Training in progress, step 475, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a136e1089288003040fb5919a64653e0afa6bd0df82d43b06f67de77b66b96a
+oid sha256:cb0169e741bdd6594ddfced3208bacc2d90534233535014c934404687e597012
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80aa00c00cfa6fcb5d954640f14e471dbaf9a925c27f23c4e87f7c4e08eb4abe
+oid sha256:8e58e12edc4960ba8a48dcb12c2b62cbc1c9b2796496a0f315b1f303e1a26f29
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bca0d31999296fa556a6701fce97a7588992bf86240e00014d78311a2fb8397
+oid sha256:1c5b69743336ac963669786ca31ed47f7c47f3334fe7c85d59591481b5cae374
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31f09120e45bcc4193cfd66ac556b20e8f26a1efecd672279cdd630bf09741a4
+oid sha256:d825824fc7007a7b00c58c661fd84159061d7728ac6b0d52a8723237e0ac3962
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0035839153877398238,
+  "epoch": 0.003783021798169814,
   "eval_steps": 500,
-  "global_step": 450,
+  "global_step": 475,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -547,6 +547,30 @@
       "reward_std": 0.29777742698788645,
       "rewards/custom_reward_simplified_v7_dblog": 0.753125,
       "step": 450
+    },
+    {
+      "completion_length": 727.13125,
+      "epoch": 0.0036635579519118198,
+      "grad_norm": 0.18630079925060272,
+      "kl": 0.003935616160742938,
+      "learning_rate": 4.873106608932585e-06,
+      "loss": 0.0002,
+      "reward": 0.678125,
+      "reward_std": 0.31932896226644514,
+      "rewards/custom_reward_simplified_v7_dblog": 0.678125,
+      "step": 460
+    },
+    {
+      "completion_length": 716.74375,
+      "epoch": 0.003743200516083816,
+      "grad_norm": 0.1637570858001709,
+      "kl": 0.004373999196104705,
+      "learning_rate": 4.861418843169012e-06,
+      "loss": 0.0002,
+      "reward": 0.646875,
+      "reward_std": 0.26624983847141265,
+      "rewards/custom_reward_simplified_v7_dblog": 0.646875,
+      "step": 470
     }
   ],
   "logging_steps": 10,