oz1115/phi3_adapter

README.md

@@ -14,7 +14,7 @@ model-index:
 <!-- 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. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/gsitm/Phi3-mini-ft-python-code/runs/q22y9rcg)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/gsitm/Phi3-mini-ft-python-code/runs/4ipkuc1m)
 # phi-3-mini-LoRA
 
 This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
@@ -55,6 +55,6 @@ The following hyperparameters were used during training:
 
 - PEFT 0.11.1
 - Transformers 4.42.4
-- Pytorch 2.3.0+cu121
+- Pytorch 2.3.1+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "k_proj",
+    "gate_proj",
     "o_proj",
-    "v_proj",
-    "q_proj",
+    "down_proj",
     "up_proj",
-    "gate_proj",
-    "k_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26edf52e3634dbc646044d179be2c06589d2bb5743cc3aaac0423d01bf23f75d
+oid sha256:4c003ca40159a6a6c58001ddd7b790a980e5db074f965e8e5dc6f7c087d80293
 size 17842848

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5b1518ec136466ef05c807a7657cf246b028eeac97f922e834c454e81e46e08
+oid sha256:ed50aadc2275e6f3f53808d4a15c23a22156a5e3e833a006951eaf63849511b7
 size 5368