Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dcfcc5c43310ecd0c961788b01c80e5440d47ed9c8f7714cccd89f2fa17bedf
+oid sha256:c6eafefee0320e815b41cd1c372de5045c92d662850ead8335e9933bded3ffee
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f460d2e5601bb9d9dcec379b1d6ceebe856b05e27a9a009dc3184ce61288dc0
+oid sha256:d6e7477ee9cd1942c3cf2071cd1e62eff9d1fb641bfc6e985991dd2a8b3d9e48
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66fb9abea73c246645ead0d444f9a4b672caf441e06583ad60e47f127001ac47
+oid sha256:441b25f23e0b238e4325eb716785213ab08957f30469c189c75a3f86ebbb4062
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5452c112a4badabde57c9618a73febc995d1a66be51910ea7f6e7405e540f5cc
+oid sha256:24517d315a7980594afa12b7baa514099581cb54a0233e1a52a9ab1668536e77
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0013937448730099314,
+  "epoch": 0.0015928512834399217,
   "eval_steps": 500,
-  "global_step": 175,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -211,6 +211,42 @@
       "reward_std": 0.3232325129210949,
       "rewards/custom_reward_simplified_v7_dblog": 0.828125,
       "step": 170
+    },
+    {
+      "completion_length": 704.2,
+      "epoch": 0.0014335661550959294,
+      "grad_norm": 0.22581899166107178,
+      "kl": 0.0008706353197339922,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0,
+      "reward": 0.621875,
+      "reward_std": 0.2438264600932598,
+      "rewards/custom_reward_simplified_v7_dblog": 0.621875,
+      "step": 180
+    },
+    {
+      "completion_length": 738.2625,
+      "epoch": 0.0015132087192679256,
+      "grad_norm": 0.20901009440422058,
+      "kl": 0.000852665287675336,
+      "learning_rate": 3.958333333333333e-06,
+      "loss": 0.0,
+      "reward": 0.659375,
+      "reward_std": 0.2661551833152771,
+      "rewards/custom_reward_simplified_v7_dblog": 0.659375,
+      "step": 190
+    },
+    {
+      "completion_length": 773.31875,
+      "epoch": 0.0015928512834399217,
+      "grad_norm": 0.14023999869823456,
+      "kl": 0.0008427878346992657,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.0,
+      "reward": 0.575,
+      "reward_std": 0.263551290333271,
+      "rewards/custom_reward_simplified_v7_dblog": 0.575,
+      "step": 200
     }
   ],
   "logging_steps": 10,