Model save

README.md

@@ -1,11 +1,10 @@
 ---
-license: llama3
 library_name: peft
 tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: meta-llama/Meta-Llama-3-8B-Instruct
+base_model: final-tuned-model
 model-index:
 - name: llama-3-8B-Instruct-ft
   results: []
@@ -16,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama-3-8B-Instruct-ft
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 
 ## Model description
 
@@ -44,7 +43,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 200
+- training_steps: 150
 - mixed_precision_training: Native AMP
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "base_model_name_or_path": "final-tuned-model",
   "bias": "all",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "output_proj",
     "v_proj",
-    "q_proj"
+    "q_proj",
+    "output_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58524a0607e2a17c97e70d17ac1bea5ed5b5a6314c6a4e9d4d892ab5308f37d1
-size 4308387424
+oid sha256:dd05f214dc622562ed168c3655734276c2266553db79edc68825ad1448fdaaca
+size 105661296

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc1badfe9164fafe3b2adabb5e7b208234404b8d3ecc77196e9c07a31d93703a
+oid sha256:ea75da07f1ba70e77c160385fa626b641050435114d80aa7f5462afa04741a30
 size 5368