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:
+- jz666/gemma2-ultrafeedback-ppl-split
 model-index:
 - name: simpo-train-large-correct
   results: []
@@ -16,7 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # simpo-train-large-correct
 
-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 jz666/gemma2-ultrafeedback-ppl-split dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.6183
+- Rewards/chosen: -17.4817
+- Rewards/rejected: -19.9149
+- Rewards/accuracies: 0.6291
+- Rewards/margins: 2.4332
+- Logps/rejected: -1.9915
+- Logps/chosen: -1.7482
+- Logits/rejected: -15.3493
+- Logits/chosen: -15.3704
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.995910949568378,
+    "eval_logits/chosen": -15.370370864868164,
+    "eval_logits/rejected": -15.3493070602417,
+    "eval_logps/chosen": -1.7481694221496582,
+    "eval_logps/rejected": -1.9914860725402832,
+    "eval_loss": 4.618270397186279,
+    "eval_rewards/accuracies": 0.6290983557701111,
+    "eval_rewards/chosen": -17.481693267822266,
+    "eval_rewards/margins": 2.4331674575805664,
+    "eval_rewards/rejected": -19.91486167907715,
+    "eval_runtime": 86.386,
+    "eval_samples": 1941,
+    "eval_samples_per_second": 22.469,
+    "eval_steps_per_second": 1.412,
     "total_flos": 0.0,
     "train_loss": 2.6376401560149922,
     "train_runtime": 2565.593,

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": 0.995910949568378,
+    "eval_logits/chosen": -15.370370864868164,
+    "eval_logits/rejected": -15.3493070602417,
+    "eval_logps/chosen": -1.7481694221496582,
+    "eval_logps/rejected": -1.9914860725402832,
+    "eval_loss": 4.618270397186279,
+    "eval_rewards/accuracies": 0.6290983557701111,
+    "eval_rewards/chosen": -17.481693267822266,
+    "eval_rewards/margins": 2.4331674575805664,
+    "eval_rewards/rejected": -19.91486167907715,
+    "eval_runtime": 86.386,
+    "eval_samples": 1941,
+    "eval_samples_per_second": 22.469,
+    "eval_steps_per_second": 1.412
+}