Training in progress, step 1150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d151f506d17ce4e0c03a3713c88478bcbdda4a3e34a91b28b4bd8b989b401da7
+oid sha256:b87a7124fc823146a12cbeaefbe5ff8d91326cefab763555aa61dbbb9e056fab
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59f54450bc787ffff804bacadefa39d8e88180d2ae39b043d6f32742458a1a52
+oid sha256:5f14effc9368161c55b1d77fbb7e90bb1cd9af0086afde89e1a683d869fb3248
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85c6ddcd387376a529404ae7199a4e5de6a96bca66488faa804a60e28809229c
+oid sha256:9b6ca00cea62eabd929fd77d62694b267d47c0603af124f659274f264d0bf70b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11fc5977afef8cdfd86c063f7ec5cbc1d6cc536eaf4ad77613e346ad3657a2d8
+oid sha256:15a1625baaf061099e4aa140afa72e1a2a32a1a3e25d7baf8a019a63d52d6e43
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008959788469349559,
+  "epoch": 0.009158894879779549,
   "eval_steps": 500,
-  "global_step": 1125,
+  "global_step": 1150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1351,6 +1351,42 @@
       "reward_std": 0.2547163799405098,
       "rewards/custom_reward_simplified_v7_dblog": 0.728125,
       "step": 1120
+    },
+    {
+      "completion_length": 733.2125,
+      "epoch": 0.008999609751435557,
+      "grad_norm": 0.2320898026227951,
+      "kl": 0.007608366897329688,
+      "learning_rate": 3.182099991668653e-06,
+      "loss": 0.0003,
+      "reward": 0.60625,
+      "reward_std": 0.2975068032741547,
+      "rewards/custom_reward_simplified_v7_dblog": 0.60625,
+      "step": 1130
+    },
+    {
+      "completion_length": 603.5,
+      "epoch": 0.009079252315607553,
+      "grad_norm": 0.23401154577732086,
+      "kl": 0.007222792156971991,
+      "learning_rate": 3.147047612756302e-06,
+      "loss": 0.0003,
+      "reward": 0.875,
+      "reward_std": 0.2553515017032623,
+      "rewards/custom_reward_simplified_v7_dblog": 0.875,
+      "step": 1140
+    },
+    {
+      "completion_length": 704.44375,
+      "epoch": 0.009158894879779549,
+      "grad_norm": 0.2538968324661255,
+      "kl": 0.007968966104090213,
+      "learning_rate": 3.1118583598858097e-06,
+      "loss": 0.0003,
+      "reward": 0.6875,
+      "reward_std": 0.29204289317131044,
+      "rewards/custom_reward_simplified_v7_dblog": 0.6875,
+      "step": 1150
     }
   ],
   "logging_steps": 10,