Training in progress, step 550, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad313288ea8bd4797fded900f5d92502d7ff0dd9d929f2a1db1ccbd3e1e33740
+oid sha256:f4e319bb72fcf881fe242f58baf5bee442bfcabe7efa8ee2a6123fc3c7753f60
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c00f667f3ffbf6137ce5e5b8baf4c98bc27a5ccc632b376e644527fc32c15ab1
+oid sha256:9fe0841833c3aef192a5f738cd288e78b91e8ce99d455d56a87784a58337db7f
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d658a8556badd62e9d6635ff217c390c629d34615e7572380487ccf0f8a9b3c0
+oid sha256:dc77916958d85e6199b5b92eb98f14f537090b2e2d1911f8da3b6892667bfb10
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:531811d0588c0d6e2bee2610f6ac488013790b41bf60e0ecfba6c4c413a7b0a2
+oid sha256:836b78645c033d7835fc1f26e632621c612ecb82d0c25e3e148a218afe148029
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004181234619029794,
+  "epoch": 0.004380341029459785,
   "eval_steps": 500,
-  "global_step": 525,
+  "global_step": 550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -631,6 +631,42 @@
       "reward_std": 0.2953102938830853,
       "rewards/custom_reward_simplified_v7_dblog": 0.759375,
       "step": 520
+    },
+    {
+      "completion_length": 633.525,
+      "epoch": 0.004221055901115793,
+      "grad_norm": 0.2159271538257599,
+      "kl": 0.004929024970624596,
+      "learning_rate": 4.780896113382536e-06,
+      "loss": 0.0002,
+      "reward": 0.75625,
+      "reward_std": 0.2647860750555992,
+      "rewards/custom_reward_simplified_v7_dblog": 0.75625,
+      "step": 530
+    },
+    {
+      "completion_length": 586.9125,
+      "epoch": 0.004300698465287789,
+      "grad_norm": 0.2394983470439911,
+      "kl": 0.004724201350472868,
+      "learning_rate": 4.765769467591626e-06,
+      "loss": 0.0002,
+      "reward": 0.975,
+      "reward_std": 0.36022927314043046,
+      "rewards/custom_reward_simplified_v7_dblog": 0.975,
+      "step": 540
+    },
+    {
+      "completion_length": 651.88125,
+      "epoch": 0.004380341029459785,
+      "grad_norm": 0.1552504301071167,
+      "kl": 0.004269527771975845,
+      "learning_rate": 4.750163529660303e-06,
+      "loss": 0.0002,
+      "reward": 0.790625,
+      "reward_std": 0.2759058982133865,
+      "rewards/custom_reward_simplified_v7_dblog": 0.790625,
+      "step": 550
     }
   ],
   "logging_steps": 10,