522504892367906,
+      "grad_norm": 118311.5234375,
+      "learning_rate": 6.855610850731017e-07,
+      "loss": 0.8081,
+      "step": 360
+    },
+    {
+      "epoch": 0.36203522504892366,
+      "grad_norm": 89621.828125,
+      "learning_rate": 6.493860129443046e-07,
+      "loss": 0.8058,
+      "step": 370
+    },
+    {
+      "epoch": 0.37181996086105673,
+      "grad_norm": 143168.65625,
+      "learning_rate": 6.123299943316975e-07,
+      "loss": 0.8028,
+      "step": 380
+    },
+    {
+      "epoch": 0.3816046966731898,
+      "grad_norm": 118598.2890625,
+      "learning_rate": 5.746115528350295e-07,
+      "loss": 0.8032,
+      "step": 390
+    },
+    {
+      "epoch": 0.3913894324853229,
+      "grad_norm": 111807.8203125,
+      "learning_rate": 5.364531184379139e-07,
+      "loss": 0.8014,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1022,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.3885144137728e+16,
+  "train_batch_size": 512,
+  "trial_name": null,
+  "trial_params": null
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d0ce832e6223863ce0cb8edb6365c4f89eeb0b5c285c88ed750e293e5ffbe9
+size 5905

graphcodebert-base-lowLR-highBatchSize/checkpoint-450/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.3,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.3,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.3,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.56.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-450/config_hyperparams.json

@@ -0,0 +1,53 @@
+{
+  "train_config": {
+    "model_name": "microsoft/graphcodebert-base",
+    "num_epochs": 1,
+    "batch_size": 256,
+    "learning_rate": 1e-06,
+    "max_length": 512,
+    "num_labels": 2,
+    "loss_type": "r-drop",
+    "focal_alpha": 1.0,
+    "focal_gamma": 2.0,
+    "r_drop_alpha": 10.0,
+    "infonce_temperature": 0.07,
+    "infonce_weight": 0.5,
+    "label_smoothing": 0.5,
+    "adversarial_epsilon": 0.5,
+    "use_swa": false,
+    "swa_start_epoch": 0,
+    "swa_lr": 1e-05,
+    "data_augmentation": true,
+    "aug_rename_prob": 0.8,
+    "aug_format_prob": 0.8,
+    "freeze_base": true,
+    "seed": 42,
+    "use_wandb": true,
+    "mixup_alpha": 1.0,
+    "low_pass_keep_ratio": 0.5,
+    "freq_consistency_weight": 0.5
+  },
+  "training_arguments": {
+    "output_dir": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/",
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 256,
+    "per_device_eval_batch_size": 512,
+    "learning_rate": 1e-06,
+    "warmup_steps": 204,
+    "weight_decay": 0.1,
+    "logging_steps": 10,
+    "eval_steps": 1000,
+    "save_steps": 50,
+    "metric_for_best_model": "macro_f1",
+    "greater_is_better": true,
+    "save_total_limit": 4,
+    "fp16": true,
+    "seed": 42
+  },
+  "training_state": {
+    "global_step": 450,
+    "epoch": 0.44031311154598823,
+    "best_metric": null,
+    "best_model_checkpoint": null
+  }
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-450/hyperparams.json

@@ -0,0 +1,35 @@
+{
+    "model_name": "microsoft/graphcodebert-base",
+    "output_dir": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/",
+    "num_epochs": 1,
+    "max_steps": -1,
+    "batch_size": 256,
+    "learning_rate": 1e-06,
+    "max_length": 512,
+    "num_labels": 2,
+    "use_wandb": true,
+    "freeze_base": true,
+    "loss_type": "r-drop",
+    "focal_alpha": 1.0,
+    "focal_gamma": 2.0,
+    "r_drop_alpha": 10.0,
+    "infonce_temperature": 0.07,
+    "infonce_weight": 0.5,
+    "seed": 42,
+    "resume_from_checkpoint": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-150",
+    "label_smoothing": 0.5,
+    "adversarial_epsilon": 0.5,
+    "use_swa": false,
+    "swa_start_epoch": 0,
+    "swa_lr": 1e-05,
+    "data_augmentation": true,
+    "aug_rename_prob": 0.8,
+    "aug_format_prob": 0.8,
+    "mixup_alpha": 1.0,
+    "low_pass_keep_ratio": 0.5,
+    "freq_consistency_weight": 0.5,
+    "hidden_dropout_prob": 0.3,
+    "attention_probs_dropout_prob": 0.3,
+    "classifier_dropout": 0.3,
+    "device": "cuda"
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-450/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3547af00f99349378f21a83a224cddcbe0bc25463fe209932447cdb2f07a1a4b
+size 498612824