End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: apache-2.0
 base_model: Qwen/Qwen2.5-32B-Instruct
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- tanliboy/orca_dpo_pairs
 model-index:
 - name: lambda-qwen2.5-32b-dpo-test
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # lambda-qwen2.5-32b-dpo-test
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) on the tanliboy/orca_dpo_pairs dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0004
-- Rewards/chosen: -10.0873
-- Rewards/rejected: -25.9319
+- Loss: 0.0003
+- Rewards/chosen: -10.1618
+- Rewards/rejected: -26.1150
 - Rewards/accuracies: 1.0
-- Rewards/margins: 15.8446
-- Logps/rejected: -3031.2175
-- Logps/chosen: -1365.4342
-- Logits/rejected: -0.2882
-- Logits/chosen: -0.0014
+- Rewards/margins: 15.9532
+- Logps/rejected: -3049.5271
+- Logps/chosen: -1372.8903
+- Logits/rejected: -0.3154
+- Logits/chosen: -0.0600
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -0.05997615307569504,
+    "eval_logits/rejected": -0.31538692116737366,
+    "eval_logps/chosen": -1372.8902587890625,
+    "eval_logps/rejected": -3049.527099609375,
+    "eval_loss": 0.00032760968315415084,
+    "eval_rewards/accuracies": 1.0,
+    "eval_rewards/chosen": -10.161836624145508,
+    "eval_rewards/margins": 15.953170776367188,
+    "eval_rewards/rejected": -26.115005493164062,
+    "eval_runtime": 107.6139,
+    "eval_samples": 643,
+    "eval_samples_per_second": 5.975,
+    "eval_steps_per_second": 0.381,
     "total_flos": 0.0,
     "train_loss": 0.10807222205026247,
     "train_runtime": 19238.6363,

config.json

@@ -22,7 +22,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 152064
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -0.05997615307569504,
+    "eval_logits/rejected": -0.31538692116737366,
+    "eval_logps/chosen": -1372.8902587890625,
+    "eval_logps/rejected": -3049.527099609375,
+    "eval_loss": 0.00032760968315415084,
+    "eval_rewards/accuracies": 1.0,
+    "eval_rewards/chosen": -10.161836624145508,
+    "eval_rewards/margins": 15.953170776367188,
+    "eval_rewards/rejected": -26.115005493164062,
+    "eval_runtime": 107.6139,
+    "eval_samples": 643,
+    "eval_samples_per_second": 5.975,
+    "eval_steps_per_second": 0.381
+}

runs/Sep22_06-14-42_action-graph-trainer/events.out.tfevents.1727006142.action-graph-trainer.3370934.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de74538ff0866da97fc1ebd7a1bc0cc15bb1619ebd600a84118e3a20d412c9f5
+size 828