Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b671d4e43950bd338a109cd4eabb2547db024316e1a83a98c6aae93409db961
+oid sha256:867703907f2f1a76d67d7ff388c676b39a85c5d30dc8a0e586099091a1cd7577
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e5e2265be877ae37fe18758b3d066d64e420b1d5aa11383c5587bbd880ac8b2
+oid sha256:d737b0cdc3d7c98a38802e1705694cfd222a94ef163897cda48e14bd9459edec
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:624837cd6e7e41c76588d8ab24417e8a1710d14110400eb078f5e1b17702d42b
+oid sha256:ff0ae421dd10b5797aff22abbbc03d9938f22a0c3263b843629b6ea2e7daedec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5450b3c0b6570b6c09cd38a0ade4e53a34ac0c033a784959f9f2bdce58322982
+oid sha256:54cc976c79460b9d33f11e645b03612019eb0d01bc3da2482d4f71d55270ef6e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010950852573649462,
+  "epoch": 0.011149958984079451,
   "eval_steps": 500,
-  "global_step": 1375,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1651,6 +1651,42 @@
       "reward_std": 0.21728940233588218,
       "rewards/custom_reward_simplified_v7_dblog": 0.65625,
       "step": 1370
+    },
+    {
+      "completion_length": 682.31875,
+      "epoch": 0.01099067385573546,
+      "grad_norm": 0.10079372674226761,
+      "kl": 0.009952771244570613,
+      "learning_rate": 2.2821106431308546e-06,
+      "loss": 0.0004,
+      "reward": 0.89375,
+      "reward_std": 0.33092204555869104,
+      "rewards/custom_reward_simplified_v7_dblog": 0.89375,
+      "step": 1380
+    },
+    {
+      "completion_length": 669.09375,
+      "epoch": 0.011070316419907454,
+      "grad_norm": 0.19604210555553436,
+      "kl": 0.011396997445262968,
+      "learning_rate": 2.2459123045429953e-06,
+      "loss": 0.0005,
+      "reward": 0.784375,
+      "reward_std": 0.29770964160561564,
+      "rewards/custom_reward_simplified_v7_dblog": 0.784375,
+      "step": 1390
+    },
+    {
+      "completion_length": 651.80625,
+      "epoch": 0.011149958984079451,
+      "grad_norm": 0.27397212386131287,
+      "kl": 0.01038803206756711,
+      "learning_rate": 2.2097677146869242e-06,
+      "loss": 0.0004,
+      "reward": 0.878125,
+      "reward_std": 0.27883157432079314,
+      "rewards/custom_reward_simplified_v7_dblog": 0.878125,
+      "step": 1400
     }
   ],
   "logging_steps": 10,