Training in progress, step 1250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca8baaba22487cdce42630abaf28904ed482a9cc8827520bc824bb81cd486cd4
+oid sha256:1b01a64a72b5add0f6fd2fb87887bf51cc687c3d81596e93d4bc43a3262efdc8
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50c6e305b6a0d4073f6216b5ff8f9f102df9985bb7e7ec1efec53cfd87ac3c
+oid sha256:362d1e054b84b0d500e8438627b240c7e2097ee86b8e098e8f3c941c83016f24
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2abe6090a2975a0c5e7fd37addef971ec2653163e71ac7336dc65e74c34c04f
+oid sha256:945a25d4c45d543ac1804f21f5b94dcfff3f3d66f6934f364600a8816d57e5dc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9debf92aca27ce6ace0aef79d370cac248bb98d16412d955b96820394066292d
+oid sha256:b1305a35e69c26a1911821f2a4173b0f97cfc01b88eb1cc64c99b91067e3e293
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00975621411106952,
+  "epoch": 0.00995532052149951,
   "eval_steps": 500,
-  "global_step": 1225,
+  "global_step": 1250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1471,6 +1471,42 @@
       "reward_std": 0.26154626756906507,
       "rewards/custom_reward_simplified_v7_dblog": 0.94375,
       "step": 1220
+    },
+    {
+      "completion_length": 635.0125,
+      "epoch": 0.009796035393155518,
+      "grad_norm": 0.14301441609859467,
+      "kl": 0.008189951698295773,
+      "learning_rate": 2.82631548055013e-06,
+      "loss": 0.0003,
+      "reward": 0.9,
+      "reward_std": 0.2126667931675911,
+      "rewards/custom_reward_simplified_v7_dblog": 0.9,
+      "step": 1230
+    },
+    {
+      "completion_length": 816.5375,
+      "epoch": 0.009875677957327514,
+      "grad_norm": 0.1681988686323166,
+      "kl": 0.01006167777813971,
+      "learning_rate": 2.7902322853130758e-06,
+      "loss": 0.0004,
+      "reward": 0.51875,
+      "reward_std": 0.27570038065314295,
+      "rewards/custom_reward_simplified_v7_dblog": 0.51875,
+      "step": 1240
+    },
+    {
+      "completion_length": 710.75,
+      "epoch": 0.00995532052149951,
+      "grad_norm": 0.09834864735603333,
+      "kl": 0.010588118969462813,
+      "learning_rate": 2.754087695457005e-06,
+      "loss": 0.0004,
+      "reward": 0.6625,
+      "reward_std": 0.19232839569449425,
+      "rewards/custom_reward_simplified_v7_dblog": 0.6625,
+      "step": 1250
     }
   ],
   "logging_steps": 10,