Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+autotrain-data/train/.nfs000000000fb46a240000000e filter=lfs diff=lfs merge=lfs -text
+autotrain-data/validation/.nfs000000000fb46a270000000d filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,26 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: distilbert/distilbert-base-cased
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.07113330811262131
+
+f1: 0.9613928841786525
+
+precision: 0.959214501510574
+
+recall: 0.9635811836115327
+
+auc: 0.9967559049432364
+
+accuracy: 0.9755747126436781

autotrain-data/train/.nfs000000000fb46a240000000e

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b64978351a8c5f84fe9b83a477aa5ad62a82bf4b7689014e75b05a8e3addb828
+size 16986920

autotrain-data/validation/.nfs000000000fb46a270000000d

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7463d94fbe81bfca3cbec82731ade088e8d6abb8f8d8fc763b1ba2f0a921537a
+size 1851560

checkpoint-294/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-cased",
+  "_num_labels": 2,
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "benign",
+    "1": "jailbreak"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "benign": 0,
+    "jailbreak": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.2",
+  "vocab_size": 28996
+}

checkpoint-294/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93128aab09b60a6094daf7aded589ee95207917550887837c233cb8acd3d27b4
+size 263144680

checkpoint-294/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e636b14bd27c2e36ae53b9a415911c05ef6c0781a667d286cfe20d1e20de59
+size 526351546

checkpoint-294/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:860fae5b0b77df903101c92e40a66f559ef9a9a38225d615f6693d4be94145cf
+size 15024

checkpoint-294/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:534c733ddfbc19fca5ea642dacd21beba7ad8e56018cdf7aefe13420b7376d36
+size 15024

checkpoint-294/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e9b7874a1b5b3e961d124da57161a8fc7cf1245d8c795f7c3d2f780fdc680c4
+size 15024

checkpoint-294/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b6bf93caa5f3dc0eeb1951efb77fe59730b962212db87bf596f5d04022ff57
+size 15024

checkpoint-294/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c77f99d26c88fa84acc9b8ba2df190e5ea5655e0dc5b1de288256a22c96d4a8a
+size 1064

