upload graphcodebert base, more training = more assign to majority class, poor f1 score T_T

graphcodebert-rdrop/checkpoint-200/config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.2,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.2,
+  "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",
+  "transformers_version": "4.56.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

graphcodebert-rdrop/checkpoint-200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac86433275c4c5f90dffc8271cd1029e8abe70a5522abf0e31073eec45c4cc88
+size 498612824

graphcodebert-rdrop/checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:761c23060e28359071290c62124dfb044d0a38ac5d9e8e3b1a604a5b25c74779
+size 4741923

graphcodebert-rdrop/checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05078194d8454a14fc0bdecb57189f4d64fb75d172e61d32a02397899f3aecad
+size 14645

graphcodebert-rdrop/checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3347c274cf8389fea5bc6a6e8736d647cc7704359db22052e77f18e8ed9d685
+size 1465

graphcodebert-rdrop/checkpoint-200/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-rdrop/checkpoint-200/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-rdrop/checkpoint-200/trainer_state.json

@@ -0,0 +1,183 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0128,
+  "eval_steps": 1000,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00064,
+      "grad_norm": 1.2594444751739502,
+      "learning_rate": 3.840409643695328e-08,
+      "loss": 0.7238,
+      "step": 10
+    },
+    {
+      "epoch": 0.00128,
+      "grad_norm": 1.3807746171951294,
+      "learning_rate": 8.10753147002347e-08,
+      "loss": 0.7178,
+      "step": 20
+    },
+    {
+      "epoch": 0.00192,
+      "grad_norm": 0.9590708613395691,
+      "learning_rate": 1.2374653296351612e-07,
+      "loss": 0.7106,
+      "step": 30
+    },
+    {
+      "epoch": 0.00256,
+      "grad_norm": 1.2128362655639648,
+      "learning_rate": 1.6641775122679754e-07,
+      "loss": 0.72,
+      "step": 40
+    },
+    {
+      "epoch": 0.0032,
+      "grad_norm": 1.0866276025772095,
+      "learning_rate": 2.0908896949007894e-07,
+      "loss": 0.7108,
+      "step": 50
+    },
+    {
+      "epoch": 0.00384,
+      "grad_norm": 1.6984202861785889,
+      "learning_rate": 2.517601877533604e-07,
+      "loss": 0.7149,
+      "step": 60
+    },
+    {
+      "epoch": 0.00448,
+      "grad_norm": 1.249053716659546,
+      "learning_rate": 2.944314060166418e-07,
+      "loss": 0.7243,
+      "step": 70
+    },
+    {
+      "epoch": 0.00512,
+      "grad_norm": 1.8781795501708984,
+      "learning_rate": 3.371026242799232e-07,
+      "loss": 0.7138,
+      "step": 80
+    },
+    {
+      "epoch": 0.00576,
+      "grad_norm": 2.162505626678467,
+      "learning_rate": 3.7977384254320464e-07,
+      "loss": 0.7117,
+      "step": 90
+    },
+    {
+      "epoch": 0.0064,
+      "grad_norm": 1.0761003494262695,
+      "learning_rate": 4.22445060806486e-07,
+      "loss": 0.7121,
+      "step": 100
+    },
+    {
+      "epoch": 0.00704,
+      "grad_norm": 2.104625940322876,
+      "learning_rate": 4.651162790697675e-07,
+      "loss": 0.7157,
+      "step": 110
+    },
+    {
+      "epoch": 0.00768,
+      "grad_norm": 1.6532983779907227,
+      "learning_rate": 5.077874973330489e-07,
+      "loss": 0.7175,
+      "step": 120
+    },
+    {
+      "epoch": 0.00832,
+      "grad_norm": 1.094260334968567,
+      "learning_rate": 5.504587155963304e-07,
+      "loss": 0.7142,
+      "step": 130
+    },
+    {
+      "epoch": 0.00896,
+      "grad_norm": 1.7268928289413452,
+      "learning_rate": 5.931299338596117e-07,
+      "loss": 0.717,
+      "step": 140
+    },
+    {
+      "epoch": 0.0096,
+      "grad_norm": 2.225884199142456,
+      "learning_rate": 6.358011521228932e-07,
+      "loss": 0.7144,
+      "step": 150
+    },
+    {
+      "epoch": 0.01024,
+      "grad_norm": 1.7743901014328003,
+      "learning_rate": 6.784723703861745e-07,
+      "loss": 0.7127,
+      "step": 160
+    },
+    {
+      "epoch": 0.01088,
+      "grad_norm": 1.1327497959136963,
+      "learning_rate": 7.21143588649456e-07,
+      "loss": 0.7148,
+      "step": 170
+    },
+    {
+      "epoch": 0.01152,
+      "grad_norm": 1.9613993167877197,
+      "learning_rate": 7.638148069127374e-07,
+      "loss": 0.711,
+      "step": 180
+    },
+    {
+      "epoch": 0.01216,
+      "grad_norm": 1.4991788864135742,
+      "learning_rate": 8.064860251760189e-07,
+      "loss": 0.713,
+      "step": 190
+    },
+    {
+      "epoch": 0.0128,
+      "grad_norm": 1.3405441045761108,
+      "learning_rate": 8.491572434393003e-07,
+      "loss": 0.7142,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 46875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "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": 1683335198870400.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

