End of training

README.md

@@ -2,13 +2,13 @@
 license: gemma
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
-- alignment-handbook
 - generated_from_trainer
 base_model: google/gemma-2b
 datasets:
-- generator
+- llama-duo/synth_summarize_dataset_dedup
 model-index:
 - name: gemma2b-summarize-gpt4o-2k
   results: []
@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gemma2b-summarize-gpt4o-2k
 
-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: 2.5878
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 10.0,
-    "eval_loss": 2.5693273544311523,
-    "eval_runtime": 0.5288,
+    "eval_loss": 2.587819814682007,
+    "eval_runtime": 0.5337,
     "eval_samples": 25,
-    "eval_samples_per_second": 18.91,
-    "eval_steps_per_second": 1.891,
+    "eval_samples_per_second": 18.738,
+    "eval_steps_per_second": 1.874,
     "total_flos": 2.9368666998964224e+16,
     "train_loss": 1.9452767181396484,
     "train_runtime": 274.5975,

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
-    "eval_loss": 2.5693273544311523,
-    "eval_runtime": 0.5288,
+    "eval_loss": 2.587819814682007,
+    "eval_runtime": 0.5337,
     "eval_samples": 25,
-    "eval_samples_per_second": 18.91,
-    "eval_steps_per_second": 1.891
+    "eval_samples_per_second": 18.738,
+    "eval_steps_per_second": 1.874
 }

runs/Jun05_13-40-36_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1717562730.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.24815.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57d84018afe7df2eff6ca55b14a9bdbcf692c8ae0569fb42267734c517e5eea2
+size 354