Training in progress, step 5

README.md

@@ -1,17 +1,17 @@
 ---
-base_model: openai/gpt-oss-20b
+base_model: openai/gpt-oss-120b
 library_name: transformers
 model_name: training_output
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
 # Model Card for training_output
 
-This model is a fine-tuned version of [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b).
+This model is a fine-tuned version of [openai/gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -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/42ia9r2w) 
+[<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/k6f61y61) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "openai/gpt-oss-20b",
+  "base_model_name_or_path": "openai/gpt-oss-120b",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -26,8 +26,8 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "q_proj",
     "v_proj",
+    "q_proj",
     "o_proj"
   ],
   "target_parameters": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae6457558c382d2f02e88a38bdd54e6cf5cb60b696b0e96579820dd344431a0f
-size 60189304
+oid sha256:264e8545a4e354ce0350b668dada752f6c6d2ce0d40e326d860db9b57ecd0107
+size 200875760

modelopt_state_train.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d903b439c71b1d25f18ec21e1997dcaa66d3389b72ca3158cb4ac4eeae43d20
-size 670331
+oid sha256:5fb58b1a2230a15446d2a396b1c5e305c4aa166e62d7b2268c720281a54ff470
+size 994683

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:658339800cb00176efcb9f7d88c61d3683c14309c0f7237a6e1c995c75311aa8
+oid sha256:e0489ff95f13a7e7bfd58ee172102fe361e99f1734e386f32c9545af44d48c07
 size 6289