End of training

README.md

@@ -3,6 +3,8 @@ library_name: transformers
 license: gemma
 base_model: google/gemma-2-9b-it
 tags:
+- llama-factory
+- full
 - trl
 - dpo
 - llama-factory
@@ -17,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gemma-oh-preferences
 
-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 cdc0b2d9-493b-4cb1-87e8-8fb1e3f4b247 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 3.9424
 - Rewards/chosen: -46.0706

all_results.json

@@ -0,0 +1,20 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": 14.471516609191895,
+    "eval_logits/rejected": 14.6997652053833,
+    "eval_logps/chosen": -4.607059001922607,
+    "eval_logps/rejected": -4.770802974700928,
+    "eval_loss": 3.942422866821289,
+    "eval_rewards/accuracies": 0.6459948420524597,
+    "eval_rewards/chosen": -46.07059097290039,
+    "eval_rewards/margins": 1.6374331712722778,
+    "eval_rewards/rejected": -47.7080192565918,
+    "eval_runtime": 439.7489,
+    "eval_samples_per_second": 112.507,
+    "eval_steps_per_second": 1.76,
+    "total_flos": 4181538261958656.0,
+    "train_loss": 4.105394068821323,
+    "train_runtime": 31326.6745,
+    "train_samples_per_second": 30.007,
+    "train_steps_per_second": 0.234
+}

eval_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": 14.471516609191895,
+    "eval_logits/rejected": 14.6997652053833,
+    "eval_logps/chosen": -4.607059001922607,
+    "eval_logps/rejected": -4.770802974700928,
+    "eval_loss": 3.942422866821289,
+    "eval_rewards/accuracies": 0.6459948420524597,
+    "eval_rewards/chosen": -46.07059097290039,
+    "eval_rewards/margins": 1.6374331712722778,
+    "eval_rewards/rejected": -47.7080192565918,
+    "eval_runtime": 439.7489,
+    "eval_samples_per_second": 112.507,
+    "eval_steps_per_second": 1.76
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 4181538261958656.0,
+    "train_loss": 4.105394068821323,
+    "train_runtime": 31326.6745,
+    "train_samples_per_second": 30.007,
+    "train_steps_per_second": 0.234
+}