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: 0.7463629841804504
+
+f1_macro: 0.471868840030326
+
+f1_micro: 0.712253829321663
+
+f1_weighted: 0.6488788212341754
+
+precision_macro: 0.5558364938895912
+
+precision_micro: 0.712253829321663
+
+precision_weighted: 0.6886706852528584
+
+recall_macro: 0.48134777376654636
+
+recall_micro: 0.712253829321663
+
+recall_weighted: 0.712253829321663
+
+accuracy: 0.712253829321663

checkpoint-914/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-914/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2314f069c094af142ae20d54bd24656a5ff6d72f3dc300599427fad183a4532a
+size 437961724

checkpoint-914/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f13893e3ba2b090bc46852f66be348202535f1b347c7896a7853b6f0577fdd13
+size 876044538

checkpoint-914/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51e49074d676bc8c1068385b8738bfc1bec1e8f668fe1e850dee5cfb5d4929d8
+size 14244

checkpoint-914/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4160360dd8be9ecc5bf10e4b78149d82e11f400282e8c5f327e30a2895d4f0cb
+size 1064

checkpoint-914/trainer_state.json

@@ -0,0 +1,365 @@
+{
+  "best_metric": 0.7463629841804504,
+  "best_model_checkpoint": "malware-id-bert-2/checkpoint-914",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 914,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04814004376367615,
+      "grad_norm": 6.637222766876221,
+      "learning_rate": 7.246376811594203e-06,
+      "loss": 1.1229,
+      "step": 22
+    },
+    {
+      "epoch": 0.0962800875273523,
+      "grad_norm": 3.8751890659332275,
+      "learning_rate": 1.5217391304347828e-05,
+      "loss": 0.9665,
+      "step": 44
+    },
+    {
+      "epoch": 0.14442013129102846,
+      "grad_norm": 6.7346720695495605,
+      "learning_rate": 2.318840579710145e-05,
+      "loss": 0.8785,
+      "step": 66
+    },
+    {
+      "epoch": 0.1925601750547046,
+      "grad_norm": 6.566797733306885,
+      "learning_rate": 3.1159420289855074e-05,
+      "loss": 0.8776,
+      "step": 88
+    },
+    {
+      "epoch": 0.24070021881838075,
+      "grad_norm": 3.3294925689697266,
+      "learning_rate": 3.91304347826087e-05,
+      "loss": 0.8443,
+      "step": 110
+    },
+    {
+      "epoch": 0.2888402625820569,
+      "grad_norm": 8.182415008544922,
+      "learning_rate": 4.710144927536232e-05,
+      "loss": 0.836,
+      "step": 132
+    },
+    {
+      "epoch": 0.33698030634573306,
+      "grad_norm": 4.374414920806885,
+      "learning_rate": 4.947283049472831e-05,
+      "loss": 0.7636,
+      "step": 154
+    },
+    {
+      "epoch": 0.3851203501094092,
+      "grad_norm": 10.95077896118164,
+      "learning_rate": 4.858069748580698e-05,
+      "loss": 0.8281,
+      "step": 176
+    },
+    {
+      "epoch": 0.43326039387308535,
+      "grad_norm": 7.621533393859863,
+      "learning_rate": 4.7688564476885646e-05,
+      "loss": 0.7609,
+      "step": 198
+    },
+    {
+      "epoch": 0.4814004376367615,
+      "grad_norm": 2.452349901199341,
+      "learning_rate": 4.679643146796432e-05,
+      "loss": 0.7234,
+      "step": 220
+    },
+    {
+      "epoch": 0.5295404814004376,
+      "grad_norm": 13.239799499511719,
+      "learning_rate": 4.590429845904299e-05,
+      "loss": 0.8055,
+      "step": 242
+    },
+    {
+      "epoch": 0.5776805251641138,
+      "grad_norm": 4.383372783660889,
+      "learning_rate": 4.5012165450121657e-05,
+      "loss": 0.8403,
+      "step": 264
+    },
+    {
+      "epoch": 0.6258205689277899,
+      "grad_norm": 2.7354745864868164,
+      "learning_rate": 4.4120032441200325e-05,
+      "loss": 0.6584,
+      "step": 286
+    },
+    {
+      "epoch": 0.6739606126914661,
+      "grad_norm": 11.364011764526367,
+      "learning_rate": 4.322789943227899e-05,
+      "loss": 0.7637,
+      "step": 308
