Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc93f9835831dfe4fe8f3fabe09b29fc36f37216ea398f53ad427fb270ac8fe5
+oid sha256:97bd2071c863777af98b0e0e6835dfbd00b846cf114dd8805232a1e59165eb4d
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96b7c7d4975d19f24910799848311416fe9ce4376edbc7f5c1ce181682b8608b
+oid sha256:8b07f59c35dc209b4c9a5c3ea67c4ff82d683bff7ee192361d73fa058b15b139
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce3fefcac352ac4ee619c7ff01acc8acab65caca37da4199453b9a9441a77444
+oid sha256:b84da873207bf99b33af0e8b6206521d9a66d95873145146735310919d6f6590
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9d2f48ad4251bd6b293d199cd40a6a67cdcf63f7330a6380c30e1422c7eaee0
+oid sha256:e33b54a8302eb57494695935487eaaa98a78a3203f913dcc4eaf73f18edd66c0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011747278215369422,
+  "epoch": 0.011946384625799411,
   "eval_steps": 500,
-  "global_step": 1475,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1771,6 +1771,42 @@
       "reward_std": 0.21832374781370162,
       "rewards/custom_reward_simplified_v7_dblog": 0.64375,
       "step": 1470
+    },
+    {
+      "completion_length": 722.06875,
+      "epoch": 0.01178709949745542,
+      "grad_norm": 0.13200955092906952,
+      "kl": 0.013854384049773216,
+      "learning_rate": 1.9234603231439e-06,
+      "loss": 0.0006,
+      "reward": 0.790625,
+      "reward_std": 0.2784456007182598,
+      "rewards/custom_reward_simplified_v7_dblog": 0.790625,
+      "step": 1480
+    },
+    {
+      "completion_length": 664.46875,
+      "epoch": 0.011866742061627416,
+      "grad_norm": 0.14230677485466003,
+      "kl": 0.012553655169904232,
+      "learning_rate": 1.8881416401141905e-06,
+      "loss": 0.0005,
+      "reward": 0.9,
+      "reward_std": 0.23252918049693108,
+      "rewards/custom_reward_simplified_v7_dblog": 0.9,
+      "step": 1490
+    },
+    {
+      "completion_length": 653.79375,
+      "epoch": 0.011946384625799411,
+      "grad_norm": 0.17014774680137634,
+      "kl": 0.01346926314290613,
+      "learning_rate": 1.852952387243698e-06,
+      "loss": 0.0005,
+      "reward": 0.740625,
+      "reward_std": 0.22115055918693544,
+      "rewards/custom_reward_simplified_v7_dblog": 0.740625,
+      "step": 1500
     }
   ],
   "logging_steps": 10,