Training in progress, step 1675, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a08895d4e442ac2e2b34ad647fa53b3803a2ac87ac3bde5ea7c21daf746efbe
+oid sha256:2113bb192f2baa5cca5eaf82cdc29cc112a196f0d353c65e596bbc93a9194868
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13c169b9001793ae00f51a8c6359d182f353030b5e9d598d5ec179ba43c8d2d4
+oid sha256:d39914c7d80371a45e6dfe8ca4f4df8415bdc590cf39528b2981db04c2d9b5ab
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2d7278507c375a46e6b19e5af767f263e425cc0e143f37a001d365b8c944b80
+oid sha256:3abc69817bfc7e8384f353860e5ac5df7fe0bc25efa8cefc94df527ed53e449a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eb29e4ad419e6973610039d5ccb9e6d7d4abe171f61a95512a9844b9eca5006
+oid sha256:3aa9ee72eac8c93f8b4aad2310d8b5495ea694aa75e620528535e72bb4aabf2e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013141023088379354,
+  "epoch": 0.013340129498809344,
   "eval_steps": 500,
-  "global_step": 1650,
+  "global_step": 1675,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1987,6 +1987,30 @@
       "reward_std": 0.24298151433467866,
       "rewards/custom_reward_simplified_v7_dblog": 0.73125,
       "step": 1650
+    },
+    {
+      "completion_length": 727.9625,
+      "epoch": 0.01322066565255135,
+      "grad_norm": 0.14750860631465912,
+      "kl": 0.018067248188890515,
+      "learning_rate": 1.313499075630899e-06,
+      "loss": 0.0007,
+      "reward": 0.721875,
+      "reward_std": 0.30838647186756135,
+      "rewards/custom_reward_simplified_v7_dblog": 0.721875,
+      "step": 1660
+    },
+    {
+      "completion_length": 780.08125,
+      "epoch": 0.013300308216723346,
+      "grad_norm": 0.2386309951543808,
+      "kl": 0.017110610962845385,
+      "learning_rate": 1.2816206721818944e-06,
+      "loss": 0.0007,
+      "reward": 0.6375,
+      "reward_std": 0.26727318242192266,
+      "rewards/custom_reward_simplified_v7_dblog": 0.6375,
+      "step": 1670
     }
   ],
   "logging_steps": 10,