Model save

README.md

@@ -2,16 +2,10 @@
 license: mit
 base_model: HuggingFaceH4/mistral-7b-sft-beta
 tags:
-- alignment-handbook
-- trl
-- dpo
-- generated_from_trainer
 - trl
 - dpo
 - alignment-handbook
 - generated_from_trainer
-datasets:
-- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: DPO-Zephyr-7B
   results: []
@@ -22,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # DPO-Zephyr-7B
 
-This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the HuggingFaceH4/ultrafeedback_binarized dataset.
+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

@@ -2,8 +2,8 @@
     "epoch": 0.8368200836820083,
     "total_flos": 0.0,
     "train_loss": 0.0,
-    "train_runtime": 11.541,
+    "train_runtime": 7.2976,
     "train_samples": 15283,
-    "train_samples_per_second": 1324.231,
-    "train_steps_per_second": 5.112
+    "train_samples_per_second": 2094.247,
+    "train_steps_per_second": 8.085
 }

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.2",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32000
 }

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 0.8368200836820083,
     "total_flos": 0.0,
     "train_loss": 0.0,
-    "train_runtime": 11.541,
+    "train_runtime": 7.2976,
     "train_samples": 15283,
-    "train_samples_per_second": 1324.231,
-    "train_steps_per_second": 5.112
+    "train_samples_per_second": 2094.247,
+    "train_steps_per_second": 8.085
 }

trainer_state.json

@@ -178,9 +178,9 @@
       "step": 100,
       "total_flos": 0.0,
       "train_loss": 0.0,
-      "train_runtime": 11.541,
-      "train_samples_per_second": 1324.231,
-      "train_steps_per_second": 5.112
+      "train_runtime": 7.2976,
+      "train_samples_per_second": 2094.247,
+      "train_steps_per_second": 8.085
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdf1865a4f5a8f66e94579ac39935b6fcdda54bdbd79a8d5e610bcd0357b96db
+oid sha256:17a5ae466f3128a7efb404e195363cb025f05cc52912c897d26639534aa5a1bd
 size 6264