Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4107159b4de1a0016c3037c95f8767db5293436cfc3872136bfe4ef2abab1c4
+oid sha256:ad0b22f4c3fa1b0139f319b31f120f94f28b3d037fbb6f6aed33ac60c75fb708
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7a2e6285b957e4b33a1874bb188455e0aee029f3189c5296dea9eb7f8a4b5e5
+oid sha256:76d5ec4547d549feb7f149095f1d9f39a0c7aba5593d21cf15934b36908fdb53
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b1cd6f4b1f4bf6d48fec1a76cbc162cf62188f491054248af00ed2b0989265a
+oid sha256:f9ae0526b1acb196d33f4ea3c92cdb224a14eb3e8764b1e44b4b785bd4d28e62
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4dd73233e298447d6740eca7860dc08eb78819edfe930a45b32b54e01d37739
+oid sha256:71b32186a2adf91b57dd5842f0100aa5d92101d2b445791e52f5e416dc7812a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003982128208599804,
+  "epoch": 0.0005973192312899706,
   "eval_steps": 500,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,30 @@
       "reward_std": 0.30715219378471376,
       "rewards/custom_reward_simplified_v7_dblog": 0.621875,
       "step": 50
+    },
+    {
+      "completion_length": 821.60625,
+      "epoch": 0.0004778553850319765,
+      "grad_norm": 0.1834840029478073,
+      "kl": 0.0007538022648077459,
+      "learning_rate": 1.25e-06,
+      "loss": 0.0,
+      "reward": 0.578125,
+      "reward_std": 0.39505376294255257,
+      "rewards/custom_reward_simplified_v7_dblog": 0.578125,
+      "step": 60
+    },
+    {
+      "completion_length": 776.75,
+      "epoch": 0.0005574979492039726,
+      "grad_norm": 0.11483483016490936,
+      "kl": 0.0007510531373554841,
+      "learning_rate": 1.4583333333333335e-06,
+      "loss": 0.0,
+      "reward": 0.584375,
+      "reward_std": 0.32483330443501474,
+      "rewards/custom_reward_simplified_v7_dblog": 0.584375,
+      "step": 70
     }
   ],
   "logging_steps": 10,