End of training

README.md

@@ -1,13 +1,13 @@
 ---
 base_model: meta-llama/Meta-Llama-3-8B
 datasets:
-- generator
+- llama-duo/synth_summarize_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_summarize-k
@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3.1-8b-gpt4o_100k_summarize-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_summarize_dataset_dedup dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.0198
 

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 1.0,
-    "eval_loss": 2.1302647590637207,
-    "eval_runtime": 1.1698,
+    "eval_loss": 2.0198426246643066,
+    "eval_runtime": 1.1656,
     "eval_samples": 25,
-    "eval_samples_per_second": 8.549,
-    "eval_steps_per_second": 0.855,
+    "eval_samples_per_second": 8.579,
+    "eval_steps_per_second": 0.858,
     "total_flos": 5.7571825768464384e+17,
     "train_loss": 0.9919692577459873,
     "train_runtime": 2099.4843,

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_loss": 2.1302647590637207,
-    "eval_runtime": 1.1698,
+    "eval_loss": 2.0198426246643066,
+    "eval_runtime": 1.1656,
     "eval_samples": 25,
-    "eval_samples_per_second": 8.549,
-    "eval_steps_per_second": 0.855
+    "eval_samples_per_second": 8.579,
+    "eval_steps_per_second": 0.858
 }

runs/Sep29_00-57-13_82b7fdadb1f8/events.out.tfevents.1727573850.82b7fdadb1f8.217552.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a9d2484fe72a4886d8b0e048691c10d0d881b606a034a25a6160c7fb6d62d2
+size 359