Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35af942f4f7e0ab45db7f903018b6cf71ae51337cced1f8f73b46d54b9a82ed8
+oid sha256:5404a6332b8b6a72fe3311d541474e0a4a7cac835f882aa6e4c17edbd0bbdc93
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57c63bb7393c415a2eb7afbc5dedea61fdbc7a7f7559d8b48dbacb220b0a5585
+oid sha256:cefc42368c6b996015654464ec319b8c9bb9b027ccb43bcc42a07681d8af08da
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba432550a2dc4d764434bf1f11c92a249b479470479a548999a9d5143e159384
+oid sha256:746dea9b4afdfb917ab5fa6ac25927dc904d33946eaf20eb284f96236a13cb73
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fdd2976348f35f1abb273dc4e2e2403036ea1ad8a823c211f3272a4ea13d175
+oid sha256:f1a555b4453d301486503fb1fa9fdc0a69449ba7dabc413ecf4077ad99751b4d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016525832065689187,
+  "epoch": 0.016724938476119177,
   "eval_steps": 500,
-  "global_step": 2075,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2491,6 +2491,42 @@
       "reward_std": 0.24814453721046448,
       "rewards/custom_reward_simplified_v7_dblog": 0.89375,
       "step": 2070
+    },
+    {
+      "completion_length": 710.6875,
+      "epoch": 0.016565653347775183,
+      "grad_norm": 0.20649504661560059,
+      "kl": 0.018557686172425748,
+      "learning_rate": 2.6591839919146963e-07,
+      "loss": 0.0007,
+      "reward": 0.828125,
+      "reward_std": 0.34967463091015816,
+      "rewards/custom_reward_simplified_v7_dblog": 0.828125,
+      "step": 2080
+    },
+    {
+      "completion_length": 642.375,
+      "epoch": 0.016645295911947182,
+      "grad_norm": 0.016043314710259438,
+      "kl": 0.018814650364220142,
+      "learning_rate": 2.4983647033969714e-07,
+      "loss": 0.0008,
+      "reward": 0.859375,
+      "reward_std": 0.3110216066241264,
+      "rewards/custom_reward_simplified_v7_dblog": 0.859375,
+      "step": 2090
+    },
+    {
+      "completion_length": 686.65625,
+      "epoch": 0.016724938476119177,
+      "grad_norm": 0.26343393325805664,
+      "kl": 0.019906887435354292,
+      "learning_rate": 2.3423053240837518e-07,
+      "loss": 0.0008,
+      "reward": 0.715625,
+      "reward_std": 0.17099330350756645,
+      "rewards/custom_reward_simplified_v7_dblog": 0.715625,
+      "step": 2100
     }
   ],
   "logging_steps": 10,