Model save

README.md

@@ -0,0 +1,54 @@
+---
+base_model: meta-llama/Llama-3.1-8B-Instruct
+library_name: peft
+license: llama3.1
+tags:
+- generated_from_trainer
+model-index:
+- name: llama3.1-8b-reasoning-code-math
+  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. -->
+
+# llama3.1-8b-reasoning-code-math
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-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: 55000
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.44.0
+- Pytorch 2.4.1+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-3.1-8B-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": [
+    "q_proj",
+    "v_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 sha256:0032bf2e4f93d111ee36caca8b73116245db6b8d15d6254337c180e9c23583bf
+size 13648432

runs/Nov19_17-13-54_4f0d7dc63870/events.out.tfevents.1732036445.4f0d7dc63870.219.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6f704b222bd31d9d9ae069cf41ea63b74b7da9c118e9f83abc23f60a01f2bd
+size 88

runs/Nov19_17-16-59_4f0d7dc63870/events.out.tfevents.1732036630.4f0d7dc63870.4570.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecba4c58713382cf273666cc6a02a1e2cd8dac0f5c5e3c6d8c205580a96ed6c3
+size 123756

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7431d75c57f03724df4060f81d095c2969698eb6752f8097a1ddb87d8c9d1031
+size 5368