End of training

README.md

@@ -3,6 +3,10 @@ library_name: transformers
 license: llama3.1
 base_model: meta-llama/Llama-3.1-8B-Instruct
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.999756275895686,
+    "eval_loss": 0.5866211652755737,
+    "eval_runtime": 1.9208,
+    "eval_samples": 20,
+    "eval_samples_per_second": 37.485,
+    "eval_steps_per_second": 2.603,
     "total_flos": 107333245992960.0,
     "train_loss": 0.6513826533214805,
     "train_runtime": 7369.8969,

config.json

@@ -34,6 +34,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.999756275895686,
+    "eval_loss": 0.5866211652755737,
+    "eval_runtime": 1.9208,
+    "eval_samples": 20,
+    "eval_samples_per_second": 37.485,
+    "eval_steps_per_second": 2.603
+}

runs/Jan14_01-58-08_dgx-a100-12/events.out.tfevents.1736824438.dgx-a100-12.1617912.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a6380f59a5b2ded9e3817fe473f19012df42a88325574ffa3f3a19765b48221
+size 359