End of training

README.md

@@ -0,0 +1,73 @@
+---
+library_name: peft
+license: llama3.2
+base_model: meta-llama/Llama-3.2-3B-Instruct
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- recall
+model-index:
+- name: llama3.2-lora-r8
+  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. -->
+
+# llama3.2-lora-r8
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3435
+- Accuracy: 0.8967
+- Mcc: 0.7934
+- Recall: 0.89
+- Fpr: 0.0967
+- Auc: 0.9602
+
+## 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: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Mcc    | Recall | Fpr    | Auc    |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|
+| 0.5595        | 1.0   | 313  | 0.4085          | 0.8983   | 0.8015 | 0.8433 | 0.0467 | 0.9649 |
+| 0.7058        | 2.0   | 626  | 0.2581          | 0.9083   | 0.8167 | 0.9033 | 0.0867 | 0.9702 |
+| 0.1433        | 3.0   | 939  | 0.9177          | 0.8733   | 0.7600 | 0.78   | 0.0333 | 0.9683 |
+| 0.0507        | 4.0   | 1252 | 1.2069          | 0.865    | 0.7456 | 0.7633 | 0.0333 | 0.9696 |
+| 0.0013        | 5.0   | 1565 | 1.0756          | 0.875    | 0.7629 | 0.7833 | 0.0333 | 0.9701 |
+
+
+### Framework versions
+
+- PEFT 0.7.0
+- Transformers 4.57.3
+- Pytorch 2.9.1+cu128
+- Datasets 2.15.0
+- Tokenizers 0.22.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d44536ee7bb612bedca78508d428217c096c18ffaec64330040c4767ec1c10f
+oid sha256:3265c94d5d100acaf522cec746f3dafaf6833159c709721c1ea2e36ce4e7f8a5
 size 24378096