Training in progress, epoch 1

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: gemma-text-to-sql
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 
@@ -34,7 +34,7 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.23.1
+- TRL: 0.24.0.dev0
 - Transformers: 4.57.0
 - Pytorch: 2.8.0+cu126
 - Datasets: 3.3.2

adapter_config.json

@@ -28,13 +28,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "down_proj",
     "q_proj",
-    "k_proj",
+    "down_proj",
     "v_proj",
-    "o_proj",
-    "gate_proj"
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d91b5433328e6327c94d25770be9e4295035554fbbd1f7632864665ba4a11688
+oid sha256:4fb8e725ef9fa47c8f8ac6905c06eb89e41e9caa630c24b31eefeaea269d9517
 size 2468152240

runs/Oct13_02-28-21_bbf643e9caf8/events.out.tfevents.1760322520.bbf643e9caf8.2963.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a272573790edafb289cb4dcea4408408cf7ae29716c45675f3f0d472d0238d0b
+size 15683

tokenizer_config.json

@@ -51336,6 +51336,7 @@
   "image_token": "<image_soft_token>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
+  "processor_class": "Gemma3Processor",
   "sp_model_kwargs": null,
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7519bb624cc7dbdb73031e2d0720ce3166879f5749178d2f1f25ef6a4096760
+oid sha256:e3f5c3824ab8287a254750f710add5ea0add3534e1890a5a172e51600243b871
 size 6289