Training in progress, epoch 3

README.md

@@ -1,15 +1,15 @@
 ---
 base_model: google/gemma-3-4b-pt
 library_name: transformers
-model_name: gemma_text_to_sql_run_20251208_051516
+model_name: gemma_text_to_sql_run_20251208_052804
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 
-# Model Card for gemma_text_to_sql_run_20251208_051516
+# Model Card for gemma_text_to_sql_run_20251208_052804
 
 This model is a fine-tuned version of [google/gemma-3-4b-pt](https://huggingface.co/google/gemma-3-4b-pt).
 It has been trained using [TRL](https://github.com/huggingface/trl).

adapter_config.json

@@ -12,7 +12,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
@@ -22,17 +22,17 @@
     "embed_tokens"
   ],
   "peft_type": "LORA",
-  "r": 64,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "v_proj",
     "down_proj",
+    "o_proj",
     "gate_proj",
-    "up_proj",
-    "v_proj",
     "k_proj",
-    "q_proj"
+    "q_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97ff7132eb161e6dad4b2ba135768fd4767859a68b7e090703926c12bf414cf0
-size 3209724888
+oid sha256:156e9816eae1f0195408e0059ea3ddcebbba24caa0df3f3f199aa35d248039d0
+size 2947416824

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f0ee528da3de243812c35efee45b1f4e6c10d4678d887b4d052b3b6285d1e53
+oid sha256:53cabff3e69bb6d1432492443d3386bff6832acca5209780eeaf5b4dd386e9f3
 size 6289