Training in progress, step 1725, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb4a26b564992bfe1b0c0cbf9877d71a7e4c4cabeff18b9fcdc775fdba1b254f
+oid sha256:1ec28caf9a7ff7339d966b76d71e03bfe0a7ddf0961ba497eb5863537c0b953c
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bda5b6a4da0480b964d69c900d61e56ab25544d0c3fbb12fa357689206e9625d
+oid sha256:a0c28c48e295c2eae425225e3940ce4a7e1793431d494d6c92db17a64cdfff4a
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21e6e0ff9935bb592aa01d75fb327a21b659c1135b9f0f607483a3ede13d0d3b
+oid sha256:4de3cd10f3b57ed5bbaf46e4112a9247d3b0d53ea96ac99da33c61ba9e7dfc33
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6a11a087092ce528653bb5e030a3a014f4a88c8ff1a2a24bc7e40980baafb9d
+oid sha256:7ac7c23214b73086bc20400e4b1d423d1e1380c5dcdbe69b8668e35e420cebc4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013539235909239333,
+  "epoch": 0.013738342319669325,
   "eval_steps": 500,
-  "global_step": 1700,
+  "global_step": 1725,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2047,6 +2047,30 @@
       "reward_std": 0.277196903526783,
       "rewards/custom_reward_simplified_v7_dblog": 0.653125,
       "step": 1700
+    },
+    {
+      "completion_length": 637.9625,
+      "epoch": 0.01361887847341133,
+      "grad_norm": 0.2428259700536728,
+      "kl": 0.014563425956293941,
+      "learning_rate": 1.1567509791329402e-06,
+      "loss": 0.0006,
+      "reward": 0.865625,
+      "reward_std": 0.23967689424753189,
+      "rewards/custom_reward_simplified_v7_dblog": 0.865625,
+      "step": 1710
+    },
+    {
+      "completion_length": 722.925,
+      "epoch": 0.013698521037583325,
+      "grad_norm": 0.21737752854824066,
+      "kl": 0.014987437543459237,
+      "learning_rate": 1.1262275548229852e-06,
+      "loss": 0.0006,
+      "reward": 0.725,
+      "reward_std": 0.26179009675979614,
+      "rewards/custom_reward_simplified_v7_dblog": 0.725,
+      "step": 1720
     }
   ],
   "logging_steps": 10,