Upload folder using huggingface_hub

checkpoints/checkpoint-2984/config.json

@@ -0,0 +1,38 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "benign",
+    "1": "malicious"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "benign": 0,
+    "malicious": 1
+  },
+  "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,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50265
+}

checkpoints/checkpoint-2984/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:963c92ed5e4eec018a97e3c32b6aa03bf997992e7fafab226a487db3500b8bd7
+size 498612824

checkpoints/checkpoint-2984/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953aa714b4659ddf8894145a5c52cdd0dd7ef1a8f04c05c0b8e172b5fe383d9c
+size 997345931

checkpoints/checkpoint-2984/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea6c409f02c7e5a62c83b4ca4e707f81c126e56b722b832d90712fd88566c44
+size 14645

checkpoints/checkpoint-2984/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064b1aa7a632d7a6f665762d00235346581136a40d00ab861cfe413c5840adf1
+size 1383

checkpoints/checkpoint-2984/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d566e9bc5a2d0346bb7786fed65abfbe11cde25504e4f918cf56ed9333d79d37
+size 1465

checkpoints/checkpoint-2984/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoints/checkpoint-2984/trainer_state.json

@@ -0,0 +1,186 @@
+{
+  "best_global_step": 373,
+  "best_metric": 0.8898085876875323,
+  "best_model_checkpoint": "/kaggle/working/outputs/codebert-all-combined/microsoft-codebert-base/checkpoint-373",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 2984,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.451900482177734,
+      "learning_rate": 1.3351206434316355e-05,
+      "loss": 3.253069430190181,
+      "step": 373
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8352668213457076,
+      "eval_f1": 0.8898085876875323,
+      "eval_loss": 0.5276884436607361,
+      "eval_precision": 0.8143939393939394,
+      "eval_recall": 0.9806157354618016,
+      "eval_runtime": 26.2521,
+      "eval_samples_per_second": 49.253,
+      "eval_steps_per_second": 3.085,
+      "step": 373
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.377457141876221,
+      "learning_rate": 6.684539767649688e-06,
+      "loss": 2.735222946862433,
+      "step": 746
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8290796597061099,
+      "eval_f1": 0.8875318066157761,
+      "eval_loss": 0.5213587880134583,
+      "eval_precision": 0.8014705882352942,
+      "eval_recall": 0.9942987457240593,
+      "eval_runtime": 26.0805,
+      "eval_samples_per_second": 49.577,
+      "eval_steps_per_second": 3.106,
+      "step": 746
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.425128936767578,
+      "learning_rate": 1.7873100983020556e-08,
+      "loss": 2.6189828826658847,
+      "step": 1119
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8360402165506574,
+      "eval_f1": 0.886021505376344,
+      "eval_loss": 0.5193805694580078,
+      "eval_precision": 0.8382502543234995,
+      "eval_recall": 0.9395667046750285,
+      "eval_runtime": 25.9863,
+      "eval_samples_per_second": 49.757,
+      "eval_steps_per_second": 3.117,
+      "step": 1119
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 8.492631912231445,
+      "learning_rate": 1.1117068811438785e-05,
+      "loss": 2.643136932127597,
+      "step": 1492
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8283062645011601,
+      "eval_f1": 0.8875379939209727,
+      "eval_loss": 0.5421428680419922,
+      "eval_precision": 0.7985414767547858,
+      "eval_recall": 0.9988597491448119,
+      "eval_runtime": 26.1276,
+      "eval_samples_per_second": 49.488,
+      "eval_steps_per_second": 3.1,
+      "step": 1492
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.1199772357940674,
+      "learning_rate": 8.894846589216563e-06,
+      "loss": 2.5547156448977884,
+      "step": 1865
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8267594740912606,
+      "eval_f1": 0.885480572597137,
+      "eval_loss": 0.5424710512161255,
+      "eval_precision": 0.8025949953660797,
+      "eval_recall": 0.9874572405929305,
+      "eval_runtime": 25.9539,
+      "eval_samples_per_second": 49.819,
+      "eval_steps_per_second": 3.121,
+      "step": 1865
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.1183524131774902,
+      "learning_rate": 6.67262436699434e-06,
+      "loss": 2.5014848069914546,
+      "step": 2238
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8290796597061099,
+      "eval_f1": 0.8868407578084997,
+      "eval_loss": 0.5805880427360535,
+      "eval_precision": 0.8048327137546468,
+      "eval_recall": 0.9874572405929305,
+      "eval_runtime": 26.5677,
+      "eval_samples_per_second": 48.668,
+      "eval_steps_per_second": 3.049,
+      "step": 2238
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 25.385547637939453,
+      "learning_rate": 4.450402144772119e-06,
+      "loss": 2.44378613019437,
+      "step": 2611
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.851508120649652,
+      "eval_f1": 0.883495145631068,
+      "eval_loss": 0.6349141001701355,
+      "eval_precision": 0.9442282749675746,
+      "eval_recall": 0.830102622576967,
+      "eval_runtime": 27.4334,
+      "eval_samples_per_second": 47.132,
+      "eval_steps_per_second": 2.953,
+      "step": 2611
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.2667272090911865,
+      "learning_rate": 2.228179922549896e-06,
+      "loss": 2.413644417361344,
+      "step": 2984
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.848414539829853,
+      "eval_f1": 0.8852459016393442,
+      "eval_loss": 0.6463340520858765,
+      "eval_precision": 0.9097472924187726,
+      "eval_recall": 0.8620296465222349,
+      "eval_runtime": 26.2292,
+      "eval_samples_per_second": 49.296,
+      "eval_steps_per_second": 3.088,
+      "step": 2984
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3357,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.507302824278304e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-2984/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e04db148db6c6cddff22306e2de39ae165d9fcd4074b007c9be41c65fcbbd49
+size 5201