Fine-tuned model with optimized GPU utilization

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # 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.
+It achieves the following results on the evaluation set:
+- Loss: 3.0230
 
 ## Model description
 
@@ -33,12 +35,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 8.698757885449884e-05
-- train_batch_size: 4
+- learning_rate: 0.0003
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 64
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
 - 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
@@ -46,6 +48,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 3.6529        | 0.8814 | 500  | 3.0230          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0a0c4005161985d92a7d758caf204289f16d99c7e9c31728584522d3c37a35e
+oid sha256:77284d3c138b11a1965863ff47495ea6413f3faccb686b6907ac20dd6bd0c763
 size 12793376