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-polynomial-3
   results: []
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-align-scan-0.0-0.0-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: 0.6749
-- Rewards/chosen: -1.2868
-- Rewards/rejected: -1.7792
-- Rewards/accuracies: 0.3313
-- Rewards/margins: 0.4925
-- Logps/rejected: -233.7709
-- Logps/chosen: -184.8848
-- Logits/rejected: -1.4185
-- Logits/chosen: -1.4498
+- Loss: 0.7364
+- Rewards/chosen: -2.3188
+- Rewards/rejected: -3.0685
+- Rewards/accuracies: 0.3194
+- Rewards/margins: 0.7497
+- Logps/rejected: -344.3773
+- Logps/chosen: -273.4246
+- Logits/rejected: 1.7116
+- Logits/chosen: 1.6027
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 3.0,
+    "eval_logits/chosen": 1.6027365922927856,
+    "eval_logits/rejected": 1.7115638256072998,
+    "eval_logps/chosen": -273.4245910644531,
+    "eval_logps/rejected": -344.37725830078125,
+    "eval_loss": 0.7364417314529419,
+    "eval_rewards/accuracies": 0.3194444477558136,
+    "eval_rewards/chosen": -2.318794012069702,
+    "eval_rewards/margins": 0.7496706247329712,
+    "eval_rewards/rejected": -3.068464756011963,
+    "eval_runtime": 113.7849,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.577,
+    "eval_steps_per_second": 0.554,
     "total_flos": 0.0,
     "train_loss": 0.5020060315728188,
     "train_runtime": 3747.4353,

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": 1.6027365922927856,
+    "eval_logits/rejected": 1.7115638256072998,
+    "eval_logps/chosen": -273.4245910644531,
+    "eval_logps/rejected": -344.37725830078125,
+    "eval_loss": 0.7364417314529419,
+    "eval_rewards/accuracies": 0.3194444477558136,
+    "eval_rewards/chosen": -2.318794012069702,
+    "eval_rewards/margins": 0.7496706247329712,
+    "eval_rewards/rejected": -3.068464756011963,
+    "eval_runtime": 113.7849,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.577,
+    "eval_steps_per_second": 0.554
+}

runs/Sep28_07-02-32_qa-a100-005.crc.nd.edu/events.out.tfevents.1727525577.qa-a100-005.crc.nd.edu.115709.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31dd751bc1d81ef295f54cb2b7051a8e9e14ed549811a9cef5dc6aef9525c489
+size 828