End of training

README.md

@@ -1,10 +1,11 @@
 ---
 base_model: meta-llama/Meta-Llama-3-8B
 datasets:
-- generator
+- llama-duo/synth_classification_dataset_dedup
 library_name: peft
 license: llama3
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-8b-classification-gpt4o-100k2
 
-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_classification_dataset_dedup dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.9855
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 4.988913525498892,
+    "eval_loss": 1.9855170249938965,
+    "eval_runtime": 0.3687,
+    "eval_samples": 16,
+    "eval_samples_per_second": 2.712,
+    "eval_steps_per_second": 2.712,
     "total_flos": 1.6629843858229821e+18,
     "train_loss": 1.2764637470245361,
     "train_runtime": 3608.211,

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.988913525498892,
-    "eval_loss": 1.8047916889190674,
-    "eval_runtime": 0.3807,
+    "eval_loss": 1.9855170249938965,
+    "eval_runtime": 0.3687,
     "eval_samples": 16,
-    "eval_samples_per_second": 2.626,
-    "eval_steps_per_second": 2.626
+    "eval_samples_per_second": 2.712,
+    "eval_steps_per_second": 2.712
 }

runs/Aug08_09-08-03_main-slippery-chicken-1-0-0/events.out.tfevents.1723126351.main-slippery-chicken-1-0-0.543.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:789816bd2837fa8746bf633c7493245461baf0dcd73776f84521dd7e4e883450
+size 359