Training in progress, step 1025, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f7212aa3c90ea7765b266c91a1c37f7ee786da363e1b2a93ee6806ed670ba7
+oid sha256:acf8b65d26bdfc64b69f3e90608a32c94c2a3f27197ae54a284d5b9245404c3f
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3a2e36062ee9a9b1c0cbf56796f1692510713b40f9b4e03b6abb5a07dd0001f
+oid sha256:7e9de85eb312429ee69f8e14426f2f3e769474f3fe34dfe733c06674a025d84a
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5120bfa84229b68a7f7f0683b8775173af411a1296a86c5d4ff0563ac31f3baf
+oid sha256:07d2e06cad0b91681c597821a2e099149e7db006cbb9841142cb4b670c31efa5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2085f58dcd21b346b3f76c21f730c3fd85efe25685c7b50b88b346f628559d6
+oid sha256:09a5009ee8663da9f77ac877c439f2699dd897893282ed3986b78e107ce06efe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007964256417199608,
+  "epoch": 0.008163362827629599,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1025,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1207,6 +1207,30 @@
       "reward_std": 0.3684743233025074,
       "rewards/custom_reward_simplified_v7_dblog": 0.83125,
       "step": 1000
+    },
+    {
+      "completion_length": 702.75,
+      "epoch": 0.008043898981371604,
+      "grad_norm": 0.25571930408477783,
+      "kl": 0.0066094894893467425,
+      "learning_rate": 3.5893870247926986e-06,
+      "loss": 0.0003,
+      "reward": 0.690625,
+      "reward_std": 0.27608626931905744,
+      "rewards/custom_reward_simplified_v7_dblog": 0.690625,
+      "step": 1010
+    },
+    {
+      "completion_length": 634.18125,
+      "epoch": 0.0081235415455436,
+      "grad_norm": 0.006109423469752073,
+      "kl": 0.006831615581177175,
+      "learning_rate": 3.556545654351749e-06,
+      "loss": 0.0003,
+      "reward": 0.85625,
+      "reward_std": 0.2714505262672901,
+      "rewards/custom_reward_simplified_v7_dblog": 0.85625,
+      "step": 1020
     }
   ],
   "logging_steps": 10,