graphcodebert-rdrop/checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55254a25b9b4efe7714049fe098b28f448ef8c65f96c91f7ece8858052ae10e
+size 5841

graphcodebert-rdrop/checkpoint-400/config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.2,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.2,
+  "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",
+  "transformers_version": "4.56.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

graphcodebert-rdrop/checkpoint-400/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c7af6794354abb5176e56711587cff4a77f32904c163a4ce14c3c94984158e1
+size 498612824

graphcodebert-rdrop/checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30f7a1f5c79291da718c4ae121ac0f4c9a180b2f3af2e9661afc6d2c49de08c1
+size 4741923

graphcodebert-rdrop/checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac91714b1ca1b10faffc2b3166093fa82f8c414c080d20fb169232c67842ca9
+size 14645

graphcodebert-rdrop/checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e84ffe93840aa81e9948975fba71e7c089d586a9a468788d126a90f534f82ff
+size 1465

graphcodebert-rdrop/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-rdrop/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-rdrop/checkpoint-400/trainer_state.json

@@ -0,0 +1,323 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0256,
+  "eval_steps": 1000,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00064,
+      "grad_norm": 1.2594444751739502,
+      "learning_rate": 3.840409643695328e-08,
+      "loss": 0.7238,
+      "step": 10
+    },
+    {
+      "epoch": 0.00128,
+      "grad_norm": 1.3807746171951294,
+      "learning_rate": 8.10753147002347e-08,
+      "loss": 0.7178,
+      "step": 20
+    },
+    {
+      "epoch": 0.00192,
+      "grad_norm": 0.9590708613395691,
+      "learning_rate": 1.2374653296351612e-07,
+      "loss": 0.7106,
+      "step": 30
+    },
+    {
+      "epoch": 0.00256,
+      "grad_norm": 1.2128362655639648,
+      "learning_rate": 1.6641775122679754e-07,
+      "loss": 0.72,
+      "step": 40
+    },
+    {
+      "epoch": 0.0032,
+      "grad_norm": 1.0866276025772095,
+      "learning_rate": 2.0908896949007894e-07,
+      "loss": 0.7108,
+      "step": 50
+    },
+    {
+      "epoch": 0.00384,
+      "grad_norm": 1.6984202861785889,
+      "learning_rate": 2.517601877533604e-07,
+      "loss": 0.7149,
+      "step": 60
+    },
+    {
+      "epoch": 0.00448,
+      "grad_norm": 1.249053716659546,
+      "learning_rate": 2.944314060166418e-07,
+      "loss": 0.7243,
+      "step": 70
+    },
+    {
+      "epoch": 0.00512,
+      "grad_norm": 1.8781795501708984,
+      "learning_rate": 3.371026242799232e-07,
+      "loss": 0.7138,
+      "step": 80
+    },
+    {
+      "epoch": 0.00576,
+      "grad_norm": 2.162505626678467,
+      "learning_rate": 3.7977384254320464e-07,
+      "loss": 0.7117,
+      "step": 90
+    },
+    {
+      "epoch": 0.0064,
+      "grad_norm": 1.0761003494262695,
+      "learning_rate": 4.22445060806486e-07,
+      "loss": 0.7121,
+      "step": 100
+    },
+    {
+      "epoch": 0.00704,
+      "grad_norm": 2.104625940322876,
+      "learning_rate": 4.651162790697675e-07,
+      "loss": 0.7157,
+      "step": 110
+    },
+    {
+      "epoch": 0.00768,
+      "grad_norm": 1.6532983779907227,
+      "learning_rate": 5.077874973330489e-07,
+      "loss": 0.7175,
+      "step": 120
+    },
+    {
+      "epoch": 0.00832,
+      "grad_norm": 1.094260334968567,
+      "learning_rate": 5.504587155963304e-07,
+      "loss": 0.7142,
+      "step": 130
+    },
+    {
+      "epoch": 0.00896,
+      "grad_norm": 1.7268928289413452,
+      "learning_rate": 5.931299338596117e-07,
+      "loss": 0.717,
+      "step": 140
+    },
+    {
+      "epoch": 0.0096,
+      "grad_norm": 2.225884199142456,
+      "learning_rate": 6.358011521228932e-07,
+      "loss": 0.7144,
+      "step": 150
+    },
+    {
+      "epoch": 0.01024,
+      "grad_norm": 1.7743901014328003,
+      "learning_rate": 6.784723703861745e-07,
+      "loss": 0.7127,
+      "step": 160
+    },
+    {
+      "epoch": 0.01088,
+      "grad_norm": 1.1327497959136963,