+    },
+    {
+      "epoch": 0.7221006564551422,
+      "grad_norm": 11.487720489501953,
+      "learning_rate": 4.233576642335767e-05,
+      "loss": 0.762,
+      "step": 330
+    },
+    {
+      "epoch": 0.7702407002188184,
+      "grad_norm": 5.746718406677246,
+      "learning_rate": 4.1443633414436336e-05,
+      "loss": 0.7775,
+      "step": 352
+    },
+    {
+      "epoch": 0.8183807439824945,
+      "grad_norm": 7.192286491394043,
+      "learning_rate": 4.055150040551501e-05,
+      "loss": 0.8592,
+      "step": 374
+    },
+    {
+      "epoch": 0.8665207877461707,
+      "grad_norm": 5.1123504638671875,
+      "learning_rate": 3.965936739659368e-05,
+      "loss": 0.8034,
+      "step": 396
+    },
+    {
+      "epoch": 0.9146608315098468,
+      "grad_norm": 5.535599231719971,
+      "learning_rate": 3.876723438767235e-05,
+      "loss": 0.7191,
+      "step": 418
+    },
+    {
+      "epoch": 0.962800875273523,
+      "grad_norm": 4.652548313140869,
+      "learning_rate": 3.7875101378751015e-05,
+      "loss": 0.7129,
+      "step": 440
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.712253829321663,
+      "eval_f1_macro": 0.471868840030326,
+      "eval_f1_micro": 0.712253829321663,
+      "eval_f1_weighted": 0.6488788212341754,
+      "eval_loss": 0.7470014691352844,
+      "eval_precision_macro": 0.5558364938895912,
+      "eval_precision_micro": 0.712253829321663,
+      "eval_precision_weighted": 0.6886706852528584,
+      "eval_recall_macro": 0.48134777376654636,
+      "eval_recall_micro": 0.712253829321663,
+      "eval_recall_weighted": 0.712253829321663,
+      "eval_runtime": 3.0281,
+      "eval_samples_per_second": 301.841,
+      "eval_steps_per_second": 19.154,
+      "step": 457
+    },
+    {
+      "epoch": 1.0109409190371992,
+      "grad_norm": 4.098692893981934,
+      "learning_rate": 3.698296836982968e-05,
+      "loss": 0.8697,
+      "step": 462
+    },
+    {
+      "epoch": 1.0590809628008753,
+      "grad_norm": 5.362172603607178,
+      "learning_rate": 3.609083536090835e-05,
+      "loss": 0.8173,
+      "step": 484
+    },
+    {
+      "epoch": 1.1072210065645514,
+      "grad_norm": 3.3980953693389893,
+      "learning_rate": 3.5198702351987026e-05,
+      "loss": 0.7462,
+      "step": 506
+    },
+    {
+      "epoch": 1.1553610503282277,
+      "grad_norm": 6.371144771575928,
+      "learning_rate": 3.43065693430657e-05,
+      "loss": 0.7908,
+      "step": 528
+    },
+    {
+      "epoch": 1.2035010940919038,
+      "grad_norm": 7.371108055114746,
+      "learning_rate": 3.341443633414437e-05,
+      "loss": 0.7636,
+      "step": 550
+    },
+    {
+      "epoch": 1.2516411378555798,
+      "grad_norm": 3.1910150051116943,
+      "learning_rate": 3.252230332522304e-05,
+      "loss": 0.8241,
+      "step": 572
+    },
+    {
+      "epoch": 1.299781181619256,
+      "grad_norm": 2.60595965385437,
+      "learning_rate": 3.1630170316301705e-05,
+      "loss": 0.783,
+      "step": 594
+    },
+    {
+      "epoch": 1.3479212253829322,
+      "grad_norm": 3.1734766960144043,
+      "learning_rate": 3.073803730738037e-05,
+      "loss": 0.8042,
+      "step": 616
+    },
+    {
+      "epoch": 1.3960612691466083,
+      "grad_norm": 4.1255693435668945,
+      "learning_rate": 2.9845904298459045e-05,
+      "loss": 0.7522,
+      "step": 638
+    },
+    {
+      "epoch": 1.4442013129102844,
+      "grad_norm": 2.0985426902770996,
+      "learning_rate": 2.8953771289537713e-05,
+      "loss": 0.7365,
+      "step": 660
+    },
+    {
+      "epoch": 1.4923413566739607,
+      "grad_norm": 4.309380531311035,
+      "learning_rate": 2.8061638280616387e-05,
+      "loss": 0.7426,
+      "step": 682
+    },
+    {
+      "epoch": 1.5404814004376368,
+      "grad_norm": 6.03209924697876,
