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-1
   results: []
@@ -16,7 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-align-scan-0.0-0.3-polynomial-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: 0.6417
+- Rewards/chosen: 0.2397
+- Rewards/rejected: 0.0477
+- Rewards/accuracies: 0.3353
+- Rewards/margins: 0.1920
+- Logps/rejected: -80.9526
+- Logps/chosen: -73.6081
+- Logits/rejected: -2.5236
+- Logits/chosen: -2.5399
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -2.5399038791656494,
+    "eval_logits/rejected": -2.523594379425049,
+    "eval_logps/chosen": -73.60810089111328,
+    "eval_logps/rejected": -80.95262908935547,
+    "eval_loss": 0.6417149901390076,
+    "eval_rewards/accuracies": 0.335317462682724,
+    "eval_rewards/chosen": 0.2396649718284607,
+    "eval_rewards/margins": 0.19197754561901093,
+    "eval_rewards/rejected": 0.04768744856119156,
+    "eval_runtime": 114.5526,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.459,
+    "eval_steps_per_second": 0.55,
     "total_flos": 0.0,
     "train_loss": 0.6600211213032404,
     "train_runtime": 962.6608,

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": -2.5399038791656494,
+    "eval_logits/rejected": -2.523594379425049,
+    "eval_logps/chosen": -73.60810089111328,
+    "eval_logps/rejected": -80.95262908935547,
+    "eval_loss": 0.6417149901390076,
+    "eval_rewards/accuracies": 0.335317462682724,
+    "eval_rewards/chosen": 0.2396649718284607,
+    "eval_rewards/margins": 0.19197754561901093,
+    "eval_rewards/rejected": 0.04768744856119156,
+    "eval_runtime": 114.5526,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 17.459,
+    "eval_steps_per_second": 0.55
+}

runs/Sep24_14-25-50_qa-a100-004.crc.nd.edu/events.out.tfevents.1727203741.qa-a100-004.crc.nd.edu.1904062.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de2975d6dac5ef7ce90551d895e820b96ca3f7990e5679ffb34bf5eb5974719
+size 815