Training in progress, step 1475, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8e88b4a46fa73626a4e6e3af725795e08dec7873381352d8a9215c673b7cb70
+oid sha256:bc93f9835831dfe4fe8f3fabe09b29fc36f37216ea398f53ad427fb270ac8fe5
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee609b22a3cef2e191ab746283011abe76b6ef33e713e5cc1497bd2b16df1b92
+oid sha256:96b7c7d4975d19f24910799848311416fe9ce4376edbc7f5c1ce181682b8608b
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdbd21fffa1a415ca30a4a7f2e0a804035ca732e3d109f97a7b2acfef9566c51
+oid sha256:ce3fefcac352ac4ee619c7ff01acc8acab65caca37da4199453b9a9441a77444
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42c8b7d228462d67de7699b9bc2d86e02c5f3a8873dc9d34175e1dded8c5dec9
+oid sha256:a9d2f48ad4251bd6b293d199cd40a6a67cdcf63f7330a6380c30e1422c7eaee0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011548171804939432,
+  "epoch": 0.011747278215369422,
   "eval_steps": 500,
-  "global_step": 1450,
+  "global_step": 1475,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1747,6 +1747,30 @@
       "reward_std": 0.26520399302244185,
       "rewards/custom_reward_simplified_v7_dblog": 0.8125,
       "step": 1450
+    },
+    {
+      "completion_length": 677.23125,
+      "epoch": 0.011627814369111427,
+      "grad_norm": 0.2590673267841339,
+      "kl": 0.011339499452151357,
+      "learning_rate": 1.994456069169906e-06,
+      "loss": 0.0005,
+      "reward": 0.64375,
+      "reward_std": 0.23993425220251083,
+      "rewards/custom_reward_simplified_v7_dblog": 0.64375,
+      "step": 1460
+    },
+    {
+      "completion_length": 702.1625,
+      "epoch": 0.011707456933283424,
+      "grad_norm": 0.012393876910209656,
+      "kl": 0.012036008480936288,
+      "learning_rate": 1.958900965154743e-06,
+      "loss": 0.0005,
+      "reward": 0.64375,
+      "reward_std": 0.21832374781370162,
+      "rewards/custom_reward_simplified_v7_dblog": 0.64375,
+      "step": 1470
     }
   ],
   "logging_steps": 10,