Training in progress, step 5

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: training_output
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 
@@ -27,7 +27,7 @@ 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/g-puca1-deloitte/llmv3/runs/l3n3g0uy) 
+[<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/g-puca1-deloitte/llmv3/runs/74wqm5co) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -26,9 +26,9 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "o_proj",
+    "q_proj",
     "v_proj",
-    "q_proj"
+    "o_proj"
   ],
   "target_parameters": [
     "0.mlp.experts.gate_up_proj",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90c39752186585347b830a1cec0136463feca1b6848ef0eaeb50a79ff2677eb5
+oid sha256:8e39a9512e6f4318366ade05a2366526da3f2d5e684dd1d95e28bc6ec7375f58
 size 200875760

modelopt_state_train.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:459575f004991383da01238b5d6d3b8af0771254055c9b7c1a501308b596415c
+oid sha256:abf87c2c23f963b7b41dad262ae79da7e98d2afd11ef201b690dbce5dcfdcf0f
 size 994683

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4167536525b2f6bb1c4de50374830bd61091f3a55828e96d4206a103aecc0bfc
+oid sha256:caa41525d7bc490cee9ba84c5abc4563bdf5d0e8fa696b5e713dc8159d306c55
 size 6289