With packing and FA2

README.md

@@ -1,16 +1,17 @@
 ---
+base_model: google/gemma-2-2b
 library_name: transformers
 model_name: ilo-toki-gemma-2-2b
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
 # Model Card for ilo-toki-gemma-2-2b
 
-This model is a fine-tuned version of [None](https://huggingface.co/None).
+This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -34,7 +35,7 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.23.0
-- Transformers: 4.56.1
+- Transformers: 4.56.2
 - Pytorch: 2.7.1+cu128
 - Datasets: 3.6.0
 - Tokenizers: 0.22.0

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "./ilo-toki-gemma-2-2b-merged",
+  "base_model_name_or_path": "google/gemma-2-2b",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -15,19 +15,17 @@
   "loftq_config": {},
   "lora_alpha": 16,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "v_proj",
-    "k_proj",
     "q_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f07ce223efd1f02ad338a64048f02f17395f9bc449524edae859d760ed03ab5e
-size 12806992
+oid sha256:1d080c1ec0026513d45661e070406b69639fa589b7fe7ec2139734fd883e7167
+size 12793376

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62ffb0ef3afe807b6d284cca0d2ab754d911010a49279a8afa96f74fd10d2cfa
+oid sha256:e3e0296f5ab1d22c575dd5537a22e0f0e5e9656e78750908b7f0da6188cc4636
 size 6161