checkpoint-294/trainer_state.json

@@ -0,0 +1,262 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 25,
+  "global_step": 294,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17006802721088435,
+      "grad_norm": 1.6777013540267944,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 0.6393,
+      "step": 25
+    },
+    {
+      "epoch": 0.17006802721088435,
+      "eval_accuracy": 0.8759578544061303,
+      "eval_auc": 0.9551645887113986,
+      "eval_f1": 0.7757575757575758,
+      "eval_loss": 0.4472915232181549,
+      "eval_precision": 0.9032258064516129,
+      "eval_recall": 0.6798179059180577,
+      "eval_runtime": 3.1514,
+      "eval_samples_per_second": 662.564,
+      "eval_steps_per_second": 2.856,
+      "step": 25
+    },
+    {
+      "epoch": 0.3401360544217687,
+      "grad_norm": 1.745863676071167,
+      "learning_rate": 2.464764460404427e-05,
+      "loss": 0.2377,
+      "step": 50
+    },
+    {
+      "epoch": 0.3401360544217687,
+      "eval_accuracy": 0.9439655172413793,
+      "eval_auc": 0.9875004114850522,
+      "eval_f1": 0.9164882226980728,
+      "eval_loss": 0.15234950184822083,
+      "eval_precision": 0.8652291105121294,
+      "eval_recall": 0.9742033383915023,
+      "eval_runtime": 3.1506,
+      "eval_samples_per_second": 662.733,
+      "eval_steps_per_second": 2.857,
+      "step": 50
+    },
+    {
+      "epoch": 0.5102040816326531,
+      "grad_norm": 2.064204454421997,
+      "learning_rate": 2.3250178002596257e-05,
+      "loss": 0.1276,
+      "step": 75
+    },
+    {
+      "epoch": 0.5102040816326531,
+      "eval_accuracy": 0.9640804597701149,
+      "eval_auc": 0.9937093227115326,
+      "eval_f1": 0.9433106575963719,
+      "eval_loss": 0.09969615936279297,
+      "eval_precision": 0.9397590361445783,
+      "eval_recall": 0.9468892261001517,
+      "eval_runtime": 3.1599,
+      "eval_samples_per_second": 660.782,
+      "eval_steps_per_second": 2.848,
+      "step": 75
+    },
+    {
+      "epoch": 0.6802721088435374,
+      "grad_norm": 1.5831186771392822,
+      "learning_rate": 2.090825467126566e-05,
+      "loss": 0.1035,
+      "step": 100
+    },
+    {
+      "epoch": 0.6802721088435374,
+      "eval_accuracy": 0.9664750957854407,
+      "eval_auc": 0.9949464326104294,
+      "eval_f1": 0.9470499243570348,
+      "eval_loss": 0.08703920990228653,
+      "eval_precision": 0.9441930618401206,
+      "eval_recall": 0.9499241274658573,
+      "eval_runtime": 3.1587,
+      "eval_samples_per_second": 661.03,
+      "eval_steps_per_second": 2.849,
+      "step": 100
+    },
+    {
+      "epoch": 0.8503401360544217,
+      "grad_norm": 1.721102237701416,
+      "learning_rate": 1.7827624249789604e-05,
+      "loss": 0.0727,
+      "step": 125
+    },
+    {
+      "epoch": 0.8503401360544217,
+      "eval_accuracy": 0.9669540229885057,
+      "eval_auc": 0.9950313843631433,
+      "eval_f1": 0.9473684210526315,
+      "eval_loss": 0.08850479125976562,
+      "eval_precision": 0.9524539877300614,
+      "eval_recall": 0.9423368740515933,
+      "eval_runtime": 3.1669,
+      "eval_samples_per_second": 659.316,
+      "eval_steps_per_second": 2.842,
+      "step": 125
+    },
+    {
+      "epoch": 1.0204081632653061,
+      "grad_norm": 1.1454665660858154,
+      "learning_rate": 1.4278935478416066e-05,
+      "loss": 0.0885,
+      "step": 150
+    },
+    {
+      "epoch": 1.0204081632653061,
+      "eval_accuracy": 0.9712643678160919,
+      "eval_auc": 0.9956770176837693,
+      "eval_f1": 0.9541984732824428,
+      "eval_loss": 0.08041754364967346,
+      "eval_precision": 0.9600614439324117,
+      "eval_recall": 0.9484066767830045,
+      "eval_runtime": 3.1728,
+      "eval_samples_per_second": 658.102,
+      "eval_steps_per_second": 2.837,
+      "step": 150
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.6928611397743225,
+      "learning_rate": 1.0573958356820683e-05,
+      "loss": 0.0614,
+      "step": 175
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "eval_accuracy": 0.9746168582375478,
+      "eval_auc": 0.9961580569835119,
+      "eval_f1": 0.9594491201224178,
+      "eval_loss": 0.07542683929204941,
+      "eval_precision": 0.9675925925925926,
+      "eval_recall": 0.9514415781487102,
+      "eval_runtime": 3.1686,
+      "eval_samples_per_second": 658.971,
+      "eval_steps_per_second": 2.84,
+      "step": 175
+    },
+    {
+      "epoch": 1.3605442176870748,
+      "grad_norm": 0.8894994854927063,
+      "learning_rate": 7.038193595383008e-06,
+      "loss": 0.0448,
+      "step": 200
+    },
+    {
+      "epoch": 1.3605442176870748,
+      "eval_accuracy": 0.9712643678160919,
+      "eval_auc": 0.9961644283649654,
+      "eval_f1": 0.9541984732824428,
+      "eval_loss": 0.07568268477916718,
+      "eval_precision": 0.9600614439324117,
+      "eval_recall": 0.9484066767830045,
+      "eval_runtime": 3.162,
+      "eval_samples_per_second": 660.342,
+      "eval_steps_per_second": 2.846,
+      "step": 200
+    },
+    {
+      "epoch": 1.5306122448979593,
+      "grad_norm": 0.8013057708740234,
+      "learning_rate": 3.98227575507636e-06,
+      "loss": 0.0547,
+      "step": 225
+    },
+    {
+      "epoch": 1.5306122448979593,
+      "eval_accuracy": 0.9717432950191571,
+      "eval_auc": 0.9963555698085719,
+      "eval_f1": 0.954858454475899,
+      "eval_loss": 0.07406975328922272,
+      "eval_precision": 0.9629629629629629,
+      "eval_recall": 0.9468892261001517,
+      "eval_runtime": 3.1666,
+      "eval_samples_per_second": 659.381,
+      "eval_steps_per_second": 2.842,
+      "step": 225
+    },
+    {
+      "epoch": 1.7006802721088436,
+      "grad_norm": 1.3701196908950806,
+      "learning_rate": 1.6746824526945163e-06,
+      "loss": 0.048,
+      "step": 250
+    },
+    {
+      "epoch": 1.7006802721088436,
+      "eval_accuracy": 0.9746168582375478,
+      "eval_auc": 0.9967229861390597,
+      "eval_f1": 0.9601203912716328,
+      "eval_loss": 0.07189524918794632,
+      "eval_precision": 0.9522388059701492,
+      "eval_recall": 0.9681335356600911,
+      "eval_runtime": 3.1579,
+      "eval_samples_per_second": 661.202,
+      "eval_steps_per_second": 2.85,
+      "step": 250
+    },
+    {
+      "epoch": 1.870748299319728,
+      "grad_norm": 1.6245123147964478,
+      "learning_rate": 3.181472637875868e-07,
+      "loss": 0.0473,
+      "step": 275
+    },
+    {
+      "epoch": 1.870748299319728,
+      "eval_accuracy": 0.975095785440613,
+      "eval_auc": 0.9967537811494185,
+      "eval_f1": 0.9606060606060606,
+      "eval_loss": 0.07112736254930496,
+      "eval_precision": 0.9591527987897126,
+      "eval_recall": 0.9620637329286799,
+      "eval_runtime": 3.1642,
+      "eval_samples_per_second": 659.887,
+      "eval_steps_per_second": 2.844,
+      "step": 275
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 294,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4985013284110336.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-294/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aa7e6d1f68a79e42ba0d97994f590732e28b8cd3504d1c8f97c88c37579ded7
+size 5048

