Training in progress, step 50

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: medgemma-4b-it-cot
 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/erdenkalilaeyev-bah-e-ehir-cyprus-university/huggingface/runs/gvqb9z2o) 
+[<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/erdenkalilaeyev-bah-e-ehir-cyprus-university/huggingface/runs/pddfjaby) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -27,16 +27,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "fc1",
+    "o_proj",
     "k_proj",
+    "v_proj",
+    "fc2",
     "q_proj",
-    "o_proj",
-    "out_proj",
-    "down_proj",
-    "up_proj",
     "gate_proj",
-    "fc2"
+    "fc1",
+    "up_proj",
+    "down_proj",
+    "out_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7d6e0b6a03e5e908d3b1c490c65c1550919ff303fde587073fab6d54582ee47
+oid sha256:f61fc05f2844adff567f59d5e366ec06d0f91983fa0c4f5fe11dd82dada7ab00
 size 2993118096

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a46dcf0580f7577a8201f41bcb9b5672d05e2f5ebe4f5cd19127113ca044d840
+oid sha256:2302e944cf78fcb479b1349e190717a509833854ebcf407a67a33cdd9e6f4bd6
 size 5752