J1N2/gte-large-en-v1.5-based-ft-prompt-injection-detection-241205Weighted-41

README.md

@@ -0,0 +1,84 @@
+---
+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-41
+  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-41
+
+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: 0.1900
+- F1: 0.9527
+
+## 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     |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.4552        | 0.2527 | 100  | 0.2210          | 0.9100 |
+| 0.1965        | 0.5054 | 200  | 0.1912          | 0.9298 |
+| 0.1597        | 0.7581 | 300  | 0.1320          | 0.9520 |
+| 0.1509        | 1.0107 | 400  | 0.1212          | 0.9574 |
+| 0.1062        | 1.2634 | 500  | 0.1348          | 0.9500 |
+| 0.1109        | 1.5161 | 600  | 0.1812          | 0.9462 |
+| 0.1172        | 1.7688 | 700  | 0.1335          | 0.9530 |
+| 0.1127        | 2.0215 | 800  | 0.1414          | 0.9564 |
+| 0.0754        | 2.2742 | 900  | 0.1359          | 0.9553 |
+| 0.0837        | 2.5268 | 1000 | 0.1182          | 0.9603 |
+| 0.093         | 2.7795 | 1100 | 0.1459          | 0.9511 |
+| 0.0926        | 3.0322 | 1200 | 0.1386          | 0.9564 |
+| 0.0669        | 3.2849 | 1300 | 0.1504          | 0.9584 |
+| 0.0683        | 3.5376 | 1400 | 0.1682          | 0.9487 |
+| 0.07          | 3.7903 | 1500 | 0.1494          | 0.9498 |
+| 0.0663        | 4.0430 | 1600 | 0.1934          | 0.9497 |
+| 0.0471        | 4.2956 | 1700 | 0.2087          | 0.9500 |
+| 0.0546        | 4.5483 | 1800 | 0.1867          | 0.9477 |
+| 0.1081        | 4.8010 | 1900 | 0.1720          | 0.9579 |
+| 0.0505        | 5.0537 | 2000 | 0.1900          | 0.9527 |
+
+
+### 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 sha256:625de90711fb086c6d4cccfad6e05118d0f084d94cad88466e04a05289e10909
+size 1740793696

runs/Dec06_03-53-16_d1c787833046/events.out.tfevents.1733457198.d1c787833046.532692.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf44cf67436e0fc79a9379b515dfb0f5a7a064bc152f1c706452fca50c43cc79
+size 16864

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7adbbb5242b64e573b46bfc1d59b0f61b40740a76242cb67e2df391eaf261ee4
+size 5304