Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bad81dc96084ab5ddee74a4664e886906e4be5ca86b50b0a9fb72bc45570188
+oid sha256:94e10e53c76f7ff04829e808c63c93839ebd5429cd67f49bbfeea277b83d07a7
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:732a3e23bab6a35c7c0b1fbd3eab25075735978514241e667277b9927b941f9d
+oid sha256:7b3cd44e38766e505ffcc5fc493c2a4306d24f1992cf69d3a5db1a4116a556db
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0622740b7f529d67896bed5f8ff648e5729882e67681daaf8eb3ef3cf2b65e92
+oid sha256:90e345de18b4130f225fcea63e9859bfd38ec06f643e0ce309fd7f3ed7f28326
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb41e5de709c0ea44e9bca507118fe887f61feeb314b07045c5c6637c0e7194
+oid sha256:dccb9bdfb0022ab0fbffb27c30bb70e7698ed3c92675c6050a89f10b3cdf6042
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0101544269319295,
+  "epoch": 0.010353533342359491,
   "eval_steps": 500,
-  "global_step": 1275,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1531,6 +1531,42 @@
       "reward_std": 0.2156815566122532,
       "rewards/custom_reward_simplified_v7_dblog": 0.60625,
       "step": 1270
+    },
+    {
+      "completion_length": 641.9125,
+      "epoch": 0.0101942482140155,
+      "grad_norm": 0.21494239568710327,
+      "kl": 0.008675340004265309,
+      "learning_rate": 2.6453620722761897e-06,
+      "loss": 0.0003,
+      "reward": 0.81875,
+      "reward_std": 0.22831376343965532,
+      "rewards/custom_reward_simplified_v7_dblog": 0.81875,
+      "step": 1280
+    },
+    {
+      "completion_length": 650.5,
+      "epoch": 0.010273890778187494,
+      "grad_norm": 0.22972695529460907,
+      "kl": 0.008116158202756196,
+      "learning_rate": 2.6090484684133406e-06,
+      "loss": 0.0003,
+      "reward": 0.921875,
+      "reward_std": 0.2564812809228897,
+      "rewards/custom_reward_simplified_v7_dblog": 0.921875,
+      "step": 1290
+    },
+    {
+      "completion_length": 657.94375,
+      "epoch": 0.010353533342359491,
+      "grad_norm": 0.15338486433029175,
+      "kl": 0.009256175020709634,
+      "learning_rate": 2.572711796857779e-06,
+      "loss": 0.0004,
+      "reward": 0.709375,
+      "reward_std": 0.21537503451108933,
+      "rewards/custom_reward_simplified_v7_dblog": 0.709375,
+      "step": 1300
     }
   ],
   "logging_steps": 10,