End of training

README.md

@@ -2,9 +2,15 @@
 license: mit
 base_model: microsoft/Phi-3-mini-128k-instruct
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- princeton-nlp/llama3-ultrafeedback
 model-index:
 - name: phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5
   results: []
@@ -15,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # phi-3-mini-128k-instruct-simpo-lr-5e-07-gamma-1.5
 
-This model is a fine-tuned version of [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) on the princeton-nlp/llama3-ultrafeedback dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6236
-- Rewards/chosen: -2.2390
-- Rewards/rejected: -2.6457
-- Rewards/accuracies: 0.6210
-- Rewards/margins: 0.4067
-- Logps/rejected: -1.0583
-- Logps/chosen: -0.8956
-- Logits/rejected: 2.0190
-- Logits/chosen: 2.0146
+- Loss: 1.6226
+- Rewards/chosen: -2.2430
+- Rewards/rejected: -2.6527
+- Rewards/accuracies: 0.625
+- Rewards/margins: 0.4097
+- Logps/rejected: -1.0611
+- Logps/chosen: -0.8972
+- Logits/rejected: 2.0148
+- Logits/chosen: 2.0096
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9981298423724285,
+    "eval_logits/chosen": 2.009596824645996,
+    "eval_logits/rejected": 2.014779806137085,
+    "eval_logps/chosen": -0.897185742855072,
+    "eval_logps/rejected": -1.061065435409546,
+    "eval_loss": 1.6225711107254028,
+    "eval_rewards/accuracies": 0.625,
+    "eval_rewards/chosen": -2.242964267730713,
+    "eval_rewards/margins": 0.40969952940940857,
+    "eval_rewards/rejected": -2.6526639461517334,
+    "eval_runtime": 44.5569,
+    "eval_samples": 1961,
+    "eval_samples_per_second": 44.011,
+    "eval_steps_per_second": 1.391,
     "total_flos": 0.0,
     "train_loss": 1.6566840494470372,
     "train_runtime": 5417.7619,

config.json

@@ -135,6 +135,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32064
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9981298423724285,
+    "eval_logits/chosen": 2.009596824645996,
+    "eval_logits/rejected": 2.014779806137085,
+    "eval_logps/chosen": -0.897185742855072,
+    "eval_logps/rejected": -1.061065435409546,
+    "eval_loss": 1.6225711107254028,
+    "eval_rewards/accuracies": 0.625,
+    "eval_rewards/chosen": -2.242964267730713,
+    "eval_rewards/margins": 0.40969952940940857,
+    "eval_rewards/rejected": -2.6526639461517334,
+    "eval_runtime": 44.5569,
+    "eval_samples": 1961,
+    "eval_samples_per_second": 44.011,
+    "eval_steps_per_second": 1.391
+}

runs/Jun21_16-34-46_131-186-38-174/events.out.tfevents.1718993931.131-186-38-174.27809.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa7fe103ce3978031e1794e815d2016e43d9268de16e572ddca034b509080b1a
+size 828