+      "learning_rate": 7.21143588649456e-07,
+      "loss": 0.7148,
+      "step": 170
+    },
+    {
+      "epoch": 0.01152,
+      "grad_norm": 1.9613993167877197,
+      "learning_rate": 7.638148069127374e-07,
+      "loss": 0.711,
+      "step": 180
+    },
+    {
+      "epoch": 0.01216,
+      "grad_norm": 1.4991788864135742,
+      "learning_rate": 8.064860251760189e-07,
+      "loss": 0.713,
+      "step": 190
+    },
+    {
+      "epoch": 0.0128,
+      "grad_norm": 1.3405441045761108,
+      "learning_rate": 8.491572434393003e-07,
+      "loss": 0.7142,
+      "step": 200
+    },
+    {
+      "epoch": 0.01344,
+      "grad_norm": 1.8038678169250488,
+      "learning_rate": 8.918284617025817e-07,
+      "loss": 0.7067,
+      "step": 210
+    },
+    {
+      "epoch": 0.01408,
+      "grad_norm": 1.2749669551849365,
+      "learning_rate": 9.344996799658632e-07,
+      "loss": 0.7133,
+      "step": 220
+    },
+    {
+      "epoch": 0.01472,
+      "grad_norm": 1.858957052230835,
+      "learning_rate": 9.771708982291445e-07,
+      "loss": 0.7093,
+      "step": 230
+    },
+    {
+      "epoch": 0.01536,
+      "grad_norm": 1.1406413316726685,
+      "learning_rate": 1.0198421164924258e-06,
+      "loss": 0.7163,
+      "step": 240
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 1.3233072757720947,
+      "learning_rate": 1.0625133347557074e-06,
+      "loss": 0.7152,
+      "step": 250
+    },
+    {
+      "epoch": 0.01664,
+      "grad_norm": 2.3287241458892822,
+      "learning_rate": 1.1051845530189888e-06,
+      "loss": 0.712,
+      "step": 260
+    },
+    {
+      "epoch": 0.01728,
+      "grad_norm": 1.6007124185562134,
+      "learning_rate": 1.1478557712822702e-06,
+      "loss": 0.711,
+      "step": 270
+    },
+    {
+      "epoch": 0.01792,
+      "grad_norm": 1.5458295345306396,
+      "learning_rate": 1.1905269895455517e-06,
+      "loss": 0.7107,
+      "step": 280
+    },
+    {
+      "epoch": 0.01856,
+      "grad_norm": 1.6052477359771729,
+      "learning_rate": 1.233198207808833e-06,
+      "loss": 0.7142,
+      "step": 290
+    },
+    {
+      "epoch": 0.0192,
+      "grad_norm": 1.7393243312835693,
+      "learning_rate": 1.2758694260721145e-06,
+      "loss": 0.7126,
+      "step": 300
+    },
+    {
+      "epoch": 0.01984,
+      "grad_norm": 1.3717942237854004,
+      "learning_rate": 1.318540644335396e-06,
+      "loss": 0.7053,
+      "step": 310
+    },
+    {
+      "epoch": 0.02048,
+      "grad_norm": 1.41959810256958,
+      "learning_rate": 1.3612118625986772e-06,
+      "loss": 0.7011,
+      "step": 320
+    },
+    {
+      "epoch": 0.02112,
+      "grad_norm": 1.365114450454712,
+      "learning_rate": 1.4038830808619588e-06,
+      "loss": 0.707,
+      "step": 330
+    },
+    {
+      "epoch": 0.02176,
+      "grad_norm": 1.775238037109375,
+      "learning_rate": 1.4465542991252401e-06,
+      "loss": 0.7148,
+      "step": 340
+    },
+    {
+      "epoch": 0.0224,
+      "grad_norm": 2.691812753677368,
+      "learning_rate": 1.4892255173885215e-06,
+      "loss": 0.6986,
+      "step": 350
+    },
+    {
+      "epoch": 0.02304,
+      "grad_norm": 1.2819510698318481,
+      "learning_rate": 1.531896735651803e-06,
+      "loss": 0.7029,
+      "step": 360
+    },
+    {
+      "epoch": 0.02368,
+      "grad_norm": 1.1647347211837769,
+      "learning_rate": 1.5745679539150842e-06,
+      "loss": 0.7108,
+      "step": 370
+    },
+    {
+      "epoch": 0.02432,
+      "grad_norm": 0.9920722246170044,
+      "learning_rate": 1.6172391721783658e-06,
+      "loss": 0.706,
+      "step": 380
+    },
+    {
+      "epoch": 0.02496,
+      "grad_norm": 1.785387396812439,
+      "learning_rate": 1.6599103904416472e-06,
+      "loss": 0.7048,
+      "step": 390
+    },
+    {
+      "epoch": 0.0256,
+      "grad_norm": 1.7709925174713135,
+      "learning_rate": 1.7025816087049288e-06,
+      "loss": 0.7035,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 46875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "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": 3366473064449280.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

