End of training

README.md

@@ -2,12 +2,13 @@
 license: gemma
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
 base_model: google/gemma-7b
 datasets:
-- generator
+- llama-duo/synth_summarize_dataset
 model-index:
 - name: gemma7b-summarize-gemini1.5flash-30k
   results: []
@@ -19,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/chansung18/huggingface/runs/go5tmp0o)
 # gemma7b-summarize-gemini1.5flash-30k
 
-This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the llama-duo/synth_summarize_dataset dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.2363
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 4.978165938864628,
+    "eval_loss": 2.236276865005493,
+    "eval_runtime": 1.0247,
+    "eval_samples": 25,
+    "eval_samples_per_second": 4.88,
+    "eval_steps_per_second": 1.952,
     "total_flos": 8.714577082329334e+17,
     "train_loss": 2.449154797771521,
     "train_runtime": 4532.0541,

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.9956331877729258,
-    "eval_loss": 2.2895236015319824,
-    "eval_runtime": 1.0337,
+    "epoch": 4.978165938864628,
+    "eval_loss": 2.236276865005493,
+    "eval_runtime": 1.0247,
     "eval_samples": 25,
-    "eval_samples_per_second": 4.837,
-    "eval_steps_per_second": 1.935
+    "eval_samples_per_second": 4.88,
+    "eval_steps_per_second": 1.952
 }

runs/May19_11-56-52_deep-diver-main-moody-turtle-1-0-0/events.out.tfevents.1716138902.deep-diver-main-moody-turtle-1-0-0.385.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e145aebfc1fd88eaf3ccbad03a3d076812abd64a87d95f5fe3811dfed49736
+size 359