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-small-wrong
   results: []
@@ -16,7 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # simpo-train-small-wrong
 
-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: 3.9708
+- Rewards/chosen: -8.2674
+- Rewards/rejected: -9.9615
+- Rewards/accuracies: 0.7049
+- Rewards/margins: 1.6941
+- Logps/rejected: -0.9961
+- Logps/chosen: -0.8267
+- Logits/rejected: -9.8184
+- Logits/chosen: -10.0914
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.995910949568378,
+    "eval_logits/chosen": -10.091446876525879,
+    "eval_logits/rejected": -9.818441390991211,
+    "eval_logps/chosen": -0.8267378211021423,
+    "eval_logps/rejected": -0.9961459040641785,
+    "eval_loss": 3.9708292484283447,
+    "eval_rewards/accuracies": 0.7049180269241333,
+    "eval_rewards/chosen": -8.267377853393555,
+    "eval_rewards/margins": 1.6940813064575195,
+    "eval_rewards/rejected": -9.96146011352539,
+    "eval_runtime": 86.365,
+    "eval_samples": 1941,
+    "eval_samples_per_second": 22.474,
+    "eval_steps_per_second": 1.413,
     "total_flos": 0.0,
     "train_loss": 4.865393144370866,
     "train_runtime": 3024.5765,

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": -10.091446876525879,
+    "eval_logits/rejected": -9.818441390991211,
+    "eval_logps/chosen": -0.8267378211021423,
+    "eval_logps/rejected": -0.9961459040641785,
+    "eval_loss": 3.9708292484283447,
+    "eval_rewards/accuracies": 0.7049180269241333,
+    "eval_rewards/chosen": -8.267377853393555,
+    "eval_rewards/margins": 1.6940813064575195,
+    "eval_rewards/rejected": -9.96146011352539,
+    "eval_runtime": 86.365,
+    "eval_samples": 1941,
+    "eval_samples_per_second": 22.474,
+    "eval_steps_per_second": 1.413
+}