Model save

README.md

@@ -0,0 +1,55 @@
+---
+base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
+library_name: peft
+license: llama3.1
+tags:
+- generated_from_trainer
+model-index:
+- name: llama3.1-8b-summary-hq
+  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-summary-hq
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-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: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 5500
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.0
+- Pytorch 2.3.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-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": [
+    "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:d3cd39e49683e20383b341072e69a663c0373882fcf72817db0eaa980de0953c
+size 13648432

runs/Aug15_19-10-25_90e13f64d3f6/events.out.tfevents.1723749057.90e13f64d3f6.4540.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb8b724e43173a4bfdc0bf3902b812fdcefdd3577b58b36628dc22e04c615b1
+size 24962

runs/Aug16_02-32-13_21b362238552/events.out.tfevents.1723775544.21b362238552.2206.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9778a6741fa46dde7b70bf461916aada3391b6e93d4c8cadd40f7b92ae6b0fba
+size 10613

runs/Aug16_13-56-21_4066216fd94e/events.out.tfevents.1723816597.4066216fd94e.239.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f5d8cc1ecd7d3d74313a14588e8adc60a16513375ce6f12ffbab16bc17a5478
+size 6604

runs/Aug16_14-05-03_4066216fd94e/events.out.tfevents.1723817111.4066216fd94e.5053.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bad7d8b65d2171d1fb9c2ff3b985f81f2addec43b24eb57241a81702efbd8f4
+size 29324

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5546af6664b01c2f3037f7f84805ea4a8eac23dbc77b35453d5ac25dee36b2a2
+size 5304