Upload checkpoint and eval results at step 800

checkpoint-800/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-800/eval_results.json

@@ -0,0 +1,12 @@
+{
+  "step": 800,
+  "epoch": 0.6472491909385113,
+  "time": "2026-06-26 20:27:20",
+  "metrics": {
+    "eval_loss": 0.14249353110790253,
+    "eval_accuracy": 0.965133906013138,
+    "eval_precision": 0.967511371020143,
+    "eval_recall": 0.9874005305039788,
+    "eval_f1": 0.9773547751887102
+  }
+}

checkpoint-800/eval_step_000800.json

@@ -0,0 +1,16 @@
+{
+  "step": 800,
+  "epoch": 0.6472491909385113,
+  "time": "2026-06-26 20:27:20",
+  "metrics": {
+    "eval_loss": 0.14249353110790253,
+    "eval_accuracy": 0.965133906013138,
+    "eval_precision": 0.967511371020143,
+    "eval_recall": 0.9874005305039788,
+    "eval_f1": 0.9773547751887102,
+    "eval_runtime": 34.6417,
+    "eval_samples_per_second": 57.128,
+    "eval_steps_per_second": 3.58,
+    "epoch": 0.6472491909385113
+  }
+}

checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:077d729a91aeb26f274d2ff2649e8566e54d505ecdfeb2e5dfa90ad4f069e8f5
+size 498612824

checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f290985c52402fdf78a8ee530e10adb2c7cd4c09c026c306a9a2f0205fec3f53
+size 997348747

checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be7ea52e301e5c370808f1b746f42154bba24d5ae179897fd70607a80bf8a1fa
+size 14645

checkpoint-800/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fef122931c86c2d2736773be787da21ac6460d41580735381e953556fb410be
+size 1383

checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d66fd3ac27d88c94392fa1c099bcc8bc02d0b72a915ac72cc4e2783c1344c7
+size 1465

checkpoint-800/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-800/trainer_state.json

@@ -0,0 +1,298 @@
+{
+  "best_global_step": 800,
+  "best_metric": 0.9773547751887102,
+  "best_model_checkpoint": "/kaggle/working/outputs/codebert_rd_keystrokes/checkpoint-800",
+  "epoch": 0.6472491909385113,
+  "eval_steps": 400,
+  "global_step": 800,
+  "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
+    },
+    {
+      "epoch": 0.34385113268608414,
+      "grad_norm": 12.952281951904297,
+      "learning_rate": 1.716599190283401e-05,
+      "loss": 0.23191883087158202,
+      "step": 425
+    },
+    {
+      "epoch": 0.3640776699029126,
+      "grad_norm": 19.496694564819336,
+      "learning_rate": 1.8178137651821864e-05,
+      "loss": 0.26200836181640624,
+      "step": 450
+    },
+    {
+      "epoch": 0.3843042071197411,
+      "grad_norm": 2.9963057041168213,
+      "learning_rate": 1.9190283400809718e-05,
+      "loss": 0.164515438079834,
+      "step": 475
+    },
+    {
+      "epoch": 0.4045307443365696,
+      "grad_norm": 0.2180398553609848,
+      "learning_rate": 1.999993769982229e-05,
+      "loss": 0.2513391304016113,
+      "step": 500
+    },
+    {
+      "epoch": 0.42475728155339804,
+      "grad_norm": 15.512799263000488,
+      "learning_rate": 1.9997757275108847e-05,
+      "loss": 0.30474105834960935,
+      "step": 525
+    },
+    {
+      "epoch": 0.4449838187702265,
+      "grad_norm": 23.762832641601562,
+      "learning_rate": 1.9992462617728763e-05,
+      "loss": 0.214493408203125,
+      "step": 550
+    },
+    {
+      "epoch": 0.465210355987055,
+      "grad_norm": 0.5767886638641357,
+      "learning_rate": 1.9984055376931414e-05,
+      "loss": 0.23740652084350586,
+      "step": 575
+    },
+    {
+      "epoch": 0.4854368932038835,
+      "grad_norm": 3.6927132606506348,
+      "learning_rate": 1.9972538171514525e-05,
+      "loss": 0.2517130470275879,
+      "step": 600
+    },
+    {
+      "epoch": 0.5056634304207119,
+      "grad_norm": 2.146721363067627,
+      "learning_rate": 1.9957914589008405e-05,
+      "loss": 0.21869991302490235,
+      "step": 625
+    },
+    {
+      "epoch": 0.5258899676375405,
+      "grad_norm": 9.424388885498047,
+      "learning_rate": 1.9940189184558487e-05,
+      "loss": 0.2582887077331543,
+      "step": 650
+    },
+    {
+      "epoch": 0.5461165048543689,
+      "grad_norm": 4.679764747619629,
+      "learning_rate": 1.9919367479506413e-05,
+      "loss": 0.2324064254760742,
+      "step": 675
+    },
+    {
+      "epoch": 0.5663430420711975,
+      "grad_norm": 3.0119147300720215,
+      "learning_rate": 1.989545595967018e-05,
+      "loss": 0.23698102951049804,
+      "step": 700
+    },
+    {
+      "epoch": 0.5865695792880259,
+      "grad_norm": 10.184627532958984,
+      "learning_rate": 1.986846207332384e-05,
+      "loss": 0.23535886764526368,
+      "step": 725
+    },
+    {
+      "epoch": 0.6067961165048543,
+      "grad_norm": 51.39314651489258,
+      "learning_rate": 1.9838394228877443e-05,
+      "loss": 0.13176690101623534,
+      "step": 750
+    },
+    {
+      "epoch": 0.6270226537216829,
+      "grad_norm": 18.441652297973633,
+      "learning_rate": 1.980526179225785e-05,
+      "loss": 0.2888069725036621,
+      "step": 775
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "grad_norm": 0.9691627621650696,
+      "learning_rate": 1.97690750839913e-05,
+      "loss": 0.29139081954956053,
+      "step": 800
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "eval_accuracy": 0.965133906013138,
+      "eval_f1": 0.9773547751887102,
+      "eval_loss": 0.14249353110790253,
+      "eval_precision": 0.967511371020143,
+      "eval_recall": 0.9874005305039788,
+      "eval_runtime": 34.6417,
+      "eval_samples_per_second": 57.128,
+      "eval_steps_per_second": 3.58,
+      "step": 800
+    }
+  ],
+  "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": 3367821508608000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-800/training_args.bin

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