upload checkpoints best at 500

graphcodebert-base-lowLR-highBatchSize/checkpoint-500/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-500/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": 500,
+    "epoch": 0.4892367906066536,
+    "best_metric": null,
+    "best_model_checkpoint": null
+  }
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-500/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-450",
+    "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-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62afd78fff103664d60d34ba3d06f2e7b451350dbc1f5f43dca6b0c42a813f0a
+size 498612824

graphcodebert-base-lowLR-highBatchSize/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bd2ec8c5a16b46ce4afe1dcac55b713136ceebbe600c657923d4c518562f65d
+size 4741859

graphcodebert-base-lowLR-highBatchSize/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d0f6ebf28238c654ab9e878a40e4b165e8986b10ff2c98367e9d4fe7118c974
+size 14645

graphcodebert-base-lowLR-highBatchSize/checkpoint-500/scaler.pt

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

graphcodebert-base-lowLR-highBatchSize/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf4e05d599e3f7350270baeea47a97754f2c1df2623cb7794b38f920e23d6222
+size 1465

graphcodebert-base-lowLR-highBatchSize/checkpoint-500/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-500/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-500/trainer_state.json

@@ -0,0 +1,393 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4892367906066536,
+  "eval_steps": 1000,
+  "global_step": 500,
+  "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
+    },
+    {
+      "epoch": 0.40117416829745595,
+      "grad_norm": 124106.1328125,
+      "learning_rate": 4.980797158126566e-07,
+      "loss": 0.8045,
+      "step": 410
+    },
+    {
+      "epoch": 0.410958904109589,
+      "grad_norm": 102746.4765625,
+      "learning_rate": 4.597176373239061e-07,
+      "loss": 0.7996,
+      "step": 420
+    },
+    {
+      "epoch": 0.4207436399217221,
+      "grad_norm": 108317.5859375,
+      "learning_rate": 4.215931085565761e-07,
+      "loss": 0.8037,
+      "step": 430
+    },
+    {
+      "epoch": 0.43052837573385516,
+      "grad_norm": 113342.515625,
+      "learning_rate": 3.8393095423757764e-07,
+      "loss": 0.8047,
+      "step": 440
+    },
+    {
+      "epoch": 0.44031311154598823,
+      "grad_norm": 111908.90625,
+      "learning_rate": 3.469532724185699e-07,
+      "loss": 0.8021,
+      "step": 450
+    },
+    {
+      "epoch": 0.4500978473581213,
+      "grad_norm": 85004.15625,
+      "learning_rate": 3.1087812473822845e-07,
+      "loss": 0.8012,
+      "step": 460
+    },
+    {
+      "epoch": 0.4598825831702544,
+      "grad_norm": 98335.1796875,
+      "learning_rate": 2.7591825048770643e-07,
+      "loss": 0.7977,
+      "step": 470
+    },
+    {
+      "epoch": 0.46966731898238745,
+      "grad_norm": 110674.03125,
+      "learning_rate": 2.422798120625886e-07,
+      "loss": 0.7979,
+      "step": 480
+    },
+    {
+      "epoch": 0.4794520547945205,
+      "grad_norm": 114861.5390625,
+      "learning_rate": 2.1016117919955512e-07,
+      "loss": 0.8014,
+      "step": 490
+    },
+    {
+      "epoch": 0.4892367906066536,
+      "grad_norm": 130109.5703125,
+      "learning_rate": 1.7975175916725031e-07,
+      "loss": 0.7994,
+      "step": 500
+    }
+  ],
+  "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": 6.735643017216e+16,
+  "train_batch_size": 512,
+  "trial_name": null,
+  "trial_params": null
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:029b4a858ef9e29cdaae98df63ce69dafcd44e3b7d6a390188782ba973f6387f
+size 5905

graphcodebert-base-lowLR-highBatchSize/checkpoint-550/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-550/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": 550,
+    "epoch": 0.538160469667319,
+    "best_metric": null,
+    "best_model_checkpoint": null
+  }
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-550/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-500",
+    "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-550/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3522ebeb3e76886d055b63e7dbb614e25d4eb7eaa31fe407b0f6ce724a359f2f
+size 498612824

