Upload folder using huggingface_hub

checkpoint-1316/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,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50265
+}

checkpoint-1316/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44a68b31eff6c0bcd96ce5a29a5b0aaed9a7b1d4cd30e1240248bfea25358dc
+size 498612800

checkpoint-1316/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f7fceabea4fdc2b48d9f2f71208d2b1b0f595630047c8bc21b3541f165712d
+size 997348747

checkpoint-1316/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:691e646269d56ed928e5b51b1f0e4ff013040b3910d238e7474d2500e28b403d
+size 14645

checkpoint-1316/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d57f046600043aaf623f83c45c9de68d54e1c6935036b82a42cde8a06467f41b
+size 1465

checkpoint-1316/trainer_state.json

@@ -0,0 +1,173 @@
+{
+  "best_global_step": 1316,
+  "best_metric": 0.987228321756666,
+  "best_model_checkpoint": "/kaggle/working/skillguard/models/roberta/checkpoint-1316",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1316,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.303951367781155,
+      "grad_norm": 26.459680557250977,
+      "learning_rate": 1.967663702506063e-05,
+      "loss": 0.8790406799316406,
+      "step": 100
+    },
+    {
+      "epoch": 0.60790273556231,
+      "grad_norm": 37.875850677490234,
+      "learning_rate": 1.8059822150363784e-05,
+      "loss": 0.20122947692871093,
+      "step": 200
+    },
+    {
+      "epoch": 0.9118541033434651,
+      "grad_norm": 0.6300860047340393,
+      "learning_rate": 1.6443007275666938e-05,
+      "loss": 0.14148117065429688,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9817777777777777,
+      "eval_f1": 0.9816472694717995,
+      "eval_loss": 0.11642087250947952,
+      "eval_precision": 0.9887285843101894,
+      "eval_recall": 0.9746666666666667,
+      "eval_runtime": 38.768,
+      "eval_samples_per_second": 116.075,
+      "eval_steps_per_second": 0.929,
+      "step": 329
+    },
+    {
+      "epoch": 1.21580547112462,
+      "grad_norm": 44.39780807495117,
+      "learning_rate": 1.482619240097009e-05,
+      "loss": 0.08979954719543456,
+      "step": 400
+    },
+    {
+      "epoch": 1.5197568389057752,
+      "grad_norm": 8.478060722351074,
+      "learning_rate": 1.3209377526273244e-05,
+      "loss": 0.06728220462799073,
+      "step": 500
+    },
+    {
+      "epoch": 1.8237082066869301,
+      "grad_norm": 15.931158065795898,
+      "learning_rate": 1.1592562651576396e-05,
+      "loss": 0.07970011711120606,
+      "step": 600
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9811111111111112,
+      "eval_f1": 0.9808169713382984,
+      "eval_loss": 0.16507814824581146,
+      "eval_precision": 0.9963319578175149,
+      "eval_recall": 0.9657777777777777,
+      "eval_runtime": 38.6568,
+      "eval_samples_per_second": 116.409,
+      "eval_steps_per_second": 0.931,
+      "step": 658
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 0.06346142292022705,
+      "learning_rate": 9.975747776879548e-06,
+      "loss": 0.06562654018402099,
+      "step": 700
+    },
+    {
+      "epoch": 2.43161094224924,
+      "grad_norm": 0.021810326725244522,
+      "learning_rate": 8.3589329021827e-06,
+      "loss": 0.037502543926239015,
+      "step": 800
+    },
+    {
+      "epoch": 2.735562310030395,
+      "grad_norm": 0.42783406376838684,
+      "learning_rate": 6.7421180274858535e-06,
+      "loss": 0.041276140213012694,
+      "step": 900
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9871111111111112,
+      "eval_f1": 0.9870013446884806,
+      "eval_loss": 0.14181749522686005,
+      "eval_precision": 0.9954792043399638,
+      "eval_recall": 0.9786666666666667,
+      "eval_runtime": 38.725,
+      "eval_samples_per_second": 116.204,
+      "eval_steps_per_second": 0.93,
+      "step": 987
+    },
+    {
+      "epoch": 3.0395136778115504,
+      "grad_norm": 5.668140888214111,
+      "learning_rate": 5.125303152789006e-06,
+      "loss": 0.024772546291351318,
+      "step": 1000
+    },
+    {
+      "epoch": 3.3434650455927053,
+      "grad_norm": 1.2623281478881836,
+      "learning_rate": 3.5084882780921584e-06,
+      "loss": 0.017916127443313598,
+      "step": 1100
+    },
+    {
+      "epoch": 3.6474164133738602,
+      "grad_norm": 2.460536479949951,
+      "learning_rate": 1.8916734033953113e-06,
+      "loss": 0.0251471209526062,
+      "step": 1200
+    },
+    {
+      "epoch": 3.951367781155015,
+      "grad_norm": 0.019897326827049255,
+      "learning_rate": 2.74858528698464e-07,
+      "loss": 0.016884679794311522,
+      "step": 1300
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9873333333333333,
+      "eval_f1": 0.987228321756666,
+      "eval_loss": 0.14398272335529327,
+      "eval_precision": 0.9954812471757795,
+      "eval_recall": 0.9791111111111112,
+      "eval_runtime": 38.4471,
+      "eval_samples_per_second": 117.044,
+      "eval_steps_per_second": 0.936,
+      "step": 1316
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1316,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.105066432512e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1316/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d417474128ff0bdb4a3aaf57717508285695b4d1787ece4a3dfa8e7dbf8f52a
+size 5201

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,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44a68b31eff6c0bcd96ce5a29a5b0aaed9a7b1d4cd30e1240248bfea25358dc
+size 498612800

test_labels.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c47485ae6b099c89047315ee67216afd4fd1763f550101a23a4e880b04eefe8
+size 36128

test_metrics.json

@@ -0,0 +1,7 @@
+{
+  "model": "roberta-base",
+  "accuracy": 0.9902222222222222,
+  "f1": 0.9901697944593387,
+  "precision": 0.995507637017071,
+  "recall": 0.9848888888888889
+}

test_preds.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83b8fa4f777d11a8a1e241e4e8e31fa1b90fa128b268b93e6ffd83b8b2e64057
+size 36128

test_probs.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a8816a3c2f57d367544772c8d5386224e48e7eba4564b5423eac355fbde4304
+size 18128

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d417474128ff0bdb4a3aaf57717508285695b4d1787ece4a3dfa8e7dbf8f52a
+size 5201