Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: google-bert/bert-base-uncased
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.2801719307899475
+
+f1_macro: 0.3141567963902989
+
+f1_micro: 0.8912
+
+f1_weighted: 0.8399296108291031
+
+precision_macro: 0.29706666666666665
+
+precision_micro: 0.8912
+
+precision_weighted: 0.79423744
+
+recall_macro: 0.3333333333333333
+
+recall_micro: 0.8912
+
+recall_weighted: 0.8912
+
+accuracy: 0.8912

checkpoint-1250/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 3,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "-1",
+    "1": "0",
+    "2": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "-1": 0,
+    "0": 1,
+    "1": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-1250/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0c3aad48b6cbebf14a4ad13ffdbb56dc233ddf4dabad78bfc50f8b4cdd549d
+size 437961724

checkpoint-1250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f30736f55a400b3ae2179bd103b12ebf37a7d8c0beef33909d73fdfced17a2
+size 876044538

checkpoint-1250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a990576500f65aedad5244d639dc658a92c92121b795f54cd3ff5c9ee3ddfac
+size 14244

checkpoint-1250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e44d64e5b63099fa495b14fd3c6ef3cdf6c574c8ed737e4a9d5b0a35c47cae7
+size 1064

checkpoint-1250/trainer_state.json

@@ -0,0 +1,410 @@
+{
+  "best_metric": 0.2801719307899475,
+  "best_model_checkpoint": "malware-id-poisoned/checkpoint-1250",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 9.681573867797852,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 1.1812,
+      "step": 25
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.9037132263183594,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.5853,
+      "step": 50
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 14.369175910949707,
+      "learning_rate": 9.733333333333334e-06,
+      "loss": 0.3379,
+      "step": 75
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.6926445960998535,
+      "learning_rate": 1.3066666666666666e-05,
+      "loss": 0.3922,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.4338544607162476,
+      "learning_rate": 1.6400000000000002e-05,
+      "loss": 0.2955,
+      "step": 125
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 6.4268693923950195,
+      "learning_rate": 1.9733333333333333e-05,
+      "loss": 0.2726,
+      "step": 150
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.671034812927246,
+      "learning_rate": 2.3066666666666667e-05,
+      "loss": 0.2958,
+      "step": 175
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.399640083312988,
+      "learning_rate": 2.64e-05,
+      "loss": 0.2918,
+      "step": 200
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 6.896551132202148,
+      "learning_rate": 2.9733333333333336e-05,
+      "loss": 0.3486,
+      "step": 225
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.040962219238281,
+      "learning_rate": 3.3066666666666666e-05,
+      "loss": 0.327,
+      "step": 250
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.5620458126068115,
+      "learning_rate": 3.6400000000000004e-05,
+      "loss": 0.3679,
+      "step": 275
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.849157333374023,
+      "learning_rate": 3.9733333333333335e-05,
+      "loss": 0.2993,
+      "step": 300
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.7911171913146973,
+      "learning_rate": 4.3066666666666665e-05,
+      "loss": 0.3898,
+      "step": 325
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.053364098072052,
+      "learning_rate": 4.64e-05,
+      "loss": 0.2598,
+      "step": 350
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.6277973651885986,
+      "learning_rate": 4.973333333333334e-05,
+      "loss": 0.3442,
+      "step": 375
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.4473252296447754,
+      "learning_rate": 4.9674074074074076e-05,
+      "loss": 0.3302,
+      "step": 400
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.1877830028533936,
+      "learning_rate": 4.9303703703703705e-05,
+      "loss": 0.303,
+      "step": 425
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.7437478303909302,
+      "learning_rate": 4.8933333333333335e-05,
+      "loss": 0.3309,
+      "step": 450
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.4954609870910645,
+      "learning_rate": 4.8562962962962964e-05,
+      "loss": 0.2334,
+      "step": 475
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.7728545665740967,
+      "learning_rate": 4.819259259259259e-05,
+      "loss": 0.2805,
+      "step": 500
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.205313801765442,
+      "learning_rate": 4.782222222222222e-05,
+      "loss": 0.3194,
+      "step": 525
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.9415230751037598,
+      "learning_rate": 4.745185185185185e-05,
+      "loss": 0.4063,
+      "step": 550
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.3622888326644897,
+      "learning_rate": 4.708148148148148e-05,
+      "loss": 0.272,
+      "step": 575
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.8100759983062744,
+      "learning_rate": 4.671111111111111e-05,
+      "loss": 0.2245,
+      "step": 600
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.7888755798339844,
+      "learning_rate": 4.6340740740740746e-05,
+      "loss": 0.3384,
+      "step": 625
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.7515454292297363,
+      "learning_rate": 4.5970370370370375e-05,
+      "loss": 0.1967,
+      "step": 650
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.5422276258468628,
+      "learning_rate": 4.5600000000000004e-05,
+      "loss": 0.3512,
+      "step": 675
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.6704206466674805,
+      "learning_rate": 4.522962962962963e-05,
+      "loss": 0.3092,
+      "step": 700
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.140597105026245,
+      "learning_rate": 4.485925925925926e-05,
+      "loss": 0.3074,
+      "step": 725
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.9749250411987305,
+      "learning_rate": 4.448888888888889e-05,
+      "loss": 0.3032,
+      "step": 750
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.9764140844345093,
+      "learning_rate": 4.411851851851852e-05,
+      "loss": 0.2985,
+      "step": 775
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.7499094009399414,
+      "learning_rate": 4.374814814814815e-05,
+      "loss": 0.2731,
+      "step": 800
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.56443190574646,
+      "learning_rate": 4.337777777777778e-05,
+      "loss": 0.3344,
+      "step": 825
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.7460238933563232,
+      "learning_rate": 4.300740740740741e-05,
+      "loss": 0.2845,
+      "step": 850
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.6011741161346436,
+      "learning_rate": 4.263703703703704e-05,
+      "loss": 0.2625,
+      "step": 875
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.260887622833252,
+      "learning_rate": 4.226666666666667e-05,
+      "loss": 0.3482,
+      "step": 900
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.081975221633911,
+      "learning_rate": 4.18962962962963e-05,
+      "loss": 0.2655,
+      "step": 925
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.251772165298462,
+      "learning_rate": 4.152592592592593e-05,
+      "loss": 0.2384,
+      "step": 950
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 5.243502140045166,
+      "learning_rate": 4.115555555555556e-05,
+      "loss": 0.3585,
+      "step": 975
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.577237129211426,
+      "learning_rate": 4.078518518518519e-05,
+      "loss": 0.3151,
+      "step": 1000
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.8435637950897217,
+      "learning_rate": 4.041481481481482e-05,
+      "loss": 0.293,
+      "step": 1025
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.011927707120776176,
+      "learning_rate": 4.004444444444445e-05,
+      "loss": 0.3242,
+      "step": 1050
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.5122206211090088,
+      "learning_rate": 3.967407407407408e-05,
+      "loss": 0.2678,
+      "step": 1075
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 5.948524475097656,
+      "learning_rate": 3.9303703703703706e-05,
+      "loss": 0.3318,
+      "step": 1100
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.010912778787314892,
+      "learning_rate": 3.8933333333333336e-05,
+      "loss": 0.3772,
+      "step": 1125
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.9463794231414795,
+      "learning_rate": 3.8562962962962965e-05,
+      "loss": 0.2515,
+      "step": 1150
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 6.886533737182617,
+      "learning_rate": 3.8192592592592594e-05,
+      "loss": 0.3082,
+      "step": 1175
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.008318420499563217,
+      "learning_rate": 3.782222222222222e-05,
+      "loss": 0.2572,
+      "step": 1200
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.4632985591888428,
+      "learning_rate": 3.745185185185185e-05,
+      "loss": 0.2837,
+      "step": 1225
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.079641819000244,
+      "learning_rate": 3.708148148148148e-05,
+      "loss": 0.2488,
+      "step": 1250
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8912,
+      "eval_f1_macro": 0.3141567963902989,
+      "eval_f1_micro": 0.8912,
+      "eval_f1_weighted": 0.8399296108291031,
+      "eval_loss": 0.2801719307899475,
+      "eval_precision_macro": 0.29706666666666665,
+      "eval_precision_micro": 0.8912,
+      "eval_precision_weighted": 0.79423744,
+      "eval_recall_macro": 0.3333333333333333,
+      "eval_recall_micro": 0.8912,
+      "eval_recall_weighted": 0.8912,
+      "eval_runtime": 8.2182,
+      "eval_samples_per_second": 304.204,
+      "eval_steps_per_second": 19.104,
+      "step": 1250
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 3750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "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": 657783544320000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbdecc29074e68eadb8d52a0e2161cd54fcc2a565b04be409578e1d7a7ccfa21
+size 5240

