End of training

README.md

@@ -3,10 +3,16 @@ library_name: transformers
 license: apache-2.0
 base_model: alignment-handbook/zephyr-7b-sft-full
 tags:
+- alignment-handbook
+- trl
+- dpo
+- generated_from_trainer
 - trl
 - dpo
 - alignment-handbook
 - generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: zephyr-7b-align-scan
   results: []
@@ -17,17 +23,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-align-scan
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the HuggingFaceH4/ultrafeedback_binarized dataset.
 It achieves the following results on the evaluation set:
-- Logits/chosen: 0.4326
-- Logits/rejected: 0.9106
-- Logps/chosen: -136.2882
-- Logps/rejected: -189.5506
-- Loss: 0.5958
-- Rewards/accuracies: 0.3710
-- Rewards/chosen: -0.6180
-- Rewards/margins: 0.4663
-- Rewards/rejected: -1.0842
+- Loss: 0.5960
+- Rewards/chosen: -0.6252
+- Rewards/rejected: -1.0907
+- Rewards/accuracies: 0.3690
+- Rewards/margins: 0.4655
+- Logps/rejected: -190.1945
+- Logps/chosen: -137.0085
+- Logits/rejected: 0.9319
+- Logits/chosen: 0.4522
 
 ## Model description
 

all_results.json

@@ -9,9 +9,9 @@
     "eval_rewards/chosen": -0.6251727342605591,
     "eval_rewards/margins": 0.4654882848262787,
     "eval_rewards/rejected": -1.0906610488891602,
-    "eval_runtime": 114.4482,
+    "eval_runtime": 114.506,
     "eval_samples": 2000,
-    "eval_samples_per_second": 17.475,
+    "eval_samples_per_second": 17.466,
     "eval_steps_per_second": 0.55,
     "total_flos": 0.0,
     "train_loss": 0.0,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -9,8 +9,8 @@
     "eval_rewards/chosen": -0.6251727342605591,
     "eval_rewards/margins": 0.4654882848262787,
     "eval_rewards/rejected": -1.0906610488891602,
-    "eval_runtime": 114.4482,
+    "eval_runtime": 114.506,
     "eval_samples": 2000,
-    "eval_samples_per_second": 17.475,
+    "eval_samples_per_second": 17.466,
     "eval_steps_per_second": 0.55
 }

runs/Sep28_03-46-54_qa-a100-005.crc.nd.edu/events.out.tfevents.1727510220.qa-a100-005.crc.nd.edu.84817.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2568820457fbfbef3616b28e7cddf5c02f153f8e8496aea43375a39d235d6ee9
+size 828