Training in progress, step 550, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b251bf8f717d2eaad015081b982f4929a58a8d9661edee6c24f307df8efcdf3
+oid sha256:d02a8faa5615c04b1d54c94aeef6dc48105f780e4600e7eb5c4867bb627bdeab
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cbe10b1599bcc43e19eaf8c8e8e5a8697c1f3e4e5b61977144271a6a8f7fed3
+oid sha256:1c5b0c837c7e20527f21e9fa9165cd1531678ee468a19f2840ff680cde906a4a
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a0f93278d443d2a03483a44ae35cd09803c07ecb28455d1fbcbcd3d1ff96845
+oid sha256:2d8dad906bd8d5d7d412b2e015c576ead9f79eec52fb6b8380d832bbdd892497
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a08ec2cb61042f6a4c8de11b52973f8ea774d1a9c9a71eab79348a724979acbf
+oid sha256:4855e84feafd6cb690dd0a0e35b0faeffec05476b505ea8cc93bf6ce3a96076f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003982128208599804,
+  "epoch": 0.004380341029459785,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -607,6 +607,66 @@
       "reward_std": 0.10076134353876114,
       "rewards/custom_reward_logic_v2": 0.13374999910593033,
       "step": 500
+    },
+    {
+      "completion_length": 18.61875,
+      "epoch": 0.0040617707727718,
+      "grad_norm": 1.673584222793579,
+      "kl": 0.3592236742377281,
+      "learning_rate": 1.7482355012393177e-06,
+      "loss": 0.0144,
+      "reward": 0.14000000134110452,
+      "reward_std": 0.09233622029423713,
+      "rewards/custom_reward_logic_v2": 0.14000000134110452,
+      "step": 510
+    },
+    {
+      "completion_length": 20.41875,
+      "epoch": 0.004141413336943796,
+      "grad_norm": 1.1183210611343384,
+      "kl": 0.33706687912344935,
+      "learning_rate": 1.6449496416858285e-06,
+      "loss": 0.0135,
+      "reward": 0.10500000081956387,
+      "reward_std": 0.09869231358170509,
+      "rewards/custom_reward_logic_v2": 0.10500000081956387,
+      "step": 520
+    },
+    {
+      "completion_length": 20.8125,
+      "epoch": 0.004221055901115793,
+      "grad_norm": 0.4382721185684204,
+      "kl": 0.3610161267220974,
+      "learning_rate": 1.5432914190872757e-06,
+      "loss": 0.0144,
+      "reward": 0.19562500044703485,
+      "reward_std": 0.1188055507838726,
+      "rewards/custom_reward_logic_v2": 0.19562500044703485,
+      "step": 530
+    },
+    {
+      "completion_length": 19.46875,
+      "epoch": 0.004300698465287789,
+      "grad_norm": 1.3095043897628784,
+      "kl": 0.34188042730093005,
+      "learning_rate": 1.443454345648252e-06,
+      "loss": 0.0137,
+      "reward": 0.20749999955296516,
+      "reward_std": 0.19307591021060944,
+      "rewards/custom_reward_logic_v2": 0.20749999955296516,
+      "step": 540
+    },
+    {
+      "completion_length": 21.63125,
+      "epoch": 0.004380341029459785,
+      "grad_norm": 0.04259713739156723,
+      "kl": 0.3633933149278164,
+      "learning_rate": 1.3456284669124159e-06,
+      "loss": 0.0145,
+      "reward": 0.11875000149011612,
+      "reward_std": 0.1355846919119358,
+      "rewards/custom_reward_logic_v2": 0.11875000149011612,
+      "step": 550
     }
   ],
   "logging_steps": 10,