Training in progress, step 1175, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b87a7124fc823146a12cbeaefbe5ff8d91326cefab763555aa61dbbb9e056fab
+oid sha256:780adb9accd35e89fa4d6e0b16d07afb98a5ad312c157c14f5c6fc3688b6b435
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f14effc9368161c55b1d77fbb7e90bb1cd9af0086afde89e1a683d869fb3248
+oid sha256:a8186daf7088705064b8cda2fa05ea5b15ac3829a5cc745cfd0463cf0775d065
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b6ca00cea62eabd929fd77d62694b267d47c0603af124f659274f264d0bf70b
+oid sha256:f4eda2caa8c1d334010b2826a85bd0fa5d6353a1455cace044b4ee905e374a02
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15a1625baaf061099e4aa140afa72e1a2a32a1a3e25d7baf8a019a63d52d6e43
+oid sha256:a7aa6200e076e6b4e3b8c147bb3db3fdb1f862f67341ccf617eae90a633431d6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009158894879779549,
+  "epoch": 0.00935800129020954,
   "eval_steps": 500,
-  "global_step": 1150,
+  "global_step": 1175,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1387,6 +1387,30 @@
       "reward_std": 0.29204289317131044,
       "rewards/custom_reward_simplified_v7_dblog": 0.6875,
       "step": 1150
+    },
+    {
+      "completion_length": 641.88125,
+      "epoch": 0.009238537443951545,
+      "grad_norm": 0.007003675680607557,
+      "kl": 0.007272082474082708,
+      "learning_rate": 3.0765396768561005e-06,
+      "loss": 0.0003,
+      "reward": 0.875,
+      "reward_std": 0.2666669487953186,
+      "rewards/custom_reward_simplified_v7_dblog": 0.875,
+      "step": 1160
+    },
+    {
+      "completion_length": 645.55625,
+      "epoch": 0.009318180008123542,
+      "grad_norm": 0.005993107333779335,
+      "kl": 0.00769920782186091,
+      "learning_rate": 3.0410990348452572e-06,
+      "loss": 0.0003,
+      "reward": 0.846875,
+      "reward_std": 0.29315834268927576,
+      "rewards/custom_reward_simplified_v7_dblog": 0.846875,
+      "step": 1170
     }
   ],
   "logging_steps": 10,