Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01fa6ef01a6129f93fc6ae1d3d024e5aafd6072c7697d70fcd0f206c28326654
+oid sha256:e4c7ad171acc26eed08c341a9378f565ef79b0d0a49d48b275a4e629f66bde23
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01490b1e711822873356262173954b6ce900ed9a0e2af7ae5d7985a1d3af5ce6
+oid sha256:71b4efc088cbb155c5abb83cd9ebd1ed31f18f6945bd368a06eda5c8994bb46c
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ef7103bbe42875565af4f48a70ea9a7ff44b820a58a131a92456b4832dc565
+oid sha256:b3f4587cc9c05047bacd95a95b2bdbe954322fbf3f11d01e0da5065ae33b61af
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bebfbbbed70f5ae11d19e53b3a1c1b070d9e484583c2d20b71f9c3ebd56e5e47
+oid sha256:acc019d4a9c743ca29c0f366c75eefcb563cbb67c7d81d654ecdcda771a351f4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01732225770740915,
+  "epoch": 0.01752136411783914,
   "eval_steps": 500,
-  "global_step": 2175,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2611,6 +2611,42 @@
       "reward_std": 0.30937733352184293,
       "rewards/custom_reward_simplified_v7_dblog": 0.9,
       "step": 2170
+    },
+    {
+      "completion_length": 650.13125,
+      "epoch": 0.017362078989495145,
+      "grad_norm": 0.013826651498675346,
+      "kl": 0.017964964429847897,
+      "learning_rate": 1.2689339106741529e-07,
+      "loss": 0.0007,
+      "reward": 0.821875,
+      "reward_std": 0.2382724992930889,
+      "rewards/custom_reward_simplified_v7_dblog": 0.821875,
+      "step": 2180
+    },
+    {
+      "completion_length": 574.075,
+      "epoch": 0.01744172155366714,
+      "grad_norm": 0.21891085803508759,
+      "kl": 0.013470867811702193,
+      "learning_rate": 1.1570762312943295e-07,
+      "loss": 0.0005,
+      "reward": 0.9875,
+      "reward_std": 0.2131643146276474,
+      "rewards/custom_reward_simplified_v7_dblog": 0.9875,
+      "step": 2190
+    },
+    {
+      "completion_length": 645.95,
+      "epoch": 0.01752136411783914,
+      "grad_norm": 0.28153711557388306,
+      "kl": 0.01899058516137302,
+      "learning_rate": 1.0502621921127776e-07,
+      "loss": 0.0008,
+      "reward": 0.834375,
+      "reward_std": 0.29732906967401507,
+      "rewards/custom_reward_simplified_v7_dblog": 0.834375,
+      "step": 2200
     }
   ],
   "logging_steps": 10,