Upload checkpoint and eval results at step 500

checkpoint-500/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": "5.13.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50265
+}

checkpoint-500/eval_results.json

@@ -0,0 +1,12 @@
+{
+  "step": 500,
+  "epoch": 0.31545741324921134,
+  "time": "2026-07-08 22:09:29",
+  "metrics": {
+    "eval_loss": 0.11268972605466843,
+    "eval_accuracy": 0.9766561514195583,
+    "eval_precision": 0.9654959950708565,
+    "eval_recall": 0.9886435331230284,
+    "eval_f1": 0.976932668329177
+  }
+}

checkpoint-500/eval_step_000500.json

@@ -0,0 +1,16 @@
+{
+  "step": 500,
+  "epoch": 0.31545741324921134,
+  "time": "2026-07-08 22:09:29",
+  "metrics": {
+    "eval_loss": 0.11268972605466843,
+    "eval_accuracy": 0.9766561514195583,
+    "eval_precision": 0.9654959950708565,
+    "eval_recall": 0.9886435331230284,
+    "eval_f1": 0.976932668329177,
+    "eval_runtime": 56.1856,
+    "eval_samples_per_second": 56.42,
+    "eval_steps_per_second": 3.542,
+    "epoch": 0.31545741324921134
+  }
+}

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:655fc84407f55b60ee8341883a9b1545c6cd641e04fae22f72e7516d45a6ae06
+size 498612824

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c28cb2c214ceb7fbe437b83a07a739ec42b2d075e744f569038816b92e8108b8
+size 997348747

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a56502a951729b45cda5d2fe620e2618857f36f85dac3347d2b38bcdadd047
+size 14645

checkpoint-500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77569c2e850b04af982cc8c1389f1430851448915c593b69e5da36ce05b71d7
+size 1383

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cce5ee7ba8e5f97c7bdb52833c201e405975fb06e05a250f21a64646077170d
+size 1465

checkpoint-500/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-500/trainer_state.json

