Training in progress, step 1750, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ec28caf9a7ff7339d966b76d71e03bfe0a7ddf0961ba497eb5863537c0b953c
+oid sha256:64cb29f82be51963b1c87a3edf410599592d499ccb583a2211299eabdac88a5e
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c28c48e295c2eae425225e3940ce4a7e1793431d494d6c92db17a64cdfff4a
+oid sha256:ba89ced11fa4b1eb1cfa02eb7f638c31d45ea49afc6a96d68cbdaf46dd9663d2
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4de3cd10f3b57ed5bbaf46e4112a9247d3b0d53ea96ac99da33c61ba9e7dfc33
+oid sha256:11f42b997535391b4778f6818a4f5d5cc944d2434ea0edc70a8def90290e971a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac7c23214b73086bc20400e4b1d423d1e1380c5dcdbe69b8668e35e420cebc4
+oid sha256:f817dba2e28a76d635b3c9e18d88eacd11804518703ee89b156fb1819d644283
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013738342319669325,
+  "epoch": 0.013937448730099314,
   "eval_steps": 500,
-  "global_step": 1725,
+  "global_step": 1750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2071,6 +2071,42 @@
       "reward_std": 0.26179009675979614,
       "rewards/custom_reward_simplified_v7_dblog": 0.725,
       "step": 1720
+    },
+    {
+      "completion_length": 633.31875,
+      "epoch": 0.013778163601755322,
+      "grad_norm": 0.22654354572296143,
+      "kl": 0.013244283269159496,
+      "learning_rate": 1.0959947330412681e-06,
+      "loss": 0.0005,
+      "reward": 0.921875,
+      "reward_std": 0.2066536843776703,
+      "rewards/custom_reward_simplified_v7_dblog": 0.921875,
+      "step": 1730
+    },
+    {
+      "completion_length": 615.29375,
+      "epoch": 0.013857806165927319,
+      "grad_norm": 0.22673261165618896,
+      "kl": 0.014753601653501392,
+      "learning_rate": 1.0660589091223854e-06,
+      "loss": 0.0006,
+      "reward": 0.815625,
+      "reward_std": 0.30853241235017775,
+      "rewards/custom_reward_simplified_v7_dblog": 0.815625,
+      "step": 1740
+    },
+    {
+      "completion_length": 630.3625,
+      "epoch": 0.013937448730099314,
+      "grad_norm": 0.012196751311421394,
+      "kl": 0.01440229129511863,
+      "learning_rate": 1.0364264155751489e-06,
+      "loss": 0.0006,
+      "reward": 0.915625,
+      "reward_std": 0.23927971720695496,
+      "rewards/custom_reward_simplified_v7_dblog": 0.915625,
+      "step": 1750
     }
   ],
   "logging_steps": 10,