Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f24d276f7fb7916ab15b39da6e2b88fa4797d8da0140e77a25bceeaed815bc3
+oid sha256:70f1baaecd115dc2627bc1fc20e77eb545d9a63c35d8d1903b2da99c859bc0b3
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51ab91babec334efadc5b34fbf32381f2ed2d09198a2b7a61be4e6940e7259f8
+oid sha256:2f682f79f389fc0fb00209bc2cc3e2a9edc3c3ec3acb8cd0de0e2caab1646c00
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdcafde9e1f0f9ecf6d844d2ef33445b6716f1049ad07534eb5ed4be8ce625d0
+oid sha256:d72e53163e0b37658920f89de25bb35e0fc65ce31407318d49ddf8c0748bde32
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38ee62f39915fab64d2f1ab670d54e213cfc2d70e4cd48a7b1400797011d55aa
+oid sha256:e4c3629b7c1260118bd8e441883da4a51d7d27eb4e80b627848880bbfe9a72d5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002986596156449853,
+  "epoch": 0.0031857025668798433,
   "eval_steps": 500,
-  "global_step": 375,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -451,6 +451,42 @@
       "reward_std": 0.28880608528852464,
       "rewards/custom_reward_simplified_v7_dblog": 0.746875,
       "step": 370
+    },
+    {
+      "completion_length": 646.95625,
+      "epoch": 0.0030264174385358513,
+      "grad_norm": 0.17787523567676544,
+      "kl": 0.003602780296932906,
+      "learning_rate": 4.948351554413879e-06,
+      "loss": 0.0001,
+      "reward": 0.753125,
+      "reward_std": 0.31493050456047056,
+      "rewards/custom_reward_simplified_v7_dblog": 0.753125,
+      "step": 380
+    },
+    {
+      "completion_length": 656.94375,
+      "epoch": 0.0031060600027078473,
+      "grad_norm": 0.18550129234790802,
+      "kl": 0.003282526368275285,
+      "learning_rate": 4.9407400177998335e-06,
+      "loss": 0.0001,
+      "reward": 0.828125,
+      "reward_std": 0.33323406875133516,
+      "rewards/custom_reward_simplified_v7_dblog": 0.828125,
+      "step": 390
+    },
+    {
+      "completion_length": 740.3125,
+      "epoch": 0.0031857025668798433,
+      "grad_norm": 0.19987954199314117,
+      "kl": 0.003102585405576974,
+      "learning_rate": 4.93261217644956e-06,
+      "loss": 0.0001,
+      "reward": 0.590625,
+      "reward_std": 0.26303397938609124,
+      "rewards/custom_reward_simplified_v7_dblog": 0.590625,
+      "step": 400
     }
   ],
   "logging_steps": 10,