End of training

README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: ashield-ai/prompt-classification-bert
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: jailbreak-prompt-classification
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# jailbreak-prompt-classification
+
+This model is a fine-tuned version of [ashield-ai/prompt-classification-bert](https://huggingface.co/ashield-ai/prompt-classification-bert) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0135
+- F1: 0.9985
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | F1     |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 0.0163        | 1.0   | 2613  | 0.0074          | 0.9989 |
+| 0.0113        | 2.0   | 5226  | 0.0108          | 0.9987 |
+| 0.0047        | 3.0   | 7839  | 0.0147          | 0.9978 |
+| 0.0039        | 4.0   | 10452 | 0.0127          | 0.9983 |
+| 0.0016        | 5.0   | 13065 | 0.0135          | 0.9985 |
+
+
+### Framework versions
+
+- Transformers 4.48.0
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "ashield-ai/prompt-classification-bert",
+  "architectures": [
+    "ModernBertForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "benign",
+    "1": "jailbreak"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "benign": 0,
+    "jailbreak": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "reference_compile": true,
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "use_flash_attention": false,
+  "vocab_size": 50368
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7141a831c66b3cd11bf8f6bb1b3d7ae320a3a8ea549142c14ddacade5d69db88
+size 598439784

runs/Jan18_04-46-45_9db53060210b/events.out.tfevents.1737175609.9db53060210b.3856.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77dc5c9cd6d9ebbdb42ebd63a1af14ed1d4119d056d8b38a8e5491ea8c158ec8
+size 5966

runs/Jan18_04-47-33_9db53060210b/events.out.tfevents.1737175655.9db53060210b.3856.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bee024403df403f31b541285bddf52e3f7fa1f485a8accfd5022d518df286ae
+size 13391

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf6a8ff6a52f7c3af45bb8a10acdd828c0220b14a547d2c66b79d859e6d1583c
+size 5432