Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e750621423ac886f4aea94ff42e480d56144368606f985fdaf1baa34df5968ae
+oid sha256:5e0c0312e5d68a617b731e5ae10eccfe40d0d64b3f27dea0ffa030ff8b83fb41
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63f1993d80d795f0978703d3b25ece81be24c6531d13aea08d3dadec69ac5310
+oid sha256:e7571d5a08ded40aaca073f6f26e15fc97673c1532bb295b78d723153bf8aabe
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b12766e373c916cb37c627e7cf53c66a451d52e6861b57d722a581e920af7724
+oid sha256:e5cd380542ca6ebdc2c9615a2d202de165264f9d2ae58f7b2bfacb9d8de839ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5452c112a4badabde57c9618a73febc995d1a66be51910ea7f6e7405e540f5cc
+oid sha256:24517d315a7980594afa12b7baa514099581cb54a0233e1a52a9ab1668536e77
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0013937448730099314,
+  "epoch": 0.0015928512834399217,
   "eval_steps": 500,
-  "global_step": 175,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -211,6 +211,42 @@
       "reward_std": 1.301654589176178,
       "rewards/custom_reward_logic_v4_batch_streak": -1.380665649473667,
       "step": 170
+    },
+    {
+      "completion_length": 676.075,
+      "epoch": 0.0014335661550959294,
+      "grad_norm": 0.23651157319545746,
+      "kl": 0.001932383590610698,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0001,
+      "reward": -2.217651057243347,
+      "reward_std": 1.1832541689276694,
+      "rewards/custom_reward_logic_v4_batch_streak": -2.217651057243347,
+      "step": 180
+    },
+    {
+      "completion_length": 716.3125,
+      "epoch": 0.0015132087192679256,
+      "grad_norm": 0.930211067199707,
+      "kl": 0.0031241982942447066,
+      "learning_rate": 3.958333333333333e-06,
+      "loss": 0.0001,
+      "reward": -2.1449333682656286,
+      "reward_std": 1.272219567000866,
+      "rewards/custom_reward_logic_v4_batch_streak": -2.1449333682656286,
+      "step": 190
+    },
+    {
+      "completion_length": 723.33125,
+      "epoch": 0.0015928512834399217,
+      "grad_norm": 0.23318283259868622,
+      "kl": 0.0023288113647140563,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.0001,
+      "reward": -2.1110031098127364,
+      "reward_std": 1.1132041677832603,
+      "rewards/custom_reward_logic_v4_batch_streak": -2.1110031098127364,
+      "step": 200
     }
   ],
   "logging_steps": 10,