Training in progress, step 850, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be08547166dacd1b7d161c2f41cf30693b0c59e1e628537d5d7645d2ea4fcbbf
+oid sha256:9ce44bac1ce014ef00371dcfe7ea68b6f02d101b1d59b1aa9f17f88cfa3a6ffd
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:718a80129d5413c606f827de20a6c1acb27fb76dcd018a018ecd6df21b62763d
+oid sha256:c6fcd046738e17acd72c93dbe6a5138541324f8eafc50e92bde39626096f2c0c
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:657c2c45e0b68fdd44aeab5a6c64190c8d2f3733cd86796d96b53daec5b3952e
+oid sha256:53c7652a6447ec0e6f7f58ed91608cc677939e784b3d87b8a23910c68dcce8f5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fc859065f77e5cbabb1b099e6f8bcbc876c53f6186972adb97152a1da9fa4d4
+oid sha256:878236b83e42d9db1519008b5ab4529f212aeb27f63481cc4016850fcb712d03
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006570511544189677,
+  "epoch": 0.006769617954619667,
   "eval_steps": 500,
-  "global_step": 825,
+  "global_step": 850,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -991,6 +991,42 @@
       "reward_std": 0.24903304055333136,
       "rewards/custom_reward_simplified_v7_dblog": 0.684375,
       "step": 820
+    },
+    {
+      "completion_length": 658.575,
+      "epoch": 0.006610332826275675,
+      "grad_norm": 0.2923766076564789,
+      "kl": 0.0068331335205584764,
+      "learning_rate": 4.134652238142674e-06,
+      "loss": 0.0003,
+      "reward": 0.73125,
+      "reward_std": 0.3243869088590145,
+      "rewards/custom_reward_simplified_v7_dblog": 0.73125,
+      "step": 830
+    },
+    {
+      "completion_length": 645.31875,
+      "epoch": 0.006689975390447671,
+      "grad_norm": 0.22414511442184448,
+      "kl": 0.006329123536124826,
+      "learning_rate": 4.106969024216348e-06,
+      "loss": 0.0003,
+      "reward": 0.728125,
+      "reward_std": 0.2578707054257393,
+      "rewards/custom_reward_simplified_v7_dblog": 0.728125,
+      "step": 840
+    },
+    {
+      "completion_length": 620.76875,
+      "epoch": 0.006769617954619667,
+      "grad_norm": 0.2500353455543518,
+      "kl": 0.006427089823409915,
+      "learning_rate": 4.078945878256244e-06,
+      "loss": 0.0003,
+      "reward": 0.85625,
+      "reward_std": 0.3704014003276825,
+      "rewards/custom_reward_simplified_v7_dblog": 0.85625,
+      "step": 850
     }
   ],
   "logging_steps": 10,