dzungpham commited on Apr 20

Commit

64048a0

verified ·

1 Parent(s): 7343966

upload best checkpoints 100 graphcodebert mixcode fft

Browse files

Files changed (37) hide show

graphcodebert-mixcode-fft/checkpoint-100/config.json +2 -2
graphcodebert-mixcode-fft/checkpoint-100/model.safetensors +1 -1
graphcodebert-mixcode-fft/checkpoint-100/optimizer.pt +1 -1
graphcodebert-mixcode-fft/checkpoint-100/trainer_state.json +3 -74
graphcodebert-mixcode-fft/checkpoint-100/training_args.bin +1 -1
graphcodebert-mixcode-fft/checkpoint-150/config.json +29 -0
graphcodebert-mixcode-fft/checkpoint-150/merges.txt +0 -0
graphcodebert-mixcode-fft/checkpoint-150/model.safetensors +3 -0
graphcodebert-mixcode-fft/checkpoint-150/optimizer.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-150/rng_state.pth +3 -0
graphcodebert-mixcode-fft/checkpoint-150/scaler.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-150/scheduler.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-150/special_tokens_map.json +51 -0
graphcodebert-mixcode-fft/checkpoint-150/tokenizer.json +0 -0
graphcodebert-mixcode-fft/checkpoint-150/tokenizer_config.json +58 -0
graphcodebert-mixcode-fft/checkpoint-150/trainer_state.json +42 -0
graphcodebert-mixcode-fft/checkpoint-150/training_args.bin +3 -0
graphcodebert-mixcode-fft/checkpoint-150/vocab.json +0 -0
graphcodebert-mixcode-fft/checkpoint-200/config.json +2 -2
graphcodebert-mixcode-fft/checkpoint-200/model.safetensors +1 -1
graphcodebert-mixcode-fft/checkpoint-200/optimizer.pt +1 -1
graphcodebert-mixcode-fft/checkpoint-200/trainer_state.json +3 -144
graphcodebert-mixcode-fft/checkpoint-200/training_args.bin +1 -1
graphcodebert-mixcode-fft/checkpoint-50/config.json +29 -0
graphcodebert-mixcode-fft/checkpoint-50/merges.txt +0 -0
graphcodebert-mixcode-fft/checkpoint-50/model.safetensors +3 -0
graphcodebert-mixcode-fft/checkpoint-50/optimizer.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-50/rng_state.pth +3 -0
graphcodebert-mixcode-fft/checkpoint-50/scaler.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-50/scheduler.pt +3 -0
graphcodebert-mixcode-fft/checkpoint-50/special_tokens_map.json +51 -0
graphcodebert-mixcode-fft/checkpoint-50/tokenizer.json +0 -0
graphcodebert-mixcode-fft/checkpoint-50/tokenizer_config.json +58 -0
graphcodebert-mixcode-fft/checkpoint-50/trainer_state.json +42 -0
graphcodebert-mixcode-fft/checkpoint-50/training_args.bin +3 -0
graphcodebert-mixcode-fft/checkpoint-50/vocab.json +0 -0
graphcodebert-mixcode-fft/training.log +48 -43

graphcodebert-mixcode-fft/checkpoint-100/config.json CHANGED Viewed

@@ -2,14 +2,14 @@
   "architectures": [
     "RobertaForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
   "classifier_dropout": null,
   "dtype": "float32",
   "eos_token_id": 2,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,

   "architectures": [
     "RobertaForSequenceClassification"
   ],
+  "attention_probs_dropout_prob": 0.3,
   "bos_token_id": 0,
   "classifier_dropout": null,
   "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,

graphcodebert-mixcode-fft/checkpoint-100/model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ce9efb0838c3bb940be1057d74141678c8cc0e3a6a330ef621cf8aad644b455
 size 498612824

 version https://git-lfs.github.com/spec/v1
+oid sha256:7ce5189acfb1b35dd7dd1285c911a2ef357086548d29168992b5938cd160e1ae
 size 498612824

graphcodebert-mixcode-fft/checkpoint-100/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78242f3b36c02c4ea7862a3f30665f7dabb9d0541c792048a92db69abafa08df
 size 4741923

 version https://git-lfs.github.com/spec/v1
+oid sha256:ace6c83a38805d8c17594db298d934b6cafb273a7cad8eb56ef68dcdc5a2a197
 size 4741923

