Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cacbbfc56d391184888aa9988c9623102b11e0c5c6148c788c143ab677975a0
+oid sha256:fd43e66f1742ac947be1f0dc761704ca288dee8b53a1f2c8ac1ceffbdd7549a1
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb171f10034814744a50a6706f15be399005a3d17ff58bf5a682ba1f7e18f775
+oid sha256:a0d3e4cffe85f4acacdf78061fcb1e34e52393afc3937dc544fb6043b383d348
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:876f813d0b3daa10f80151c471970ca9ac357d5142b2911eac6c7f304a8b5d03
+oid sha256:5ff9aa06f3822fca277644ab91ef439c8d8d33c82c9dcaffe93fc59938b3059f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3d7fb31ee0a8472be5b464827ea90bb43e1dac4d2373a8313c33126d4dc9adc
+oid sha256:36405581658bcd0529d0f6715e48fce527aa3927cda602e0b7c0c66f1886419d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012543703857089384,
+  "epoch": 0.012742810267519373,
   "eval_steps": 500,
-  "global_step": 1575,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1891,6 +1891,42 @@
       "reward_std": 0.2820776253938675,
       "rewards/custom_reward_simplified_v7_dblog": 0.79375,
       "step": 1570
+    },
+    {
+      "completion_length": 695.91875,
+      "epoch": 0.012583525139175381,
+      "grad_norm": 0.2425900250673294,
+      "kl": 0.013333506928756834,
+      "learning_rate": 1.5769846317182894e-06,
+      "loss": 0.0005,
+      "reward": 0.7625,
+      "reward_std": 0.2879462748765945,
+      "rewards/custom_reward_simplified_v7_dblog": 0.7625,
+      "step": 1580
+    },
+    {
+      "completion_length": 673.99375,
+      "epoch": 0.012663167703347376,
+      "grad_norm": 0.2331763356924057,
+      "kl": 0.013234515953809024,
+      "learning_rate": 1.5432914190872757e-06,
+      "loss": 0.0005,
+      "reward": 0.775,
+      "reward_std": 0.2913659870624542,
+      "rewards/custom_reward_simplified_v7_dblog": 0.775,
+      "step": 1590
+    },
+    {
+      "completion_length": 678.54375,
+      "epoch": 0.012742810267519373,
+      "grad_norm": 0.16657988727092743,
+      "kl": 0.012798944069072605,
+      "learning_rate": 1.509800584902108e-06,
+      "loss": 0.0005,
+      "reward": 0.759375,
+      "reward_std": 0.2901748239994049,
+      "rewards/custom_reward_simplified_v7_dblog": 0.759375,
+      "step": 1600
     }
   ],
   "logging_steps": 10,