graphcodebert-base-lowLR-highBatchSize/checkpoint-550/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ae0d8c7eb0dc55da7708c72806401e00399ec15bc9baffb93e7d1dd7df1855b
+size 4741859

graphcodebert-base-lowLR-highBatchSize/checkpoint-550/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474796bdfb8d46c532dcad5c0ea3578a64f5414e0a71f978bc8ddf579ad2fe06
+size 14645

graphcodebert-base-lowLR-highBatchSize/checkpoint-550/scaler.pt

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

graphcodebert-base-lowLR-highBatchSize/checkpoint-550/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ca58c7fdf81d7990567985713093efa517628c10ca166dff7d9b633a6876e26
+size 1465

graphcodebert-base-lowLR-highBatchSize/checkpoint-550/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-550/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-550/trainer_state.json

@@ -0,0 +1,428 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.538160469667319,
+  "eval_steps": 1000,
+  "global_step": 550,
+  "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
+    },
+    {
+      "epoch": 0.40117416829745595,
+      "grad_norm": 124106.1328125,
+      "learning_rate": 4.980797158126566e-07,
+      "loss": 0.8045,
+      "step": 410
+    },
+    {
+      "epoch": 0.410958904109589,
+      "grad_norm": 102746.4765625,
+      "learning_rate": 4.597176373239061e-07,
+      "loss": 0.7996,
+      "step": 420
+    },
+    {
+      "epoch": 0.4207436399217221,
+      "grad_norm": 108317.5859375,
+      "learning_rate": 4.215931085565761e-07,
+      "loss": 0.8037,
+      "step": 430
+    },
+    {
+      "epoch": 0.43052837573385516,
+      "grad_norm": 113342.515625,
+      "learning_rate": 3.8393095423757764e-07,
+      "loss": 0.8047,
+      "step": 440
+    },
+    {
+      "epoch": 0.44031311154598823,
+      "grad_norm": 111908.90625,
+      "learning_rate": 3.469532724185699e-07,
+      "loss": 0.8021,
+      "step": 450
+    },
+    {
+      "epoch": 0.4500978473581213,
+      "grad_norm": 85004.15625,
+      "learning_rate": 3.1087812473822845e-07,
+      "loss": 0.8012,
+      "step": 460
+    },
+    {
+      "epoch": 0.4598825831702544,
+      "grad_norm": 98335.1796875,
+      "learning_rate": 2.7591825048770643e-07,
+      "loss": 0.7977,
+      "step": 470
+    },
+    {
+      "epoch": 0.46966731898238745,
+      "grad_norm": 110674.03125,
+      "learning_rate": 2.422798120625886e-07,
+      "loss": 0.7979,
+      "step": 480
+    },
+    {
+      "epoch": 0.4794520547945205,
+      "grad_norm": 114861.5390625,
+      "learning_rate": 2.1016117919955512e-07,
+      "loss": 0.8014,
+      "step": 490
+    },
+    {
+      "epoch": 0.4892367906066536,
+      "grad_norm": 130109.5703125,
+      "learning_rate": 1.7975175916725031e-07,
+      "loss": 0.7994,
+      "step": 500
+    },
+    {
+      "epoch": 0.49902152641878667,
+      "grad_norm": 100678.8671875,
+      "learning_rate": 1.5123087980985606e-07,
+      "loss": 0.802,
+      "step": 510
+    },
+    {
+      "epoch": 0.5088062622309197,
+      "grad_norm": 115718.078125,
+      "learning_rate": 1.2476673203018728e-07,
+      "loss": 0.7971,
+      "step": 520
+    },
+    {
+      "epoch": 0.5185909980430529,
+      "grad_norm": 94845.9453125,
+      "learning_rate": 1.0051537794861287e-07,
+      "loss": 0.7952,
+      "step": 530
+    },
+    {
+      "epoch": 0.5283757338551859,
+      "grad_norm": 106283.5703125,
+      "learning_rate": 7.861983058679871e-08,
+      "loss": 0.8013,
+      "step": 540
+    },
+    {
+      "epoch": 0.538160469667319,
+      "grad_norm": 93847.1640625,
+      "learning_rate": 5.920921050348626e-08,
+      "loss": 0.7968,
+      "step": 550
+    }
+  ],
+  "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": 7.4092073189376e+16,
+  "train_batch_size": 512,
+  "trial_name": null,
+  "trial_params": null
+}

