Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:401978961dd1168d49db0c001e44ddbf141e35d069554f8c55cdb9ad2b54715d
+oid sha256:d558d1688ac2b0773f776e1b01f11ad8d6b0eb98b60b2c83c0a92982a67ea9ef
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45d67aae647ebf61e529eb6feca11e0d9cafeb5cce07e2f59b87bfdd75d11fa3
+oid sha256:e7a8d7e6d4c609cc4c9c06b2f897ea7480f74fe48ee69c6f4734353d452ce614
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f4e21ffdf14984df4f5069eb504ded8dd4c4b808399dffa9af68fdbe44d61f1
+oid sha256:4221eac67cb2222c2e69aeda63b681815cb4044bdeac0d3934f95aca477f1f85
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c9ec2f0cbd550f46761b2fa563ee60b733852f3295892a4071d16a20f455efe
+oid sha256:8a1181d7867e1e99d3e40b537197ac0f6f5cff5e55e17adc3195122e9858dab9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006172298723329696,
+  "epoch": 0.006371405133759687,
   "eval_steps": 500,
-  "global_step": 775,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -931,6 +931,42 @@
       "reward_std": 0.282283828407526,
       "rewards/custom_reward_simplified_v7_dblog": 0.65,
       "step": 770
+    },
+    {
+      "completion_length": 634.79375,
+      "epoch": 0.006212120005415695,
+      "grad_norm": 0.11762549728155136,
+      "kl": 0.005472023575566709,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.0002,
+      "reward": 0.878125,
+      "reward_std": 0.31506996527314185,
+      "rewards/custom_reward_simplified_v7_dblog": 0.878125,
+      "step": 780
+    },
+    {
+      "completion_length": 719.05625,
+      "epoch": 0.006291762569587691,
+      "grad_norm": 0.0052847606129944324,
+      "kl": 0.006504135020077228,
+      "learning_rate": 4.241869758026638e-06,
+      "loss": 0.0003,
+      "reward": 0.628125,
+      "reward_std": 0.2685270056128502,
+      "rewards/custom_reward_simplified_v7_dblog": 0.628125,
+      "step": 790
+    },
+    {
+      "completion_length": 699.19375,
+      "epoch": 0.006371405133759687,
+      "grad_norm": 0.2003583461046219,
+      "kl": 0.005931918846908957,
+      "learning_rate": 4.215604094671835e-06,
+      "loss": 0.0002,
+      "reward": 0.746875,
+      "reward_std": 0.25832219421863556,
+      "rewards/custom_reward_simplified_v7_dblog": 0.746875,
+      "step": 800
     }
   ],
   "logging_steps": 10,