Training in progress, epoch 1

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: gemma-text-to-sql
 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/qgksc4x6) 
+[<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/mmn8yxiw) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -25,16 +25,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "fc2",
-    "up_proj",
+    "q_proj",
+    "gate_proj",
     "down_proj",
-    "fc1",
-    "out_proj",
     "k_proj",
-    "gate_proj",
-    "v_proj",
+    "fc2",
     "o_proj",
-    "q_proj"
+    "v_proj",
+    "out_proj",
+    "up_proj",
+    "fc1"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b4e9c58f5578d528770050366ec40ea43ccd05c28db068718c3a680375fa7f9
+oid sha256:fa499e68a452e7feef1ea349a8da1c2254f4439bf3ced849b2918484b8fa89cd
 size 154116312

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15f5869ef0e8dd0cd9445975cd45cf2640bdbaff3a8bc1e02b94bd43a2c7c25c
+oid sha256:a71a9f83737aefb84c60be8d1d9bec5f40d75faf70f8ae45ad82f0925431b73e
 size 6225