graphcodebert-rdrop/checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b29dd79ae441841dc571db61d494e30f73624176dfb9556119a957227915b449
+size 5841

graphcodebert-rdrop/checkpoint-600/config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.2,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.2,
+  "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",
+  "transformers_version": "4.56.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

graphcodebert-rdrop/checkpoint-600/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:237a188dd89cb8f8787a556a958e47d123d8a5545f8fb983ac22180e1d8fdb26
+size 498612824

graphcodebert-rdrop/checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63969bd711b3b9a06f9ee5ce6fd1f54e14c69bbd566d87e2f76269921f9a42e1
+size 4741923

graphcodebert-rdrop/checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553b98652394d48ab7a54806010d744d4b985d5fa251013aa99bbeec34071858
+size 14645

graphcodebert-rdrop/checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc3b50716096a3599e2b59ac0e24bd96040981e5d6cff058a87c0845284d3026
+size 1465

graphcodebert-rdrop/checkpoint-600/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-rdrop/checkpoint-600/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-rdrop/checkpoint-600/trainer_state.json

@@ -0,0 +1,463 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0384,
+  "eval_steps": 1000,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00064,
+      "grad_norm": 1.2594444751739502,
+      "learning_rate": 3.840409643695328e-08,
+      "loss": 0.7238,
+      "step": 10
+    },
+    {
+      "epoch": 0.00128,
+      "grad_norm": 1.3807746171951294,
+      "learning_rate": 8.10753147002347e-08,
+      "loss": 0.7178,
+      "step": 20
+    },
+    {
+      "epoch": 0.00192,
+      "grad_norm": 0.9590708613395691,
+      "learning_rate": 1.2374653296351612e-07,
+      "loss": 0.7106,
+      "step": 30
+    },
+    {
+      "epoch": 0.00256,
+      "grad_norm": 1.2128362655639648,
+      "learning_rate": 1.6641775122679754e-07,
+      "loss": 0.72,
+      "step": 40
+    },
+    {
+      "epoch": 0.0032,
+      "grad_norm": 1.0866276025772095,
+      "learning_rate": 2.0908896949007894e-07,
+      "loss": 0.7108,
+      "step": 50
+    },
+    {
+      "epoch": 0.00384,
+      "grad_norm": 1.6984202861785889,
+      "learning_rate": 2.517601877533604e-07,
+      "loss": 0.7149,
+      "step": 60
+    },
+    {
+      "epoch": 0.00448,
+      "grad_norm": 1.249053716659546,
+      "learning_rate": 2.944314060166418e-07,
+      "loss": 0.7243,
+      "step": 70
+    },
+    {
+      "epoch": 0.00512,
+      "grad_norm": 1.8781795501708984,
+      "learning_rate": 3.371026242799232e-07,
+      "loss": 0.7138,
+      "step": 80
+    },
+    {
+      "epoch": 0.00576,
+      "grad_norm": 2.162505626678467,
+      "learning_rate": 3.7977384254320464e-07,
+      "loss": 0.7117,
+      "step": 90
+    },
+    {
