End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: apache-2.0
 base_model: Qwen/Qwen2.5-14B-Instruct
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: lambda-qwen2.5-14b-dpo-test
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # lambda-qwen2.5-14b-dpo-test
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4924
-- Rewards/chosen: -2.4470
-- Rewards/rejected: -3.3410
+- Loss: 0.4919
+- Rewards/chosen: -2.4745
+- Rewards/rejected: -3.3729
 - Rewards/accuracies: 0.7400
-- Rewards/margins: 0.8939
-- Logps/rejected: -828.8748
-- Logps/chosen: -734.7765
-- Logits/rejected: -1.2644
-- Logits/chosen: -1.2477
+- Rewards/margins: 0.8984
+- Logps/rejected: -832.0724
+- Logps/chosen: -737.5234
+- Logits/rejected: -1.2739
+- Logits/chosen: -1.2560
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.998691442030882,
+    "eval_logits/chosen": -1.2559658288955688,
+    "eval_logits/rejected": -1.27387535572052,
+    "eval_logps/chosen": -737.5234375,
+    "eval_logps/rejected": -832.0723876953125,
+    "eval_loss": 0.4919165074825287,
+    "eval_rewards/accuracies": 0.7400000095367432,
+    "eval_rewards/chosen": -2.4745123386383057,
+    "eval_rewards/margins": 0.8984242081642151,
+    "eval_rewards/rejected": -3.372936964035034,
+    "eval_runtime": 171.7011,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 11.648,
+    "eval_steps_per_second": 0.728,
     "total_flos": 0.0,
     "train_loss": 0.5192520058629898,
     "train_runtime": 13862.6582,

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": 0.998691442030882,
+    "eval_logits/chosen": -1.2559658288955688,
+    "eval_logits/rejected": -1.27387535572052,
+    "eval_logps/chosen": -737.5234375,
+    "eval_logps/rejected": -832.0723876953125,
+    "eval_loss": 0.4919165074825287,
+    "eval_rewards/accuracies": 0.7400000095367432,
+    "eval_rewards/chosen": -2.4745123386383057,
+    "eval_rewards/margins": 0.8984242081642151,
+    "eval_rewards/rejected": -3.372936964035034,
+    "eval_runtime": 171.7011,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 11.648,
+    "eval_steps_per_second": 0.728
+}

runs/Sep20_06-57-19_action-graph-trainer/events.out.tfevents.1726830666.action-graph-trainer.2950951.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db571b57bf9273880e77d43e711992ab399746b6048fb1ff1baba3d9e04d96da
+size 828