Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad0b22f4c3fa1b0139f319b31f120f94f28b3d037fbb6f6aed33ac60c75fb708
+oid sha256:48406050723c4632b096d9bb5f922fc4638bde018d7273a6c359d2017a3916b8
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76d5ec4547d549feb7f149095f1d9f39a0c7aba5593d21cf15934b36908fdb53
+oid sha256:e6f81017639429f085cf1beb42eb4e21b11abf84c9e1924adaa18ff234eacd34
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9ae0526b1acb196d33f4ea3c92cdb224a14eb3e8764b1e44b4b785bd4d28e62
+oid sha256:012809816f8c97fb24144c32b6f5a3f835af1ad5ede967dfa219831a392cc24c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71b32186a2adf91b57dd5842f0100aa5d92101d2b445791e52f5e416dc7812a5
+oid sha256:f27b85f7221203fd913f6c70f81149a3b5542007e2a85414a014e6774bb0b432
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005973192312899706,
+  "epoch": 0.0007964256417199608,
   "eval_steps": 500,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,42 @@
       "reward_std": 0.32483330443501474,
       "rewards/custom_reward_simplified_v7_dblog": 0.584375,
       "step": 70
+    },
+    {
+      "completion_length": 804.675,
+      "epoch": 0.0006371405133759687,
+      "grad_norm": 0.17995329201221466,
+      "kl": 0.0007302156562218442,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.0,
+      "reward": 0.703125,
+      "reward_std": 0.32263160347938535,
+      "rewards/custom_reward_simplified_v7_dblog": 0.703125,
+      "step": 80
+    },
+    {
+      "completion_length": 793.0875,
+      "epoch": 0.0007167830775479647,
+      "grad_norm": 0.16513389348983765,
+      "kl": 0.0007239854254294187,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 0.0,
+      "reward": 0.709375,
+      "reward_std": 0.3102527566254139,
+      "rewards/custom_reward_simplified_v7_dblog": 0.709375,
+      "step": 90
+    },
+    {
+      "completion_length": 812.0,
+      "epoch": 0.0007964256417199608,
+      "grad_norm": 0.1802467256784439,
+      "kl": 0.0007639184041181579,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 0.0,
+      "reward": 0.528125,
+      "reward_std": 0.21242836564779283,
+      "rewards/custom_reward_simplified_v7_dblog": 0.528125,
+      "step": 100
     }
   ],
   "logging_steps": 10,