Training in progress, step 1575, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4620c952d9d47f51b52dbaa4d676d99f0fa4424c13c706daf27aef599e4f2780
+oid sha256:7cacbbfc56d391184888aa9988c9623102b11e0c5c6148c788c143ab677975a0
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dcd3d1e5ce9aeb2f3a0a439162a6354e3a87bdd42c2d824aa351222059be0bd
+oid sha256:cb171f10034814744a50a6706f15be399005a3d17ff58bf5a682ba1f7e18f775
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3862494dcb8330500216500c3c10e90221d897be72203e9a311c19db30c18205
+oid sha256:876f813d0b3daa10f80151c471970ca9ac357d5142b2911eac6c7f304a8b5d03
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbfbb7156838856bc44aea3d88f369f30c1abce4e6c21899507c2f357e97b51c
+oid sha256:d3d7fb31ee0a8472be5b464827ea90bb43e1dac4d2373a8313c33126d4dc9adc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012344597446659392,
+  "epoch": 0.012543703857089384,
   "eval_steps": 500,
-  "global_step": 1550,
+  "global_step": 1575,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1867,6 +1867,30 @@
       "reward_std": 0.3321776181459427,
       "rewards/custom_reward_simplified_v7_dblog": 0.84375,
       "step": 1550
+    },
+    {
+      "completion_length": 645.28125,
+      "epoch": 0.01242424001083139,
+      "grad_norm": 0.1851159930229187,
+      "kl": 0.014482964109629393,
+      "learning_rate": 1.6449496416858285e-06,
+      "loss": 0.0006,
+      "reward": 0.85625,
+      "reward_std": 0.20507382601499557,
+      "rewards/custom_reward_simplified_v7_dblog": 0.85625,
+      "step": 1560
+    },
+    {
+      "completion_length": 614.08125,
+      "epoch": 0.012503882575003384,
+      "grad_norm": 0.27418458461761475,
+      "kl": 0.013118641986511647,
+      "learning_rate": 1.6108730954628093e-06,
+      "loss": 0.0005,
+      "reward": 0.79375,
+      "reward_std": 0.2820776253938675,
+      "rewards/custom_reward_simplified_v7_dblog": 0.79375,
+      "step": 1570
     }
   ],
   "logging_steps": 10,