graphcodebert-mixcode-fft/checkpoint-100/trainer_state.json CHANGED Viewed

@@ -8,83 +8,12 @@
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.0012799180852425445,
-      "grad_norm": 1.2002202272415161,
-      "learning_rate": 1.4404609475032012e-07,
-      "loss": 0.714,
-      "step": 10
-    },
-    {
-      "epoch": 0.002559836170485089,
-      "grad_norm": 1.0710716247558594,
-      "learning_rate": 3.040973111395647e-07,
-      "loss": 0.7181,
-      "step": 20
-    },
-    {
-      "epoch": 0.0038397542557276334,
-      "grad_norm": 1.0631524324417114,
-      "learning_rate": 4.641485275288093e-07,
-      "loss": 0.7114,
-      "step": 30
-    },
-    {
-      "epoch": 0.005119672340970178,
-      "grad_norm": 1.1470946073532104,
-      "learning_rate": 6.241997439180538e-07,
-      "loss": 0.7083,
-      "step": 40
-    },
-    {
-      "epoch": 0.006399590426212722,
-      "grad_norm": 1.1680080890655518,
-      "learning_rate": 7.842509603072984e-07,
-      "loss": 0.7109,
-      "step": 50
-    },
-    {
-      "epoch": 0.007679508511455267,
-      "grad_norm": 0.6832358241081238,
-      "learning_rate": 9.44302176696543e-07,
-      "loss": 0.7131,
-      "step": 60
-    },
-    {
-      "epoch": 0.008959426596697812,
-      "grad_norm": 1.8029249906539917,
-      "learning_rate": 1.1043533930857875e-06,
-      "loss": 0.7092,
-      "step": 70
-    },
-    {
-      "epoch": 0.010239344681940356,
-      "grad_norm": 1.795204758644104,
-      "learning_rate": 1.264404609475032e-06,
-      "loss": 0.7063,
-      "step": 80
-    },
-    {
-      "epoch": 0.011519262767182901,
-      "grad_norm": 1.2713547945022583,
-      "learning_rate": 1.4244558258642767e-06,
-      "loss": 0.7126,
-      "step": 90
-    },
-    {
-      "epoch": 0.012799180852425445,
-      "grad_norm": 1.2709708213806152,
-      "learning_rate": 1.5845070422535212e-06,
-      "loss": 0.7069,
-      "step": 100
-    }
-  ],
-  "logging_steps": 10,
   "max_steps": 31252,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
-  "save_steps": 100,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {
       "args": {

   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 500,
   "max_steps": 31252,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
+  "save_steps": 50,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {
       "args": {

graphcodebert-mixcode-fft/checkpoint-100/training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55e805564976941c69ed81dd4f57f02f704352ee18e811a5a0c0eac53999ccb7
 size 5841

 version https://git-lfs.github.com/spec/v1
+oid sha256:fa9c87e083ead14f7252ffb7793b3455ceabdb506eb70b2e796633daaa744b3b
 size 5841

graphcodebert-mixcode-fft/checkpoint-150/config.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.3,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "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-mixcode-fft/checkpoint-150/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/checkpoint-150/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:566a457eebb14580aa532ff7a91f8a93a38c52de2a1c6c9154c6ab26dc2b235b
+size 498612824

graphcodebert-mixcode-fft/checkpoint-150/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:639008735bd5220a1a441168bcd7b2a6e6e7e9e2be36e0bb75b4f134f1e97524
+size 4741923

graphcodebert-mixcode-fft/checkpoint-150/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1ab5d9b7883402158b06e19f8996822866b180c7aea06211a57c26674b791a4c
+size 14645

graphcodebert-mixcode-fft/checkpoint-150/scaler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a646a858b71ab76099f4dca96d8db39ffde2f88258f5a4b082ff62947bcc11
+size 1383

graphcodebert-mixcode-fft/checkpoint-150/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:573db9e756c43820af5da9e296f458088b3276c8732587d9f6c86702a7309804
+size 1465

graphcodebert-mixcode-fft/checkpoint-150/special_tokens_map.json ADDED Viewed

	@@ -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-mixcode-fft/checkpoint-150/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/checkpoint-150/tokenizer_config.json ADDED Viewed

