Training in progress, step 1625, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd43e66f1742ac947be1f0dc761704ca288dee8b53a1f2c8ac1ceffbdd7549a1
+oid sha256:423b64fbb1ea140492cfc24ef9ece60648b191c70dd895716bfd7089e67b8208
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d3e4cffe85f4acacdf78061fcb1e34e52393afc3937dc544fb6043b383d348
+oid sha256:c5d3b30fa482768f1ad2b80ee5bc9e5292d3baf25108f33db5b8a542a06ce420
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff9aa06f3822fca277644ab91ef439c8d8d33c82c9dcaffe93fc59938b3059f
+oid sha256:8eed12b44c80cdfb15b0a3f1fe87a11acc2ec200f42a39d9eb205ab6178ed036
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36405581658bcd0529d0f6715e48fce527aa3927cda602e0b7c0c66f1886419d
+oid sha256:72ed1d5ef4494540c37a040ccc45c1b5c7b0e918a3cfabfd70bfd42fcea055f3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012742810267519373,
+  "epoch": 0.012941916677949363,
   "eval_steps": 500,
-  "global_step": 1600,
+  "global_step": 1625,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1927,6 +1927,30 @@
       "reward_std": 0.2901748239994049,
       "rewards/custom_reward_simplified_v7_dblog": 0.759375,
       "step": 1600
+    },
+    {
+      "completion_length": 652.49375,
+      "epoch": 0.012822452831691368,
+      "grad_norm": 0.12168209999799728,
+      "kl": 0.012750855972990393,
+      "learning_rate": 1.4765192136847686e-06,
+      "loss": 0.0005,
+      "reward": 0.728125,
+      "reward_std": 0.26915703564882276,
+      "rewards/custom_reward_simplified_v7_dblog": 0.728125,
+      "step": 1610
+    },
+    {
+      "completion_length": 660.95625,
+      "epoch": 0.012902095395863365,
+      "grad_norm": 0.13546766340732574,
+      "kl": 0.013546877074986696,
+      "learning_rate": 1.443454345648252e-06,
+      "loss": 0.0005,
+      "reward": 0.790625,
+      "reward_std": 0.1937400370836258,
+      "rewards/custom_reward_simplified_v7_dblog": 0.790625,
+      "step": 1620
     }
   ],
   "logging_steps": 10,