Training in progress, epoch 1

README.md

@@ -1,17 +1,18 @@
 ---
-base_model: google/gemma-3-1b-pt
+base_model: unsloth/gemma-3-270m-it-bnb-4bit
 library_name: transformers
 model_name: gemma-text-to-sql
 tags:
 - generated_from_trainer
 - trl
 - sft
+- unsloth
 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).
+This model is a fine-tuned version of [unsloth/gemma-3-270m-it-bnb-4bit](https://huggingface.co/unsloth/gemma-3-270m-it-bnb-4bit).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -34,11 +35,11 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.15.2
-- Transformers: 4.53.0
-- Pytorch: 2.6.0+cu124
-- Datasets: 3.6.0
-- Tokenizers: 0.21.2
+- TRL: 0.22.2
+- Transformers: 4.56.2
+- Pytorch: 2.9.0+cu126
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
 
 ## Citations
 
@@ -49,7 +50,7 @@ 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 Gallouédec},
+	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},
 	year         = 2020,
 	journal      = {GitHub repository},
 	publisher    = {GitHub},

adapter_config.json

@@ -1,8 +1,16 @@
 {
+  "alora_invocation_tokens": null,
   "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "google/gemma-3-1b-pt",
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Gemma3ForCausalLM",
+    "parent_library": "transformers.models.gemma3.modeling_gemma3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/gemma-3-270m-it-bnb-4bit",
   "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -14,27 +22,29 @@
   "loftq_config": {},
   "lora_alpha": 16,
   "lora_bias": false,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": [
-    "lm_head",
-    "embed_tokens"
-  ],
+  "modules_to_save": null,
   "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "gate_proj",
     "v_proj",
-    "down_proj",
+    "o_proj",
     "q_proj",
     "up_proj",
-    "o_proj",
-    "gate_proj"
+    "down_proj",
+    "k_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 sha256:0e6e331992a639f2f511b3f647ab638a2b639b6a51165ce5cf60efd8e2987fd6
-size 2468152240
+oid sha256:77f4433025e1ea907f9452ef0d86b5111def381db80a76bc930a264613676256
+size 15220968

chat_template.jinja

@@ -42,6 +42,6 @@
 ' }}
 {%- endfor -%}
 {%- if add_generation_prompt -%}
-    {{'<start_of_turn>model
-'}}
+    {{ '<start_of_turn>model
+' }}
 {%- endif -%}

special_tokens_map.json

@@ -9,7 +9,7 @@
   },
   "eoi_token": "<end_of_image>",
   "eos_token": {
-    "content": "<eos>",
+    "content": "<end_of_turn>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -51327,16 +51327,16 @@
   "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
   "eoi_token": "<end_of_image>",
-  "eos_token": "<eos>",
+  "eos_token": "<end_of_turn>",
   "extra_special_tokens": {
     "boi_token": "<start_of_image>",
     "eoi_token": "<end_of_image>",
     "image_token": "<image_soft_token>"
   },
   "image_token": "<image_soft_token>",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 32768,
   "pad_token": "<pad>",
-  "processor_class": "Gemma3Processor",
+  "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 sha256:1ca4fac3db2cdc011b13d452d378ffccd4c4524ca8a7b76d76e625f7a41651cb
-size 5624
+oid sha256:690412784d2a73305c384c52dac6539174a0ac481e01f127f8bcfc75d063c285
+size 6289