	@@ -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-mixcode-fft/checkpoint-150/trainer_state.json ADDED Viewed

	@@ -0,0 +1,42 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.019198771278638168,
+  "eval_steps": 1000,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 500,
+  "max_steps": 31252,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 2525866131456000.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

graphcodebert-mixcode-fft/checkpoint-150/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:fa9c87e083ead14f7252ffb7793b3455ceabdb506eb70b2e796633daaa744b3b
+size 5841

graphcodebert-mixcode-fft/checkpoint-150/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/checkpoint-200/config.json CHANGED Viewed

@@ -2,14 +2,14 @@
   "architectures": [
     "RobertaForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
   "classifier_dropout": null,
   "dtype": "float32",
   "eos_token_id": 2,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,

   "architectures": [
     "RobertaForSequenceClassification"
   ],
+  "attention_probs_dropout_prob": 0.3,
   "bos_token_id": 0,
   "classifier_dropout": null,
   "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,

graphcodebert-mixcode-fft/checkpoint-200/model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c44ac861ac2b8fa337d7fb36dbec3be1474c43bf7e3cd7ab7daad107f775dc3
 size 498612824

 version https://git-lfs.github.com/spec/v1
+oid sha256:4959ac49df25d850e0647dc016dfaa25f8e9d95e4c1a7dfa21d2dfb4d297221f
 size 498612824

graphcodebert-mixcode-fft/checkpoint-200/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f717867bc2c783e925375ba468503dfe9d122ce9405c04cfa35dbce370d3459
 size 4741923

 version https://git-lfs.github.com/spec/v1
+oid sha256:9be0a3572824221e76a9dea62a892f90890c9b5f53c5e85f3c5d9d5247276b01
 size 4741923

graphcodebert-mixcode-fft/checkpoint-200/trainer_state.json CHANGED Viewed

@@ -8,153 +8,12 @@
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.0012799180852425445,
-      "grad_norm": 1.2002202272415161,
-      "learning_rate": 1.4404609475032012e-07,
-      "loss": 0.714,
-      "step": 10
-    },
-    {
-      "epoch": 0.002559836170485089,
-      "grad_norm": 1.0710716247558594,
-      "learning_rate": 3.040973111395647e-07,
-      "loss": 0.7181,
-      "step": 20
-    },
-    {
-      "epoch": 0.0038397542557276334,
-      "grad_norm": 1.0631524324417114,
-      "learning_rate": 4.641485275288093e-07,
-      "loss": 0.7114,
-      "step": 30
-    },
-    {
-      "epoch": 0.005119672340970178,
-      "grad_norm": 1.1470946073532104,
-      "learning_rate": 6.241997439180538e-07,
-      "loss": 0.7083,
-      "step": 40
-    },
-    {
-      "epoch": 0.006399590426212722,
-      "grad_norm": 1.1680080890655518,
-      "learning_rate": 7.842509603072984e-07,
-      "loss": 0.7109,
-      "step": 50
-    },
-    {
-      "epoch": 0.007679508511455267,
-      "grad_norm": 0.6832358241081238,
-      "learning_rate": 9.44302176696543e-07,
-      "loss": 0.7131,
-      "step": 60
-    },
-    {
-      "epoch": 0.008959426596697812,
-      "grad_norm": 1.8029249906539917,
-      "learning_rate": 1.1043533930857875e-06,
-      "loss": 0.7092,
-      "step": 70
-    },
-    {
-      "epoch": 0.010239344681940356,
-      "grad_norm": 1.795204758644104,
-      "learning_rate": 1.264404609475032e-06,
-      "loss": 0.7063,
-      "step": 80
-    },
-    {
-      "epoch": 0.011519262767182901,
-      "grad_norm": 1.2713547945022583,
-      "learning_rate": 1.4244558258642767e-06,
-      "loss": 0.7126,
-      "step": 90
-    },
-    {
-      "epoch": 0.012799180852425445,
-      "grad_norm": 1.2709708213806152,
-      "learning_rate": 1.5845070422535212e-06,
-      "loss": 0.7069,
-      "step": 100
-    },
-    {
-      "epoch": 0.01407909893766799,
-      "grad_norm": 0.8230543732643127,
-      "learning_rate": 1.7445582586427658e-06,
-      "loss": 0.7036,
-      "step": 110
-    },
-    {
-      "epoch": 0.015359017022910534,
-      "grad_norm": 0.7209059596061707,
-      "learning_rate": 1.9046094750320101e-06,
-      "loss": 0.7058,
-      "step": 120
-    },
-    {
-      "epoch": 0.016638935108153077,
-      "grad_norm": 0.7314836978912354,
-      "learning_rate": 2.064660691421255e-06,
-      "loss": 0.7046,
-      "step": 130
-    },
-    {
-      "epoch": 0.017918853193395624,
-      "grad_norm": 0.7659752368927002,
-      "learning_rate": 2.2247119078104993e-06,
-      "loss": 0.6989,
-      "step": 140
-    },
-    {
-      "epoch": 0.019198771278638168,
-      "grad_norm": 0.9008486866950989,
-      "learning_rate": 2.384763124199744e-06,
-      "loss": 0.6998,
-      "step": 150
-    },
-    {
-      "epoch": 0.02047868936388071,
-      "grad_norm": 1.0409601926803589,
-      "learning_rate": 2.5448143405889883e-06,
-      "loss": 0.7016,
-      "step": 160
-    },
-    {
-      "epoch": 0.021758607449123255,
-      "grad_norm": 0.8855634927749634,
-      "learning_rate": 2.704865556978233e-06,
-      "loss": 0.6947,
-      "step": 170
-    },
-    {
-      "epoch": 0.023038525534365802,
-      "grad_norm": 0.798701286315918,
-      "learning_rate": 2.8649167733674777e-06,
-      "loss": 0.6935,
-      "step": 180
-    },
-    {
-      "epoch": 0.024318443619608346,
-      "grad_norm": 1.1289243698120117,
-      "learning_rate": 3.024967989756722e-06,
-      "loss": 0.6937,
-      "step": 190
-    },
-    {
-      "epoch": 0.02559836170485089,
-      "grad_norm": 1.4480715990066528,
-      "learning_rate": 3.185019206145967e-06,
-      "loss": 0.6948,
-      "step": 200
-    }
-  ],
-  "logging_steps": 10,
   "max_steps": 31252,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
-  "save_steps": 100,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {
       "args": {

