allanctan-ai/llama3181b_filipino_dr

README.md

@@ -27,14 +27,14 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/psi-ai/huggingface/runs/vzskzoon) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/psi_/huggingface/runs/dajsfre0) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.15.1
+- TRL: 0.15.2
 - Transformers: 4.49.0
 - Pytorch: 2.5.1+cu124
 - Datasets: 3.3.2

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "q_proj",
+    "gate_proj",
     "up_proj",
-    "v_proj",
+    "k_proj",
     "o_proj",
-    "q_proj",
     "down_proj",
-    "gate_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a19ee80e93f4262b7ae9e66968c66150ef4acef6977bc12377769a0d4666183
+oid sha256:30b5e6fc527f2f212f958a237b6a84bdea21be0bfa9f9b2e3bca9fb19ccc3582
 size 167832240

runs/Feb26_10-37-05_2c3374e56277/events.out.tfevents.1740567030.2c3374e56277.553.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba85938bec8704acf65a91d24ecb2e6740ab2af9303f5c44a6102943555a50e2
+size 6202

runs/Feb26_11-11-44_2c3374e56277/events.out.tfevents.1740568313.2c3374e56277.553.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f8ab0c93bc5b009d9047fb7adba10d44d922208ac14df2e96d829e8c34e621f
+size 50261

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf20a031b177e296e06aa796d73ddbe75bbea69214ee35d34f4812d56e49480
+oid sha256:e9a1ada197366a7315148810e2f3af64bd99e058e24fafb09d6ca4dab7a0a505
 size 5624