Training in progress, epoch 1

README.md

@@ -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/8tuwsyz2) 
+[<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) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -25,16 +25,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "fc1",
+    "up_proj",
     "k_proj",
-    "v_proj",
-    "q_proj",
     "gate_proj",
-    "out_proj",
-    "o_proj",
-    "down_proj",
+    "fc1",
     "fc2",
-    "up_proj"
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "out_proj",
+    "o_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 sha256:8ec4025da15e9d17824e212f3e676bb568ba84d6d1fe50c2885c8182ff20cce6
+oid sha256:e083911bd9e32e88dbcdfc8424b412fa569b38dae9382319e9703634dd95661e
 size 154116312

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e436b7dc62a171fa4dc1a1ebc7ac87728860f0e5f56f0605bd3ba9a51dea501
+oid sha256:5db43c457f4b7e89e491ccd9ea69a9ff119cf1343bdf736656c755346fcaad57
 size 6225