Training in progress, step 325, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51885749d7e0b43a3daa2be73b7b2a85f53f51bf3f2b4c4f68f741d5cc3d7865
+oid sha256:5f91ff678ec612a5fb1a8bf0f9a0fa6494a3f983961a4be554fd148a39f98ca6
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37212643c4136b70f407996bc4c91afa08c3933531b919b7c6db8a24b9a4f1ae
+oid sha256:a7f30a4fdbdd97dabca0d7d36136146658cc92e4d507b8be644fe7a0ffeb0c57
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b6edf3402d665dc804156e1f42b2872a7f5e9fbf05da017ddad3c4fe71434af
+oid sha256:1e72b108b0017730ff1fc6d924ce3590eb91b3a06a3827ad9e642344e9bd450c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ec9a27cf5cbc363143d5683468f5f375f2f3889ae8160526593a29051413551
+oid sha256:cb505857bd564bb81d4dfe3d81be04ff6342c0ec4fa225ccc8dfd554aa405567
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0023892769251598824,
+  "epoch": 0.002588383335589873,
   "eval_steps": 500,
-  "global_step": 300,
+  "global_step": 325,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -367,6 +367,30 @@
       "reward_std": 0.24568462520837783,
       "rewards/custom_reward_simplified_v7_dblog": 0.621875,
       "step": 300
+    },
+    {
+      "completion_length": 733.675,
+      "epoch": 0.0024689194893318784,
+      "grad_norm": 0.13222694396972656,
+      "kl": 0.001577114372048527,
+      "learning_rate": 4.9870543707400835e-06,
+      "loss": 0.0001,
+      "reward": 0.653125,
+      "reward_std": 0.27914761677384375,
+      "rewards/custom_reward_simplified_v7_dblog": 0.653125,
+      "step": 310
+    },
+    {
+      "completion_length": 711.91875,
+      "epoch": 0.002548562053503875,
+      "grad_norm": 0.19241130352020264,
+      "kl": 0.0017230566183570773,
+      "learning_rate": 4.983095894354858e-06,
+      "loss": 0.0001,
+      "reward": 0.68125,
+      "reward_std": 0.3178554192185402,
+      "rewards/custom_reward_simplified_v7_dblog": 0.68125,
+      "step": 320
     }
   ],
   "logging_steps": 10,