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
@@ -17,6 +21,8 @@ should probably proofread and complete it, then remove this comment. -->
 # llama_3_o1_01_full
 
 This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8604
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.860390305519104,
+    "eval_runtime": 0.8362,
+    "eval_samples": 20,
+    "eval_samples_per_second": 23.918,
+    "eval_steps_per_second": 2.392,
     "total_flos": 1227996790784.0,
     "train_loss": 0.8530778586864471,
     "train_runtime": 78.9989,

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": 1.0,
+    "eval_loss": 0.860390305519104,
+    "eval_runtime": 0.8362,
+    "eval_samples": 20,
+    "eval_samples_per_second": 23.918,
+    "eval_steps_per_second": 2.392
+}

runs/Jan07_17-25-22_dgx-a100-12/events.out.tfevents.1736267673.dgx-a100-12.2129712.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2864df574914edebf4c3f7d856097e0314d862fb029e3be7132edf946c761faf
+size 354