Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:780adb9accd35e89fa4d6e0b16d07afb98a5ad312c157c14f5c6fc3688b6b435
+oid sha256:472e657d76af3eaaba42ec25426bc8bf27658485a28e4350ab29bca535ba53df
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8186daf7088705064b8cda2fa05ea5b15ac3829a5cc745cfd0463cf0775d065
+oid sha256:d30a42988942974010016e3abeab1862bbe509a565ab524b099e23a588f2133b
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4eda2caa8c1d334010b2826a85bd0fa5d6353a1455cace044b4ee905e374a02
+oid sha256:81a3ed0d969db11340b9a2b2a125fd49ce838279261922aff0d2c0ec5a501918
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7aa6200e076e6b4e3b8c147bb3db3fdb1f862f67341ccf617eae90a633431d6
+oid sha256:eec1c860a4f3642f2a110b103ddd4dbbb21291c74e6d644477d4ed922650e638
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00935800129020954,
+  "epoch": 0.00955710770063953,
   "eval_steps": 500,
-  "global_step": 1175,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1411,6 +1411,42 @@
       "reward_std": 0.29315834268927576,
       "rewards/custom_reward_simplified_v7_dblog": 0.846875,
       "step": 1170
+    },
+    {
+      "completion_length": 690.65625,
+      "epoch": 0.009397822572295537,
+      "grad_norm": 0.196693554520607,
+      "kl": 0.007807633420452475,
+      "learning_rate": 3.0055439308300954e-06,
+      "loss": 0.0003,
+      "reward": 0.80625,
+      "reward_std": 0.34684801325201986,
+      "rewards/custom_reward_simplified_v7_dblog": 0.80625,
+      "step": 1180
+    },
+    {
+      "completion_length": 652.125,
+      "epoch": 0.009477465136467534,
+      "grad_norm": 0.009493391960859299,
+      "kl": 0.008702660608105362,
+      "learning_rate": 2.96988188600028e-06,
+      "loss": 0.0003,
+      "reward": 0.85625,
+      "reward_std": 0.21074047386646272,
+      "rewards/custom_reward_simplified_v7_dblog": 0.85625,
+      "step": 1190
+    },
+    {
+      "completion_length": 660.8125,
+      "epoch": 0.00955710770063953,
+      "grad_norm": 0.250519335269928,
+      "kl": 0.008729650382883846,
+      "learning_rate": 2.9341204441673267e-06,
+      "loss": 0.0003,
+      "reward": 0.728125,
+      "reward_std": 0.33152099549770353,
+      "rewards/custom_reward_simplified_v7_dblog": 0.728125,
+      "step": 1200
     }
   ],
   "logging_steps": 10,