upload unixcoder checkpoint 50

unixcoder-base/checkpoint-50/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": 1026,
+  "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": 10,
+  "use_cache": true,
+  "vocab_size": 51416
+}

unixcoder-base/checkpoint-50/config_hyperparams.json

@@ -0,0 +1,53 @@
+{
+  "train_config": {
+    "model_name": "microsoft/unixcoder-base",
+    "num_epochs": 0.5,
+    "batch_size": 32,
+    "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": 6.0,
+    "infonce_temperature": 0.07,
+    "infonce_weight": 0.5,
+    "label_smoothing": 0.3,
+    "adversarial_epsilon": 0.5,
+    "use_swa": false,
+    "swa_start_epoch": 0,
+    "swa_lr": 1e-05,
+    "data_augmentation": true,
+    "aug_rename_prob": 0.6,
+    "aug_format_prob": 0.6,
+    "freeze_base": true,
+    "seed": 42,
+    "use_wandb": true,
+    "mixup_alpha": 1.0,
+    "low_pass_keep_ratio": 0.5,
+    "freq_consistency_weight": 0.2
+  },
+  "training_arguments": {
+    "output_dir": "output_checkpoints/unixcoder-base/",
+    "num_train_epochs": 0.5,
+    "per_device_train_batch_size": 32,
+    "per_device_eval_batch_size": 64,
+    "learning_rate": 1e-06,
+    "warmup_steps": 781,
+    "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": 50,
+    "epoch": 0.006399590426212722,
+    "best_metric": null,
+    "best_model_checkpoint": null
+  }
+}

unixcoder-base/checkpoint-50/hyperparams.json

@@ -0,0 +1,35 @@
+{
+    "model_name": "microsoft/unixcoder-base",
+    "output_dir": "output_checkpoints/unixcoder-base/",
+    "num_epochs": 0.5,
+    "max_steps": 50,
+    "batch_size": 32,
+    "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": 6.0,
+    "infonce_temperature": 0.07,
+    "infonce_weight": 0.5,
+    "seed": 42,
+    "resume_from_checkpoint": null,
+    "label_smoothing": 0.3,
+    "adversarial_epsilon": 0.5,
+    "use_swa": false,
+    "swa_start_epoch": 0,
+    "swa_lr": 1e-05,
+    "data_augmentation": true,
+    "aug_rename_prob": 0.6,
+    "aug_format_prob": 0.6,
+    "mixup_alpha": 1.0,
+    "low_pass_keep_ratio": 0.5,
+    "freq_consistency_weight": 0.2,
+    "hidden_dropout_prob": 0.3,
+    "attention_probs_dropout_prob": 0.3,
+    "classifier_dropout": 0.3,
+    "device": "cuda"
+}

unixcoder-base/checkpoint-50/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eac14ed59a07a54ac4e696a827dbd07481c2c2e61a0b6fb79b373aa86d1ca27
+size 503749208

unixcoder-base/checkpoint-50/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18084ee24aa7c3f530476c469a3a46d151546383116de30be055e61fdb72b1f9
+size 4741859

unixcoder-base/checkpoint-50/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9ab4f75b99203755841ed328e95e73d1e090a77e9b99ba1e6303dd9271f635
+size 14645

unixcoder-base/checkpoint-50/scaler.pt

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

unixcoder-base/checkpoint-50/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2915d03c29503502184966928010b43e225be9484b2fb51440baa31032967c
+size 1465

unixcoder-base/checkpoint-50/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
+  }
+}

unixcoder-base/checkpoint-50/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
+    },
+    "4": {
+      "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": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

unixcoder-base/checkpoint-50/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "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": [
+    {
+      "epoch": 0.0012799180852425445,
+      "grad_norm": 395827.90625,
+      "learning_rate": 1.1523687580025607e-08,
+      "loss": 1.0217,
+      "step": 10
+    },
+    {
+      "epoch": 0.002559836170485089,
+      "grad_norm": 425641.125,
+      "learning_rate": 2.4327784891165172e-08,
+      "loss": 0.9895,
+      "step": 20
+    },
+    {
+      "epoch": 0.0038397542557276334,
+      "grad_norm": 322450.875,
+      "learning_rate": 3.713188220230474e-08,
+      "loss": 1.0297,
+      "step": 30
+    },
+    {
+      "epoch": 0.005119672340970178,
+      "grad_norm": 362794.28125,
+      "learning_rate": 4.9935979513444295e-08,
+      "loss": 1.0126,
+      "step": 40
+    },
+    {
+      "epoch": 0.006399590426212722,
+      "grad_norm": 402867.875,
+      "learning_rate": 6.274007682458386e-08,
+      "loss": 1.0,
+      "step": 50
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 50,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 841955377152000.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

unixcoder-base/checkpoint-50/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a78a2eb6799e96da4580dc622a59464b1e6878a568d917ed75044c6fd0570b8
+size 5905

unixcoder-base/final_model/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": 1026,
+  "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": 10,
+  "use_cache": true,
+  "vocab_size": 51416
+}