@@ -0,0 +1,202 @@
+{
+  "best_global_step": 500,
+  "best_metric": 0.976932668329177,
+  "best_model_checkpoint": "/kaggle/working/outputs/codebert_rd_keystrokes_v3_1/checkpoint-500",
+  "epoch": 0.31545741324921134,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0006309148264984228,
+      "grad_norm": 2.571892738342285,
+      "learning_rate": 0.0,
+      "loss": 0.6932622194290161,
+      "step": 1
+    },
+    {
+      "epoch": 0.015772870662460567,
+      "grad_norm": 2.436145544052124,
+      "learning_rate": 7.570977917981073e-07,
+      "loss": 0.7295282681783041,
+      "step": 25
+    },
+    {
+      "epoch": 0.031545741324921134,
+      "grad_norm": 5.32429838180542,
+      "learning_rate": 1.545741324921136e-06,
+      "loss": 0.7090779113769531,
+      "step": 50
+    },
+    {
+      "epoch": 0.0473186119873817,
+      "grad_norm": 5.425052165985107,
+      "learning_rate": 2.3343848580441643e-06,
+      "loss": 0.6694438171386718,
+      "step": 75
+    },
+    {
+      "epoch": 0.06309148264984227,
+      "grad_norm": 5.74971866607666,
+      "learning_rate": 3.1230283911671926e-06,
+      "loss": 0.6196812057495117,
+      "step": 100
+    },
+    {
+      "epoch": 0.07886435331230283,
+      "grad_norm": 4.759191989898682,
+      "learning_rate": 3.911671924290221e-06,
+      "loss": 0.43090095520019533,
+      "step": 125
+    },
+    {
+      "epoch": 0.0946372239747634,
+      "grad_norm": 5.838165283203125,
+      "learning_rate": 4.70031545741325e-06,
+      "loss": 0.29434648513793943,
+      "step": 150
+    },
+    {
+      "epoch": 0.11041009463722397,
+      "grad_norm": 6.797428131103516,
+      "learning_rate": 5.4889589905362786e-06,
+      "loss": 0.1876709747314453,
+      "step": 175
+    },
+    {
+      "epoch": 0.12618296529968454,
+      "grad_norm": 3.7547245025634766,
+      "learning_rate": 6.2776025236593065e-06,
+      "loss": 0.20350841522216798,
+      "step": 200
+    },
+    {
+      "epoch": 0.14195583596214512,
+      "grad_norm": 11.165263175964355,
+      "learning_rate": 7.066246056782335e-06,
+      "loss": 0.1446442985534668,
+      "step": 225
+    },
+    {
+      "epoch": 0.15772870662460567,
+      "grad_norm": 4.109164237976074,
+      "learning_rate": 7.854889589905364e-06,
+      "loss": 0.17608392715454102,
+      "step": 250
+    },
+    {
+      "epoch": 0.17350157728706625,
+      "grad_norm": 0.37571197748184204,
+      "learning_rate": 8.643533123028391e-06,
+      "loss": 0.08311139106750488,
+      "step": 275
+    },
+    {
+      "epoch": 0.1892744479495268,
+      "grad_norm": 0.21334795653820038,
+      "learning_rate": 9.43217665615142e-06,
+      "loss": 0.10653317451477051,
+      "step": 300
+    },
+    {
+      "epoch": 0.20504731861198738,
+      "grad_norm": 0.21560309827327728,
+      "learning_rate": 1.022082018927445e-05,
+      "loss": 0.12078428268432617,
+      "step": 325
+    },
+    {
+      "epoch": 0.22082018927444794,
+      "grad_norm": 0.07722581177949905,
+      "learning_rate": 1.1009463722397478e-05,
+      "loss": 0.10522660255432129,
+      "step": 350
+    },
+    {
+      "epoch": 0.23659305993690852,
+      "grad_norm": 13.963035583496094,
+      "learning_rate": 1.1798107255520506e-05,
+      "loss": 0.10268622398376465,
+      "step": 375
+    },
+    {
+      "epoch": 0.25236593059936907,
+      "grad_norm": 1.7228655815124512,
+      "learning_rate": 1.2586750788643533e-05,
+      "loss": 0.1168508243560791,
+      "step": 400
+    },
+    {
+      "epoch": 0.26813880126182965,
+      "grad_norm": 4.807567596435547,
+      "learning_rate": 1.3375394321766562e-05,
+      "loss": 0.1246561050415039,
+      "step": 425
+    },
+    {
+      "epoch": 0.28391167192429023,
+      "grad_norm": 0.10336830466985703,
+      "learning_rate": 1.4164037854889591e-05,
+      "loss": 0.06862223625183106,
+      "step": 450
+    },
+    {
+      "epoch": 0.2996845425867508,
+      "grad_norm": 0.18726640939712524,
+      "learning_rate": 1.495268138801262e-05,
+      "loss": 0.10785533905029297,
+      "step": 475
+    },
+    {
+      "epoch": 0.31545741324921134,
+      "grad_norm": 7.849733829498291,
+      "learning_rate": 1.574132492113565e-05,
+      "loss": 0.08045989990234376,
+      "step": 500
+    },
+    {
+      "epoch": 0.31545741324921134,
+      "eval_accuracy": 0.9766561514195583,
+      "eval_f1": 0.976932668329177,
+      "eval_loss": 0.11268972605466843,
+      "eval_precision": 0.9654959950708565,
+      "eval_recall": 0.9886435331230284,
+      "eval_runtime": 56.1856,
+      "eval_samples_per_second": 56.42,
+      "eval_steps_per_second": 3.542,
+      "step": 500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 6340,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "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": 2098047555440640.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc2d91b4b45762cdc84d5992a9a91e97b307eafcda062ebc5e2bf98dcfb03854
+size 5201