Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b4a21428d6c7636bb544f872b5623df6e884e7437687862a5f3d04f923b6d48
+oid sha256:51885749d7e0b43a3daa2be73b7b2a85f53f51bf3f2b4c4f68f741d5cc3d7865
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e508ee4172c367fc5f059f559b7960256770a6c6ad6409ef65eb2f354d318ca6
+oid sha256:37212643c4136b70f407996bc4c91afa08c3933531b919b7c6db8a24b9a4f1ae
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da9a63ca771fcdbabf21b707c3680464f1a559a6fb7c42095ebd8941c7fa90b5
+oid sha256:1b6edf3402d665dc804156e1f42b2872a7f5e9fbf05da017ddad3c4fe71434af
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:373aad709c251f92b29c15e15959fdc2aaf4ffb38eba8495b44748a1f4d8fb58
+oid sha256:8ec9a27cf5cbc363143d5683468f5f375f2f3889ae8160526593a29051413551
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0021901705147298924,
+  "epoch": 0.0023892769251598824,
   "eval_steps": 500,
-  "global_step": 275,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -331,6 +331,42 @@
       "reward_std": 0.1583670809864998,
       "rewards/custom_reward_simplified_v7_dblog": 0.653125,
       "step": 270
+    },
+    {
+      "completion_length": 646.63125,
+      "epoch": 0.0022299917968158904,
+      "grad_norm": 0.11776451766490936,
+      "kl": 0.0026803009008290247,
+      "learning_rate": 4.995770395678171e-06,
+      "loss": 0.0001,
+      "reward": 0.78125,
+      "reward_std": 0.37105962783098223,
+      "rewards/custom_reward_simplified_v7_dblog": 0.78125,
+      "step": 280
+    },
+    {
+      "completion_length": 850.5125,
+      "epoch": 0.0023096343609878864,
+      "grad_norm": 0.17029190063476562,
+      "kl": 0.0011812534503405914,
+      "learning_rate": 4.993392291751431e-06,
+      "loss": 0.0,
+      "reward": 0.503125,
+      "reward_std": 0.2320079453289509,
+      "rewards/custom_reward_simplified_v7_dblog": 0.503125,
+      "step": 290
+    },
+    {
+      "completion_length": 774.4125,
+      "epoch": 0.0023892769251598824,
+      "grad_norm": 0.17417992651462555,
+      "kl": 0.001456298804259859,
+      "learning_rate": 4.990486745229364e-06,
+      "loss": 0.0001,
+      "reward": 0.621875,
+      "reward_std": 0.24568462520837783,
+      "rewards/custom_reward_simplified_v7_dblog": 0.621875,
+      "step": 300
     }
   ],
   "logging_steps": 10,