Training in progress, step 1875, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5394825a795e8c2ec586e2ccde14f9f1732bd83cb73a2e054c0fd16cab24bbf
+oid sha256:ab7a3cc73a57abaa32bade03bcebcd46587be72de73ccad8f65d675d659bd3c2
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3baa6fc86afbc2ac24ca4ccb3c82a2a206a33c1941bd40fbf22e526547f85bc
+oid sha256:16781c4c05f933a0d66537177cf999078ef923f2303c5757e160d0c77ddbe1d7
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bffd2e290b62c75abc87ca6dd76b6027bd06ea1ad6cc5c7d19bce5cce9b4ccc3
+oid sha256:60cf851845831763d89f8c634d4284cf46d7d7219c65e4abfb8aa8606aff0f23
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66c13a1a0518ee90714d59f79891d6fed6babf24ee82c1c888d7fca0cfbcc3ac
+oid sha256:096c9e47abe9885224f469325252f1a965fb84f05e97eef04fa163160aa871e9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014733874371819274,
+  "epoch": 0.014932980782249266,
   "eval_steps": 500,
-  "global_step": 1850,
+  "global_step": 1875,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2227,6 +2227,30 @@
       "reward_std": 0.32810748890042307,
       "rewards/custom_reward_simplified_v7_dblog": 0.690625,
       "step": 1850
+    },
+    {
+      "completion_length": 649.98125,
+      "epoch": 0.014813516935991271,
+      "grad_norm": 0.013280795887112617,
+      "kl": 0.01633880774024874,
+      "learning_rate": 7.322330470336314e-07,
+      "loss": 0.0007,
+      "reward": 0.91875,
+      "reward_std": 0.24432293996214866,
+      "rewards/custom_reward_simplified_v7_dblog": 0.91875,
+      "step": 1860
+    },
+    {
+      "completion_length": 669.09375,
+      "epoch": 0.014893159500163268,
+      "grad_norm": 0.2837064266204834,
+      "kl": 0.014348302804864942,
+      "learning_rate": 7.067097987017762e-07,
+      "loss": 0.0006,
+      "reward": 0.690625,
+      "reward_std": 0.2307182878255844,
+      "rewards/custom_reward_simplified_v7_dblog": 0.690625,
+      "step": 1870
     }
   ],
   "logging_steps": 10,