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
 ---
 
@@ -34,11 +34,11 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.18.1
-- Transformers: 4.52.4
-- Pytorch: 2.7.0+cu118
-- Datasets: 3.6.0
-- Tokenizers: 0.21.1
+- TRL: 0.19.1
+- Transformers: 4.53.2
+- Pytorch: 2.7.1+cu118
+- Datasets: 4.0.0
+- Tokenizers: 0.21.2
 
 ## Citations
 

adapter_config.json

@@ -20,20 +20,22 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "o_proj",
-    "down_proj",
     "k_proj",
     "up_proj",
-    "v_proj",
     "q_proj",
-    "gate_proj"
+    "gate_proj",
+    "v_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,
+  "use_qalora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9566f3cfb7db387835c8302a42348a3523acc0e874dfc125125c9d62321abffb
+oid sha256:991e98d6dd5ae8e900786b786f86a27f6dd9997fd2d396bfa074c70a04c184bc
 size 52231312

runs/Jul19_03-03-05_DESKTOP-NKD4QD0/events.out.tfevents.1752883387.DESKTOP-NKD4QD0.15504.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9228dca491b6791fa5d5e5a0be0979e49eb88286006417347e3d85722bc62cf
+size 6898

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae60ed5b58c845f6b4a063623062db18eca22dda99aeb0c7aae3690bcbc52374
-size 6097
+oid sha256:d183d4dc9532af96d8f32f89272661e4d9d08773227b09d74445c6c524c1c698
+size 6225