graphcodebert-base-lowLR-highBatchSize/checkpoint-550/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede5769c73b6c610c4628bbd74325244be057dfbd9cce16276706ada4cb7f175
+size 5905

graphcodebert-base-lowLR-highBatchSize/training.log

@@ -1,40 +1,40 @@
-2026-04-24 15:00:13,875 - INFO - ===== Training Configuration =====
-2026-04-24 15:00:13,877 - INFO - model_name           : microsoft/graphcodebert-base
-2026-04-24 15:00:13,878 - INFO - output_dir           : output_checkpoints/graphcodebert-base-lowLR-highBatchSize/
-2026-04-24 15:00:13,880 - INFO - num_epochs           : 1
-2026-04-24 15:00:13,882 - INFO - max_steps            : -1
-2026-04-24 15:00:13,883 - INFO - batch_size           : 256
-2026-04-24 15:00:13,884 - INFO - learning_rate        : 1e-06
-2026-04-24 15:00:13,885 - INFO - max_length           : 512
-2026-04-24 15:00:13,887 - INFO - num_labels           : 2
-2026-04-24 15:00:13,889 - INFO - use_wandb            : True
-2026-04-24 15:00:13,890 - INFO - freeze_base          : True
-2026-04-24 15:00:13,891 - INFO - loss_type            : r-drop
-2026-04-24 15:00:13,893 - INFO - focal_alpha          : 1.0
-2026-04-24 15:00:13,895 - INFO - focal_gamma          : 2.0
-2026-04-24 15:00:13,896 - INFO - r_drop_alpha         : 10.0
-2026-04-24 15:00:13,897 - INFO - infonce_temperature  : 0.07
-2026-04-24 15:00:13,899 - INFO - infonce_weight       : 0.5
-2026-04-24 15:00:13,900 - INFO - seed                 : 42
-2026-04-24 15:00:13,901 - INFO - resume_from_checkpoint : output_checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-150
-2026-04-24 15:00:13,903 - INFO - label_smoothing      : 0.5
-2026-04-24 15:00:13,904 - INFO - adversarial_epsilon  : 0.5
-2026-04-24 15:00:13,906 - INFO - use_swa              : False
-2026-04-24 15:00:13,907 - INFO - swa_start_epoch      : 0
-2026-04-24 15:00:13,909 - INFO - swa_lr               : 1e-05
-2026-04-24 15:00:13,910 - INFO - data_augmentation    : True
-2026-04-24 15:00:13,912 - INFO - aug_rename_prob      : 0.8
-2026-04-24 15:00:13,913 - INFO - aug_format_prob      : 0.8
-2026-04-24 15:00:13,914 - INFO - mixup_alpha          : 1.0
-2026-04-24 15:00:13,916 - INFO - low_pass_keep_ratio  : 0.5
-2026-04-24 15:00:13,918 - INFO - freq_consistency_weight : 0.5
-2026-04-24 15:00:13,920 - INFO - hidden_dropout_prob  : 0.3
-2026-04-24 15:00:13,921 - INFO - attention_probs_dropout_prob : 0.3
-2026-04-24 15:00:13,922 - INFO - classifier_dropout   : 0.3
-2026-04-24 15:00:13,924 - INFO - =================================
-2026-04-24 15:00:15,022 - INFO - Model placed on cuda
-2026-04-24 15:00:15,027 - INFO - ===== Model Architecture =====
-2026-04-24 15:00:15,029 - INFO - 
+2026-04-24 16:49:08,923 - INFO - ===== Training Configuration =====
+2026-04-24 16:49:08,924 - INFO - model_name           : microsoft/graphcodebert-base
+2026-04-24 16:49:08,924 - INFO - output_dir           : output_checkpoints/graphcodebert-base-lowLR-highBatchSize/
+2026-04-24 16:49:08,925 - INFO - num_epochs           : 1
+2026-04-24 16:49:08,926 - INFO - max_steps            : -1
+2026-04-24 16:49:08,927 - INFO - batch_size           : 256
+2026-04-24 16:49:08,928 - INFO - learning_rate        : 1e-06
+2026-04-24 16:49:08,929 - INFO - max_length           : 512
+2026-04-24 16:49:08,930 - INFO - num_labels           : 2
