Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dd5a7b1213204ca747b9b853b134bfc9b44111c378177fe7af78d584b5b29e8
+oid sha256:4a136e1089288003040fb5919a64653e0afa6bd0df82d43b06f67de77b66b96a
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb0de15ef9aa9c8d8b4a7dae7fc40eba340f4539f15aaf8fc8ec93c76311885f
+oid sha256:80aa00c00cfa6fcb5d954640f14e471dbaf9a925c27f23c4e87f7c4e08eb4abe
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b049339d11661c45a143cb633e7745d099ed4f1c430b6f684cd48142f304fe9a
+oid sha256:4bca0d31999296fa556a6701fce97a7588992bf86240e00014d78311a2fb8397
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc973e3447bd6a6f5ad5fae82ce35cd91650677852104987fd5a5dacd81b436
+oid sha256:31f09120e45bcc4193cfd66ac556b20e8f26a1efecd672279cdd630bf09741a4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0033848089773098333,
+  "epoch": 0.0035839153877398238,
   "eval_steps": 500,
-  "global_step": 425,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -511,6 +511,42 @@
       "reward_std": 0.3109076008200645,
       "rewards/custom_reward_simplified_v7_dblog": 0.765625,
       "step": 420
+    },
+    {
+      "completion_length": 638.51875,
+      "epoch": 0.0034246302593958313,
+      "grad_norm": 0.17778904736042023,
+      "kl": 0.0034626491484232246,
+      "learning_rate": 4.905148561184033e-06,
+      "loss": 0.0001,
+      "reward": 0.671875,
+      "reward_std": 0.2665500298142433,
+      "rewards/custom_reward_simplified_v7_dblog": 0.671875,
+      "step": 430
+    },
+    {
+      "completion_length": 597.475,
+      "epoch": 0.0035042728235678278,
+      "grad_norm": 0.127123162150383,
+      "kl": 0.0039646215736866,
+      "learning_rate": 4.894973780788722e-06,
+      "loss": 0.0002,
+      "reward": 0.88125,
+      "reward_std": 0.28942874893546106,
+      "rewards/custom_reward_simplified_v7_dblog": 0.88125,
+      "step": 440
+    },
+    {
+      "completion_length": 651.6625,
+      "epoch": 0.0035839153877398238,
+      "grad_norm": 0.21087874472141266,
+      "kl": 0.004210945626255125,
+      "learning_rate": 4.884292376870567e-06,
+      "loss": 0.0002,
+      "reward": 0.753125,
+      "reward_std": 0.29777742698788645,
+      "rewards/custom_reward_simplified_v7_dblog": 0.753125,
+      "step": 450
     }
   ],
   "logging_steps": 10,