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:a656f61ae1ccd60f5456798788c8e6ded39b418346d6fe6071eb8ce468298a83
+oid sha256:ff241d617f452617d3c88f6cf63325935d4668c5daf5e939cf72829f92a221d4
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf849eb44752b2c9a42282b0505698ef4c3181196d5a7e2c98af9389f0ba6ef6
+oid sha256:1870f17179349635d5e9f8dc264de59804f82c37fb07d8c3e59aa2307ca2761a
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd3ccbab0f5afd279e81643827121534f4d8480da4449b3d948c3974c92f9bbd
+oid sha256:fb5fd2bad97b0505323e94353254cc1ebf7b1bbfc6106a6a54db604a83d738b3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8241f030a944f045c9ceca4728f16fdc2a35629a475d8a3997b745440061990
+oid sha256:bf5539fcaa2354df9ab3f6e01030e649c726b26d278c21ce5b06138c07200265
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0031857025668798433,
+  "epoch": 0.0035839153877398238,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -487,6 +487,66 @@
       "reward_std": 0.09467698186635971,
       "rewards/custom_reward_logic_v2": 0.09312500022351741,
       "step": 400
+    },
+    {
+      "completion_length": 21.9125,
+      "epoch": 0.0032653451310518393,
+      "grad_norm": 0.12919628620147705,
+      "kl": 0.3515960440039635,
+      "learning_rate": 2.82631548055013e-06,
+      "loss": 0.0141,
+      "reward": 0.07376250103116036,
+      "reward_std": 0.15707473903894426,
+      "rewards/custom_reward_logic_v2": 0.07376250103116036,
+      "step": 410
+    },
+    {
+      "completion_length": 20.325,
+      "epoch": 0.0033449876952238353,
+      "grad_norm": 0.08202961087226868,
+      "kl": 0.34852803200483323,
+      "learning_rate": 2.717889356869146e-06,
+      "loss": 0.0139,
+      "reward": 0.2074999999254942,
+      "reward_std": 0.11485048606991768,
+      "rewards/custom_reward_logic_v2": 0.2074999999254942,
+      "step": 420
+    },
+    {
+      "completion_length": 19.7375,
+      "epoch": 0.0034246302593958313,
+      "grad_norm": 1.5309367179870605,
+      "kl": 0.339575307816267,
+      "learning_rate": 2.6090484684133406e-06,
+      "loss": 0.0136,
+      "reward": 0.03375000059604645,
+      "reward_std": 0.08364979848265648,
+      "rewards/custom_reward_logic_v2": 0.03375000059604645,
+      "step": 430
+    },
+    {
+      "completion_length": 29.5375,
+      "epoch": 0.0035042728235678278,
+      "grad_norm": 0.08438611030578613,
+      "kl": 0.34286700189113617,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0137,
+      "reward": 0.08044999912381172,
+      "reward_std": 0.16319628208875656,
+      "rewards/custom_reward_logic_v2": 0.08044999912381172,
+      "step": 440
+    },
+    {
+      "completion_length": 23.2125,
+      "epoch": 0.0035839153877398238,
+      "grad_norm": 0.11283387243747711,
+      "kl": 0.3263735562562943,
+      "learning_rate": 2.3909515315866606e-06,
+      "loss": 0.0131,
+      "reward": 0.11125000230967999,
+      "reward_std": 0.10089804157614708,
+      "rewards/custom_reward_logic_v2": 0.11125000230967999,
+      "step": 450
     }
   ],
   "logging_steps": 10,