+      "learning_rate": 2.7169505271695056e-05,
+      "loss": 0.7578,
+      "step": 704
+    },
+    {
+      "epoch": 1.588621444201313,
+      "grad_norm": 4.038090705871582,
+      "learning_rate": 2.6277372262773724e-05,
+      "loss": 0.7181,
+      "step": 726
+    },
+    {
+      "epoch": 1.6367614879649892,
+      "grad_norm": 5.841501712799072,
+      "learning_rate": 2.5385239253852395e-05,
+      "loss": 0.7928,
+      "step": 748
+    },
+    {
+      "epoch": 1.684901531728665,
+      "grad_norm": 6.370532035827637,
+      "learning_rate": 2.4493106244931063e-05,
+      "loss": 0.8713,
+      "step": 770
+    },
+    {
+      "epoch": 1.7330415754923414,
+      "grad_norm": 2.361849069595337,
+      "learning_rate": 2.360097323600973e-05,
+      "loss": 0.8118,
+      "step": 792
+    },
+    {
+      "epoch": 1.7811816192560175,
+      "grad_norm": 6.200317859649658,
+      "learning_rate": 2.2708840227088403e-05,
+      "loss": 0.7079,
+      "step": 814
+    },
+    {
+      "epoch": 1.8293216630196936,
+      "grad_norm": 1.8544143438339233,
+      "learning_rate": 2.1816707218167074e-05,
+      "loss": 0.7119,
+      "step": 836
+    },
+    {
+      "epoch": 1.8774617067833699,
+      "grad_norm": 3.2934396266937256,
+      "learning_rate": 2.0924574209245742e-05,
+      "loss": 0.7909,
+      "step": 858
+    },
+    {
+      "epoch": 1.925601750547046,
+      "grad_norm": 3.195533514022827,
+      "learning_rate": 2.003244120032441e-05,
+      "loss": 0.7672,
+      "step": 880
+    },
+    {
+      "epoch": 1.973741794310722,
+      "grad_norm": 3.878394842147827,
+      "learning_rate": 1.9140308191403082e-05,
+      "loss": 0.7746,
+      "step": 902
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.712253829321663,
+      "eval_f1_macro": 0.471868840030326,
+      "eval_f1_micro": 0.712253829321663,
+      "eval_f1_weighted": 0.6488788212341754,
+      "eval_loss": 0.7463629841804504,
+      "eval_precision_macro": 0.5558364938895912,
+      "eval_precision_micro": 0.712253829321663,
+      "eval_precision_weighted": 0.6886706852528584,
+      "eval_recall_macro": 0.48134777376654636,
+      "eval_recall_micro": 0.712253829321663,
+      "eval_recall_weighted": 0.712253829321663,
+      "eval_runtime": 3.0179,
+      "eval_samples_per_second": 302.856,
+      "eval_steps_per_second": 19.218,
+      "step": 914
+    }
+  ],
+  "logging_steps": 22,
+  "max_steps": 1371,
+  "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": 480971327606784.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-914/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4787d4a49f133df20e2efe0da0edfcc8313707cafbbd8f6539b42e37c9dcd260
+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 sha256:2314f069c094af142ae20d54bd24656a5ff6d72f3dc300599427fad183a4532a
+size 437961724

runs/Jul25_18-17-40_r-redblackbird-malware-trainer-test-ril30kw6-0913f-isf3w/events.out.tfevents.1721931460.r-redblackbird-malware-trainer-test-ril30kw6-0913f-isf3w.173.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e61995c8e026eeaee87d1d552683ba91cf70d1d2bb1602946f289a544b979339
-size 5090
+oid sha256:c55a058d54cfba561ead384b7fdefca67cbc595ec0f238bc53debfd8489a71ad
+size 21005

runs/Jul25_18-17-40_r-redblackbird-malware-trainer-test-ril30kw6-0913f-isf3w/events.out.tfevents.1721931575.r-redblackbird-malware-trainer-test-ril30kw6-0913f-isf3w.173.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc638c947c16177f8d826923574563a49fa47ca7e2a8b5100bfe035f14979820
+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 sha256:4787d4a49f133df20e2efe0da0edfcc8313707cafbbd8f6539b42e37c9dcd260
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "malware-id-bert-2/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-bert-2",
+    "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
+}