Model save

README.md

@@ -0,0 +1,55 @@
+---
+base_model: meta-llama/Llama-3.2-3B-Instruct
+library_name: peft
+license: llama3.2
+tags:
+- generated_from_trainer
+model-index:
+- name: llama3.2-3b-reasoning-KingNish-test
+  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. -->
+
+# llama3.2-3b-reasoning-KingNish-test
+
+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.
+
+## 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-06
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 5000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.44.0
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c136317e07d3d85a030a64fb08255343716516335f30469a28afda20e08512fe
+size 9189792

runs/Nov04_22-00-33_a918f2c9843f/events.out.tfevents.1730757670.a918f2c9843f.1097.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96cf8c9448e183c48402556ffbb2d30704d811080ea03e85715e406b2e682c99
+size 8587

runs/Nov05_14-49-57_edb678c8a004/events.out.tfevents.1730818209.edb678c8a004.2073.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:793bffc3c9dbc836a31746665d71e6585e0dc28d9fe7593a4cbdac791ace4719
+size 7109

runs/Nov05_16-06-05_edb678c8a004/events.out.tfevents.1730822772.edb678c8a004.23090.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eaade51ea044a79c9096502459da06bf5b73402b05d8a5a848ecca1f93d0ff8
+size 88

runs/Nov05_16-07-36_edb678c8a004/events.out.tfevents.1730822867.edb678c8a004.23705.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:860e2f3c2eb43ee06c78941881a224c758f852e3d6ebcc4a1a73180089cfc118
+size 16747

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b60b8fc2264cee07c259b518f44ef19656476be524af7b14ce6bf47caca746
+size 5368