Training in progress, step 1375, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b901f880fa9ed0f060f71cce70c866baf6b12ff9b46744f1cd5db7d6a751126
+oid sha256:8b671d4e43950bd338a109cd4eabb2547db024316e1a83a98c6aae93409db961
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0632dbbf29d2931fe7ce743e19d0f3cf69ee7a7d9e92be339d9792d785000ee2
+oid sha256:2e5e2265be877ae37fe18758b3d066d64e420b1d5aa11383c5587bbd880ac8b2
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa7f2184140c298d88f1de4da49013475309ad1f88b477c6a086754fa7764dc5
+oid sha256:624837cd6e7e41c76588d8ab24417e8a1710d14110400eb078f5e1b17702d42b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:023537b1d42d463489031d31c03e4c8fead35d65882bdcee8e6825976c4bcbf6
+oid sha256:5450b3c0b6570b6c09cd38a0ade4e53a34ac0c033a784959f9f2bdce58322982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01075174616321947,
+  "epoch": 0.010950852573649462,
   "eval_steps": 500,
-  "global_step": 1350,
+  "global_step": 1375,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1627,6 +1627,30 @@
       "reward_std": 0.29604131579399107,
       "rewards/custom_reward_simplified_v7_dblog": 0.79375,
       "step": 1350
+    },
+    {
+      "completion_length": 633.9125,
+      "epoch": 0.010831388727391467,
+      "grad_norm": 0.1637645810842514,
+      "kl": 0.00936238830909133,
+      "learning_rate": 2.3546379277238107e-06,
+      "loss": 0.0004,
+      "reward": 0.90625,
+      "reward_std": 0.324691192060709,
+      "rewards/custom_reward_simplified_v7_dblog": 0.90625,
+      "step": 1360
+    },
+    {
+      "completion_length": 674.03125,
+      "epoch": 0.010911031291563462,
+      "grad_norm": 0.2471015304327011,
+      "kl": 0.010726678185164928,
+      "learning_rate": 2.318355073193474e-06,
+      "loss": 0.0004,
+      "reward": 0.65625,
+      "reward_std": 0.21728940233588218,
+      "rewards/custom_reward_simplified_v7_dblog": 0.65625,
+      "step": 1370
     }
   ],
   "logging_steps": 10,