Training in progress, step 525, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59ec13225013227af4efcb5bdbfb640d7212e59b3beb094f4872af16f10b82ef
+oid sha256:ad313288ea8bd4797fded900f5d92502d7ff0dd9d929f2a1db1ccbd3e1e33740
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91143a9dcc019124f810bc23d4848cd1c6049b7a67d72b83be9f91f7038a75d7
+oid sha256:c00f667f3ffbf6137ce5e5b8baf4c98bc27a5ccc632b376e644527fc32c15ab1
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca22256892f07c3d3627994a755a937bba7e1c876608b0bbfd5c6993d9a4ef72
+oid sha256:d658a8556badd62e9d6635ff217c390c629d34615e7572380487ccf0f8a9b3c0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb5afe87d3cf7dc745f288e9b6e22d0c86761093d76c6bd9bf6e768d81be8a7d
+oid sha256:531811d0588c0d6e2bee2610f6ac488013790b41bf60e0ecfba6c4c413a7b0a2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003982128208599804,
+  "epoch": 0.004181234619029794,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 525,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -607,6 +607,30 @@
       "reward_std": 0.25718758851289747,
       "rewards/custom_reward_simplified_v7_dblog": 0.603125,
       "step": 500
+    },
+    {
+      "completion_length": 646.7,
+      "epoch": 0.0040617707727718,
+      "grad_norm": 0.14925876259803772,
+      "kl": 0.003934591950383037,
+      "learning_rate": 4.809698831278217e-06,
+      "loss": 0.0002,
+      "reward": 0.734375,
+      "reward_std": 0.2696119427680969,
+      "rewards/custom_reward_simplified_v7_dblog": 0.734375,
+      "step": 510
+    },
+    {
+      "completion_length": 726.08125,
+      "epoch": 0.004141413336943796,
+      "grad_norm": 0.2107785940170288,
+      "kl": 0.004233359964564443,
+      "learning_rate": 4.7955402672006855e-06,
+      "loss": 0.0002,
+      "reward": 0.759375,
+      "reward_std": 0.2953102938830853,
+      "rewards/custom_reward_simplified_v7_dblog": 0.759375,
+      "step": 520
     }
   ],
   "logging_steps": 10,