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-2b
 datasets:
-- generator
+- llama-duo/synth_summarize_dataset_dedup
 model-index:
 - name: gemma2b-summarize-gpt4o-128k
   results: []
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gemma2b-summarize-gpt4o-128k
 
-This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
+This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the llama-duo/synth_summarize_dataset_dedup dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.7978
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 10.0,
+    "eval_loss": 2.7977683544158936,
+    "eval_runtime": 0.5252,
+    "eval_samples": 25,
+    "eval_samples_per_second": 19.042,
+    "eval_steps_per_second": 1.904,
     "total_flos": 1.7464232891960525e+18,
     "train_loss": 0.9647074054125633,
     "train_runtime": 17674.2713,

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 15.0,
-    "eval_loss": 2.523277521133423,
-    "eval_runtime": 0.5332,
+    "epoch": 10.0,
+    "eval_loss": 2.7977683544158936,
+    "eval_runtime": 0.5252,
     "eval_samples": 25,
-    "eval_samples_per_second": 18.753,
-    "eval_steps_per_second": 1.875
+    "eval_samples_per_second": 19.042,
+    "eval_steps_per_second": 1.904
 }

runs/Jun10_18-07-27_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1718028152.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.8637.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0161d57a41eb00621b9fdf13b197f614c16d55bfb2df71c42e523dac2bff809f
+size 359