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-0.0-0.3-polynomial-3
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-align-scan-0.0-0.3-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: 0.6854
-- Rewards/chosen: -0.2626
-- Rewards/rejected: -0.8523
-- Rewards/accuracies: 0.3254
-- Rewards/margins: 0.5897
-- Logps/rejected: -84.2922
-- Logps/chosen: -75.4660
-- Logits/rejected: -2.5243
-- Logits/chosen: -2.5414
+- Loss: 0.7657
+- Rewards/chosen: -1.7538
+- Rewards/rejected: -2.6151
+- Rewards/accuracies: 0.3194
+- Rewards/margins: 0.8612
+- Logps/rejected: -90.8353
+- Logps/chosen: -81.0013
+- Logits/rejected: -2.4771
+- Logits/chosen: -2.4954
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 3.0,
+    "eval_logits/chosen": -2.4954090118408203,
+    "eval_logits/rejected": -2.477094888687134,
+    "eval_logps/chosen": -81.00131225585938,
+    "eval_logps/rejected": -90.83526611328125,
+    "eval_loss": 0.7656615972518921,
+    "eval_rewards/accuracies": 0.3194444477558136,
+    "eval_rewards/chosen": -1.753847360610962,
+    "eval_rewards/margins": 0.8612387776374817,
+    "eval_rewards/rejected": -2.615086078643799,
+    "eval_runtime": 113.6621,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.596,
+    "eval_steps_per_second": 0.554,
     "total_flos": 0.0,
     "train_loss": 0.4762688593731986,
     "train_runtime": 3179.8752,

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": -2.4954090118408203,
+    "eval_logits/rejected": -2.477094888687134,
+    "eval_logps/chosen": -81.00131225585938,
+    "eval_logps/rejected": -90.83526611328125,
+    "eval_loss": 0.7656615972518921,
+    "eval_rewards/accuracies": 0.3194444477558136,
+    "eval_rewards/chosen": -1.753847360610962,
+    "eval_rewards/margins": 0.8612387776374817,
+    "eval_rewards/rejected": -2.615086078643799,
+    "eval_runtime": 113.6621,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.596,
+    "eval_steps_per_second": 0.554
+}

runs/Sep24_08-15-53_qa-a100-004.crc.nd.edu/events.out.tfevents.1727183856.qa-a100-004.crc.nd.edu.1794966.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3315923f081e65bdaa06f80f5eaccf7464bc6a45c139f34640603c5718831c42
+size 828