Training in progress, epoch 1

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: google/gemma-3-1b-pt
 library_name: transformers
-model_name: gemma-3-1b-text-to-sql
+model_name: gemma-text-to-sql
 tags:
 - generated_from_trainer
 - trl
@@ -9,7 +9,7 @@ tags:
 licence: license
 ---
 
-# Model Card for gemma-3-1b-text-to-sql
+# 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).
@@ -20,7 +20,7 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 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="java2core/gemma-3-1b-text-to-sql", device="cuda")
+generator = pipeline("text-generation", model="java2core/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"])
 ```
@@ -34,10 +34,10 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.21.0
-- Transformers: 4.55.0
-- Pytorch: 2.9.0.dev20250810
-- Datasets: 4.0.0
+- TRL: 0.15.2
+- Transformers: 4.55.2
+- Pytorch: 2.8.0
+- Datasets: 3.3.2
 - Tokenizers: 0.21.4
 
 ## Citations
@@ -49,7 +49,7 @@ 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 Gallou{\'e}dec},
+	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},

adapter_config.json

@@ -3,7 +3,6 @@
   "auto_mapping": null,
   "base_model_name_or_path": "google/gemma-3-1b-pt",
   "bias": "none",
-  "corda_config": null,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -23,23 +22,19 @@
     "embed_tokens"
   ],
   "peft_type": "LORA",
-  "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
+    "q_proj",
     "down_proj",
     "k_proj",
+    "o_proj",
+    "up_proj",
     "gate_proj",
-    "v_proj",
-    "q_proj"
+    "v_proj"
   ],
-  "target_parameters": null,
   "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 sha256:69a5cf91cdbab50130676051885bdfe237edca7af7e06062795cf22a13dab893
+oid sha256:79bab42b7f3ffd7e08bbc107b7a4963ff093c228ddccea4d0eeb8604ac9a810d
 size 1260191096

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

runs/Aug15_08-16-06_gemma-3-test.us-central1-c.c.sayouzone-ai.internal/events.out.tfevents.1755245780.gemma-3-test.us-central1-c.c.sayouzone-ai.internal.1935.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d70adf2173b38bc539c6a403fd6b5939c8ec753e71de7006a620fc34fde2067f
+size 8098

runs/Aug15_08-21-14_gemma-3-test.us-central1-c.c.sayouzone-ai.internal/events.out.tfevents.1755246089.gemma-3-test.us-central1-c.c.sayouzone-ai.internal.2603.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4092697de987cc78b131a38814e58793610a5b5baa6fb6d0f9ada60eea203563
+size 7018

runs/Aug15_08-25-26_gemma-3-test.us-central1-c.c.sayouzone-ai.internal/events.out.tfevents.1755246341.gemma-3-test.us-central1-c.c.sayouzone-ai.internal.2719.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2aa622acdfdf10ad727d3b64fa31f35ee2c79941968cddc13d43f441e5a472
+size 93732

runs/Aug15_13-42-42_gemma-3-test.us-central1-c.c.sayouzone-ai.internal/events.out.tfevents.1755265377.gemma-3-test.us-central1-c.c.sayouzone-ai.internal.16219.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e435eed14df04b3bca88de5f5ab08e5d3388db6ae33e485b5f90eb696dd41d41
+size 11923

runs/Aug16_02-55-56_gemma-3-test.us-central1-c.c.sayouzone-ai.internal/events.out.tfevents.1755312971.gemma-3-test.us-central1-c.c.sayouzone-ai.internal.2359.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58b00b79278bf81d454ae3eb0d1ad04e954936e5062f059d8ce889257e6912ec
+size 35573

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:297637400f593b1cebed7ad48d8f7c337539f1e29f9436c3f64b77cb14f50ec9
-size 6225
+oid sha256:0dafb40541f3fc8eaedf077e4207fa71556b83d32c4968c44105f27c5a76e483
+size 6097