Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: google/gemma-3-1b-pt
+library_name: transformers
+model_name: gemma-text-to-sql
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for gemma-text-to-sql
+
+This model is a fine-tuned version of [google/gemma-3-1b-pt](https://huggingface.co/google/gemma-3-1b-pt).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="kylemite/gemma-text-to-sql", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.2
+- Transformers: 4.50.0.dev0
+- Pytorch: 2.6.0
+- Datasets: 3.3.2
+- Tokenizers: 0.21.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -12,7 +12,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 8,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
@@ -22,12 +22,12 @@
     "embed_tokens"
   ],
   "peft_type": "LORA",
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "gate_proj",
+    "down_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa5e9df79e032169a89d9876cd7de4b626ac6e2f7be08ac28718baa783462a03
-size 1248236248
+oid sha256:6d31e10e52ebc45fa4d8e020b5cea906b6268e90b149e7220ac307b71e8e79f2
+size 1228108352

runs/Mar22_17-56-18_HAL/events.out.tfevents.1742684196.HAL.17165.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f26ef761ec5fe250663b9a219836879c1fb36bbe9ccafa10d00d3dc47689544
+size 6141

runs/Mar22_17-57-48_HAL/events.out.tfevents.1742684290.HAL.17315.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c84eeca93198b3f01862194e4ce9f61e31942b5fd0a4d9283a5d75512c87599
+size 6142

runs/Mar22_18-00-53_HAL/events.out.tfevents.1742684618.HAL.17556.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d9c5a6b1de037b85b0d368953685ac5aa58c37e14b1996eb3e48b331aca7c5
+size 6142

runs/Mar22_18-04-24_HAL/events.out.tfevents.1742684733.HAL.17866.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e4f9bfecd9831052bc26587832b6d4437b7c018cd6c53103fea3399aec58eab
+size 20382

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e2c230221420843591186280209b0c149306f4087c98a6d6978aea92a25118d
+oid sha256:2049d239a16c106c8f2493f742f5b6933d63e39c1eb3cb48306735ab8d39df78
 size 5624