Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51d2bfe427ae3327bc33ac81631f2aa644863894dc2053c7a9baffcc189de959
+oid sha256:659d6e1779ca606e9015006ef5de68aba0e8374af8c18cedc60c33a7bf451e5c
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a853020d3765589fb3bb1ff546e98661c228054d39f41c9223f630545c6ea646
+oid sha256:1671a35686771c80a687de1f74c1a702fdc2a1104adb9e2bf4d994f98392f085
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11d2e7595e9ba9bfe2c796cf0b04f0964398eb3358cd06be11438c9c6d1e9663
+oid sha256:8306b273eeea1e7d7babc48af3074feb456a19148c20b9d256b84d0476e8efcc
 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": 0.20657491832971572,
       "rewards/custom_reward_logic_v4_batch_streak_dblog": 0.26712499260902406,
       "step": 320
+    },
+    {
+      "completion_length": 18.91875,
+      "epoch": 0.002628204617675871,
+      "grad_norm": 1.5010004043579102,
+      "kl": 0.4104623213410378,
+      "learning_rate": 4.978612153434527e-06,
+      "loss": 0.0164,
+      "reward": 0.3325000023469329,
+      "reward_std": 0.2386787176132202,
+      "rewards/custom_reward_logic_v4_batch_streak_dblog": 0.3325000023469329,
+      "step": 330
+    },
+    {
+      "completion_length": 17.9875,
+      "epoch": 0.002707847181847867,
+      "grad_norm": 3.6247098445892334,
+      "kl": 0.45523770749568937,
+      "learning_rate": 4.973604096452361e-06,
+      "loss": 0.0182,
+      "reward": 0.19924999605864285,
+      "reward_std": 0.153281569480896,
+      "rewards/custom_reward_logic_v4_batch_streak_dblog": 0.19924999605864285,
+      "step": 340
+    },
+    {
+      "completion_length": 19.43125,
+      "epoch": 0.002787489746019863,
+      "grad_norm": 0.7098278403282166,
+      "kl": 0.3987171895802021,
+      "learning_rate": 4.968072782793436e-06,
+      "loss": 0.0159,
+      "reward": 0.33292500320822,
+      "reward_std": 0.07614715248346329,
+      "rewards/custom_reward_logic_v4_batch_streak_dblog": 0.33292500320822,
+      "step": 350
     }
   ],
   "logging_steps": 10,