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-gpt4o-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/gtgsbwvu)
 # gemma7b-summarize-gpt4o-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: 3.2430
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 10.0,
+    "eval_loss": 3.242992401123047,
+    "eval_runtime": 1.0372,
+    "eval_samples": 25,
+    "eval_samples_per_second": 4.821,
+    "eval_steps_per_second": 1.928,
     "total_flos": 1.697049221804327e+18,
     "train_loss": 1.8630313719715084,
     "train_runtime": 9058.6901,

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 5.0,
-    "eval_loss": 2.3811252117156982,
-    "eval_runtime": 1.024,
+    "epoch": 10.0,
+    "eval_loss": 3.242992401123047,
+    "eval_runtime": 1.0372,
     "eval_samples": 25,
-    "eval_samples_per_second": 4.883,
-    "eval_steps_per_second": 1.953
+    "eval_samples_per_second": 4.821,
+    "eval_steps_per_second": 1.928
 }

runs/May21_04-02-00_deep-diver-main-tough-snake-1-0-0/events.out.tfevents.1716287730.deep-diver-main-tough-snake-1-0-0.385.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432bd5b84dc497d6d4d25e2f8aabd6f90d864be4050f6d9fc8462f0d4b036549
+size 359