Training in progress, step 2050, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee2c4957d38c92a35e2e3a9382278d93a60be6d048e22e2962b28edcfeb9f100
+oid sha256:e7ea22847e98188a86453340ded8ab9bdf3230793a2c9bc304a2ffd7869e39af
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:981c9ca2b7a4413155c1784a3b128f562c7cb222b2b00cf2bcd73b66aba50336
+oid sha256:1fa35385ff4e32a5427f6c13df901c2e95399515d52ec2d928f1cd7ff7c2583f
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e6d264aea217f296bd9612ca82a53239d5b10338e8322f94ac8e49def93b492
+oid sha256:eb420055fb63f75d57b1b7545369c8d9657f0a03d860d3f376a6359b71c8ff8d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:675f1831a53f04b0e24989b6bc8d9a17d48e7e3a0e3b788250eb946e8a1ecf93
+oid sha256:bef8bb0cf1916b1807bc9a190bcd4e45ed3fa199d3f2937269b8cfea43853b36
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016127619244829205,
+  "epoch": 0.016326725655259198,
   "eval_steps": 500,
-  "global_step": 2025,
+  "global_step": 2050,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2431,6 +2431,42 @@
       "reward_std": 0.37898894101381303,
       "rewards/custom_reward_simplified_v7_dblog": 1.0125,
       "step": 2020
+    },
+    {
+      "completion_length": 633.40625,
+      "epoch": 0.016167440526915204,
+      "grad_norm": 0.009714637883007526,
+      "kl": 0.01524353977292776,
+      "learning_rate": 3.5334535719846767e-07,
+      "loss": 0.0006,
+      "reward": 0.775,
+      "reward_std": 0.1905590772628784,
+      "rewards/custom_reward_simplified_v7_dblog": 0.775,
+      "step": 2030
+    },
+    {
+      "completion_length": 674.3625,
+      "epoch": 0.0162470830910872,
+      "grad_norm": 0.2587895095348358,
+      "kl": 0.015684280125424267,
+      "learning_rate": 3.3493649053890325e-07,
+      "loss": 0.0006,
+      "reward": 0.978125,
+      "reward_std": 0.33772673830389977,
+      "rewards/custom_reward_simplified_v7_dblog": 0.978125,
+      "step": 2040
+    },
+    {
+      "completion_length": 623.1375,
+      "epoch": 0.016326725655259198,
+      "grad_norm": 0.24910244345664978,
+      "kl": 0.014677197439596057,
+      "learning_rate": 3.1698561306951065e-07,
+      "loss": 0.0006,
+      "reward": 0.925,
+      "reward_std": 0.3512172996997833,
+      "rewards/custom_reward_simplified_v7_dblog": 0.925,
+      "step": 2050
     }
   ],
   "logging_steps": 10,