Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dde5e9886df1a06cfdfe007189a6433cb7a5f73cb42b5a5b386732a460844a5b
+oid sha256:a5a04e84830bbd6a9d15a7f1b7837c35b2c5aa3c3d810fb936a39fabd501f732
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6af8a0ed34f4ca382db8716933993dfd5adf698a5f8abc4921176880d589a90
+oid sha256:d9d953155e50b0ab53fcf21d7698c3548b16bde8faffe38265b83b4c176691fe
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c09760c610e47668e35c66624317f7474be74f8d6ddb09b4e5b00e8bf9d9f0ca
+oid sha256:d69b3ec032c894f09c29bf70e7979ef1f260d871795cce9f40bc39aed3eb516f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59f0296be23c202d35d7785a2cf57d4f962424acd2684f32b917f44308d185d8
+oid sha256:29fe942acb075168b131d317a2f6faee5c51c7e00aad3609dac6f7c5e3261669
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005375873081609735,
+  "epoch": 0.005574979492039726,
   "eval_steps": 500,
-  "global_step": 675,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -811,6 +811,42 @@
       "reward_std": 0.26030006259679794,
       "rewards/custom_reward_simplified_v7_dblog": 0.81875,
       "step": 670
+    },
+    {
+      "completion_length": 696.30625,
+      "epoch": 0.005415694363695734,
+      "grad_norm": 0.2144252061843872,
+      "kl": 0.005292760988231749,
+      "learning_rate": 4.50530798188761e-06,
+      "loss": 0.0002,
+      "reward": 0.609375,
+      "reward_std": 0.2595392823219299,
+      "rewards/custom_reward_simplified_v7_dblog": 0.609375,
+      "step": 680
+    },
+    {
+      "completion_length": 696.99375,
+      "epoch": 0.00549533692786773,
+      "grad_norm": 0.006262101698666811,
+      "kl": 0.005413674132432789,
+      "learning_rate": 4.4833833507280884e-06,
+      "loss": 0.0002,
+      "reward": 0.684375,
+      "reward_std": 0.24843912497162818,
+      "rewards/custom_reward_simplified_v7_dblog": 0.684375,
+      "step": 690
+    },
+    {
+      "completion_length": 675.50625,
+      "epoch": 0.005574979492039726,
+      "grad_norm": 0.16301825642585754,
+      "kl": 0.005892223375849426,
+      "learning_rate": 4.46103916229894e-06,
+      "loss": 0.0002,
+      "reward": 0.80625,
+      "reward_std": 0.34091843143105505,
+      "rewards/custom_reward_simplified_v7_dblog": 0.80625,
+      "step": 700
     }
   ],
   "logging_steps": 10,