Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2113bb192f2baa5cca5eaf82cdc29cc112a196f0d353c65e596bbc93a9194868
+oid sha256:fb4a26b564992bfe1b0c0cbf9877d71a7e4c4cabeff18b9fcdc775fdba1b254f
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d39914c7d80371a45e6dfe8ca4f4df8415bdc590cf39528b2981db04c2d9b5ab
+oid sha256:bda5b6a4da0480b964d69c900d61e56ab25544d0c3fbb12fa357689206e9625d
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3abc69817bfc7e8384f353860e5ac5df7fe0bc25efa8cefc94df527ed53e449a
+oid sha256:21e6e0ff9935bb592aa01d75fb327a21b659c1135b9f0f607483a3ede13d0d3b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aa9ee72eac8c93f8b4aad2310d8b5495ea694aa75e620528535e72bb4aabf2e
+oid sha256:d6a11a087092ce528653bb5e030a3a014f4a88c8ff1a2a24bc7e40980baafb9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013340129498809344,
+  "epoch": 0.013539235909239333,
   "eval_steps": 500,
-  "global_step": 1675,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2011,6 +2011,42 @@
       "reward_std": 0.26727318242192266,
       "rewards/custom_reward_simplified_v7_dblog": 0.6375,
       "step": 1670
+    },
+    {
+      "completion_length": 655.70625,
+      "epoch": 0.013379950780895341,
+      "grad_norm": 0.2751936614513397,
+      "kl": 0.01622524333652109,
+      "learning_rate": 1.2500000000000007e-06,
+      "loss": 0.0006,
+      "reward": 0.878125,
+      "reward_std": 0.284642493724823,
+      "rewards/custom_reward_simplified_v7_dblog": 0.878125,
+      "step": 1680
+    },
+    {
+      "completion_length": 684.98125,
+      "epoch": 0.013459593345067338,
+      "grad_norm": 0.23118546605110168,
+      "kl": 0.01642036633566022,
+      "learning_rate": 1.218643748000337e-06,
+      "loss": 0.0007,
+      "reward": 0.85625,
+      "reward_std": 0.339317075163126,
+      "rewards/custom_reward_simplified_v7_dblog": 0.85625,
+      "step": 1690
+    },
+    {
+      "completion_length": 743.51875,
+      "epoch": 0.013539235909239333,
+      "grad_norm": 0.22867274284362793,
+      "kl": 0.01721250016707927,
+      "learning_rate": 1.1875585491636e-06,
+      "loss": 0.0007,
+      "reward": 0.653125,
+      "reward_std": 0.277196903526783,
+      "rewards/custom_reward_simplified_v7_dblog": 0.653125,
+      "step": 1700
     }
   ],
   "logging_steps": 10,