Training in progress, step 1900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab7a3cc73a57abaa32bade03bcebcd46587be72de73ccad8f65d675d659bd3c2
+oid sha256:013e1a4a2e514b45c1477302c11e1065adcc3bbe1c09bc675409e2c5ae75c7df
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16781c4c05f933a0d66537177cf999078ef923f2303c5757e160d0c77ddbe1d7
+oid sha256:ea3f86dcd6bd8021e80606e175ae4af07751c3370190d4d053658d8ae6e55f26
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60cf851845831763d89f8c634d4284cf46d7d7219c65e4abfb8aa8606aff0f23
+oid sha256:81580e1e88878dfebd843045199ab5edec2e92f7c132f2ea86bcce1ce7f5e2ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:096c9e47abe9885224f469325252f1a965fb84f05e97eef04fa163160aa871e9
+oid sha256:875915e5d6f2e2f0e0a7a4a850b61c3c410ff67126d9daeb7cdaa64d28801ee5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014932980782249266,
+  "epoch": 0.015132087192679255,
   "eval_steps": 500,
-  "global_step": 1875,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2251,6 +2251,42 @@
       "reward_std": 0.2307182878255844,
       "rewards/custom_reward_simplified_v7_dblog": 0.690625,
       "step": 1870
+    },
+    {
+      "completion_length": 662.9625,
+      "epoch": 0.014972802064335263,
+      "grad_norm": 0.25689443945884705,
+      "kl": 0.01656266492791474,
+      "learning_rate": 6.815658960673782e-07,
+      "loss": 0.0007,
+      "reward": 0.85625,
+      "reward_std": 0.22758262380957603,
+      "rewards/custom_reward_simplified_v7_dblog": 0.85625,
+      "step": 1880
+    },
+    {
+      "completion_length": 719.24375,
+      "epoch": 0.01505244462850726,
+      "grad_norm": 0.22542421519756317,
+      "kl": 0.01744127394631505,
+      "learning_rate": 6.568066579746901e-07,
+      "loss": 0.0007,
+      "reward": 0.76875,
+      "reward_std": 0.2790658660233021,
+      "rewards/custom_reward_simplified_v7_dblog": 0.76875,
+      "step": 1890
+    },
+    {
+      "completion_length": 633.64375,
+      "epoch": 0.015132087192679255,
+      "grad_norm": 0.00903425831347704,
+      "kl": 0.014375879801809788,
+      "learning_rate": 6.324373218975105e-07,
+      "loss": 0.0006,
+      "reward": 0.725,
+      "reward_std": 0.2382744610309601,
+      "rewards/custom_reward_simplified_v7_dblog": 0.725,
+      "step": 1900
     }
   ],
   "logging_steps": 10,