Training in progress, step 2325, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51607906ace2c98e569d183ab45677434a935eac30550ca59fcf7e6b0aa28ecc
+oid sha256:dae3d4e40288a9a85470e81968cc542ae99732242c2e711b5ec3c6dc29c5dc7f
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9808d74ff94c8178a179d50be213199f49e72f74fef5bb8d5f22f51d5b64db0e
+oid sha256:0701d3503af7517781360633bf2a4d275c745b1596af93b69ab0eadb14b67678
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e5009569494f30f2940455df04e4f5368d219ec998b9ebf88b01d9bbb842107
+oid sha256:ff61bce8d1cc7e6d4f9dafc5a23895c1167ecb9ed38c33c525dd5129824b65cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16e85494c48f97d81e46f2565e394f0b90477ea8854b7c074fd4e2bd18c4915c
+oid sha256:a226d58f171c5be256edf332cbc2ab5d760146cebf53f08b9f5344f55257bab0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018317789759559097,
+  "epoch": 0.01851689616998909,
   "eval_steps": 500,
-  "global_step": 2300,
+  "global_step": 2325,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2767,6 +2767,30 @@
       "reward_std": 0.2881218962371349,
       "rewards/custom_reward_simplified_v7_dblog": 0.78125,
       "step": 2300
+    },
+    {
+      "completion_length": 565.125,
+      "epoch": 0.018397432323731096,
+      "grad_norm": 0.25337040424346924,
+      "kl": 0.01471406095661223,
+      "learning_rate": 2.1387846565474047e-08,
+      "loss": 0.0006,
+      "reward": 1.078125,
+      "reward_std": 0.4393742740154266,
+      "rewards/custom_reward_simplified_v7_dblog": 1.078125,
+      "step": 2310
+    },
+    {
+      "completion_length": 692.70625,
+      "epoch": 0.01847707488790309,
+      "grad_norm": 0.20416221022605896,
+      "kl": 0.02145941834896803,
+      "learning_rate": 1.6904105645142443e-08,
+      "loss": 0.0009,
+      "reward": 0.5625,
+      "reward_std": 0.1467035911977291,
+      "rewards/custom_reward_simplified_v7_dblog": 0.5625,
+      "step": 2320
     }
   ],
   "logging_steps": 10,