Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f91ff678ec612a5fb1a8bf0f9a0fa6494a3f983961a4be554fd148a39f98ca6
+oid sha256:8de23388570c9c810f5c012fe5f79293c683389ee14efbf7548903bedc02443c
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7f30a4fdbdd97dabca0d7d36136146658cc92e4d507b8be644fe7a0ffeb0c57
+oid sha256:4c1f16e4f6ca73d6b0d0b653f80247fdd3507861ab8750db5c0fca342cc5adf0
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e72b108b0017730ff1fc6d924ce3590eb91b3a06a3827ad9e642344e9bd450c
+oid sha256:631bee6c95d1479c29399db52e8b982c9c130ac80a19f6b7aa7d80cfc04f08ec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb505857bd564bb81d4dfe3d81be04ff6342c0ec4fa225ccc8dfd554aa405567
+oid sha256:8b017f223f7cbfcbd91ec9cfbd378a9bc9c27e3fa5227c019815cc49a05577b2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002588383335589873,
+  "epoch": 0.002787489746019863,
   "eval_steps": 500,
-  "global_step": 325,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -391,6 +391,42 @@
       "reward_std": 0.3178554192185402,
       "rewards/custom_reward_simplified_v7_dblog": 0.68125,
       "step": 320
+    },
+    {
+      "completion_length": 780.34375,
+      "epoch": 0.002628204617675871,
+      "grad_norm": 0.1997414082288742,
+      "kl": 0.002029248425969854,
+      "learning_rate": 4.978612153434527e-06,
+      "loss": 0.0001,
+      "reward": 0.696875,
+      "reward_std": 0.32896072417497635,
+      "rewards/custom_reward_simplified_v7_dblog": 0.696875,
+      "step": 330
+    },
+    {
+      "completion_length": 695.63125,
+      "epoch": 0.002707847181847867,
+      "grad_norm": 0.18966233730316162,
+      "kl": 0.002277573832543567,
+      "learning_rate": 4.973604096452361e-06,
+      "loss": 0.0001,
+      "reward": 0.684375,
+      "reward_std": 0.2995404839515686,
+      "rewards/custom_reward_simplified_v7_dblog": 0.684375,
+      "step": 340
+    },
+    {
+      "completion_length": 719.425,
+      "epoch": 0.002787489746019863,
+      "grad_norm": 0.17769980430603027,
+      "kl": 0.002305405435618013,
+      "learning_rate": 4.968072782793436e-06,
+      "loss": 0.0001,
+      "reward": 0.74375,
+      "reward_std": 0.3807508498430252,
+      "rewards/custom_reward_simplified_v7_dblog": 0.74375,
+      "step": 350
     }
   ],
   "logging_steps": 10,