Training in progress, step 425, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f1baaecd115dc2627bc1fc20e77eb545d9a63c35d8d1903b2da99c859bc0b3
+oid sha256:2dd5a7b1213204ca747b9b853b134bfc9b44111c378177fe7af78d584b5b29e8
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f682f79f389fc0fb00209bc2cc3e2a9edc3c3ec3acb8cd0de0e2caab1646c00
+oid sha256:bb0de15ef9aa9c8d8b4a7dae7fc40eba340f4539f15aaf8fc8ec93c76311885f
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d72e53163e0b37658920f89de25bb35e0fc65ce31407318d49ddf8c0748bde32
+oid sha256:b049339d11661c45a143cb633e7745d099ed4f1c430b6f684cd48142f304fe9a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4c3629b7c1260118bd8e441883da4a51d7d27eb4e80b627848880bbfe9a72d5
+oid sha256:0bc973e3447bd6a6f5ad5fae82ce35cd91650677852104987fd5a5dacd81b436
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0031857025668798433,
+  "epoch": 0.0033848089773098333,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 425,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -487,6 +487,30 @@
       "reward_std": 0.26303397938609124,
       "rewards/custom_reward_simplified_v7_dblog": 0.590625,
       "step": 400
+    },
+    {
+      "completion_length": 641.26875,
+      "epoch": 0.0032653451310518393,
+      "grad_norm": 0.21161562204360962,
+      "kl": 0.003351045388262719,
+      "learning_rate": 4.9239697496952904e-06,
+      "loss": 0.0001,
+      "reward": 0.909375,
+      "reward_std": 0.3579762116074562,
+      "rewards/custom_reward_simplified_v7_dblog": 0.909375,
+      "step": 410
+    },
+    {
+      "completion_length": 692.06875,
+      "epoch": 0.0033449876952238353,
+      "grad_norm": 0.17584940791130066,
+      "kl": 0.003339459316339344,
+      "learning_rate": 4.914814565722671e-06,
+      "loss": 0.0001,
+      "reward": 0.765625,
+      "reward_std": 0.3109076008200645,
+      "rewards/custom_reward_simplified_v7_dblog": 0.765625,
+      "step": 420
     }
   ],
   "logging_steps": 10,