End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: llama3.2
 base_model: meta-llama/Llama-3.2-3B-Instruct
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- preference-data
 model-index:
 - name: llama3.2_feedback_3b
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3.2_feedback_3b
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the preference-data dataset.
 
 ## Model description
 

all_results.json

@@ -1,5 +1,9 @@
 {
     "epoch": 1.0,
+    "eval_runtime": 1.4063,
+    "eval_samples": 10,
+    "eval_samples_per_second": 7.111,
+    "eval_steps_per_second": 2.133,
     "total_flos": 114021718032384.0,
     "train_loss": 0.7685830109361289,
     "train_runtime": 7351.6585,

config.json

@@ -35,6 +35,6 @@
   "tie_word_embeddings": true,
   "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": 1.4063,
+    "eval_samples": 10,
+    "eval_samples_per_second": 7.111,
+    "eval_steps_per_second": 2.133
+}

runs/Oct01_14-39-44_COE-CS-sv003/events.out.tfevents.1727801561.COE-CS-sv003.1421075.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2285cc155f26e01763a652428afd865fefbff253989e32e09fabab5b679a1437
+size 311