Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0169e741bdd6594ddfced3208bacc2d90534233535014c934404687e597012
+oid sha256:59ec13225013227af4efcb5bdbfb640d7212e59b3beb094f4872af16f10b82ef
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e58e12edc4960ba8a48dcb12c2b62cbc1c9b2796496a0f315b1f303e1a26f29
+oid sha256:91143a9dcc019124f810bc23d4848cd1c6049b7a67d72b83be9f91f7038a75d7
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c5b69743336ac963669786ca31ed47f7c47f3334fe7c85d59591481b5cae374
+oid sha256:ca22256892f07c3d3627994a755a937bba7e1c876608b0bbfd5c6993d9a4ef72
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d825824fc7007a7b00c58c661fd84159061d7728ac6b0d52a8723237e0ac3962
+oid sha256:fb5afe87d3cf7dc745f288e9b6e22d0c86761093d76c6bd9bf6e768d81be8a7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003783021798169814,
+  "epoch": 0.003982128208599804,
   "eval_steps": 500,
-  "global_step": 475,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -571,6 +571,42 @@
       "reward_std": 0.26624983847141265,
       "rewards/custom_reward_simplified_v7_dblog": 0.646875,
       "step": 470
+    },
+    {
+      "completion_length": 581.90625,
+      "epoch": 0.003822843080255812,
+      "grad_norm": 0.0051241409964859486,
+      "kl": 0.004909415659494698,
+      "learning_rate": 4.849231551964771e-06,
+      "loss": 0.0002,
+      "reward": 0.75625,
+      "reward_std": 0.19474873542785645,
+      "rewards/custom_reward_simplified_v7_dblog": 0.75625,
+      "step": 480
+    },
+    {
+      "completion_length": 680.94375,
+      "epoch": 0.003902485644427808,
+      "grad_norm": 0.15670013427734375,
+      "kl": 0.004694941581692547,
+      "learning_rate": 4.836547313372472e-06,
+      "loss": 0.0002,
+      "reward": 0.73125,
+      "reward_std": 0.2675834000110626,
+      "rewards/custom_reward_simplified_v7_dblog": 0.73125,
+      "step": 490
+    },
+    {
+      "completion_length": 699.1,
+      "epoch": 0.003982128208599804,
+      "grad_norm": 0.1365301012992859,
+      "kl": 0.00405421577161178,
+      "learning_rate": 4.823368810567056e-06,
+      "loss": 0.0002,
+      "reward": 0.603125,
+      "reward_std": 0.25718758851289747,
+      "rewards/custom_reward_simplified_v7_dblog": 0.603125,
+      "step": 500
     }
   ],
   "logging_steps": 10,