Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02a8faa5615c04b1d54c94aeef6dc48105f780e4600e7eb5c4867bb627bdeab
+oid sha256:8552145847bfeab4636144433c43db62dcc91675e6d80bf8a61ef9290e9fc440
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c5b0c837c7e20527f21e9fa9165cd1531678ee468a19f2840ff680cde906a4a
+oid sha256:eea82d271c17fd83a4656876cadcc33c1faa5ce883f21449769fbb145e1864a9
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d8dad906bd8d5d7d412b2e015c576ead9f79eec52fb6b8380d832bbdd892497
+oid sha256:ee66f0b7a716e07b51f02c7e7cb42ecc8627dd065518adcf55ce909d0ef818d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4855e84feafd6cb690dd0a0e35b0faeffec05476b505ea8cc93bf6ce3a96076f
+oid sha256:c12eb55eb955504de5fa1d8a599d32de65813670b5001ef30e45d7a6b99dbe1f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004380341029459785,
+  "epoch": 0.004778553850319765,
   "eval_steps": 500,
-  "global_step": 550,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -667,6 +667,66 @@
       "reward_std": 0.1355846919119358,
       "rewards/custom_reward_logic_v2": 0.11875000149011612,
       "step": 550
+    },
+    {
+      "completion_length": 19.2625,
+      "epoch": 0.004459983593631781,
+      "grad_norm": 0.5744329690933228,
+      "kl": 0.3458960048854351,
+      "learning_rate": 1.2500000000000007e-06,
+      "loss": 0.0138,
+      "reward": 0.3293750025331974,
+      "reward_std": 0.104243653267622,
+      "rewards/custom_reward_logic_v2": 0.3293750025331974,
+      "step": 560
+    },
+    {
+      "completion_length": 20.05625,
+      "epoch": 0.004539626157803777,
+      "grad_norm": 0.1549508273601532,
+      "kl": 0.346449576318264,
+      "learning_rate": 1.1567509791329402e-06,
+      "loss": 0.0139,
+      "reward": 0.17625000029802323,
+      "reward_std": 0.1429968483746052,
+      "rewards/custom_reward_logic_v2": 0.17625000029802323,
+      "step": 570
+    },
+    {
+      "completion_length": 19.86875,
+      "epoch": 0.004619268721975773,
+      "grad_norm": 0.14351911842823029,
+      "kl": 0.39532790407538415,
+      "learning_rate": 1.0660589091223854e-06,
+      "loss": 0.0158,
+      "reward": 0.17437500022351743,
+      "reward_std": 0.13940104842185974,
+      "rewards/custom_reward_logic_v2": 0.17437500022351743,
+      "step": 580
+    },
+    {
+      "completion_length": 19.28125,
+      "epoch": 0.004698911286147769,
+      "grad_norm": 1.1975979804992676,
+      "kl": 0.3690756544470787,
+      "learning_rate": 9.780964274781984e-07,
+      "loss": 0.0148,
+      "reward": 0.20562500059604644,
+      "reward_std": 0.11339747980237007,
+      "rewards/custom_reward_logic_v2": 0.20562500059604644,
+      "step": 590
+    },
+    {
+      "completion_length": 18.3125,
+      "epoch": 0.004778553850319765,
+      "grad_norm": 0.03664500266313553,
+      "kl": 0.34169030636548997,
+      "learning_rate": 8.930309757836517e-07,
+      "loss": 0.0137,
+      "reward": 0.12624999806284903,
+      "reward_std": 0.1257291093468666,
+      "rewards/custom_reward_logic_v2": 0.12624999806284903,
+      "step": 600
     }
   ],
   "logging_steps": 10,