Training in progress, step 225, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6eafefee0320e815b41cd1c372de5045c92d662850ead8335e9933bded3ffee
+oid sha256:34a6411e06d7323b4ba886f2f2461b8afd426ed479ff597b19ef7b0359672d82
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6e7477ee9cd1942c3cf2071cd1e62eff9d1fb641bfc6e985991dd2a8b3d9e48
+oid sha256:3222dd986f2cf0b4418ec1028d6d51867a1d80b2acb6a7355e159672cb0f0ecc
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:441b25f23e0b238e4325eb716785213ab08957f30469c189c75a3f86ebbb4062
+oid sha256:ea827f0182c4966515c873c0790f7092bd1409f92c72ee68bf8c3a64814f2cda
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24517d315a7980594afa12b7baa514099581cb54a0233e1a52a9ab1668536e77
+oid sha256:e7650a78b3490703284735e08ba7951c4a36bd15b43b4406fe9c06b41821adef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0015928512834399217,
+  "epoch": 0.0017919576938699119,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 225,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,30 @@
       "reward_std": 0.263551290333271,
       "rewards/custom_reward_simplified_v7_dblog": 0.575,
       "step": 200
+    },
+    {
+      "completion_length": 760.4,
+      "epoch": 0.0016724938476119177,
+      "grad_norm": 0.15415024757385254,
+      "kl": 0.0009272771596442908,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 0.0,
+      "reward": 0.578125,
+      "reward_std": 0.3055797599256039,
+      "rewards/custom_reward_simplified_v7_dblog": 0.578125,
+      "step": 210
+    },
+    {
+      "completion_length": 824.94375,
+      "epoch": 0.0017521364117839139,
+      "grad_norm": 0.18523605167865753,
+      "kl": 0.0008898543601389974,
+      "learning_rate": 4.583333333333333e-06,
+      "loss": 0.0,
+      "reward": 0.58125,
+      "reward_std": 0.2951655209064484,
+      "rewards/custom_reward_simplified_v7_dblog": 0.58125,
+      "step": 220
     }
   ],
   "logging_steps": 10,