Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57e448179f163f02dce1db6a2ed8f06113ccac7dbbd3940ddd0928f3493e3587
+oid sha256:2c4096722f61b9f08b3ed290c1ad856624d55b23c6af75829f3062a4c172eadd
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de08977e7da7ce3c09df6909587a0ba30167acf070be772d460e08ad845627fd
+oid sha256:d81bc033a5700fa27dbb81c9943b205da6e2f0eeac2c7f21a7122e7fa46074df
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a738b6930d71dfc873290f4343d30e6bb11aaab4b6548400b3329e4b4787377
+oid sha256:5134dce65814f94d568234e504c6a81c488a705fdf68f481871040907b9769ba
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc973e3447bd6a6f5ad5fae82ce35cd91650677852104987fd5a5dacd81b436
+oid sha256:31f09120e45bcc4193cfd66ac556b20e8f26a1efecd672279cdd630bf09741a4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0033848089773098333,
+  "epoch": 0.0035839153877398238,
   "eval_steps": 500,
-  "global_step": 425,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -511,6 +511,42 @@
       "reward_std": 0.14162895157933236,
       "rewards/custom_reward_logic_v4_batch_streak": 0.28562499955296516,
       "step": 420
+    },
+    {
+      "completion_length": 19.39375,
+      "epoch": 0.0034246302593958313,
+      "grad_norm": 0.124000184237957,
+      "kl": 0.36893701553344727,
+      "learning_rate": 4.905148561184033e-06,
+      "loss": 0.0148,
+      "reward": 0.10037499703466893,
+      "reward_std": 0.09048115760087967,
+      "rewards/custom_reward_logic_v4_batch_streak": 0.10037499703466893,
+      "step": 430
+    },
+    {
+      "completion_length": 20.575,
+      "epoch": 0.0035042728235678278,
+      "grad_norm": 0.5444723963737488,
+      "kl": 0.34243927001953123,
+      "learning_rate": 4.894973780788722e-06,
+      "loss": 0.0137,
+      "reward": 0.17549999970942737,
+      "reward_std": 0.09591511413455009,
+      "rewards/custom_reward_logic_v4_batch_streak": 0.17549999970942737,
+      "step": 440
+    },
+    {
+      "completion_length": 30.30625,
+      "epoch": 0.0035839153877398238,
+      "grad_norm": 0.46829524636268616,
+      "kl": 0.31388519033789636,
+      "learning_rate": 4.884292376870567e-06,
+      "loss": 0.0126,
+      "reward": 0.10238021239638329,
+      "reward_std": 0.17024155631661414,
+      "rewards/custom_reward_logic_v4_batch_streak": 0.10238021239638329,
+      "step": 450
     }
   ],
   "logging_steps": 10,