Training in progress, step 2075, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7ea22847e98188a86453340ded8ab9bdf3230793a2c9bc304a2ffd7869e39af
+oid sha256:35af942f4f7e0ab45db7f903018b6cf71ae51337cced1f8f73b46d54b9a82ed8
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fa35385ff4e32a5427f6c13df901c2e95399515d52ec2d928f1cd7ff7c2583f
+oid sha256:57c63bb7393c415a2eb7afbc5dedea61fdbc7a7f7559d8b48dbacb220b0a5585
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb420055fb63f75d57b1b7545369c8d9657f0a03d860d3f376a6359b71c8ff8d
+oid sha256:ba432550a2dc4d764434bf1f11c92a249b479470479a548999a9d5143e159384
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bef8bb0cf1916b1807bc9a190bcd4e45ed3fa199d3f2937269b8cfea43853b36
+oid sha256:9fdd2976348f35f1abb273dc4e2e2403036ea1ad8a823c211f3272a4ea13d175
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016326725655259198,
+  "epoch": 0.016525832065689187,
   "eval_steps": 500,
-  "global_step": 2050,
+  "global_step": 2075,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2467,6 +2467,30 @@
       "reward_std": 0.3512172996997833,
       "rewards/custom_reward_simplified_v7_dblog": 0.925,
       "step": 2050
+    },
+    {
+      "completion_length": 678.0375,
+      "epoch": 0.016406368219431193,
+      "grad_norm": 0.20536966621875763,
+      "kl": 0.017746813944540918,
+      "learning_rate": 2.9949652204972257e-07,
+      "loss": 0.0007,
+      "reward": 0.828125,
+      "reward_std": 0.34475562572479246,
+      "rewards/custom_reward_simplified_v7_dblog": 0.828125,
+      "step": 2060
+    },
+    {
+      "completion_length": 634.36875,
+      "epoch": 0.016486010783603188,
+      "grad_norm": 0.26798176765441895,
+      "kl": 0.017110086302272974,
+      "learning_rate": 2.8247291705444575e-07,
+      "loss": 0.0007,
+      "reward": 0.89375,
+      "reward_std": 0.24814453721046448,
+      "rewards/custom_reward_simplified_v7_dblog": 0.89375,
+      "step": 2070
     }
   ],
   "logging_steps": 10,