Training in progress, step 625, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6980c4f88d74c446304ac0f4d5b03ec7010edd1231d1218c9dbbc1702d7b7beb
+oid sha256:9eb3aa44f269ffa5572efdf1fb7fc717225ec2c5cb1f0c48883e932186e48135
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69bbba57bdd38187db933f55c17e252bc60bc71cba5d9518f16fbeda46291a94
+oid sha256:875f7c60ca5bfb35ef2ee985d4da925dfcc149e6e487b381cd6f5c04c4247823
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aed5e2dcd18747e1af4ff3f9c9eeac57cc1c5ec6b4e8897a41d8493d19b7f54
+oid sha256:f1d2b20723f64b1ac04e3f994e5af1f73988278694f53314ca6efef6bb7012b0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab161cf33c0c9cc9b1323e9ac1c9b613001b96e466c0008a00d953dff6bc6adc
+oid sha256:874d9ce62dc6f45e681b63f622889e24984460dea2c83350ae46c74f8b0e00de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004778553850319765,
+  "epoch": 0.004977660260749755,
   "eval_steps": 500,
-  "global_step": 600,
+  "global_step": 625,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -727,6 +727,30 @@
       "reward_std": 0.23772156983613968,
       "rewards/custom_reward_simplified_v7_dblog": 0.75,
       "step": 600
+    },
+    {
+      "completion_length": 629.7625,
+      "epoch": 0.004858196414491761,
+      "grad_norm": 0.21860064566135406,
+      "kl": 0.0044788535917177795,
+      "learning_rate": 4.646654642801533e-06,
+      "loss": 0.0002,
+      "reward": 0.8125,
+      "reward_std": 0.27716630697250366,
+      "rewards/custom_reward_simplified_v7_dblog": 0.8125,
+      "step": 610
+    },
+    {
+      "completion_length": 727.06875,
+      "epoch": 0.004937838978663757,
+      "grad_norm": 0.1765265315771103,
+      "kl": 0.004957099666353315,
+      "learning_rate": 4.627791681092499e-06,
+      "loss": 0.0002,
+      "reward": 0.6,
+      "reward_std": 0.2689620770514011,
+      "rewards/custom_reward_simplified_v7_dblog": 0.6,
+      "step": 620
     }
   ],
   "logging_steps": 10,