Model save

README.md

@@ -2,15 +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: []
@@ -21,7 +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

@@ -1,9 +1,9 @@
 {
     "epoch": 0.99581589958159,
     "total_flos": 0.0,
-    "train_loss": 0.6207737401753914,
-    "train_runtime": 2197.4341,
+    "train_loss": 0.09242776261658228,
+    "train_runtime": 417.0202,
     "train_samples": 15283,
-    "train_samples_per_second": 6.955,
-    "train_steps_per_second": 0.054
+    "train_samples_per_second": 36.648,
+    "train_steps_per_second": 0.285
 }

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
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26cca4b287c978b5da15afb90e3213e3c13eada6ce39254e1af4af6124a65797
+oid sha256:2fd2a19ccb0893f580a7235f0f8fd0fd9a589129b99b84c3395259a864ae8c57
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f6001ee57f534204dade687209d56b14fab77802aabbf7342040c93123d5415
+oid sha256:cdcfd1a54675ca8e337ea7dd8b603926c8a5b117479c8c4dd42792b8f743f605
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dddc589e77483ccca76ae5c994b2e991a0658f090b51b2a10ad407152b70e722
+oid sha256:98370412ab5b475b5891780bc29108d4652c88f67530631146785e0f11bd27f2
 size 4540516344

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 0.99581589958159,
     "total_flos": 0.0,
-    "train_loss": 0.6207737401753914,
-    "train_runtime": 2197.4341,
+    "train_loss": 0.09242776261658228,
+    "train_runtime": 417.0202,
     "train_samples": 15283,
-    "train_samples_per_second": 6.955,
-    "train_steps_per_second": 0.054
+    "train_samples_per_second": 36.648,
+    "train_steps_per_second": 0.285
 }

trainer_state.json

@@ -175,27 +175,27 @@
     },
     {
       "epoch": 0.9205020920502092,
-      "grad_norm": 15.784629310581684,
+      "grad_norm": 15.709464172960688,
       "learning_rate": 8.677580722139671e-09,
-      "logits/chosen": -2.7726333141326904,
-      "logits/rejected": -2.7129316329956055,
-      "logps/chosen": -367.2535095214844,
-      "logps/rejected": -343.4007568359375,
-      "loss": 0.5944,
+      "logits/chosen": -2.7726309299468994,
+      "logits/rejected": -2.7129008769989014,
+      "logps/chosen": -367.25946044921875,
+      "logps/rejected": -343.40789794921875,
+      "loss": 0.5946,
       "rewards/accuracies": 0.699999988079071,
-      "rewards/chosen": -0.4677084982395172,
-      "rewards/margins": 0.3370305001735687,
-      "rewards/rejected": -0.8047389984130859,
+      "rewards/chosen": -0.4677678644657135,
+      "rewards/margins": 0.3370424211025238,
+      "rewards/rejected": -0.8048103451728821,
       "step": 110
     },
     {
       "epoch": 0.99581589958159,
       "step": 119,
       "total_flos": 0.0,
-      "train_loss": 0.6207737401753914,
-      "train_runtime": 2197.4341,
-      "train_samples_per_second": 6.955,
-      "train_steps_per_second": 0.054
+      "train_loss": 0.09242776261658228,
+      "train_runtime": 417.0202,
+      "train_samples_per_second": 36.648,
+      "train_steps_per_second": 0.285
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53e3bf661f988f74d812917404c9504100734c564b6d07061a95819b6487c21
+oid sha256:c65cd7b5c101d95a5dfadd2ce76f2e9250c4bc66203ed4673ccb1be24637b335
 size 6264