End of training

README.md

@@ -3,9 +3,15 @@ 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
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: zephyr-7b-align-scan-0.0-0.0-linear-1
   results: []
@@ -16,7 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-align-scan-0.0-0.0-linear-1
 
-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:
+- Loss: 0.6357
+- Rewards/chosen: -0.0757
+- Rewards/rejected: -0.3058
+- Rewards/accuracies: 0.3353
+- Rewards/margins: 0.2301
+- Logps/rejected: -89.7913
+- Logps/chosen: -76.6356
+- Logits/rejected: -2.3906
+- Logits/chosen: -2.4061
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.406076192855835,
+    "eval_logits/rejected": -2.390552282333374,
+    "eval_logps/chosen": -76.63563537597656,
+    "eval_logps/rejected": -89.79125213623047,
+    "eval_loss": 0.635656476020813,
+    "eval_rewards/accuracies": 0.335317462682724,
+    "eval_rewards/chosen": -0.07570639997720718,
+    "eval_rewards/margins": 0.23013043403625488,
+    "eval_rewards/rejected": -0.30583682656288147,
+    "eval_runtime": 113.694,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.591,
+    "eval_steps_per_second": 0.554,
     "total_flos": 0.0,
     "train_loss": 0.6540692721803983,
     "train_runtime": 977.0227,

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

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.406076192855835,
+    "eval_logits/rejected": -2.390552282333374,
+    "eval_logps/chosen": -76.63563537597656,
+    "eval_logps/rejected": -89.79125213623047,
+    "eval_loss": 0.635656476020813,
+    "eval_rewards/accuracies": 0.335317462682724,
+    "eval_rewards/chosen": -0.07570639997720718,
+    "eval_rewards/margins": 0.23013043403625488,
+    "eval_rewards/rejected": -0.30583682656288147,
+    "eval_runtime": 113.694,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.591,
+    "eval_steps_per_second": 0.554
+}

runs/Sep28_08-58-33_qa-a100-005.crc.nd.edu/events.out.tfevents.1727529692.qa-a100-005.crc.nd.edu.134294.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b3f75c76a0688ea137aa19c79bcf88002841ba195eedd7d9c2f24042889ee0
+size 815