+      "epoch": 0.0064,
+      "grad_norm": 1.0761003494262695,
+      "learning_rate": 4.22445060806486e-07,
+      "loss": 0.7121,
+      "step": 100
+    },
+    {
+      "epoch": 0.00704,
+      "grad_norm": 2.104625940322876,
+      "learning_rate": 4.651162790697675e-07,
+      "loss": 0.7157,
+      "step": 110
+    },
+    {
+      "epoch": 0.00768,
+      "grad_norm": 1.6532983779907227,
+      "learning_rate": 5.077874973330489e-07,
+      "loss": 0.7175,
+      "step": 120
+    },
+    {
+      "epoch": 0.00832,
+      "grad_norm": 1.094260334968567,
+      "learning_rate": 5.504587155963304e-07,
+      "loss": 0.7142,
+      "step": 130
+    },
+    {
+      "epoch": 0.00896,
+      "grad_norm": 1.7268928289413452,
+      "learning_rate": 5.931299338596117e-07,
+      "loss": 0.717,
+      "step": 140
+    },
+    {
+      "epoch": 0.0096,
+      "grad_norm": 2.225884199142456,
+      "learning_rate": 6.358011521228932e-07,
+      "loss": 0.7144,
+      "step": 150
+    },
+    {
+      "epoch": 0.01024,
+      "grad_norm": 1.7743901014328003,
+      "learning_rate": 6.784723703861745e-07,
+      "loss": 0.7127,
+      "step": 160
+    },
+    {
+      "epoch": 0.01088,
+      "grad_norm": 1.1327497959136963,
+      "learning_rate": 7.21143588649456e-07,
+      "loss": 0.7148,
+      "step": 170
+    },
+    {
+      "epoch": 0.01152,
+      "grad_norm": 1.9613993167877197,
+      "learning_rate": 7.638148069127374e-07,
+      "loss": 0.711,
+      "step": 180
+    },
+    {
+      "epoch": 0.01216,
+      "grad_norm": 1.4991788864135742,
+      "learning_rate": 8.064860251760189e-07,
+      "loss": 0.713,
+      "step": 190
+    },
+    {
+      "epoch": 0.0128,
+      "grad_norm": 1.3405441045761108,
+      "learning_rate": 8.491572434393003e-07,
+      "loss": 0.7142,
+      "step": 200
+    },
+    {
+      "epoch": 0.01344,
+      "grad_norm": 1.8038678169250488,
+      "learning_rate": 8.918284617025817e-07,
+      "loss": 0.7067,
+      "step": 210
+    },
+    {
+      "epoch": 0.01408,
+      "grad_norm": 1.2749669551849365,
+      "learning_rate": 9.344996799658632e-07,
+      "loss": 0.7133,
+      "step": 220
+    },
+    {
+      "epoch": 0.01472,
+      "grad_norm": 1.858957052230835,
+      "learning_rate": 9.771708982291445e-07,
+      "loss": 0.7093,
+      "step": 230
+    },
+    {
+      "epoch": 0.01536,
+      "grad_norm": 1.1406413316726685,
+      "learning_rate": 1.0198421164924258e-06,
+      "loss": 0.7163,
+      "step": 240
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 1.3233072757720947,
+      "learning_rate": 1.0625133347557074e-06,
+      "loss": 0.7152,
+      "step": 250
+    },
+    {
+      "epoch": 0.01664,
+      "grad_norm": 2.3287241458892822,
+      "learning_rate": 1.1051845530189888e-06,
+      "loss": 0.712,
+      "step": 260
+    },
+    {
+      "epoch": 0.01728,
+      "grad_norm": 1.6007124185562134,
