Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff241d617f452617d3c88f6cf63325935d4668c5daf5e939cf72829f92a221d4
+oid sha256:8b251bf8f717d2eaad015081b982f4929a58a8d9661edee6c24f307df8efcdf3
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1870f17179349635d5e9f8dc264de59804f82c37fb07d8c3e59aa2307ca2761a
+oid sha256:9cbe10b1599bcc43e19eaf8c8e8e5a8697c1f3e4e5b61977144271a6a8f7fed3
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb5fd2bad97b0505323e94353254cc1ebf7b1bbfc6106a6a54db604a83d738b3
+oid sha256:2a0f93278d443d2a03483a44ae35cd09803c07ecb28455d1fbcbcd3d1ff96845
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf5539fcaa2354df9ab3f6e01030e649c726b26d278c21ce5b06138c07200265
+oid sha256:a08ec2cb61042f6a4c8de11b52973f8ea774d1a9c9a71eab79348a724979acbf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0035839153877398238,
+  "epoch": 0.003982128208599804,
   "eval_steps": 500,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -547,6 +547,66 @@
       "reward_std": 0.10089804157614708,
       "rewards/custom_reward_logic_v2": 0.11125000230967999,
       "step": 450
+    },
+    {
+      "completion_length": 20.14375,
+      "epoch": 0.0036635579519118198,
+      "grad_norm": 0.7745999693870544,
+      "kl": 0.3447819516062737,
+      "learning_rate": 2.2821106431308546e-06,
+      "loss": 0.0138,
+      "reward": 0.11187500096857547,
+      "reward_std": 0.12871785834431648,
+      "rewards/custom_reward_logic_v2": 0.11187500096857547,
+      "step": 460
+    },
+    {
+      "completion_length": 27.35,
+      "epoch": 0.003743200516083816,
+      "grad_norm": 1.4974488019943237,
+      "kl": 0.3425402037799358,
+      "learning_rate": 2.173684519449872e-06,
+      "loss": 0.0137,
+      "reward": 0.10542500019073486,
+      "reward_std": 0.22862085253000258,
+      "rewards/custom_reward_logic_v2": 0.10542500019073486,
+      "step": 470
+    },
+    {
+      "completion_length": 19.40625,
+      "epoch": 0.003822843080255812,
+      "grad_norm": 1.1579034328460693,
+      "kl": 0.3382424309849739,
+      "learning_rate": 2.0658795558326745e-06,
+      "loss": 0.0135,
+      "reward": 0.15562499947845937,
+      "reward_std": 0.1210292175412178,
+      "rewards/custom_reward_logic_v2": 0.15562499947845937,
+      "step": 480
+    },
+    {
+      "completion_length": 37.24375,
+      "epoch": 0.003902485644427808,
+      "grad_norm": 0.7052723169326782,
+      "kl": 0.35214473977684974,
+      "learning_rate": 1.958900965154743e-06,
+      "loss": 0.0141,
+      "reward": 0.07051250115036964,
+      "reward_std": 0.20176818892359732,
+      "rewards/custom_reward_logic_v2": 0.07051250115036964,
+      "step": 490
+    },
+    {
+      "completion_length": 19.23125,
+      "epoch": 0.003982128208599804,
+      "grad_norm": 0.062097422778606415,
+      "kl": 0.3568013899028301,
+      "learning_rate": 1.852952387243698e-06,
+      "loss": 0.0143,
+      "reward": 0.13374999910593033,
+      "reward_std": 0.10076134353876114,
+      "rewards/custom_reward_logic_v2": 0.13374999910593033,
+      "step": 500
     }
   ],
   "logging_steps": 10,