Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34a6411e06d7323b4ba886f2f2461b8afd426ed479ff597b19ef7b0359672d82
+oid sha256:b7e059af2fa1682f997e031ec3ea16d4b7f1a901f0a40a963cb0c2bf88a6dcc6
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3222dd986f2cf0b4418ec1028d6d51867a1d80b2acb6a7355e159672cb0f0ecc
+oid sha256:ab6fd2dd4d4671d2a95fba6147743f118484bc79d3ce4925e5e5ad064766fc4a
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea827f0182c4966515c873c0790f7092bd1409f92c72ee68bf8c3a64814f2cda
+oid sha256:c41acd26c86d70d331c5563ab0c5313662afe31133e12a8b590736afe2c91d4c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7650a78b3490703284735e08ba7951c4a36bd15b43b4406fe9c06b41821adef
+oid sha256:5d1617b580f1638489e3c8c2c28b0fae6efb39474b08ccf2fbee4f3c8bf63bcd
 size 1064

last-checkpoint/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0017919576938699119,
+  "epoch": 0.001991064104299902,
   "eval_steps": 500,
-  "global_step": 225,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -271,6 +271,42 @@
       "reward_std": 0.2951655209064484,
       "rewards/custom_reward_simplified_v7_dblog": 0.58125,
       "step": 220
+    },
+    {
+      "completion_length": 748.5375,
+      "epoch": 0.0018317789759559099,
+      "grad_norm": 0.11306847631931305,
+      "kl": 0.0009787698683794588,
+      "learning_rate": 4.791666666666668e-06,
+      "loss": 0.0,
+      "reward": 0.590625,
+      "reward_std": 0.2887454777956009,
+      "rewards/custom_reward_simplified_v7_dblog": 0.590625,
+      "step": 230
+    },
+    {
+      "completion_length": 753.39375,
+      "epoch": 0.001911421540127906,
+      "grad_norm": 0.0014718669699504972,
+      "kl": 0.0010118414385942743,
+      "learning_rate": 5e-06,
+      "loss": 0.0,
+      "reward": 0.55625,
+      "reward_std": 0.1977315753698349,
+      "rewards/custom_reward_simplified_v7_dblog": 0.55625,
+      "step": 240
+    },
+    {
+      "completion_length": 812.71875,
+      "epoch": 0.001991064104299902,
+      "grad_norm": 0.11223085969686508,
+      "kl": 0.0010390775743871928,
+      "learning_rate": 4.999735579817769e-06,
+      "loss": 0.0,
+      "reward": 0.6875,
+      "reward_std": 0.24264758601784706,
+      "rewards/custom_reward_simplified_v7_dblog": 0.6875,
+      "step": 250
     }
   ],
   "logging_steps": 10,