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_dirty
   results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # feedback_gemma_dirty
 
-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": 3.9604,
+    "eval_samples": 10,
+    "eval_samples_per_second": 2.525,
+    "eval_steps_per_second": 0.758,
     "total_flos": 116982426894336.0,
     "train_loss": 0.6940072515278861,
     "train_runtime": 20640.2326,

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": 3.9604,
+    "eval_samples": 10,
+    "eval_samples_per_second": 2.525,
+    "eval_steps_per_second": 0.758
+}

runs/Sep19_17-38-55_COE-CS-sv003/events.out.tfevents.1726788742.COE-CS-sv003.388702.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ab2872fe9fc8d5089b0c70db1012da6d67201699992906e068eb900e093520
+size 311