Upload checkpoint and eval results at step 400

checkpoint-400/config.json

@@ -0,0 +1,37 @@
+{
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50265
+}

checkpoint-400/eval_results.json

@@ -0,0 +1,12 @@
+{
+  "step": 400,
+  "epoch": 0.32362459546925565,
+  "time": "2026-06-26 20:20:21",
+  "metrics": {
+    "eval_loss": 0.16199301183223724,
+    "eval_accuracy": 0.9560384032339565,
+    "eval_precision": 0.9539936102236422,
+    "eval_recall": 0.9900530503978779,
+    "eval_f1": 0.9716889033517735
+  }
+}

checkpoint-400/eval_step_000400.json

@@ -0,0 +1,16 @@
+{
+  "step": 400,
+  "epoch": 0.32362459546925565,
+  "time": "2026-06-26 20:20:21",
+  "metrics": {
+    "eval_loss": 0.16199301183223724,
+    "eval_accuracy": 0.9560384032339565,
+    "eval_precision": 0.9539936102236422,
+    "eval_recall": 0.9900530503978779,
+    "eval_f1": 0.9716889033517735,
+    "eval_runtime": 34.745,
+    "eval_samples_per_second": 56.958,
+    "eval_steps_per_second": 3.569,
+    "epoch": 0.32362459546925565
+  }
+}

checkpoint-400/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f46e89f79ca5430a8129b12193f6c838cf5d640299cbfd7c61c248463ac1a81f
+size 498612824

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f1d3b02dc6155bb8bc72111bca9844730fd82fb029f516e10ee80dce2ef653d
+size 997348747

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200f02172478cb5a16379b16f4d12141a4d3522bdd7e1d91fd78412a6a8173ab
+size 14645

checkpoint-400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30858f23bcb22d0baef45bd4add9d6fa474141308c12653c706077b87d932e49
+size 1383

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3adcd664068c7d91429362b86fa0051a6fc411fec08c6dffd3a537a40dedb9e5
+size 1465

checkpoint-400/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": 1000000000,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-400/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_global_step": 400,
+  "best_metric": 0.9716889033517735,
+  "best_model_checkpoint": "/kaggle/working/outputs/codebert_rd_keystrokes/checkpoint-400",
+  "epoch": 0.32362459546925565,
+  "eval_steps": 400,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008090614886731392,
+      "grad_norm": 4.001261234283447,
+      "learning_rate": 0.0,
+      "loss": 0.748644232749939,
+      "step": 1
+    },
+    {
+      "epoch": 0.020226537216828478,
+      "grad_norm": 2.0581886768341064,
+      "learning_rate": 9.716599190283402e-07,
+      "loss": 0.7263915538787842,
+      "step": 25
+    },
+    {
+      "epoch": 0.040453074433656956,
+      "grad_norm": 3.1348977088928223,
+      "learning_rate": 1.9838056680161946e-06,
+      "loss": 0.7004936218261719,
+      "step": 50
+    },
+    {
+      "epoch": 0.06067961165048544,
+      "grad_norm": 7.536289215087891,
+      "learning_rate": 2.995951417004049e-06,
+      "loss": 0.6983621978759765,
+      "step": 75
+    },
+    {
+      "epoch": 0.08090614886731391,
+      "grad_norm": 5.387710094451904,
+      "learning_rate": 4.008097165991903e-06,
+      "loss": 0.6408506774902344,
+      "step": 100
+    },
+    {
+      "epoch": 0.1011326860841424,
+      "grad_norm": 4.4866790771484375,
+      "learning_rate": 5.020242914979757e-06,
+      "loss": 0.5292000961303711,
+      "step": 125
+    },
+    {
+      "epoch": 0.12135922330097088,
+      "grad_norm": 5.9393534660339355,
+      "learning_rate": 6.0323886639676124e-06,
+      "loss": 0.4315451049804688,
+      "step": 150
+    },
+    {
+      "epoch": 0.14158576051779936,
+      "grad_norm": 4.814444065093994,
+      "learning_rate": 7.044534412955466e-06,
+      "loss": 0.3674881362915039,
+      "step": 175
+    },
+    {
+      "epoch": 0.16181229773462782,
+      "grad_norm": 2.463817834854126,
+      "learning_rate": 8.056680161943322e-06,
+      "loss": 0.29549776077270506,
+      "step": 200
+    },
+    {
+      "epoch": 0.1820388349514563,
+      "grad_norm": 1.6270427703857422,
+      "learning_rate": 9.068825910931175e-06,
+      "loss": 0.19513965606689454,
+      "step": 225
+    },
+    {
+      "epoch": 0.2022653721682848,
+      "grad_norm": 15.206025123596191,
+      "learning_rate": 1.008097165991903e-05,
+      "loss": 0.258267822265625,
+      "step": 250
+    },
+    {
+      "epoch": 0.22249190938511326,
+      "grad_norm": 5.6893134117126465,
+      "learning_rate": 1.1093117408906884e-05,
+      "loss": 0.3252030563354492,
+      "step": 275
+    },
+    {
+      "epoch": 0.24271844660194175,
+      "grad_norm": 15.90676498413086,
+      "learning_rate": 1.2105263157894737e-05,
+      "loss": 0.2558871841430664,
+      "step": 300
+    },
+    {
+      "epoch": 0.26294498381877024,
+      "grad_norm": 1.5257281064987183,
+      "learning_rate": 1.3117408906882592e-05,
+      "loss": 0.20428178787231446,
+      "step": 325
+    },
+    {
+      "epoch": 0.28317152103559873,
+      "grad_norm": 20.172571182250977,
+      "learning_rate": 1.4129554655870446e-05,
+      "loss": 0.2579817008972168,
+      "step": 350
+    },
+    {
+      "epoch": 0.30339805825242716,
+      "grad_norm": 0.42674902081489563,
+      "learning_rate": 1.5141700404858302e-05,
+      "loss": 0.3013817977905273,
+      "step": 375
+    },
+    {
+      "epoch": 0.32362459546925565,
+      "grad_norm": 0.6443495750427246,
+      "learning_rate": 1.6153846153846154e-05,
+      "loss": 0.22500619888305665,
+      "step": 400
+    },
+    {
+      "epoch": 0.32362459546925565,
+      "eval_accuracy": 0.9560384032339565,
+      "eval_f1": 0.9716889033517735,
+      "eval_loss": 0.16199301183223724,
+      "eval_precision": 0.9539936102236422,
+      "eval_recall": 0.9900530503978779,
+      "eval_runtime": 34.745,
+      "eval_samples_per_second": 56.958,
+      "eval_steps_per_second": 3.569,
+      "step": 400
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 4944,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "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": 1683910754304000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab81eb8f627d496428c93c1d48c52e0479518be7570628b71c7a023704823dee
+size 5201