Shekswess
/

gemma-1.1-7b-it-bnb-4bit-medical

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Shekswess commited on Apr 13, 2024

Commit

6f1933b

·

verified ·

1 Parent(s): 719b573

Update README.md

Files changed (1) hide show

README.md +7 -6

README.md CHANGED Viewed

@@ -25,12 +25,13 @@ To utilize the finetuning of the model, you need to use the gemma instruction pr
 Metrics:
-- train_runtime: 4544.6901
-- train_samples_per_second: 0.66
-- train_steps_per_second: 0.083
-- total_flos: 5.862681923842867e+16
-- train_loss: 1.7245690104166667
 - steps: 375
 - epoch: 1.0
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/6569f13004643352df96e40f/L22u9s2ShJRwg3AdYs-06.png)

 Metrics:
+- train_runtime: 2470.9842
+- train_samples_per_second: 0.809
+- train_steps_per_second: 0.101
+- total_flos: 3.168381674611507e+16
+- train_loss: 1.843041015625
 - steps: 375
 - epoch: 1.0
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6569f13004643352df96e40f/pwzrX8QniKdNOKmb0Z8LL.png)