End of training

README.md

@@ -2,12 +2,13 @@
 license: llama3
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
 base_model: meta-llama/Meta-Llama-3-8B
 datasets:
-- generator
+- preference-data
 model-index:
 - name: sanity_style
   results: []
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sanity_style
 
-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 preference-data dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.3294
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9975550122249389,
+    "eval_loss": 1.3294435739517212,
+    "eval_runtime": 1.8237,
+    "eval_samples": 10,
+    "eval_samples_per_second": 3.838,
+    "eval_steps_per_second": 0.548,
     "total_flos": 2562962409652224.0,
     "train_loss": 1.4071934585477792,
     "train_runtime": 4285.5681,

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.9962073324905183,
-    "eval_loss": 1.2391942739486694,
-    "eval_runtime": 1568.9917,
-    "eval_samples": 23110,
-    "eval_samples_per_second": 8.526,
-    "eval_steps_per_second": 0.533
+    "epoch": 0.9975550122249389,
+    "eval_loss": 1.3294435739517212,
+    "eval_runtime": 1.8237,
+    "eval_samples": 10,
+    "eval_samples_per_second": 3.838,
+    "eval_steps_per_second": 0.548
 }

runs/Aug23_10-34-13_COE-CS-sv003/events.out.tfevents.1724413645.COE-CS-sv003.2792060.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25723c35aabb8444adffc11e43f6e61db40ecc0b9493bb9342fe954c84e18ec2
+size 359