Training in progress, step 2275, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc373811286053bff81db740613656f4ba9fe7fdb7e406401d4cb430f04ff3ec
+oid sha256:ea4152a2ecb2a36c2f03c57c1af9834e82d74af2d98b546ef377df84e9217079
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc14306598d59f4093a6835603acdc7be8c34d58f259448f089f55239326eef9
+oid sha256:d3b771aa162d23f5298ffa3d4a7478a5f8ca06ca450f343b659dff96388c05cc
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31a4e7954a06ef587699673e6f8e225350e2c0f70b9309dc051a495886a330f3
+oid sha256:c4ce68317885d0fab0d249ff862a16f04f6bddc55d10bc7c8820876e15315633
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88b9816dd9ff2c86931b2a1a597995744d96003dfef41dde5f6e6cc74bd8f07f
+oid sha256:578d6fda5043112e1e2d7094db2258c237f4222eb739591bdc6ff4137fd79fa1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017919576938699118,
+  "epoch": 0.018118683349129108,
   "eval_steps": 500,
-  "global_step": 2250,
+  "global_step": 2275,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2707,6 +2707,30 @@
       "reward_std": 0.2905955038964748,
       "rewards/custom_reward_simplified_v7_dblog": 0.853125,
       "step": 2250
+    },
+    {
+      "completion_length": 610.85,
+      "epoch": 0.017999219502871113,
+      "grad_norm": 0.28028422594070435,
+      "kl": 0.017966749798506498,
+      "learning_rate": 5.164844558612131e-08,
+      "loss": 0.0007,
+      "reward": 0.971875,
+      "reward_std": 0.3067967638373375,
+      "rewards/custom_reward_simplified_v7_dblog": 0.971875,
+      "step": 2260
+    },
+    {
+      "completion_length": 566.9625,
+      "epoch": 0.018078862067043112,
+      "grad_norm": 0.3413483202457428,
+      "kl": 0.01525729293935001,
+      "learning_rate": 4.455482382342336e-08,
+      "loss": 0.0006,
+      "reward": 0.959375,
+      "reward_std": 0.3084723956882954,
+      "rewards/custom_reward_simplified_v7_dblog": 0.959375,
+      "step": 2270
     }
   ],
   "logging_steps": 10,