Training in progress, step 2225, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4c7ad171acc26eed08c341a9378f565ef79b0d0a49d48b275a4e629f66bde23
+oid sha256:77b4d8ec59c75cbd29c1373a150cd6676c15212c5086c6d8411cc0ba90aab5c6
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71b4efc088cbb155c5abb83cd9ebd1ed31f18f6945bd368a06eda5c8994bb46c
+oid sha256:f3b9397c2d7a6e54c8bdd82d78a1f67791c66fe1c65a90cafd67110df65ca963
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3f4587cc9c05047bacd95a95b2bdbe954322fbf3f11d01e0da5065ae33b61af
+oid sha256:62563564114f07c55d673b83157579ed006c954c798b78b19cdb4e6590a7a7e5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acc019d4a9c743ca29c0f366c75eefcb563cbb67c7d81d654ecdcda771a351f4
+oid sha256:8815a24b224041b13ab7cbf09bd12ddf87977f385c87ba515e891819a21f4935
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01752136411783914,
+  "epoch": 0.01772047052826913,
   "eval_steps": 500,
-  "global_step": 2200,
+  "global_step": 2225,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2647,6 +2647,30 @@
       "reward_std": 0.29732906967401507,
       "rewards/custom_reward_simplified_v7_dblog": 0.834375,
       "step": 2200
+    },
+    {
+      "completion_length": 618.19375,
+      "epoch": 0.017601006682011134,
+      "grad_norm": 0.25354552268981934,
+      "kl": 0.016854454204440115,
+      "learning_rate": 9.485143881596715e-08,
+      "loss": 0.0007,
+      "reward": 0.85625,
+      "reward_std": 0.25810291022062304,
+      "rewards/custom_reward_simplified_v7_dblog": 0.85625,
+      "step": 2210
+    },
+    {
+      "completion_length": 638.425,
+      "epoch": 0.01768064924618313,
+      "grad_norm": 0.2272520810365677,
+      "kl": 0.018312370544299482,
+      "learning_rate": 8.518543427732951e-08,
+      "loss": 0.0007,
+      "reward": 0.753125,
+      "reward_std": 0.2212974861264229,
+      "rewards/custom_reward_simplified_v7_dblog": 0.753125,
+      "step": 2220
     }
   ],
   "logging_steps": 10,