Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb6e71a1e28b3aba614e426a2fbc2bcb705c83f0b070a3e888b842f40310d841
+oid sha256:575fd8a3463636b0a5ed47406da03696ed99629f29cacc881d9a4b56ea27aac1
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8413b33e2e85a340cbcc68703f3aa46c996cc4c32c529fddfcc3fbf619f63bf
+oid sha256:e76d32c587c90bf3d5827d1d9ffa22ffbea8639febe11e8dcb6fb12c5cd9882b
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7b818151754691e6d6ffe05a86f56abc9f9f5205b4e49f106fe82c8a94db19d
+oid sha256:83c1bb9c73018fe7474ba6ddcf921b0802e6c3218e062b8431ab82c45d2a02a9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:969fe9983cc765478664b8c72ec157254f1c831b497badf8d15b3e12b0b55e10
+oid sha256:9d0bbbfb70ecfaf471fd7271fe38ee4e61cc2a6b26655685db6d059ed6469e6b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006968724365049657,
+  "epoch": 0.0071678307754796475,
   "eval_steps": 500,
-  "global_step": 875,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1051,6 +1051,42 @@
       "reward_std": 0.1984293892979622,
       "rewards/custom_reward_simplified_v7_dblog": 0.71875,
       "step": 870
+    },
+    {
+      "completion_length": 591.325,
+      "epoch": 0.0070085456471356555,
+      "grad_norm": 0.12898898124694824,
+      "kl": 0.006013317289762199,
+      "learning_rate": 3.992896479256966e-06,
+      "loss": 0.0002,
+      "reward": 0.875,
+      "reward_std": 0.31373453289270403,
+      "rewards/custom_reward_simplified_v7_dblog": 0.875,
+      "step": 880
+    },
+    {
+      "completion_length": 709.64375,
+      "epoch": 0.0070881882113076515,
+      "grad_norm": 0.1858564019203186,
+      "kl": 0.006654553860425949,
+      "learning_rate": 3.963573584424852e-06,
+      "loss": 0.0003,
+      "reward": 0.875,
+      "reward_std": 0.40053595080971716,
+      "rewards/custom_reward_simplified_v7_dblog": 0.875,
+      "step": 890
+    },
+    {
+      "completion_length": 693.86875,
+      "epoch": 0.0071678307754796475,
+      "grad_norm": 0.23618744313716888,
+      "kl": 0.006588698271661997,
+      "learning_rate": 3.933941090877615e-06,
+      "loss": 0.0003,
+      "reward": 0.6875,
+      "reward_std": 0.22922600656747819,
+      "rewards/custom_reward_simplified_v7_dblog": 0.6875,
+      "step": 900
     }
   ],
   "logging_steps": 10,