Training in progress, step 1050, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acf8b65d26bdfc64b69f3e90608a32c94c2a3f27197ae54a284d5b9245404c3f
+oid sha256:c517880b0082e2bcb63d8211700cdd79ad1d1f579b6f02724e95147c38123717
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e9de85eb312429ee69f8e14426f2f3e769474f3fe34dfe733c06674a025d84a
+oid sha256:5406ffadfafdfa7cf7f681c6664efb80bcc0b985474ab680a228faccaf8306e8
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d2e06cad0b91681c597821a2e099149e7db006cbb9841142cb4b670c31efa5
+oid sha256:fb85692bb929f1b45dfc4dfc2779fe5d2efe84959814e3288f8282f3bc4be529
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a5009ee8663da9f77ac877c439f2699dd897893282ed3986b78e107ce06efe
+oid sha256:142ecd6835d46a3b266c47dbf70129eebe02431f0096c3935ee9314ce11a43fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008163362827629599,
+  "epoch": 0.008362469238059589,
   "eval_steps": 500,
-  "global_step": 1025,
+  "global_step": 1050,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1231,6 +1231,42 @@
       "reward_std": 0.2714505262672901,
       "rewards/custom_reward_simplified_v7_dblog": 0.85625,
       "step": 1020
+    },
+    {
+      "completion_length": 768.13125,
+      "epoch": 0.008203184109715597,
+      "grad_norm": 0.20112627744674683,
+      "kl": 0.006995444605126977,
+      "learning_rate": 3.5234807863152316e-06,
+      "loss": 0.0003,
+      "reward": 0.609375,
+      "reward_std": 0.2496856138110161,
+      "rewards/custom_reward_simplified_v7_dblog": 0.609375,
+      "step": 1030
+    },
+    {
+      "completion_length": 777.525,
+      "epoch": 0.008282826673887592,
+      "grad_norm": 0.2836349606513977,
+      "kl": 0.007392951846122741,
+      "learning_rate": 3.4901994150978926e-06,
+      "loss": 0.0003,
+      "reward": 0.675,
+      "reward_std": 0.26406350955367086,
+      "rewards/custom_reward_simplified_v7_dblog": 0.675,
+      "step": 1040
+    },
+    {
+      "completion_length": 719.2875,
+      "epoch": 0.008362469238059589,
+      "grad_norm": 0.1799333542585373,
+      "kl": 0.007057315914425999,
+      "learning_rate": 3.4567085809127247e-06,
+      "loss": 0.0003,
+      "reward": 0.790625,
+      "reward_std": 0.33950999528169634,
+      "rewards/custom_reward_simplified_v7_dblog": 0.790625,
+      "step": 1050
     }
   ],
   "logging_steps": 10,