End of training

README.md

@@ -2,9 +2,15 @@
 license: apache-2.0
 base_model: Qwen/Qwen2-0.5B-Instruct
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- princeton-nlp/llama3-ultrafeedback
 model-index:
 - name: qwen2-0.5b-instruct-simpo-lr-5e-07-gamma-1.5
   results: []
@@ -15,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwen2-0.5b-instruct-simpo-lr-5e-07-gamma-1.5
 
-This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on the princeton-nlp/llama3-ultrafeedback dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6598
-- Rewards/chosen: -3.3421
-- Rewards/rejected: -3.4735
+- Loss: 1.6594
+- Rewards/chosen: -3.3473
+- Rewards/rejected: -3.4798
 - Rewards/accuracies: 0.5282
-- Rewards/margins: 0.1314
-- Logps/rejected: -1.3894
-- Logps/chosen: -1.3368
-- Logits/rejected: -5.2590
-- Logits/chosen: -5.3573
+- Rewards/margins: 0.1325
+- Logps/rejected: -1.3919
+- Logps/chosen: -1.3389
+- Logits/rejected: -5.2419
+- Logits/chosen: -5.3398
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9981298423724285,
+    "eval_logits/chosen": -5.339814186096191,
+    "eval_logits/rejected": -5.241891384124756,
+    "eval_logps/chosen": -1.3389328718185425,
+    "eval_logps/rejected": -1.3919367790222168,
+    "eval_loss": 1.659356713294983,
+    "eval_rewards/accuracies": 0.5282257795333862,
+    "eval_rewards/chosen": -3.347332239151001,
+    "eval_rewards/margins": 0.13250981271266937,
+    "eval_rewards/rejected": -3.479841947555542,
+    "eval_runtime": 29.2769,
+    "eval_samples": 1961,
+    "eval_samples_per_second": 66.981,
+    "eval_steps_per_second": 2.118,
     "total_flos": 0.0,
     "train_loss": 1.7099600828689476,
     "train_runtime": 3104.7014,

config.json

@@ -22,7 +22,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9981298423724285,
+    "eval_logits/chosen": -5.339814186096191,
+    "eval_logits/rejected": -5.241891384124756,
+    "eval_logps/chosen": -1.3389328718185425,
+    "eval_logps/rejected": -1.3919367790222168,
+    "eval_loss": 1.659356713294983,
+    "eval_rewards/accuracies": 0.5282257795333862,
+    "eval_rewards/chosen": -3.347332239151001,
+    "eval_rewards/margins": 0.13250981271266937,
+    "eval_rewards/rejected": -3.479841947555542,
+    "eval_runtime": 29.2769,
+    "eval_samples": 1961,
+    "eval_samples_per_second": 66.981,
+    "eval_steps_per_second": 2.118
+}

runs/Jun21_14-04-01_131-186-38-174/events.out.tfevents.1718982473.131-186-38-174.21907.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b082f0481f7337f6161a345fe253c664e64247cdac02f6dad4d708e35a6824
+size 828