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
 - unsloth
 licence: license
 ---
@@ -35,8 +35,8 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.22.2
-- Transformers: 4.56.2
+- TRL: 0.26.2
+- Transformers: 4.57.5
 - Pytorch: 2.9.0+cu126
 - Datasets: 4.3.0
 - Tokenizers: 0.22.2

adapter_config.json

@@ -33,12 +33,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "v_proj",
     "o_proj",
-    "q_proj",
-    "up_proj",
+    "gate_proj",
     "down_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
     "k_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a13d889a867278538273011302b130d31102cd1a5c8e687f43ca57a4b96d70ca
-size 15220968
+oid sha256:d55fdc059a84861c238190e005ba610b8350aa47f63ff43174104390646467bd
+size 7627024

tokenizer_config.json

@@ -51336,7 +51336,7 @@
   "image_token": "<image_soft_token>",
   "model_max_length": 32768,
   "pad_token": "<pad>",
-  "padding_side": "left",
+  "padding_side": "right",
   "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 sha256:690412784d2a73305c384c52dac6539174a0ac481e01f127f8bcfc75d063c285
-size 6289
+oid sha256:77c8e32232ed3c832435abbd70ff218dba09b04fb745b92cc80bd5ea47c1a202
+size 6481