End of training

README.md

@@ -1,59 +1,59 @@
 ---
-library_name: peft
-license: apache-2.0
-base_model: unsloth/whisper-small
+base_model: unsloth/gemma-3-270m
+library_name: transformers
+model_name: outputs
 tags:
-- base_model:adapter:unsloth/whisper-small
-- lora
-- transformers
+- generated_from_trainer
+- sft
+- trl
 - unsloth
-model-index:
-- name: outputs
-  results: []
+licence: license
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# Model Card for outputs
 
-# outputs
+This model is a fine-tuned version of [unsloth/gemma-3-270m](https://huggingface.co/unsloth/gemma-3-270m).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
-This model is a fine-tuned version of [unsloth/whisper-small](https://huggingface.co/unsloth/whisper-small) on an unknown dataset.
+## Quick start
 
-## Model description
+```python
+from transformers import pipeline
 
-More information needed
+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="Kibalama/outputs", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
 
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
+## Training procedure
 
-More information needed
+ 
 
-## Training procedure
 
-### Training hyperparameters
+This model was trained with SFT.
 
-The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 8
-- eval_batch_size: 8
-- seed: 3407
-- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 5
-- num_epochs: 1
-- mixed_precision_training: Native AMP
+### Framework versions
 
-### Training results
+- TRL: 0.21.0
+- Transformers: 4.55.4
+- Pytorch: 2.8.0+cu126
+- Datasets: 3.6.0
+- Tokenizers: 0.21.4
 
+## Citations
 
 
-### Framework versions
 
-- PEFT 0.17.0
-- Transformers 4.51.3
-- Pytorch 2.8.0+cu126
-- Datasets 3.6.0
-- Tokenizers 0.21.4
+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},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -1,10 +1,10 @@
 {
   "alpha_pattern": {},
   "auto_mapping": {
-    "base_model_class": "WhisperForConditionalGeneration",
-    "parent_library": "transformers.models.whisper.modeling_whisper"
+    "base_model_class": "Gemma3ForCausalLM",
+    "parent_library": "transformers.models.gemma3.modeling_gemma3"
   },
-  "base_model_name_or_path": "unsloth/whisper-small",
+  "base_model_name_or_path": "unsloth/gemma-3-270m",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -16,7 +16,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 128,
   "lora_bias": false,
   "lora_dropout": 0,
   "megatron_config": null,
@@ -24,12 +24,19 @@
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 64,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "q_proj",
-    "v_proj"
+    "o_proj",
+    "v_proj",
+    "lm_head",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "embed_tokens"
   ],
   "target_parameters": null,
   "task_type": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d24ebb17304bd909e4e39750c0a10f09888966636e0c36d20ff9fb101b538a4c
-size 28331952
+oid sha256:46a638c4e142b5538d2bbffcb624127c2180a6115da10624ae5f13928a1cdc86
+size 1061718040

special_tokens_map.json

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

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d786405177734910d7a3db625c2826640964a0b4e5cdbbd70620ae3313a01bef
-size 33384722
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer_config.json

@@ -51327,7 +51327,7 @@
   "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
   "eoi_token": "<end_of_image>",
-  "eos_token": "<end_of_turn>",
+  "eos_token": "<eos>",
   "extra_special_tokens": {
     "boi_token": "<start_of_image>",
     "eoi_token": "<end_of_image>",
@@ -51337,7 +51337,6 @@
   "model_max_length": 32768,
   "pad_token": "<pad>",
   "padding_side": "right",
-  "processor_class": "Gemma3Processor",
   "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 sha256:3928f2f1f33609eb571f2c221bb5ea2c5f9486dee64666e45183b06bcfc7f34a
-size 5841
+oid sha256:4a4b022f8aa910777f0cd4b714648a8c9c451fd1512f72dd40a1a8f3297e3f24
+size 6161