+      "learning_rate": 1.1478557712822702e-06,
+      "loss": 0.711,
+      "step": 270
+    },
+    {
+      "epoch": 0.01792,
+      "grad_norm": 1.5458295345306396,
+      "learning_rate": 1.1905269895455517e-06,
+      "loss": 0.7107,
+      "step": 280
+    },
+    {
+      "epoch": 0.01856,
+      "grad_norm": 1.6052477359771729,
+      "learning_rate": 1.233198207808833e-06,
+      "loss": 0.7142,
+      "step": 290
+    },
+    {
+      "epoch": 0.0192,
+      "grad_norm": 1.7393243312835693,
+      "learning_rate": 1.2758694260721145e-06,
+      "loss": 0.7126,
+      "step": 300
+    },
+    {
+      "epoch": 0.01984,
+      "grad_norm": 1.3717942237854004,
+      "learning_rate": 1.318540644335396e-06,
+      "loss": 0.7053,
+      "step": 310
+    },
+    {
+      "epoch": 0.02048,
+      "grad_norm": 1.41959810256958,
+      "learning_rate": 1.3612118625986772e-06,
+      "loss": 0.7011,
+      "step": 320
+    },
+    {
+      "epoch": 0.02112,
+      "grad_norm": 1.365114450454712,
+      "learning_rate": 1.4038830808619588e-06,
+      "loss": 0.707,
+      "step": 330
+    },
+    {
+      "epoch": 0.02176,
+      "grad_norm": 1.775238037109375,
+      "learning_rate": 1.4465542991252401e-06,
+      "loss": 0.7148,
+      "step": 340
+    },
+    {
+      "epoch": 0.0224,
+      "grad_norm": 2.691812753677368,
+      "learning_rate": 1.4892255173885215e-06,
+      "loss": 0.6986,
+      "step": 350
+    },
+    {
+      "epoch": 0.02304,
+      "grad_norm": 1.2819510698318481,
+      "learning_rate": 1.531896735651803e-06,
+      "loss": 0.7029,
+      "step": 360
+    },
+    {
+      "epoch": 0.02368,
+      "grad_norm": 1.1647347211837769,
+      "learning_rate": 1.5745679539150842e-06,
+      "loss": 0.7108,
+      "step": 370
+    },
+    {
+      "epoch": 0.02432,
+      "grad_norm": 0.9920722246170044,
+      "learning_rate": 1.6172391721783658e-06,
+      "loss": 0.706,
+      "step": 380
+    },
+    {
+      "epoch": 0.02496,
+      "grad_norm": 1.785387396812439,
+      "learning_rate": 1.6599103904416472e-06,
+      "loss": 0.7048,
+      "step": 390
+    },
+    {
+      "epoch": 0.0256,
+      "grad_norm": 1.7709925174713135,
+      "learning_rate": 1.7025816087049288e-06,
+      "loss": 0.7035,
+      "step": 400
+    },
+    {
+      "epoch": 0.02624,
+      "grad_norm": 1.1243155002593994,
+      "learning_rate": 1.7452528269682101e-06,
+      "loss": 0.705,
+      "step": 410
+    },
+    {
+      "epoch": 0.02688,
+      "grad_norm": 1.0578358173370361,
+      "learning_rate": 1.7879240452314913e-06,
+      "loss": 0.6991,
+      "step": 420
+    },
+    {
+      "epoch": 0.02752,
+      "grad_norm": 1.3893680572509766,
+      "learning_rate": 1.8305952634947729e-06,
+      "loss": 0.7035,
+      "step": 430
+    },
+    {
+      "epoch": 0.02816,
+      "grad_norm": 1.2484132051467896,
+      "learning_rate": 1.8732664817580542e-06,
+      "loss": 0.7039,
+      "step": 440
