Training in progress, epoch 1

README.md

@@ -4,9 +4,9 @@ library_name: transformers
 model_name: kto_simplification_balanced
 tags:
 - generated_from_trainer
-- kto
 - trl
 - unsloth
+- kto
 licence: license
 ---
 
@@ -28,7 +28,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ioakeime-aristotle-university-of-thessaloniki/kto_smiplification_balanced/runs/03yvzoja) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ioakeime-aristotle-university-of-thessaloniki/kto_smiplification_balanced/runs/q9oqzg79) 
 
 
 This model was trained with KTO, a method introduced in [KTO: Model Alignment as Prospect Theoretic Optimization](https://huggingface.co/papers/2402.01306).
@@ -37,7 +37,7 @@ This model was trained with KTO, a method introduced in [KTO: Model Alignment as
 
 - TRL: 0.19.0
 - Transformers: 4.53.0
-- Pytorch: 2.7.0
+- Pytorch: 2.7.0+cu128
 - Datasets: 3.6.0
 - Tokenizers: 0.21.2
 

adapter_config.json

@@ -20,20 +20,23 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "down_proj",
     "k_proj",
+    "o_proj",
     "q_proj",
     "v_proj",
-    "o_proj",
-    "down_proj",
-    "up_proj"
+    "up_proj",
+    "gate_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 sha256:7b9125c6bca6062d364355433af1e6a7a176e4bf378b88e92f04d6d428f2b2db
+oid sha256:f0c8f878bce0be5e0b96a6ec17d6ace34dfbac172c3ee5fa1c85e078d23c79db
 size 167832240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:575a474e0304ca68f8db8af319d11e3b89f403b6faf6d035564a9656ba7e3bb4
-size 6353
+oid sha256:91aa7e4b24a73bf63f76da8b8a36dc9a5ef4061cb2771c5a599bf78a8a1546f2
+size 6417