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-gemini1_5flash-256k
   results: []
@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gemma2b-summarize-gemini1_5flash-256k
 
-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: 2.5681
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 9.997590361445782,
-    "eval_loss": 2.566892147064209,
-    "eval_runtime": 0.495,
+    "eval_loss": 2.5681488513946533,
+    "eval_runtime": 0.4885,
     "eval_samples": 25,
-    "eval_samples_per_second": 20.203,
-    "eval_steps_per_second": 2.02,
+    "eval_samples_per_second": 20.469,
+    "eval_steps_per_second": 2.047,
     "total_flos": 3.290190024938619e+18,
     "train_loss": 0.02805145143886695,
     "train_runtime": 534.5593,

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 9.975903614457831,
-    "eval_loss": 2.566892147064209,
-    "eval_runtime": 0.495,
+    "epoch": 9.997590361445782,
+    "eval_loss": 2.5681488513946533,
+    "eval_runtime": 0.4885,
     "eval_samples": 25,
-    "eval_samples_per_second": 20.203,
-    "eval_steps_per_second": 2.02
+    "eval_samples_per_second": 20.469,
+    "eval_steps_per_second": 2.047
 }

runs/Jun10_15-56-44_6511c8cdb6e6/events.out.tfevents.1718035591.6511c8cdb6e6.3078.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71d70d094fb2e9754d082bc842423ec7ad693fa059a4f8eff46d5d0e41a8db3d
+size 359