+    },
+    {
+      "epoch": 0.0288,
+      "grad_norm": 1.351940393447876,
+      "learning_rate": 1.915937700021336e-06,
+      "loss": 0.7015,
+      "step": 450
+    },
+    {
+      "epoch": 0.02944,
+      "grad_norm": 1.9895719289779663,
+      "learning_rate": 1.958608918284617e-06,
+      "loss": 0.6939,
+      "step": 460
+    },
+    {
+      "epoch": 0.03008,
+      "grad_norm": 1.3872898817062378,
+      "learning_rate": 2.0012801365478988e-06,
+      "loss": 0.6943,
+      "step": 470
+    },
+    {
+      "epoch": 0.03072,
+      "grad_norm": 1.570786476135254,
+      "learning_rate": 2.04395135481118e-06,
+      "loss": 0.6956,
+      "step": 480
+    },
+    {
+      "epoch": 0.03136,
+      "grad_norm": 1.5123223066329956,
+      "learning_rate": 2.0866225730744615e-06,
+      "loss": 0.6993,
+      "step": 490
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 1.3728066682815552,
+      "learning_rate": 2.129293791337743e-06,
+      "loss": 0.7037,
+      "step": 500
+    },
+    {
+      "epoch": 0.03264,
+      "grad_norm": 1.3556452989578247,
+      "learning_rate": 2.1719650096010242e-06,
+      "loss": 0.701,
+      "step": 510
+    },
+    {
+      "epoch": 0.03328,
+      "grad_norm": 0.9301255941390991,
+      "learning_rate": 2.214636227864306e-06,
+      "loss": 0.6907,
+      "step": 520
+    },
+    {
+      "epoch": 0.03392,
+      "grad_norm": 1.0869609117507935,
+      "learning_rate": 2.257307446127587e-06,
+      "loss": 0.7002,
+      "step": 530
+    },
+    {
+      "epoch": 0.03456,
+      "grad_norm": 0.9792824387550354,
+      "learning_rate": 2.2999786643908685e-06,
+      "loss": 0.6968,
+      "step": 540
+    },
+    {
+      "epoch": 0.0352,
+      "grad_norm": 1.4169834852218628,
+      "learning_rate": 2.34264988265415e-06,
+      "loss": 0.6899,
+      "step": 550
+    },
+    {
+      "epoch": 0.03584,
+      "grad_norm": 1.0012285709381104,
+      "learning_rate": 2.3853211009174317e-06,
+      "loss": 0.6933,
+      "step": 560
+    },
+    {
+      "epoch": 0.03648,
+      "grad_norm": 1.2250874042510986,
+      "learning_rate": 2.427992319180713e-06,
+      "loss": 0.6916,
+      "step": 570
+    },
+    {
+      "epoch": 0.03712,
+      "grad_norm": 0.9640677571296692,
+      "learning_rate": 2.470663537443994e-06,
+      "loss": 0.6966,
+      "step": 580
+    },
+    {
+      "epoch": 0.03776,
+      "grad_norm": 2.0081069469451904,
+      "learning_rate": 2.5133347557072756e-06,
+      "loss": 0.6887,
+      "step": 590
+    },
+    {
+      "epoch": 0.0384,
+      "grad_norm": 1.0421005487442017,
+      "learning_rate": 2.556005973970557e-06,
+      "loss": 0.6901,
+      "step": 600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 46875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "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": 5048476263601920.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

