Upload folder using huggingface_hub

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d55cd39dfa0bf2eeea8f8b2c78d426b1b786396a1f5221e7e2ded577535aff3
+oid sha256:d530af524a734089f722e9edcc4e6aceb89e4085c6dbd4aa99460ca1d9143a8a
 size 497786496

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76d571a09ae602ac936a1ffe89782e0e8dd39c79ffb6bc996f548603fe54dc0b
+oid sha256:303dcd9921430b115dc430584599708742253fcac3a5d402dea9f93597097608
 size 995666874

trainer_state.json

@@ -11,15 +11,15 @@
     {
       "epoch": 0.05,
       "learning_rate": 4.976714865090827e-05,
-      "logits/chosen": -10.627127647399902,
-      "logits/rejected": -7.845921516418457,
-      "logps/chosen": -296.1811828613281,
-      "logps/rejected": -265.0650634765625,
-      "loss": 0.031,
-      "rewards/accuracies": 0.9868749976158142,
-      "rewards/chosen": 2.7860028743743896,
-      "rewards/margins": 35.578575134277344,
-      "rewards/rejected": -32.792572021484375,
+      "logits/chosen": -30.543472290039062,
+      "logits/rejected": -67.6454086303711,
+      "logps/chosen": -383.7469482421875,
+      "logps/rejected": -404.8834228515625,
+      "loss": 0.2274,
+      "rewards/accuracies": 0.9768750071525574,
+      "rewards/chosen": -33.849693298339844,
+      "rewards/margins": 80.87075805664062,
+      "rewards/rejected": -114.72045135498047,
       "step": 200
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4128496d17e86f3228a418cbab2c1bab6bebe29461cf603a075c52115b3897d9
+oid sha256:60180af3658717020da1d3233556d6e15ae97a8d517729961e9be4f667d3a26d
 size 4600