Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed689bc9d114ea626fa2c2dd07adc051073905d93ea41544d44e4421628b6148
+oid sha256:6980c4f88d74c446304ac0f4d5b03ec7010edd1231d1218c9dbbc1702d7b7beb
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56962b691b9bc8f4d52ec4572b9d7fd359ce8193dcd99091525e5a1bc27541fc
+oid sha256:69bbba57bdd38187db933f55c17e252bc60bc71cba5d9518f16fbeda46291a94
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5180f4d523a9de4af4495107558231395f34a23f975704672276aa3635592846
+oid sha256:8aed5e2dcd18747e1af4ff3f9c9eeac57cc1c5ec6b4e8897a41d8493d19b7f54
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e72cac8f8761735629463ac20d72c8e4ba79e021aecc7000b5e7881e01391cb9
+oid sha256:ab161cf33c0c9cc9b1323e9ac1c9b613001b96e466c0008a00d953dff6bc6adc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004579447439889774,
+  "epoch": 0.004778553850319765,
   "eval_steps": 500,
-  "global_step": 575,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -691,6 +691,42 @@
       "reward_std": 0.3310479797422886,
       "rewards/custom_reward_simplified_v7_dblog": 0.925,
       "step": 570
+    },
+    {
+      "completion_length": 693.2625,
+      "epoch": 0.004619268721975773,
+      "grad_norm": 0.11388376355171204,
+      "kl": 0.004154781624674797,
+      "learning_rate": 4.700503477950278e-06,
+      "loss": 0.0002,
+      "reward": 0.6875,
+      "reward_std": 0.29332098439335824,
+      "rewards/custom_reward_simplified_v7_dblog": 0.6875,
+      "step": 580
+    },
+    {
+      "completion_length": 662.7625,
+      "epoch": 0.004698911286147769,
+      "grad_norm": 0.15470421314239502,
+      "kl": 0.00541011628229171,
+      "learning_rate": 4.6830143869304904e-06,
+      "loss": 0.0002,
+      "reward": 0.809375,
+      "reward_std": 0.32753978818655016,
+      "rewards/custom_reward_simplified_v7_dblog": 0.809375,
+      "step": 590
+    },
+    {
+      "completion_length": 698.95625,
+      "epoch": 0.004778553850319765,
+      "grad_norm": 0.004228990990668535,
+      "kl": 0.004637495230417699,
+      "learning_rate": 4.665063509461098e-06,
+      "loss": 0.0002,
+      "reward": 0.75,
+      "reward_std": 0.23772156983613968,
+      "rewards/custom_reward_simplified_v7_dblog": 0.75,
+      "step": 600
     }
   ],
   "logging_steps": 10,