Model save

README.md

@@ -3,15 +3,10 @@ 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
+- alignment-handbook
 - generated_from_trainer
-datasets:
-- data/zephyr_uf_rlced_conifer_ref
 model-index:
 - name: uf-rlced-conifer-zephyr-7b-group-dpo-no-clip
   results: []
@@ -22,17 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # uf-rlced-conifer-zephyr-7b-group-dpo-no-clip
 
-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 data/zephyr_uf_rlced_conifer_ref dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.6931
-- Rewards/chosen: 0.0
-- Rewards/rejected: 0.0
-- Rewards/accuracies: 0.0
-- Rewards/margins: 0.0
-- Logps/rejected: -314.9812
-- Logps/chosen: -425.9340
-- Logits/rejected: -2.6874
-- Logits/chosen: -2.7334
+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.
 
 ## Model description
 

all_results.json

@@ -1,5 +1,5 @@
 {
-    "epoch": 1.0,
+    "epoch": 0.9993060374739764,
     "eval_logits/chosen": -2.7333760261535645,
     "eval_logits/rejected": -2.687427043914795,
     "eval_logps/chosen": -425.93402099609375,
@@ -14,9 +14,9 @@
     "eval_samples_per_second": 16.512,
     "eval_steps_per_second": 0.33,
     "total_flos": 0.0,
-    "train_loss": 0.24032984673976898,
-    "train_runtime": 97.8271,
-    "train_samples": 100,
-    "train_samples_per_second": 1.022,
-    "train_steps_per_second": 0.01
+    "train_loss": 0.1315754380491045,
+    "train_runtime": 20812.0317,
+    "train_samples": 184443,
+    "train_samples_per_second": 8.862,
+    "train_steps_per_second": 0.035
 }

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 1.0,
+    "epoch": 0.9993060374739764,
     "total_flos": 0.0,
-    "train_loss": 0.24032984673976898,
-    "train_runtime": 97.8271,
-    "train_samples": 100,
-    "train_samples_per_second": 1.022,
-    "train_steps_per_second": 0.01
+    "train_loss": 0.1315754380491045,
+    "train_runtime": 20812.0317,
+    "train_samples": 184443,
+    "train_samples_per_second": 8.862,
+    "train_steps_per_second": 0.035
 }