Training in progress, step 2125, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5404a6332b8b6a72fe3311d541474e0a4a7cac835f882aa6e4c17edbd0bbdc93
+oid sha256:5e4cdedefbc08e52a106dd1cda00ce357a19a652b9800eb784f0f1307cc43d1f
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cefc42368c6b996015654464ec319b8c9bb9b027ccb43bcc42a07681d8af08da
+oid sha256:65fb08110ee38613bcd192ba1aba3314492e8466845e6293f310b5afb02a7b1e
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:746dea9b4afdfb917ab5fa6ac25927dc904d33946eaf20eb284f96236a13cb73
+oid sha256:8c3700e8b436e0bb6d4386467f582113bce4defdd80381438810f0ff98ab850a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1a555b4453d301486503fb1fa9fdc0a69449ba7dabc413ecf4077ad99751b4d
+oid sha256:823f545a614848455ef557579867553ca1e0ed28d34695c57c4a484f3da883fe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016724938476119177,
+  "epoch": 0.016924044886549167,
   "eval_steps": 500,
-  "global_step": 2100,
+  "global_step": 2125,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2527,6 +2527,30 @@
       "reward_std": 0.17099330350756645,
       "rewards/custom_reward_simplified_v7_dblog": 0.715625,
       "step": 2100
+    },
+    {
+      "completion_length": 656.8,
+      "epoch": 0.016804581040291172,
+      "grad_norm": 0.01307599525898695,
+      "kl": 0.020065448177047075,
+      "learning_rate": 2.1910388661746495e-07,
+      "loss": 0.0008,
+      "reward": 0.8,
+      "reward_std": 0.20212240219116212,
+      "rewards/custom_reward_simplified_v7_dblog": 0.8,
+      "step": 2110
+    },
+    {
+      "completion_length": 714.25625,
+      "epoch": 0.01688422360446317,
+      "grad_norm": 0.2202935814857483,
+      "kl": 0.02329984272364527,
+      "learning_rate": 2.044597327993153e-07,
+      "loss": 0.0009,
+      "reward": 0.7875,
+      "reward_std": 0.307485481351614,
+      "rewards/custom_reward_simplified_v7_dblog": 0.7875,
+      "step": 2120
     }
   ],
   "logging_steps": 10,