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-0.0-0.9-polynomial-3
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-align-scan-0.0-0.9-polynomial-3
 
-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: 0.9404
-- Rewards/chosen: 1.5621
-- Rewards/rejected: 0.3036
-- Rewards/accuracies: 0.3294
-- Rewards/margins: 1.2585
-- Logps/rejected: -80.8042
-- Logps/chosen: -72.8236
-- Logits/rejected: -2.5182
-- Logits/chosen: -2.5344
+- Loss: 0.9815
+- Rewards/chosen: 0.2790
+- Rewards/rejected: -1.2918
+- Rewards/accuracies: 0.3452
+- Rewards/margins: 1.5708
+- Logps/rejected: -82.5074
+- Logps/chosen: -74.1934
+- Logits/rejected: -2.5411
+- Logits/chosen: -2.5570
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 3.0,
+    "eval_logits/chosen": -2.5570387840270996,
+    "eval_logits/rejected": -2.5411317348480225,
+    "eval_logps/chosen": -74.19338989257812,
+    "eval_logps/rejected": -82.50736999511719,
+    "eval_loss": 0.9815396666526794,
+    "eval_rewards/accuracies": 0.3452380895614624,
+    "eval_rewards/chosen": 0.2789943516254425,
+    "eval_rewards/margins": 1.5707836151123047,
+    "eval_rewards/rejected": -1.2917892932891846,
+    "eval_runtime": 113.7681,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.58,
+    "eval_steps_per_second": 0.554,
     "total_flos": 0.0,
     "train_loss": 0.479405563738611,
     "train_runtime": 3137.8924,

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": 3.0,
+    "eval_logits/chosen": -2.5570387840270996,
+    "eval_logits/rejected": -2.5411317348480225,
+    "eval_logps/chosen": -74.19338989257812,
+    "eval_logps/rejected": -82.50736999511719,
+    "eval_loss": 0.9815396666526794,
+    "eval_rewards/accuracies": 0.3452380895614624,
+    "eval_rewards/chosen": 0.2789943516254425,
+    "eval_rewards/margins": 1.5707836151123047,
+    "eval_rewards/rejected": -1.2917892932891846,
+    "eval_runtime": 113.7681,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.58,
+    "eval_steps_per_second": 0.554
+}

runs/Sep24_10-01-26_qa-a100-004.crc.nd.edu/events.out.tfevents.1727190047.qa-a100-004.crc.nd.edu.1811337.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71760997e359817a03bee45deb37222f7b9f457f897f40edf4b33933283458ab
+size 828