Model save

README.md

@@ -1,13 +1,13 @@
 ---
-base_model: Qwen/Qwen2.5-0.5B-Instruct
-datasets:
-- generator
 library_name: peft
 license: apache-2.0
+base_model: Qwen/Qwen2.5-0.5B-Instruct
 tags:
 - trl
 - sft
 - generated_from_trainer
+datasets:
+- generator
 model-index:
 - name: trained_models
   results: []
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 2
 - total_train_batch_size: 6
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
 - num_epochs: 1
@@ -55,7 +55,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.13.2
-- Transformers 4.45.2
+- Transformers 4.46.0
 - Pytorch 2.2.1+cu121
-- Datasets 3.0.1
+- Datasets 3.0.2
 - Tokenizers 0.20.1