Training in progress, step 1775, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64cb29f82be51963b1c87a3edf410599592d499ccb583a2211299eabdac88a5e
+oid sha256:8e2c3606d105778d2ad52a9929454b6500e9dad632955abc53e367369ee8cf11
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba89ced11fa4b1eb1cfa02eb7f638c31d45ea49afc6a96d68cbdaf46dd9663d2
+oid sha256:a09d65533862bb84db4ad2c2ef03e6893ae717ada1dde1f28e1eb0545f110c48
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11f42b997535391b4778f6818a4f5d5cc944d2434ea0edc70a8def90290e971a
+oid sha256:b93ee4ceedea4c9809598398bc87394d87452555dce21749fc446d80d119bbbb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f817dba2e28a76d635b3c9e18d88eacd11804518703ee89b156fb1819d644283
+oid sha256:acadfa6d8db3781b893a2bf0f73f52abc764193d670917cda9d349cab0588ef0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013937448730099314,
+  "epoch": 0.014136555140529304,
   "eval_steps": 500,
-  "global_step": 1750,
+  "global_step": 1775,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2107,6 +2107,30 @@
       "reward_std": 0.23927971720695496,
       "rewards/custom_reward_simplified_v7_dblog": 0.915625,
       "step": 1750
+    },
+    {
+      "completion_length": 715.2125,
+      "epoch": 0.014017091294271311,
+      "grad_norm": 0.2587921619415283,
+      "kl": 0.017100332980044188,
+      "learning_rate": 1.0071035207430352e-06,
+      "loss": 0.0007,
+      "reward": 0.74375,
+      "reward_std": 0.2990465022623539,
+      "rewards/custom_reward_simplified_v7_dblog": 0.74375,
+      "step": 1760
+    },
+    {
+      "completion_length": 682.74375,
+      "epoch": 0.014096733858443306,
+      "grad_norm": 0.24313370883464813,
+      "kl": 0.01778110705781728,
+      "learning_rate": 9.780964274781984e-07,
+      "loss": 0.0007,
+      "reward": 0.68125,
+      "reward_std": 0.2005969136953354,
+      "rewards/custom_reward_simplified_v7_dblog": 0.68125,
+      "step": 1770
     }
   ],
   "logging_steps": 10,