End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: llama3
 base_model: meta-llama/Meta-Llama-3-8B
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- preference-data
 model-index:
 - name: llama3_feedback
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3_feedback
 
-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 None 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.
 
 ## Model description
 

all_results.json

@@ -1,5 +1,9 @@
 {
     "epoch": 1.0,
+    "eval_runtime": 3.7526,
+    "eval_samples": 10,
+    "eval_samples_per_second": 2.665,
+    "eval_steps_per_second": 0.799,
     "total_flos": 173366354903040.0,
     "train_loss": 0.6223726071021407,
     "train_runtime": 17321.1955,

config.json

@@ -25,6 +25,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_runtime": 3.7526,
+    "eval_samples": 10,
+    "eval_samples_per_second": 2.665,
+    "eval_steps_per_second": 0.799
+}

runs/Sep29_17-51-15_COE-CS-sv003/events.out.tfevents.1727650299.COE-CS-sv003.1214200.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2de66098e489d3b094587da6b8630ec61931182ac28c0577f644a5540eebfa7e
+size 311