Training in progress, step 1225, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472e657d76af3eaaba42ec25426bc8bf27658485a28e4350ab29bca535ba53df
+oid sha256:ca8baaba22487cdce42630abaf28904ed482a9cc8827520bc824bb81cd486cd4
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d30a42988942974010016e3abeab1862bbe509a565ab524b099e23a588f2133b
+oid sha256:0c50c6e305b6a0d4073f6216b5ff8f9f102df9985bb7e7ec1efec53cfd87ac3c
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a3ed0d969db11340b9a2b2a125fd49ce838279261922aff0d2c0ec5a501918
+oid sha256:b2abe6090a2975a0c5e7fd37addef971ec2653163e71ac7336dc65e74c34c04f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eec1c860a4f3642f2a110b103ddd4dbbb21291c74e6d644477d4ed922650e638
+oid sha256:9debf92aca27ce6ace0aef79d370cac248bb98d16412d955b96820394066292d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00955710770063953,
+  "epoch": 0.00975621411106952,
   "eval_steps": 500,
-  "global_step": 1200,
+  "global_step": 1225,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1447,6 +1447,30 @@
       "reward_std": 0.33152099549770353,
       "rewards/custom_reward_simplified_v7_dblog": 0.728125,
       "step": 1200
+    },
+    {
+      "completion_length": 660.7375,
+      "epoch": 0.009636750264811526,
+      "grad_norm": 0.20679971575737,
+      "kl": 0.00826664932537824,
+      "learning_rate": 2.898267170168807e-06,
+      "loss": 0.0003,
+      "reward": 0.665625,
+      "reward_std": 0.25403511226177217,
+      "rewards/custom_reward_simplified_v7_dblog": 0.665625,
+      "step": 1210
+    },
+    {
+      "completion_length": 653.59375,
+      "epoch": 0.009716392828983521,
+      "grad_norm": 0.14609546959400177,
+      "kl": 0.007603704649955034,
+      "learning_rate": 2.862329648268117e-06,
+      "loss": 0.0003,
+      "reward": 0.94375,
+      "reward_std": 0.26154626756906507,
+      "rewards/custom_reward_simplified_v7_dblog": 0.94375,
+      "step": 1220
     }
   ],
   "logging_steps": 10,