   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 500,
   "max_steps": 31252,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
+  "save_steps": 50,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {
       "args": {

graphcodebert-mixcode-fft/checkpoint-200/training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55e805564976941c69ed81dd4f57f02f704352ee18e811a5a0c0eac53999ccb7
 size 5841

 version https://git-lfs.github.com/spec/v1
+oid sha256:fa9c87e083ead14f7252ffb7793b3455ceabdb506eb70b2e796633daaa744b3b
 size 5841

graphcodebert-mixcode-fft/checkpoint-50/config.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.3,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "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-mixcode-fft/checkpoint-50/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/checkpoint-50/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2db14f5114245d187b99f238d17b991310a9158b9f15747570eed5a460543c19
+size 498612824

graphcodebert-mixcode-fft/checkpoint-50/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1d5f2a4e29cfecb88fea98d32a77638bb186493bafd4d26755ec5399033d3225
+size 4741923

graphcodebert-mixcode-fft/checkpoint-50/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:08caf38b13d45258389b41019ea11e8ec28ca9257b10c167e0da2af4ab8e3ec5
+size 14645

graphcodebert-mixcode-fft/checkpoint-50/scaler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd0e9d505fbc3f97feb166d29026132bdf14eb3e5c7ff77beebc303ee666f96
+size 1383

graphcodebert-mixcode-fft/checkpoint-50/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7756c907490b9f11094d9d0b65eab9e2f6c0d2e9db730159269a95547e959a02
+size 1465

graphcodebert-mixcode-fft/checkpoint-50/special_tokens_map.json ADDED Viewed

	@@ -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-mixcode-fft/checkpoint-50/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/checkpoint-50/tokenizer_config.json ADDED Viewed

	@@ -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-mixcode-fft/checkpoint-50/trainer_state.json ADDED Viewed