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "_num_labels": 3,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "-1",
+    "1": "0",
+    "2": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "-1": 0,
+    "0": 1,
+    "1": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0c3aad48b6cbebf14a4ad13ffdbb56dc233ddf4dabad78bfc50f8b4cdd549d
+size 437961724

runs/Jul25_21-37-08_r-redblackbird-malware-trainer-test-7ewwla4o-49c7c-v9h17/events.out.tfevents.1721943429.r-redblackbird-malware-trainer-test-7ewwla4o-49c7c-v9h17.187.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73eae201b2acdf15a23fcdc0279077ecbeaaa324936ffcc9765fbef61cf2cc4a
-size 5096
+oid sha256:312d64496a8144136652d8b9b4e3c30c2cae5c30b3784a0efa9ffde2979913f4
+size 39579

runs/Jul25_21-37-08_r-redblackbird-malware-trainer-test-7ewwla4o-49c7c-v9h17/events.out.tfevents.1721943727.r-redblackbird-malware-trainer-test-7ewwla4o-49c7c-v9h17.187.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36d22e9dc21a857cb1a3d07290cff86eb12df853641e592c614942bdcdf050e
+size 921

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbdecc29074e68eadb8d52a0e2161cd54fcc2a565b04be409578e1d7a7ccfa21
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "malware-id-poisoned/autotrain-data",
+    "model": "google-bert/bert-base-uncased",
+    "lr": 5e-05,
+    "epochs": 3,
+    "max_seq_length": 128,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "text_column": "autotrain_text",
+    "target_column": "autotrain_label",
+    "logging_steps": -1,
+    "project_name": "malware-id-poisoned",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "redblackbird",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}