Training in progress, epoch 1

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: gemma-desc-to-code
 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/alternis-universit-de-gen-ve/gemma-text-to-sql/runs/sz2f97ia) 
+[<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/alternis-universit-de-gen-ve/desc2code/runs/dsv5d24k) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -25,16 +25,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "k_proj",
-    "gate_proj",
+    "out_proj",
     "fc1",
-    "fc2",
-    "q_proj",
     "v_proj",
-    "down_proj",
-    "out_proj",
-    "o_proj"
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "fc2",
+    "up_proj",
+    "down_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 sha256:73bad397d19e32559dee8eefbe6595d7149575ff6ace7f288cd086e05d7b28bc
+oid sha256:870e3986dedf7fcc65fdc5d28ad4db5e503b0e611dfd69c764c49cf4c05ca397
 size 154116312

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5db43c457f4b7e89e491ccd9ea69a9ff119cf1343bdf736656c755346fcaad57
+oid sha256:386ee6983873855c950a653f04fa6935de229bd9f1bce803767dee4c0e1a59ed
 size 6225