Training in progress, step 1525, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97bd2071c863777af98b0e0e6835dfbd00b846cf114dd8805232a1e59165eb4d
+oid sha256:684ffe225c9700091e981d7024210dc263a03c53399f30fe5949b6f253fdbcc7
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b07f59c35dc209b4c9a5c3ea67c4ff82d683bff7ee192361d73fa058b15b139
+oid sha256:a687432a9d28051c1c39f8f0f4a0e50ee514d1a0fd3655eab260eb68945b822d
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b84da873207bf99b33af0e8b6206521d9a66d95873145146735310919d6f6590
+oid sha256:99aee5f4fee1e5dcba147a263eab258ec9ed62b758fd41d69b67bd6b96aba2c6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e33b54a8302eb57494695935487eaaa98a78a3203f913dcc4eaf73f18edd66c0
+oid sha256:f8bce7973cc00369755cc2848c8e4a859027c75254c0a4740d15b2cd113fceee
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011946384625799411,
+  "epoch": 0.012145491036229403,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 1525,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1807,6 +1807,30 @@
       "reward_std": 0.22115055918693544,
       "rewards/custom_reward_simplified_v7_dblog": 0.740625,
       "step": 1500
+    },
+    {
+      "completion_length": 640.39375,
+      "epoch": 0.012026027189971408,
+      "grad_norm": 0.17104946076869965,
+      "kl": 0.013007838977500796,
+      "learning_rate": 1.8179000083313483e-06,
+      "loss": 0.0005,
+      "reward": 0.9,
+      "reward_std": 0.28725912123918534,
+      "rewards/custom_reward_simplified_v7_dblog": 0.9,
+      "step": 1510
+    },
+    {
+      "completion_length": 650.7125,
+      "epoch": 0.012105669754143405,
+      "grad_norm": 0.1524449735879898,
+      "kl": 0.012339419685304165,
+      "learning_rate": 1.7829919182222752e-06,
+      "loss": 0.0005,
+      "reward": 0.790625,
+      "reward_std": 0.3324665643274784,
+      "rewards/custom_reward_simplified_v7_dblog": 0.790625,
+      "step": 1520
     }
   ],
   "logging_steps": 10,