Training in progress, step 650, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eb3aa44f269ffa5572efdf1fb7fc717225ec2c5cb1f0c48883e932186e48135
+oid sha256:625a21c77a03e7670d44e04f71c2473872e7ed4ad5d475a7e76da3c29e1b9a27
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:875f7c60ca5bfb35ef2ee985d4da925dfcc149e6e487b381cd6f5c04c4247823
+oid sha256:c67fcdb36d157f73a4a0452b62d3475bd17106fae465e9d1344b8e4b91254250
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d2b20723f64b1ac04e3f994e5af1f73988278694f53314ca6efef6bb7012b0
+oid sha256:0e76c8093c9b880e90996470acd3b3e3832c8c82b9cf3e1531ae1a9a546d6e57
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:874d9ce62dc6f45e681b63f622889e24984460dea2c83350ae46c74f8b0e00de
+oid sha256:c9bfd244e2fa1bd0110a4ec7d9f4a9b3e95e47c2873117c7c7046f6378741404
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004977660260749755,
+  "epoch": 0.005176766671179746,
   "eval_steps": 500,
-  "global_step": 625,
+  "global_step": 650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -751,6 +751,42 @@
       "reward_std": 0.2689620770514011,
       "rewards/custom_reward_simplified_v7_dblog": 0.6,
       "step": 620
+    },
+    {
+      "completion_length": 718.825,
+      "epoch": 0.005017481542835753,
+      "grad_norm": 0.12771090865135193,
+      "kl": 0.005165508517529815,
+      "learning_rate": 4.608478614532215e-06,
+      "loss": 0.0002,
+      "reward": 0.728125,
+      "reward_std": 0.3053886480629444,
+      "rewards/custom_reward_simplified_v7_dblog": 0.728125,
+      "step": 630
+    },
+    {
+      "completion_length": 629.525,
+      "epoch": 0.00509712410700775,
+      "grad_norm": 0.17840693891048431,
+      "kl": 0.005059469246771186,
+      "learning_rate": 4.588719528532342e-06,
+      "loss": 0.0002,
+      "reward": 0.721875,
+      "reward_std": 0.298052953928709,
+      "rewards/custom_reward_simplified_v7_dblog": 0.721875,
+      "step": 640
+    },
+    {
+      "completion_length": 668.68125,
+      "epoch": 0.005176766671179746,
+      "grad_norm": 0.12746350467205048,
+      "kl": 0.004331990797072649,
+      "learning_rate": 4.568518602853776e-06,
+      "loss": 0.0002,
+      "reward": 0.746875,
+      "reward_std": 0.22913563549518584,
+      "rewards/custom_reward_simplified_v7_dblog": 0.746875,
+      "step": 650
     }
   ],
   "logging_steps": 10,