Model save

README.md

@@ -2,14 +2,9 @@
 license: mit
 base_model: HuggingFaceH4/mistral-7b-sft-beta
 tags:
-- alignment-handbook
-- generated_from_trainer
 - trl
 - dpo
 - generated_from_trainer
-datasets:
-- updated
-- original
 model-index:
 - name: 0.0_ablation_4iters_bs128_nodpo_iter_1
   results: []
@@ -20,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # 0.0_ablation_4iters_bs128_nodpo_iter_1
 
-This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the updated and the original datasets.
+This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the None dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.5675088297419187,
-    "train_runtime": 3571.2847,
+    "train_runtime": 3570.6254,
     "train_samples": 15283,
-    "train_samples_per_second": 4.279,
+    "train_samples_per_second": 4.28,
     "train_steps_per_second": 0.033
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.5675088297419187,
-    "train_runtime": 3571.2847,
+    "train_runtime": 3570.6254,
     "train_samples": 15283,
-    "train_samples_per_second": 4.279,
+    "train_samples_per_second": 4.28,
     "train_steps_per_second": 0.033
 }

trainer_state.json

@@ -205,8 +205,8 @@
       "step": 119,
       "total_flos": 0.0,
       "train_loss": 0.5675088297419187,
-      "train_runtime": 3571.2847,
-      "train_samples_per_second": 4.279,
+      "train_runtime": 3570.6254,
+      "train_samples_per_second": 4.28,
       "train_steps_per_second": 0.033
     }
   ],