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/gx8z9rab)
 # 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: 3.3804
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 10.0,
+    "eval_loss": 3.380370616912842,
+    "eval_runtime": 1.0285,
+    "eval_samples": 25,
+    "eval_samples_per_second": 4.862,
+    "eval_steps_per_second": 1.945,
     "total_flos": 1.6817604900715233e+18,
     "train_loss": 1.8264882094209844,
     "train_runtime": 8654.8771,

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 4.978165938864628,
-    "eval_loss": 2.236276865005493,
-    "eval_runtime": 1.0247,
+    "epoch": 10.0,
+    "eval_loss": 3.380370616912842,
+    "eval_runtime": 1.0285,
     "eval_samples": 25,
-    "eval_samples_per_second": 4.88,
-    "eval_steps_per_second": 1.952
+    "eval_samples_per_second": 4.862,
+    "eval_steps_per_second": 1.945
 }

runs/May21_04-03-21_deep-diver-main-fluffy-octopus-1-0-0/events.out.tfevents.1716287409.deep-diver-main-fluffy-octopus-1-0-0.384.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66919c5662bd4cda71f1345f3019c57c00b1355b61f537e267b0861a61ee9fcf
+size 359