unixcoder-base/final_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eac14ed59a07a54ac4e696a827dbd07481c2c2e61a0b6fb79b373aa86d1ca27
+size 503749208

unixcoder-base/final_model/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
+  }
+}

unixcoder-base/final_model/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
+    },
+    "4": {
+      "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": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

unixcoder-base/training.log

@@ -0,0 +1,92 @@
+2026-04-23 14:52:26,578 - INFO - ===== Training Configuration =====
+2026-04-23 14:52:26,580 - INFO - model_name           : microsoft/unixcoder-base
+2026-04-23 14:52:26,582 - INFO - output_dir           : output_checkpoints/unixcoder-base/
+2026-04-23 14:52:26,583 - INFO - num_epochs           : 0.5
+2026-04-23 14:52:26,584 - INFO - max_steps            : 50
+2026-04-23 14:52:26,585 - INFO - batch_size           : 32
+2026-04-23 14:52:26,587 - INFO - learning_rate        : 1e-06
+2026-04-23 14:52:26,588 - INFO - max_length           : 512
+2026-04-23 14:52:26,589 - INFO - num_labels           : 2
+2026-04-23 14:52:26,591 - INFO - use_wandb            : True
+2026-04-23 14:52:26,592 - INFO - freeze_base          : True
+2026-04-23 14:52:26,593 - INFO - loss_type            : r-drop
+2026-04-23 14:52:26,594 - INFO - focal_alpha          : 1.0
+2026-04-23 14:52:26,595 - INFO - focal_gamma          : 2.0
+2026-04-23 14:52:26,596 - INFO - r_drop_alpha         : 6.0
+2026-04-23 14:52:26,597 - INFO - infonce_temperature  : 0.07
+2026-04-23 14:52:26,598 - INFO - infonce_weight       : 0.5
+2026-04-23 14:52:26,599 - INFO - seed                 : 42
+2026-04-23 14:52:26,600 - INFO - resume_from_checkpoint : None
+2026-04-23 14:52:26,601 - INFO - label_smoothing      : 0.3
+2026-04-23 14:52:26,602 - INFO - adversarial_epsilon  : 0.5
+2026-04-23 14:52:26,604 - INFO - use_swa              : False
+2026-04-23 14:52:26,606 - INFO - swa_start_epoch      : 0
+2026-04-23 14:52:26,606 - INFO - swa_lr               : 1e-05
+2026-04-23 14:52:26,607 - INFO - data_augmentation    : True
+2026-04-23 14:52:26,609 - INFO - aug_rename_prob      : 0.6
+2026-04-23 14:52:26,610 - INFO - aug_format_prob      : 0.6
+2026-04-23 14:52:26,612 - INFO - mixup_alpha          : 1.0
+2026-04-23 14:52:26,613 - INFO - low_pass_keep_ratio  : 0.5
+2026-04-23 14:52:26,614 - INFO - freq_consistency_weight : 0.2
+2026-04-23 14:52:26,615 - INFO - hidden_dropout_prob  : 0.3
+2026-04-23 14:52:26,616 - INFO - attention_probs_dropout_prob : 0.3
+2026-04-23 14:52:26,618 - INFO - classifier_dropout   : 0.3
+2026-04-23 14:52:26,619 - INFO - =================================
+2026-04-23 14:52:27,631 - INFO - Model placed on cuda
+2026-04-23 14:52:27,635 - INFO - ===== Model Architecture =====
+2026-04-23 14:52:27,638 - INFO - 
+RobertaForSequenceClassification(
+  (roberta): RobertaModel(
+    (embeddings): RobertaEmbeddings(
+      (word_embeddings): Embedding(51416, 768, padding_idx=1)
+      (position_embeddings): Embedding(1026, 768, padding_idx=1)
+      (token_type_embeddings): Embedding(10, 768)
+      (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
+      (dropout): Dropout(p=0.3, 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=0.3, 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=0.3, 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=0.3, inplace=False)
+          )
+        )
+      )
+    )
+  )
+  (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)
+  )
+)
+2026-04-23 14:52:27,640 - INFO - ===== Parameter Summary =====
+2026-04-23 14:52:27,642 - INFO - Total Parameters:         125,931,266
+2026-04-23 14:52:27,643 - INFO - Trainable Parameters:     592,130
+2026-04-23 14:52:27,646 - INFO - Non-trainable Parameters: 125,339,136
+2026-04-23 14:52:27,647 - INFO - ===== Tokenizer Summary =====
+2026-04-23 14:52:27,663 - INFO - Vocab size: 51416 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']
+2026-04-23 14:52:27,665 - INFO - ===== End of Architecture Log =====
+2026-04-23 14:52:27,666 - INFO - Data augmentation enabled (rename=0.6, format=0.6)
+2026-04-23 14:52:28,797 - INFO - === Starting training with MixCode + FFT low-pass consistency ===
+2026-04-23 14:54:25,677 - INFO - Training complete!
+2026-04-23 14:54:26,437 - INFO - Final model saved to output_checkpoints/unixcoder-base/final_model