	@@ -0,0 +1,42 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.006399590426212722,
+  "eval_steps": 1000,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 500,
+  "max_steps": 31252,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 841955377152000.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

graphcodebert-mixcode-fft/checkpoint-50/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:fa9c87e083ead14f7252ffb7793b3455ceabdb506eb70b2e796633daaa744b3b
+size 5841

graphcodebert-mixcode-fft/checkpoint-50/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

graphcodebert-mixcode-fft/training.log CHANGED Viewed

@@ -1,36 +1,41 @@
-2026-04-17 15:38:49,100 - INFO - ===== Training Configuration =====
-2026-04-17 15:38:49,102 - INFO - model_name           : microsoft/graphcodebert-base
-2026-04-17 15:38:49,105 - INFO - output_dir           : output_checkpoints/graphcodebert-mixcode-fft
-2026-04-17 15:38:49,108 - INFO - num_epochs           : 4
-2026-04-17 15:38:49,110 - INFO - batch_size           : 64
-2026-04-17 15:38:49,112 - INFO - learning_rate        : 5e-05
-2026-04-17 15:38:49,114 - INFO - max_length           : 512
-2026-04-17 15:38:49,116 - INFO - num_labels           : 2
-2026-04-17 15:38:49,117 - INFO - use_wandb            : True
-2026-04-17 15:38:49,120 - INFO - freeze_base          : True
-2026-04-17 15:38:49,122 - INFO - loss_type            : r-drop
-2026-04-17 15:38:49,124 - INFO - focal_alpha          : 1.0
-2026-04-17 15:38:49,125 - INFO - focal_gamma          : 2.0
-2026-04-17 15:38:49,127 - INFO - r_drop_alpha         : 6.0
-2026-04-17 15:38:49,129 - INFO - infonce_temperature  : 0.07
-2026-04-17 15:38:49,131 - INFO - infonce_weight       : 0.5
-2026-04-17 15:38:49,134 - INFO - seed                 : 42
-2026-04-17 15:38:49,136 - INFO - resume_from_checkpoint : None
-2026-04-17 15:38:49,138 - INFO - label_smoothing      : 0.2
-2026-04-17 15:38:49,140 - INFO - adversarial_epsilon  : 0.5
-2026-04-17 15:38:49,141 - INFO - use_swa              : True
-2026-04-17 15:38:49,142 - INFO - swa_start_epoch      : 2
-2026-04-17 15:38:49,144 - INFO - swa_lr               : 1e-05
-2026-04-17 15:38:49,146 - INFO - data_augmentation    : True
-2026-04-17 15:38:49,147 - INFO - aug_rename_prob      : 0.6
-2026-04-17 15:38:49,149 - INFO - aug_format_prob      : 0.6
-2026-04-17 15:38:49,151 - INFO - mixup_alpha          : 1.0
-2026-04-17 15:38:49,152 - INFO - low_pass_keep_ratio  : 0.5
-2026-04-17 15:38:49,153 - INFO - freq_consistency_weight : 0.1
-2026-04-17 15:38:49,154 - INFO - =================================
-2026-04-17 15:38:51,130 - INFO - Model placed on cuda
-2026-04-17 15:38:51,137 - INFO - ===== Model Architecture =====
-2026-04-17 15:38:51,140 - INFO -
 RobertaForSequenceClassification(
   (roberta): RobertaModel(
     (embeddings): RobertaEmbeddings(
@@ -71,16 +76,16 @@ RobertaForSequenceClassification(
   )
   (classifier): RobertaClassificationHead(
     (dense): Linear(in_features=768, out_features=768, bias=True)
-    (dropout): Dropout(p=0.1, inplace=False)
     (out_proj): Linear(in_features=768, out_features=2, bias=True)
   )
 )
-2026-04-17 15:38:51,145 - INFO - ===== Parameter Summary =====
-2026-04-17 15:38:51,148 - INFO - Total Parameters:         124,647,170
-2026-04-17 15:38:51,150 - INFO - Trainable Parameters:     592,130
-2026-04-17 15:38:51,153 - INFO - Non-trainable Parameters: 124,055,040
-2026-04-17 15:38:51,155 - INFO - ===== Tokenizer Summary =====
-2026-04-17 15:38:51,176 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']
-2026-04-17 15:38:51,177 - INFO - ===== End of Architecture Log =====
-2026-04-17 15:38:51,179 - INFO - Data augmentation enabled (rename=0.6, format=0.6)
-2026-04-17 15:38:59,697 - INFO - === Starting training with MixCode + FFT low-pass consistency ===

