End of training

README.md

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

all_results.json

@@ -1,5 +1,9 @@
 {
     "epoch": 1.0,
+    "eval_runtime": 4.8635,
+    "eval_samples": 10,
+    "eval_samples_per_second": 2.056,
+    "eval_steps_per_second": 0.617,
     "total_flos": 117051280588800.0,
     "train_loss": 0.691351400122923,
     "train_runtime": 20676.98,

config.json

@@ -24,6 +24,6 @@
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_runtime": 4.8635,
+    "eval_samples": 10,
+    "eval_samples_per_second": 2.056,
+    "eval_steps_per_second": 0.617
+}

runs/Sep19_05-49-17_COE-CS-sv003/events.out.tfevents.1726746544.COE-CS-sv003.346740.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:191bc05fcf0eeac8c2357bbff6f6ee6fd3047ad9a267be985c05dac495c674f8
+size 311