End of training

README.md

@@ -1,13 +1,13 @@
 ---
 base_model: meta-llama/Meta-Llama-3-8B
 datasets:
-- generator
+- llama-duo/synth_closed_qa_dataset_dedup
 library_name: peft
 license: llama3
 tags:
+- alignment-handbook
 - trl
 - sft
-- alignment-handbook
 - generated_from_trainer
 model-index:
 - name: llama3.1-8b-gpt4o_100k_closedqa-k
@@ -19,7 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3.1-8b-gpt4o_100k_closedqa-k
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the llama-duo/synth_closed_qa_dataset_dedup dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9355
 
 ## Model description
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 1.0,
     "eval_loss": 1.93549382686615,
-    "eval_runtime": 1.1627,
+    "eval_runtime": 1.455,
     "eval_samples": 15,
-    "eval_samples_per_second": 5.161,
-    "eval_steps_per_second": 0.86,
+    "eval_samples_per_second": 4.124,
+    "eval_steps_per_second": 0.687,
     "total_flos": 7.558147382936863e+17,
     "train_loss": 0.0,
     "train_runtime": 1.5255,

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "eval_loss": 1.93549382686615,
-    "eval_runtime": 1.1627,
+    "eval_runtime": 1.455,
     "eval_samples": 15,
-    "eval_samples_per_second": 5.161,
-    "eval_steps_per_second": 0.86
+    "eval_samples_per_second": 4.124,
+    "eval_steps_per_second": 0.687
 }

runs/Sep29_05-21-03_82b7fdadb1f8/events.out.tfevents.1727587455.82b7fdadb1f8.380653.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9122b77e7f36f4ba64eb0049851fae9333770987e5bb6e3e9024929746f640b
+size 359