Training in progress, step 825, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d558d1688ac2b0773f776e1b01f11ad8d6b0eb98b60b2c83c0a92982a67ea9ef
+oid sha256:be08547166dacd1b7d161c2f41cf30693b0c59e1e628537d5d7645d2ea4fcbbf
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7a8d7e6d4c609cc4c9c06b2f897ea7480f74fe48ee69c6f4734353d452ce614
+oid sha256:718a80129d5413c606f827de20a6c1acb27fb76dcd018a018ecd6df21b62763d
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4221eac67cb2222c2e69aeda63b681815cb4044bdeac0d3934f95aca477f1f85
+oid sha256:657c2c45e0b68fdd44aeab5a6c64190c8d2f3733cd86796d96b53daec5b3952e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a1181d7867e1e99d3e40b537197ac0f6f5cff5e55e17adc3195122e9858dab9
+oid sha256:2fc859065f77e5cbabb1b099e6f8bcbc876c53f6186972adb97152a1da9fa4d4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006371405133759687,
+  "epoch": 0.006570511544189677,
   "eval_steps": 500,
-  "global_step": 800,
+  "global_step": 825,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -967,6 +967,30 @@
       "reward_std": 0.25832219421863556,
       "rewards/custom_reward_simplified_v7_dblog": 0.746875,
       "step": 800
+    },
+    {
+      "completion_length": 652.925,
+      "epoch": 0.006451047697931683,
+      "grad_norm": 0.0062674470245838165,
+      "kl": 0.006221415114123374,
+      "learning_rate": 4.188975519039151e-06,
+      "loss": 0.0002,
+      "reward": 0.73125,
+      "reward_std": 0.3172403134405613,
+      "rewards/custom_reward_simplified_v7_dblog": 0.73125,
+      "step": 810
+    },
+    {
+      "completion_length": 668.63125,
+      "epoch": 0.006530690262103679,
+      "grad_norm": 0.13624051213264465,
+      "kl": 0.0063671735813841225,
+      "learning_rate": 4.161989664034844e-06,
+      "loss": 0.0003,
+      "reward": 0.684375,
+      "reward_std": 0.24903304055333136,
+      "rewards/custom_reward_simplified_v7_dblog": 0.684375,
+      "step": 820
     }
   ],
   "logging_steps": 10,