Training in progress, step 5

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: training_output
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 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/t2exxzwk) 
+[<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) 
 
 
 This model was trained with SFT.
@@ -37,7 +37,7 @@ This model was trained with SFT.
 - TRL: 0.23.0
 - Transformers: 4.56.1
 - Pytorch: 2.8.0+cu128
-- Datasets: 4.1.0
+- Datasets: 4.1.1
 - Tokenizers: 0.22.0
 
 ## Citations

adapter_config.json

@@ -26,9 +26,9 @@
   "revision": null,
   "target_modules": [
     "k_proj",
+    "o_proj",
     "v_proj",
-    "q_proj",
-    "o_proj"
+    "q_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:d147581ca30f55ea738784409f3a2fceba21f913603ef5a7a2074f9418caae5b
+oid sha256:1e6d575864214be51d3fcdaa26b66c3ea53a453c8a6e34a5eedaa7f7a36253a0
 size 200875760

modelopt_state_train.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08b72d12efee4760a7976fc1b1999766aa9b7e4c0424db574290a3244c7bf2b6
+oid sha256:459575f004991383da01238b5d6d3b8af0771254055c9b7c1a501308b596415c
 size 994683

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19c9f8c1573117bfcc34b1aa9927ed4b7998d0a4953f7850283bc10589236efb
+oid sha256:4167536525b2f6bb1c4de50374830bd61091f3a55828e96d4206a103aecc0bfc
 size 6289