Training in progress, step 375, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de23388570c9c810f5c012fe5f79293c683389ee14efbf7548903bedc02443c
+oid sha256:7f24d276f7fb7916ab15b39da6e2b88fa4797d8da0140e77a25bceeaed815bc3
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c1f16e4f6ca73d6b0d0b653f80247fdd3507861ab8750db5c0fca342cc5adf0
+oid sha256:51ab91babec334efadc5b34fbf32381f2ed2d09198a2b7a61be4e6940e7259f8
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631bee6c95d1479c29399db52e8b982c9c130ac80a19f6b7aa7d80cfc04f08ec
+oid sha256:fdcafde9e1f0f9ecf6d844d2ef33445b6716f1049ad07534eb5ed4be8ce625d0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b017f223f7cbfcbd91ec9cfbd378a9bc9c27e3fa5227c019815cc49a05577b2
+oid sha256:38ee62f39915fab64d2f1ab670d54e213cfc2d70e4cd48a7b1400797011d55aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002787489746019863,
+  "epoch": 0.002986596156449853,
   "eval_steps": 500,
-  "global_step": 350,
+  "global_step": 375,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,6 +427,30 @@
       "reward_std": 0.3807508498430252,
       "rewards/custom_reward_simplified_v7_dblog": 0.74375,
       "step": 350
+    },
+    {
+      "completion_length": 732.4375,
+      "epoch": 0.002867132310191859,
+      "grad_norm": 0.21898534893989563,
+      "kl": 0.002607938600704074,
+      "learning_rate": 4.962019382530521e-06,
+      "loss": 0.0001,
+      "reward": 0.596875,
+      "reward_std": 0.303117785602808,
+      "rewards/custom_reward_simplified_v7_dblog": 0.596875,
+      "step": 360
+    },
+    {
+      "completion_length": 703.21875,
+      "epoch": 0.002946774874363855,
+      "grad_norm": 0.20463985204696655,
+      "kl": 0.0030091375578194858,
+      "learning_rate": 4.955445176176577e-06,
+      "loss": 0.0001,
+      "reward": 0.746875,
+      "reward_std": 0.28880608528852464,
+      "rewards/custom_reward_simplified_v7_dblog": 0.746875,
+      "step": 370
     }
   ],
   "logging_steps": 10,