End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: gemma
 base_model: google/gemma-2-9b-it
 tags:
+- alignment-handbook
 - trl
 - simpo
 - generated_from_trainer
+- trl
+- simpo
+- generated_from_trainer
+datasets:
+- princeton-nlp/gemma2-ultrafeedback-armorm
 model-index:
 - name: simpo
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # simpo
 
-This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) on an unknown dataset.
+This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) on the princeton-nlp/gemma2-ultrafeedback-armorm dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7580
-- Rewards/chosen: -18.9526
-- Rewards/rejected: -23.9387
-- Rewards/accuracies: 0.7705
-- Rewards/margins: 4.9861
-- Logps/rejected: -2.3939
-- Logps/chosen: -1.8953
-- Logits/rejected: -14.4321
-- Logits/chosen: -14.5024
+- Loss: 2.7459
+- Rewards/chosen: -18.9664
+- Rewards/rejected: -23.9949
+- Rewards/accuracies: 0.7725
+- Rewards/margins: 5.0285
+- Logps/rejected: -2.3995
+- Logps/chosen: -1.8966
+- Logits/rejected: -14.4878
+- Logits/chosen: -14.5537
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9990600241708071,
+    "eval_logits/chosen": -14.553688049316406,
+    "eval_logits/rejected": -14.48775863647461,
+    "eval_logps/chosen": -1.8966439962387085,
+    "eval_logps/rejected": -2.3994932174682617,
+    "eval_loss": 2.7458858489990234,
+    "eval_rewards/accuracies": 0.7725409865379333,
+    "eval_rewards/chosen": -18.966440200805664,
+    "eval_rewards/margins": 5.028491497039795,
+    "eval_rewards/rejected": -23.994932174682617,
+    "eval_runtime": 86.405,
+    "eval_samples": 1941,
+    "eval_samples_per_second": 22.464,
+    "eval_steps_per_second": 1.412,
     "total_flos": 0.0,
     "train_loss": 3.541660060677477,
     "train_runtime": 9046.6245,

config.json

@@ -29,6 +29,6 @@
   "sliding_window_size": 4096,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9990600241708071,
+    "eval_logits/chosen": -14.553688049316406,
+    "eval_logits/rejected": -14.48775863647461,
+    "eval_logps/chosen": -1.8966439962387085,
+    "eval_logps/rejected": -2.3994932174682617,
+    "eval_loss": 2.7458858489990234,
+    "eval_rewards/accuracies": 0.7725409865379333,
+    "eval_rewards/chosen": -18.966440200805664,
+    "eval_rewards/margins": 5.028491497039795,
+    "eval_rewards/rejected": -23.994932174682617,
+    "eval_runtime": 86.405,
+    "eval_samples": 1941,
+    "eval_samples_per_second": 22.464,
+    "eval_steps_per_second": 1.412
+}