Training in progress, step 1425, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:867703907f2f1a76d67d7ff388c676b39a85c5d30dc8a0e586099091a1cd7577
+oid sha256:418230f6279ba94346b4a25eaaedad80a6e32f2d21e69114c0a6c87588ebceac
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d737b0cdc3d7c98a38802e1705694cfd222a94ef163897cda48e14bd9459edec
+oid sha256:c7e5b0e1a6742969cbb3193e671a8e477f4a0f699e78d37903126a313c6d98d4
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff0ae421dd10b5797aff22abbbc03d9938f22a0c3263b843629b6ea2e7daedec
+oid sha256:9cef8571d01f4838718fba5380f91f15fe0df712d95099c4c8c70dcaff3de787
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54cc976c79460b9d33f11e645b03612019eb0d01bc3da2482d4f71d55270ef6e
+oid sha256:8c84f1b8f26cb0725d070a7236f279e1e8fdd989b9e7956aaf12382e1101fc41
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011149958984079451,
+  "epoch": 0.011349065394509441,
   "eval_steps": 500,
-  "global_step": 1400,
+  "global_step": 1425,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1687,6 +1687,30 @@
       "reward_std": 0.27883157432079314,
       "rewards/custom_reward_simplified_v7_dblog": 0.878125,
       "step": 1400
+    },
+    {
+      "completion_length": 687.5125,
+      "epoch": 0.011229601548251448,
+      "grad_norm": 0.22397036850452423,
+      "kl": 0.012094876240007579,
+      "learning_rate": 2.173684519449872e-06,
+      "loss": 0.0005,
+      "reward": 0.834375,
+      "reward_std": 0.28866922557353974,
+      "rewards/custom_reward_simplified_v7_dblog": 0.834375,
+      "step": 1410
+    },
+    {
+      "completion_length": 661.26875,
+      "epoch": 0.011309244112423443,
+      "grad_norm": 0.2519758939743042,
+      "kl": 0.011373027227818966,
+      "learning_rate": 2.1376703517318835e-06,
+      "loss": 0.0005,
+      "reward": 0.853125,
+      "reward_std": 0.32343359887599943,
+      "rewards/custom_reward_simplified_v7_dblog": 0.853125,
+      "step": 1420
     }
   ],
   "logging_steps": 10,