Training in progress, step 875, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ce44bac1ce014ef00371dcfe7ea68b6f02d101b1d59b1aa9f17f88cfa3a6ffd
+oid sha256:fb6e71a1e28b3aba614e426a2fbc2bcb705c83f0b070a3e888b842f40310d841
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6fcd046738e17acd72c93dbe6a5138541324f8eafc50e92bde39626096f2c0c
+oid sha256:f8413b33e2e85a340cbcc68703f3aa46c996cc4c32c529fddfcc3fbf619f63bf
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53c7652a6447ec0e6f7f58ed91608cc677939e784b3d87b8a23910c68dcce8f5
+oid sha256:b7b818151754691e6d6ffe05a86f56abc9f9f5205b4e49f106fe82c8a94db19d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:878236b83e42d9db1519008b5ab4529f212aeb27f63481cc4016850fcb712d03
+oid sha256:969fe9983cc765478664b8c72ec157254f1c831b497badf8d15b3e12b0b55e10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006769617954619667,
+  "epoch": 0.006968724365049657,
   "eval_steps": 500,
-  "global_step": 850,
+  "global_step": 875,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1027,6 +1027,30 @@
       "reward_std": 0.3704014003276825,
       "rewards/custom_reward_simplified_v7_dblog": 0.85625,
       "step": 850
+    },
+    {
+      "completion_length": 545.075,
+      "epoch": 0.006849260518791663,
+      "grad_norm": 0.18576188385486603,
+      "kl": 0.005737546656746417,
+      "learning_rate": 4.0505887281706505e-06,
+      "loss": 0.0002,
+      "reward": 0.9125,
+      "reward_std": 0.27787805944681165,
+      "rewards/custom_reward_simplified_v7_dblog": 0.9125,
+      "step": 860
+    },
+    {
+      "completion_length": 671.1375,
+      "epoch": 0.0069289030829636595,
+      "grad_norm": 0.27761420607566833,
+      "kl": 0.005926149617880583,
+      "learning_rate": 4.021903572521802e-06,
+      "loss": 0.0002,
+      "reward": 0.71875,
+      "reward_std": 0.1984293892979622,
+      "rewards/custom_reward_simplified_v7_dblog": 0.71875,
+      "step": 870
     }
   ],
   "logging_steps": 10,