graphcodebert-rdrop/checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd447c2d3c829ce951a029be939fd0b0d41ad5502fac28bccaae84457b935a5f
+size 5841

graphcodebert-rdrop/training.log

@@ -0,0 +1,58 @@
+2026-04-15 15:50:02,250 - INFO - train_pipeline - Logging to ./output_checkpoints/graphcodebert-rdrop/training.log
+2026-04-15 15:50:02,253 - INFO - train_pipeline - Loading model & tokenizer for 'microsoft/graphcodebert-base'
+2026-04-15 15:50:07,672 - INFO - train_pipeline - Model placed on cuda
+2026-04-15 15:50:07,680 - INFO - train_pipeline - Base model weights frozen – only classifier head will be trained.
+2026-04-15 15:50:07,686 - INFO - train_pipeline - ===== Model Architecture =====
+2026-04-15 15:50:07,691 - INFO - train_pipeline - 
+RobertaForSequenceClassification(
+  (roberta): RobertaModel(
+    (embeddings): RobertaEmbeddings(
+      (word_embeddings): Embedding(50265, 768, padding_idx=1)
+      (position_embeddings): Embedding(514, 768, padding_idx=1)
+      (token_type_embeddings): Embedding(1, 768)
+      (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+      (dropout): Dropout(p=0.2, inplace=False)
+    )
+    (encoder): RobertaEncoder(
+      (layer): ModuleList(
+        (0-11): 12 x RobertaLayer(
+          (attention): RobertaAttention(
+            (self): RobertaSdpaSelfAttention(
+              (query): Linear(in_features=768, out_features=768, bias=True)
+              (key): Linear(in_features=768, out_features=768, bias=True)
+              (value): Linear(in_features=768, out_features=768, bias=True)
+              (dropout): Dropout(p=0.2, inplace=False)
+            )
+            (output): RobertaSelfOutput(
+              (dense): Linear(in_features=768, out_features=768, bias=True)
+              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+              (dropout): Dropout(p=0.2, inplace=False)
+            )
+          )
+          (intermediate): RobertaIntermediate(
+            (dense): Linear(in_features=768, out_features=3072, bias=True)
+            (intermediate_act_fn): GELUActivation()
+          )
+          (output): RobertaOutput(
+            (dense): Linear(in_features=3072, out_features=768, bias=True)
+            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+            (dropout): Dropout(p=0.2, inplace=False)
+          )
+        )
+      )
+    )
+  )
+  (classifier): RobertaClassificationHead(
+    (dense): Linear(in_features=768, out_features=768, bias=True)
+    (dropout): Dropout(p=0.2, inplace=False)
+    (out_proj): Linear(in_features=768, out_features=2, bias=True)
+  )
+)
+2026-04-15 15:50:07,701 - INFO - train_pipeline - ===== Parameter Summary =====
+2026-04-15 15:50:07,703 - INFO - train_pipeline - Total Parameters:         124,647,170
+2026-04-15 15:50:07,707 - INFO - train_pipeline - Trainable Parameters:     592,130
+2026-04-15 15:50:07,712 - INFO - train_pipeline - Non-trainable Parameters: 124,055,040
+2026-04-15 15:50:07,713 - INFO - train_pipeline - ===== Tokenizer Summary =====
+2026-04-15 15:50:07,777 - INFO - train_pipeline - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']
+2026-04-15 15:50:07,778 - INFO - train_pipeline - ===== End of Architecture Log =====
+2026-04-15 15:50:11,291 - INFO - train_pipeline - === Starting training ===