Training in progress, step 1100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e63f562503cde4d1609bdfb5b6ab6f77c5fe28e4f0a6050e851ea2af44237d5
+oid sha256:49b80ac9e71a99d4c4c6a019f92f74ac748ae8a3db5b19d23b29551127562576
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d72c9de7fe76e79fa0ee85dee9ef7d5c5eb70eeb4012b9f202e48837659a1230
+oid sha256:2b954913df4d8f33fa5530a046cefed963703da18792e9717aec1ad27ac9b9ac
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0d186837651a0003ac9e9fbed4fdf98fb1ae1d63f07bd77dc2bd854dfe532ca
+oid sha256:29c2d81a2ee2dbcbac40eefdb89ca90568c2c93f1ddee20eba510e848b8988fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380aefd38169e510ac1b1face660871b8639e3f1495c211aa0b0ddac9bd8c95d
+oid sha256:fa66b03381b0dfe975a2c18907018f054a16534d5b1412711280057eb4458970
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008561575648489578,
+  "epoch": 0.00876068205891957,
   "eval_steps": 500,
-  "global_step": 1075,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1291,6 +1291,42 @@
       "reward_std": 0.37070034593343737,
       "rewards/custom_reward_simplified_v7_dblog": 0.865625,
       "step": 1070
+    },
+    {
+      "completion_length": 638.23125,
+      "epoch": 0.008601396930575577,
+      "grad_norm": 0.23796696960926056,
+      "kl": 0.0075248789740726355,
+      "learning_rate": 3.3550503583141726e-06,
+      "loss": 0.0003,
+      "reward": 0.746875,
+      "reward_std": 0.25020881071686746,
+      "rewards/custom_reward_simplified_v7_dblog": 0.746875,
+      "step": 1080
+    },
+    {
+      "completion_length": 634.9375,
+      "epoch": 0.008681039494747573,
+      "grad_norm": 0.2958204448223114,
+      "kl": 0.006533738202415406,
+      "learning_rate": 3.3207929380339034e-06,
+      "loss": 0.0003,
+      "reward": 0.896875,
+      "reward_std": 0.38549663573503495,
+      "rewards/custom_reward_simplified_v7_dblog": 0.896875,
+      "step": 1090
+    },
+    {
+      "completion_length": 661.2625,
+      "epoch": 0.00876068205891957,
+      "grad_norm": 0.007367302197962999,
+      "kl": 0.007355101336725056,
+      "learning_rate": 3.2863618903790346e-06,
+      "loss": 0.0003,
+      "reward": 0.71875,
+      "reward_std": 0.25932966247200967,
+      "rewards/custom_reward_simplified_v7_dblog": 0.71875,
+      "step": 1100
     }
   ],
   "logging_steps": 10,