End of training

README.md

@@ -16,12 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 2.3283
-- eval_runtime: 110.0722
-- eval_samples_per_second: 8.703
-- eval_steps_per_second: 2.18
-- epoch: 1.98
-- step: 3600
+- eval_loss: 2.2063
+- eval_runtime: 109.4319
+- eval_samples_per_second: 8.754
+- eval_steps_per_second: 2.193
+- epoch: 8.97
+- step: 16300
 
 ## Model description
 
@@ -40,12 +40,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 2e-05
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.01
 - num_epochs: 10
 - mixed_precision_training: Native AMP
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df1bdbe5a935a8ae287c3a9afe1572afaf3b97a57b3683ad9af94e53ea2ed381
+oid sha256:01ba0f68eb0ec5162a9078fc876b7fae87096b3e83689968458bd5ace98b7a43
 size 1852600

runs/Mar11_05-15-53_37d41d6d3514/events.out.tfevents.1710134153.37d41d6d3514.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef828a5a77a05f5e5e3b8f32e1348dfc5550604323f541296055b525060c5840
+size 83579

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64bbb0f279837e5743052a3d4e6af044de0dda013afcba38386f2ff789449bea
+oid sha256:199b647d1a9b8ae70ee4dcd3f906d2ce3eec70d30c35a1c94fafb1498a02f391
 size 4856