Training in progress, step 2400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf8a4840744445d7b5c7b194ce939998d6352bc50adf06a5d078481ee8297373
+oid sha256:1501691ebe2cf9397cb54c3eeb500f35a68345eee09e02b5b4f2c21ce641dc93
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b9dc156f7ab8d8c101ab11f89633c51a3e1ef772e6f7e5bdbdb528550c82290
+oid sha256:31d048cbd8874c66c3f4744500a21e9f43f21818be56aa86e8f173d24b0cf6c6
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f8e4772e690bdadd5a1f02432bda81d45b48b1b69475cf388770c2e827ad5db
+oid sha256:07c283c17e83831f8f940a4594b9e35974034ae78d97c9584daa26ac8cfdfe19
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bf8199a4f0174f0fea821cfd5e9428ebb987d6fd85e497fec1ce048c10e54b7
+oid sha256:1da024a2e17d577be47c292f1def586de73347617fba9e5b52c7197d45c2dfdc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01891510899084907,
+  "epoch": 0.01911421540127906,
   "eval_steps": 500,
-  "global_step": 2375,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2851,6 +2851,42 @@
       "reward_std": 0.6412660963833332,
       "rewards/custom_reward_logic_v4_batch_streak_dblog": 1.284224995970726,
       "step": 2370
+    },
+    {
+      "completion_length": 788.575,
+      "epoch": 0.01895493027293507,
+      "grad_norm": 4.536673069000244,
+      "kl": 2.9731951540336015,
+      "learning_rate": 1.0576247944985018e-09,
+      "loss": 0.1189,
+      "reward": 0.850387492030859,
+      "reward_std": 0.4183545672596665,
+      "rewards/custom_reward_logic_v4_batch_streak_dblog": 0.850387492030859,
+      "step": 2380
+    },
+    {
+      "completion_length": 720.825,
+      "epoch": 0.019034572837107064,
+      "grad_norm": 0.19723933935165405,
+      "kl": 1.869138080254197,
+      "learning_rate": 2.6442018223132857e-10,
+      "loss": 0.0748,
+      "reward": 1.344549997150898,
+      "reward_std": 0.4945951491594315,
+      "rewards/custom_reward_logic_v4_batch_streak_dblog": 1.344549997150898,
+      "step": 2390
+    },
+    {
+      "completion_length": 815.04375,
+      "epoch": 0.01911421540127906,
+      "grad_norm": 2.070497989654541,
+      "kl": 3.4263820610009135,
+      "learning_rate": 0.0,
+      "loss": 0.1371,
+      "reward": 0.9367499954998493,
+      "reward_std": 0.5499310284852982,
+      "rewards/custom_reward_logic_v4_batch_streak_dblog": 0.9367499954998493,
+      "step": 2400
     }
   ],
   "logging_steps": 10,
@@ -2865,7 +2901,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }