Training in progress, step 1650, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:423b64fbb1ea140492cfc24ef9ece60648b191c70dd895716bfd7089e67b8208
+oid sha256:6a08895d4e442ac2e2b34ad647fa53b3803a2ac87ac3bde5ea7c21daf746efbe
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5d3b30fa482768f1ad2b80ee5bc9e5292d3baf25108f33db5b8a542a06ce420
+oid sha256:13c169b9001793ae00f51a8c6359d182f353030b5e9d598d5ec179ba43c8d2d4
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eed12b44c80cdfb15b0a3f1fe87a11acc2ec200f42a39d9eb205ab6178ed036
+oid sha256:b2d7278507c375a46e6b19e5af767f263e425cc0e143f37a001d365b8c944b80
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ed1d5ef4494540c37a040ccc45c1b5c7b0e918a3cfabfd70bfd42fcea055f3
+oid sha256:6eb29e4ad419e6973610039d5ccb9e6d7d4abe171f61a95512a9844b9eca5006
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012941916677949363,
+  "epoch": 0.013141023088379354,
   "eval_steps": 500,
-  "global_step": 1625,
+  "global_step": 1650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1951,6 +1951,42 @@
       "reward_std": 0.1937400370836258,
       "rewards/custom_reward_simplified_v7_dblog": 0.790625,
       "step": 1620
+    },
+    {
+      "completion_length": 638.00625,
+      "epoch": 0.012981737960035362,
+      "grad_norm": 0.17955924570560455,
+      "kl": 0.012779112858697771,
+      "learning_rate": 1.4106129752073023e-06,
+      "loss": 0.0005,
+      "reward": 0.790625,
+      "reward_std": 0.2674853280186653,
+      "rewards/custom_reward_simplified_v7_dblog": 0.790625,
+      "step": 1630
+    },
+    {
+      "completion_length": 678.1125,
+      "epoch": 0.013061380524207357,
+      "grad_norm": 0.2616170644760132,
+      "kl": 0.01720189054030925,
+      "learning_rate": 1.3780020494988447e-06,
+      "loss": 0.0007,
+      "reward": 0.771875,
+      "reward_std": 0.27255760729312895,
+      "rewards/custom_reward_simplified_v7_dblog": 0.771875,
+      "step": 1640
+    },
+    {
+      "completion_length": 639.43125,
+      "epoch": 0.013141023088379354,
+      "grad_norm": 0.1487816423177719,
+      "kl": 0.014415727299638092,
+      "learning_rate": 1.3456284669124159e-06,
+      "loss": 0.0006,
+      "reward": 0.73125,
+      "reward_std": 0.24298151433467866,
+      "rewards/custom_reward_simplified_v7_dblog": 0.73125,
+      "step": 1650
     }
   ],
   "logging_steps": 10,