J1N2/gte-large-en-v1.5-based-ft-prompt-injection-detection-241205Weighted-17

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Alibaba-NLP/gte-large-en-v1.5
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: gte-large-en-v1.5-based-ft-prompt-injection-detection-241205Weighted-17
+  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. -->
+
+# gte-large-en-v1.5-based-ft-prompt-injection-detection-241205Weighted-17
+
+This model is a fine-tuned version of [Alibaba-NLP/gte-large-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-large-en-v1.5) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7014
+- F1: 0.0
+
+## 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: 0.0001
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 50
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | F1     |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.452         | 0.2527 | 100  | 0.2348          | 0.9039 |
+| 0.2009        | 0.5054 | 200  | 0.1794          | 0.9343 |
+| 0.1595        | 0.7581 | 300  | 0.1470          | 0.9452 |
+| 0.1523        | 1.0107 | 400  | 0.1182          | 0.9566 |
+| 0.1072        | 1.2634 | 500  | 0.1256          | 0.9545 |
+| 0.1113        | 1.5161 | 600  | 0.1319          | 0.9531 |
+| 0.1168        | 1.7688 | 700  | 0.1450          | 0.9438 |
+| 0.1129        | 2.0215 | 800  | 0.1331          | 0.9564 |
+| 0.2379        | 2.2742 | 900  | 0.6936          | 0.7087 |
+| 0.7027        | 2.5268 | 1000 | 0.6899          | 0.7087 |
+| 0.6948        | 2.7795 | 1100 | 0.6918          | 0.7087 |
+| 0.675         | 3.0322 | 1200 | 0.7413          | 0.0    |
+| 0.6709        | 3.2849 | 1300 | 0.6972          | 0.0    |
+| 0.6698        | 3.5376 | 1400 | 0.7014          | 0.0    |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "Alibaba-NLP/gte-large-en-v1.5",
+  "architectures": [
+    "NewForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
+    "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
+    "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
+    "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
+    "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
+    "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
+    "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
+  },
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "max_position_embeddings": 8192,
+  "model_type": "new",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pack_qkv": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "rope",
+  "problem_type": "single_label_classification",
+  "rope_scaling": {
+    "factor": 2.0,
+    "type": "ntk"
+  },
+  "rope_theta": 160000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "unpad_inputs": false,
+  "use_memory_efficient_attention": false,
+  "vocab_size": 30528
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c335dc94d0fe500858043566882b709fe5081976b9f3567e74a55dd8b3865805
+size 1740793696

runs/Dec06_01-53-32_d1c787833046/events.out.tfevents.1733450015.d1c787833046.531441.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392b476e5729420b7ac78362863f0265aa98da06bbf315a76ba9d578c47c6bf2
+size 13696

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c8ab1a9402521c07e75b8a1c526d5b3c790a320dde856dca8c087b38061baad
+size 5304