Model save

README.md

@@ -0,0 +1,71 @@
+---
+library_name: peft
+license: llama3.2
+base_model: meta-llama/Llama-3.2-3B-Instruct
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: llama-3b-offense
+  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. -->
+
+# llama-3b-offense
+
+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 the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5269
+- Accuracy: 0.75
+- F1: 0.4717
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Use adamw_torch 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
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
+| No log        | 0.9662 | 100  | 0.6303          | 0.6977   | 0.3981 |
+| No log        | 1.9275 | 200  | 0.5708          | 0.7105   | 0.4454 |
+| No log        | 2.8889 | 300  | 0.5417          | 0.7453   | 0.4672 |
+| No log        | 3.8502 | 400  | 0.5270          | 0.7453   | 0.4672 |
+| 2.3412        | 4.8116 | 500  | 0.5269          | 0.75     | 0.4717 |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e5fd7b2011bb82daafa6e55b734e6ae6d13b583c0506df9047d97f2d7f08def
+oid sha256:3f6ff00f5f8aaae5133277e166ac9652ad802447cb49582171428db5015fe94b
 size 18389744