Training in progress, step 1450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:418230f6279ba94346b4a25eaaedad80a6e32f2d21e69114c0a6c87588ebceac
+oid sha256:e8e88b4a46fa73626a4e6e3af725795e08dec7873381352d8a9215c673b7cb70
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7e5b0e1a6742969cbb3193e671a8e477f4a0f699e78d37903126a313c6d98d4
+oid sha256:ee609b22a3cef2e191ab746283011abe76b6ef33e713e5cc1497bd2b16df1b92
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cef8571d01f4838718fba5380f91f15fe0df712d95099c4c8c70dcaff3de787
+oid sha256:bdbd21fffa1a415ca30a4a7f2e0a804035ca732e3d109f97a7b2acfef9566c51
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c84f1b8f26cb0725d070a7236f279e1e8fdd989b9e7956aaf12382e1101fc41
+oid sha256:42c8b7d228462d67de7699b9bc2d86e02c5f3a8873dc9d34175e1dded8c5dec9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011349065394509441,
+  "epoch": 0.011548171804939432,
   "eval_steps": 500,
-  "global_step": 1425,
+  "global_step": 1450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1711,6 +1711,42 @@
       "reward_std": 0.32343359887599943,
       "rewards/custom_reward_simplified_v7_dblog": 0.853125,
       "step": 1420
+    },
+    {
+      "completion_length": 677.73125,
+      "epoch": 0.01138888667659544,
+      "grad_norm": 0.2689824104309082,
+      "kl": 0.011312256497330964,
+      "learning_rate": 2.101732829831194e-06,
+      "loss": 0.0005,
+      "reward": 0.765625,
+      "reward_std": 0.27808423787355424,
+      "rewards/custom_reward_simplified_v7_dblog": 0.765625,
+      "step": 1430
+    },
+    {
+      "completion_length": 619.71875,
+      "epoch": 0.011468529240767435,
+      "grad_norm": 0.32441073656082153,
+      "kl": 0.010685316193848849,
+      "learning_rate": 2.0658795558326745e-06,
+      "loss": 0.0004,
+      "reward": 0.871875,
+      "reward_std": 0.2622031569480896,
+      "rewards/custom_reward_simplified_v7_dblog": 0.871875,
+      "step": 1440
+    },
+    {
+      "completion_length": 613.3875,
+      "epoch": 0.011548171804939432,
+      "grad_norm": 0.15561087429523468,
+      "kl": 0.012302201450802385,
+      "learning_rate": 2.0301181139997206e-06,
+      "loss": 0.0005,
+      "reward": 0.8125,
+      "reward_std": 0.26520399302244185,
+      "rewards/custom_reward_simplified_v7_dblog": 0.8125,
+      "step": 1450
     }
   ],
   "logging_steps": 10,