Fine-tuned educational model with LoRA and 8-bit quantization

README.md

@@ -5,14 +5,14 @@ base_model: google/gemma-2-2b
 tags:
 - generated_from_trainer
 model-index:
-- name: tuned-educational-model
+- name: t-modelV2
   results: []
 ---
 
 <!-- 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. -->
 
-# tuned-educational-model
+# t-modelV2
 
 This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on an unknown dataset.
 
@@ -33,12 +33,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
-- train_batch_size: 1
+- learning_rate: 8.698757885449884e-05
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 16
-- total_train_batch_size: 16
+- total_train_batch_size: 64
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - num_epochs: 1