+2026-04-20 11:06:55,458 - INFO - ===== Training Configuration =====
+2026-04-20 11:06:55,460 - INFO - model_name           : microsoft/graphcodebert-base
+2026-04-20 11:06:55,464 - INFO - output_dir           : output_checkpoints/graphcodebert-mixcode-fft
+2026-04-20 11:06:55,466 - INFO - num_epochs           : 4
+2026-04-20 11:06:55,467 - INFO - batch_size           : 64
+2026-04-20 11:06:55,468 - INFO - learning_rate        : 5e-05
+2026-04-20 11:06:55,471 - INFO - max_length           : 512
+2026-04-20 11:06:55,472 - INFO - num_labels           : 2
+2026-04-20 11:06:55,474 - INFO - use_wandb            : True
+2026-04-20 11:06:55,475 - INFO - freeze_base          : True
+2026-04-20 11:06:55,476 - INFO - loss_type            : r-drop
+2026-04-20 11:06:55,478 - INFO - focal_alpha          : 1.0
+2026-04-20 11:06:55,480 - INFO - focal_gamma          : 2.0
+2026-04-20 11:06:55,482 - INFO - r_drop_alpha         : 6.0
+2026-04-20 11:06:55,483 - INFO - infonce_temperature  : 0.07
+2026-04-20 11:06:55,485 - INFO - infonce_weight       : 0.5
+2026-04-20 11:06:55,487 - INFO - seed                 : 42
+2026-04-20 11:06:55,488 - INFO - resume_from_checkpoint : None
+2026-04-20 11:06:55,490 - INFO - save_steps           : 50
+2026-04-20 11:06:55,491 - INFO - eval_steps           : 1000
+2026-04-20 11:06:55,494 - INFO - label_smoothing      : 0.3
+2026-04-20 11:06:55,499 - INFO - adversarial_epsilon  : 0.5
+2026-04-20 11:06:55,504 - INFO - use_swa              : True
+2026-04-20 11:06:55,508 - INFO - swa_start_epoch      : 2
+2026-04-20 11:06:55,510 - INFO - swa_lr               : 1e-05
+2026-04-20 11:06:55,511 - INFO - data_augmentation    : True
+2026-04-20 11:06:55,512 - INFO - aug_rename_prob      : 0.6
+2026-04-20 11:06:55,514 - INFO - aug_format_prob      : 0.6
+2026-04-20 11:06:55,516 - INFO - hidden_dropout_prob  : 0.3
+2026-04-20 11:06:55,518 - INFO - attention_probs_dropout_prob : 0.3
+2026-04-20 11:06:55,519 - INFO - classifier_dropout   : 0.3
+2026-04-20 11:06:55,521 - INFO - mixup_alpha          : 1.0
+2026-04-20 11:06:55,523 - INFO - low_pass_keep_ratio  : 0.5
+2026-04-20 11:06:55,524 - INFO - freq_consistency_weight : 0.2
+2026-04-20 11:06:55,526 - INFO - =================================
+2026-04-20 11:06:59,772 - INFO - Model placed on cuda
+2026-04-20 11:06:59,789 - INFO - ===== Model Architecture =====
+2026-04-20 11:06:59,794 - INFO -
 RobertaForSequenceClassification(
   (roberta): RobertaModel(
     (embeddings): RobertaEmbeddings(
   )
   (classifier): RobertaClassificationHead(
     (dense): Linear(in_features=768, out_features=768, bias=True)
+    (dropout): Dropout(p=0.3, inplace=False)
     (out_proj): Linear(in_features=768, out_features=2, bias=True)
   )
 )
+2026-04-20 11:06:59,803 - INFO - ===== Parameter Summary =====
+2026-04-20 11:06:59,809 - INFO - Total Parameters:         124,647,170
+2026-04-20 11:06:59,810 - INFO - Trainable Parameters:     592,130
+2026-04-20 11:06:59,811 - INFO - Non-trainable Parameters: 124,055,040
+2026-04-20 11:06:59,813 - INFO - ===== Tokenizer Summary =====
+2026-04-20 11:06:59,908 - INFO - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']
+2026-04-20 11:06:59,912 - INFO - ===== End of Architecture Log =====
+2026-04-20 11:06:59,917 - INFO - Data augmentation enabled (rename=0.6, format=0.6)
+2026-04-20 11:07:10,050 - INFO - === Starting training with MixCode + FFT low-pass consistency ===