Training in progress, step 2175, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b6cad65a1239e0e03962e7f4ef559abd941989cf40db0a80d0189112e42eb72
+oid sha256:01fa6ef01a6129f93fc6ae1d3d024e5aafd6072c7697d70fcd0f206c28326654
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b8a70c19523d8c6e08995eab7545028af88fed635908dfc05a7946675d3475a
+oid sha256:01490b1e711822873356262173954b6ce900ed9a0e2af7ae5d7985a1d3af5ce6
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9759af3432ea363e3c64dd28f0228b81e57792402129de6cb79a2e5033a37e1
+oid sha256:67ef7103bbe42875565af4f48a70ea9a7ff44b820a58a131a92456b4832dc565
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e6aaab334f3a9481d30ef9495cbe830ba9fac2b9efdeee34a635582fea7ec27
+oid sha256:bebfbbbed70f5ae11d19e53b3a1c1b070d9e484583c2d20b71f9c3ebd56e5e47
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017123151296979156,
+  "epoch": 0.01732225770740915,
   "eval_steps": 500,
-  "global_step": 2150,
+  "global_step": 2175,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2587,6 +2587,30 @@
       "reward_std": 0.2917635254561901,
       "rewards/custom_reward_simplified_v7_dblog": 0.7125,
       "step": 2150
+    },
+    {
+      "completion_length": 702.025,
+      "epoch": 0.017202793861151155,
+      "grad_norm": 0.008707295171916485,
+      "kl": 0.01914967515040189,
+      "learning_rate": 1.507684480352292e-07,
+      "loss": 0.0008,
+      "reward": 0.821875,
+      "reward_std": 0.2691307656466961,
+      "rewards/custom_reward_simplified_v7_dblog": 0.821875,
+      "step": 2160
+    },
+    {
+      "completion_length": 704.90625,
+      "epoch": 0.01728243642532315,
+      "grad_norm": 0.1347748190164566,
+      "kl": 0.017809830722399056,
+      "learning_rate": 1.3858115683098832e-07,
+      "loss": 0.0007,
+      "reward": 0.9,
+      "reward_std": 0.30937733352184293,
+      "rewards/custom_reward_simplified_v7_dblog": 0.9,
+      "step": 2170
     }
   ],
   "logging_steps": 10,