+2026-04-24 16:49:08,931 - INFO - use_wandb            : True
+2026-04-24 16:49:08,931 - INFO - freeze_base          : True
+2026-04-24 16:49:08,932 - INFO - loss_type            : r-drop
+2026-04-24 16:49:08,933 - INFO - focal_alpha          : 1.0
+2026-04-24 16:49:08,934 - INFO - focal_gamma          : 2.0
+2026-04-24 16:49:08,934 - INFO - r_drop_alpha         : 10.0
+2026-04-24 16:49:08,936 - INFO - infonce_temperature  : 0.07
+2026-04-24 16:49:08,937 - INFO - infonce_weight       : 0.5
+2026-04-24 16:49:08,937 - INFO - seed                 : 42
+2026-04-24 16:49:08,938 - INFO - resume_from_checkpoint : output_checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-500
+2026-04-24 16:49:08,939 - INFO - label_smoothing      : 0.5
+2026-04-24 16:49:08,939 - INFO - adversarial_epsilon  : 0.5
+2026-04-24 16:49:08,940 - INFO - use_swa              : False
+2026-04-24 16:49:08,941 - INFO - swa_start_epoch      : 0
+2026-04-24 16:49:08,942 - INFO - swa_lr               : 1e-05
+2026-04-24 16:49:08,943 - INFO - data_augmentation    : True
+2026-04-24 16:49:08,944 - INFO - aug_rename_prob      : 0.8
+2026-04-24 16:49:08,944 - INFO - aug_format_prob      : 0.8
+2026-04-24 16:49:08,945 - INFO - mixup_alpha          : 1.0
+2026-04-24 16:49:08,946 - INFO - low_pass_keep_ratio  : 0.5
+2026-04-24 16:49:08,947 - INFO - freq_consistency_weight : 0.5
+2026-04-24 16:49:08,947 - INFO - hidden_dropout_prob  : 0.3
+2026-04-24 16:49:08,948 - INFO - attention_probs_dropout_prob : 0.3
+2026-04-24 16:49:08,949 - INFO - classifier_dropout   : 0.3
+2026-04-24 16:49:08,949 - INFO - =================================
+2026-04-24 16:49:10,130 - INFO - Model placed on cuda
+2026-04-24 16:49:10,132 - INFO - ===== Model Architecture =====
+2026-04-24 16:49:10,134 - INFO - 
 RobertaForSequenceClassification(
   (roberta): RobertaModel(
     (embeddings): RobertaEmbeddings(
@@ -79,12 +79,12 @@ RobertaForSequenceClassification(
     (out_proj): Linear(in_features=768, out_features=2, bias=True)
   )
 )
-2026-04-24 15:00:15,032 - INFO - ===== Parameter Summary =====
-2026-04-24 15:00:15,033 - INFO - Total Parameters:         124,647,170
-2026-04-24 15:00:15,035 - INFO - Trainable Parameters:     592,130
-2026-04-24 15:00:15,036 - INFO - Non-trainable Parameters: 124,055,040
-2026-04-24 15:00:15,037 - INFO - ===== Tokenizer Summary =====
-2026-04-24 15:00:15,053 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']
-2026-04-24 15:00:15,054 - INFO - ===== End of Architecture Log =====
-2026-04-24 15:00:15,056 - INFO - Data augmentation enabled (rename=0.8, format=0.8)
-2026-04-24 15:00:50,114 - INFO - === Starting training with MixCode + FFT low-pass consistency ===
+2026-04-24 16:49:10,136 - INFO - ===== Parameter Summary =====
+2026-04-24 16:49:10,137 - INFO - Total Parameters:         124,647,170
+2026-04-24 16:49:10,138 - INFO - Trainable Parameters:     592,130
+2026-04-24 16:49:10,138 - INFO - Non-trainable Parameters: 124,055,040
+2026-04-24 16:49:10,139 - INFO - ===== Tokenizer Summary =====
+2026-04-24 16:49:10,153 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']
+2026-04-24 16:49:10,154 - INFO - ===== End of Architecture Log =====
+2026-04-24 16:49:10,155 - INFO - Data augmentation enabled (rename=0.8, format=0.8)
+2026-04-24 16:49:44,436 - INFO - === Starting training with MixCode + FFT low-pass consistency ===