Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e2c3606d105778d2ad52a9929454b6500e9dad632955abc53e367369ee8cf11
+oid sha256:47a7f2a9e5514ded39fec42ccf85affb0ea83765d8cd5710f5ffae2ac93a7539
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a09d65533862bb84db4ad2c2ef03e6893ae717ada1dde1f28e1eb0545f110c48
+oid sha256:ad0f2461614af492d300b806eb46f3bbcfd9aac2534006fb03315af5654f03d1
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b93ee4ceedea4c9809598398bc87394d87452555dce21749fc446d80d119bbbb
+oid sha256:8238871797f984a007bcc429ff439a023be817586923e09bedcced1680e3b8e1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acadfa6d8db3781b893a2bf0f73f52abc764193d670917cda9d349cab0588ef0
+oid sha256:5affcab53c6bf0c312245e4ec3117742a7ae09a65ad0d199a0c62a7385ad2300
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014136555140529304,
+  "epoch": 0.014335661550959295,
   "eval_steps": 500,
-  "global_step": 1775,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2131,6 +2131,42 @@
       "reward_std": 0.2005969136953354,
       "rewards/custom_reward_simplified_v7_dblog": 0.68125,
       "step": 1770
+    },
+    {
+      "completion_length": 718.31875,
+      "epoch": 0.014176376422615303,
+      "grad_norm": 0.18841393291950226,
+      "kl": 0.015946343122050167,
+      "learning_rate": 9.494112718293503e-07,
+      "loss": 0.0006,
+      "reward": 0.771875,
+      "reward_std": 0.27307887077331544,
+      "rewards/custom_reward_simplified_v7_dblog": 0.771875,
+      "step": 1780
+    },
+    {
+      "completion_length": 707.1875,
+      "epoch": 0.014256018986787298,
+      "grad_norm": 0.2333621084690094,
+      "kl": 0.01652351173106581,
+      "learning_rate": 9.210541217437566e-07,
+      "loss": 0.0007,
+      "reward": 0.8125,
+      "reward_std": 0.2497081995010376,
+      "rewards/custom_reward_simplified_v7_dblog": 0.8125,
+      "step": 1790
+    },
+    {
+      "completion_length": 728.5375,
+      "epoch": 0.014335661550959295,
+      "grad_norm": 0.26783886551856995,
+      "kl": 0.018553019547834993,
+      "learning_rate": 8.930309757836517e-07,
+      "loss": 0.0007,
+      "reward": 0.75,
+      "reward_std": 0.28967257887125014,
+      "rewards/custom_reward_simplified_v7_dblog": 0.75,
+      "step": 1800
     }
   ],
   "logging_steps": 10,