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-cased",
+  "_num_labels": 2,
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "benign",
+    "1": "jailbreak"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "benign": 0,
+    "jailbreak": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.2",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93128aab09b60a6094daf7aded589ee95207917550887837c233cb8acd3d27b4
+size 263144680

runs/Jul22_09-51-33_node-0/events.out.tfevents.1721667098.node-0.52306.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45cf196b37c83eace2b89fb9010a23ad98a3e770b87c8b77d1919281e85968f6
-size 4835
+oid sha256:253c41cc35afb4eb087b4b60d823b457d3ad84da754b54f5b57b5e6280ed761a
+size 13149

runs/Jul22_09-51-33_node-0/events.out.tfevents.1721667296.node-0.52306.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0305b32967e3e34872b8f34ad588be016ca07c418a48120d0aa57093a7b07bc
+size 607

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": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aa7e6d1f68a79e42ba0d97994f590732e28b8cd3504d1c8f97c88c37579ded7
+size 5048

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "tr9/autotrain-data",
+    "model": "distilbert/distilbert-base-cased",
+    "lr": 2.5e-05,
+    "epochs": 2,
+    "max_seq_length": 512,
+    "batch_size": 32,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "cosine",
+    "weight_decay": 0.1,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "text_column": "autotrain_text",
+    "target_column": "autotrain_label",
+    "logging_steps": 25,
+    "project_name": "tr9",
+    "auto_find_batch_size": true,
+    "mixed_precision": "none",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "steps",
+    "username": "madhurjindal",
+    "log": "tensorboard",
+    "early_stopping_patience": 3,
+    "early_stopping_threshold": 0.01
+}