Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd787e707294bb8bff5a0916c3fc1454572d55e0dd5aa3f2c0e8c49ccd9c4af3
+oid sha256:cc3cf965cb3e46bce1a07e647d9e64ded38cef1306287e6c24c592e3bafdafa6
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6f84bfa1b6ca95587c76a1fd509c395f4674dc76fe078a46e0a319386062a54
+oid sha256:99f35c97132fdb9c45702a3a626946b943e4f0e9d6e04d821cf969f555bfc36f
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a3313de4fd5d6c377ad3ad093a56c26fc951ef200a8e1b32181726369bbbd9a
+oid sha256:9dc64f06f07f11b5133abb444d47a3661de90bef33673b0253120e1e16093534
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d875190fd38553ed31bf8899557c08005bdf782b4117087e46fd1724f637210
+oid sha256:e96b3a3c408ef67987cac348d29150759cd1e3152271b07b879ff530abc69a0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001991064104299902,
+  "epoch": 0.0023892769251598824,
   "eval_steps": 500,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -307,6 +307,66 @@
       "reward_std": 0.11504097878932953,
       "rewards/custom_reward_logic_v2": 0.17062499970197678,
       "step": 250
+    },
+    {
+      "completion_length": 20.475,
+      "epoch": 0.002070706668471898,
+      "grad_norm": 0.03645075112581253,
+      "kl": 0.3291649468243122,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.0132,
+      "reward": 0.16500000059604644,
+      "reward_std": 0.1858065977692604,
+      "rewards/custom_reward_logic_v2": 0.16500000059604644,
+      "step": 260
+    },
+    {
+      "completion_length": 24.5625,
+      "epoch": 0.0021503492326438944,
+      "grad_norm": 1.1167131662368774,
+      "kl": 0.33756194859743116,
+      "learning_rate": 4.188975519039151e-06,
+      "loss": 0.0135,
+      "reward": 0.10505000110715627,
+      "reward_std": 0.0828484557569027,
+      "rewards/custom_reward_logic_v2": 0.10505000110715627,
+      "step": 270
+    },
+    {
+      "completion_length": 19.925,
+      "epoch": 0.0022299917968158904,
+      "grad_norm": 0.8635123372077942,
+      "kl": 0.32979664355516436,
+      "learning_rate": 4.106969024216348e-06,
+      "loss": 0.0132,
+      "reward": 0.20062500163912772,
+      "reward_std": 0.1258012667298317,
+      "rewards/custom_reward_logic_v2": 0.20062500163912772,
+      "step": 280
+    },
+    {
+      "completion_length": 41.35625,
+      "epoch": 0.0023096343609878864,
+      "grad_norm": 0.7731335163116455,
+      "kl": 0.29900490418076514,
+      "learning_rate": 4.021903572521802e-06,
+      "loss": 0.012,
+      "reward": 0.13356250263750552,
+      "reward_std": 0.11855373680591583,
+      "rewards/custom_reward_logic_v2": 0.13356250263750552,
+      "step": 290
+    },
+    {
+      "completion_length": 21.425,
+      "epoch": 0.0023892769251598824,
+      "grad_norm": 0.050558220595121384,
+      "kl": 0.30905950888991357,
+      "learning_rate": 3.933941090877615e-06,
+      "loss": 0.0124,
+      "reward": 0.10625000111758709,
+      "reward_std": 0.07851103022694587,
+      "rewards/custom_reward_logic_v2": 0.10625000111758709,
+      "step": 300
     }
   ],
   "logging_steps": 10,