Model save

README.md

@@ -5,7 +5,7 @@ tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: google/gemma-7b
+base_model: google/gemma-2b
 model-index:
 - name: results
   results: []
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on an unknown dataset.
+This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
 
 ## Model description
 
@@ -35,25 +35,18 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 4
+- learning_rate: 2e-06
+- train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
-- lr_scheduler_warmup_ratio: 0.2
-- num_epochs: 1
-- mixed_precision_training: Native AMP
-
-### Training results
-
-
+- lr_scheduler_warmup_ratio: 0.03
+- training_steps: 4000
 
 ### Framework versions
 
-- PEFT 0.9.1.dev0
+- PEFT 0.10.0
 - Transformers 4.38.2
 - Pytorch 2.2.1+cu121
 - Datasets 2.18.0