Training in progress, step 925, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:575fd8a3463636b0a5ed47406da03696ed99629f29cacc881d9a4b56ea27aac1
+oid sha256:b84ee20fdeed3b9de615bfb8c89a604ad31460bf4be8d9981259bc49daba7689
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e76d32c587c90bf3d5827d1d9ffa22ffbea8639febe11e8dcb6fb12c5cd9882b
+oid sha256:568ebac81b184bad78bc6124292e26514957855d6547ab1ff84685977fe672bd
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c1bb9c73018fe7474ba6ddcf921b0802e6c3218e062b8431ab82c45d2a02a9
+oid sha256:8bac1fa9dca95bae4349472079f496cd88fa65635d594e791ca9b0c9c4124f64
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d0bbbfb70ecfaf471fd7271fe38ee4e61cc2a6b26655685db6d059ed6469e6b
+oid sha256:078bc51854d278434d7ff9f22a495ff6f5ffaa9f8a1b36cbdab8eec0ef4607eb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0071678307754796475,
+  "epoch": 0.007366937185909637,
   "eval_steps": 500,
-  "global_step": 900,
+  "global_step": 925,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1087,6 +1087,30 @@
       "reward_std": 0.22922600656747819,
       "rewards/custom_reward_simplified_v7_dblog": 0.6875,
       "step": 900
+    },
+    {
+      "completion_length": 655.1,
+      "epoch": 0.0072474733396516436,
+      "grad_norm": 0.18607589602470398,
+      "kl": 0.006554636568762362,
+      "learning_rate": 3.9040052669587325e-06,
+      "loss": 0.0003,
+      "reward": 0.79375,
+      "reward_std": 0.26788339093327523,
+      "rewards/custom_reward_simplified_v7_dblog": 0.79375,
+      "step": 910
+    },
+    {
+      "completion_length": 678.36875,
+      "epoch": 0.0073271159038236396,
+      "grad_norm": 0.15605397522449493,
+      "kl": 0.006827571708709001,
+      "learning_rate": 3.8737724451770155e-06,
+      "loss": 0.0003,
+      "reward": 0.74375,
+      "reward_std": 0.25242582634091376,
+      "rewards/custom_reward_simplified_v7_dblog": 0.74375,
+      "step": 920
     }
   ],
   "logging_steps": 10,