Training in progress, step 225, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e0c0312e5d68a617b731e5ae10eccfe40d0d64b3f27dea0ffa030ff8b83fb41
+oid sha256:f6d4f82c92299dca63120186f0dfcfc4397d8035916baeae054019f9d4571b31
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7571d5a08ded40aaca073f6f26e15fc97673c1532bb295b78d723153bf8aabe
+oid sha256:06441d5b8f7c6df96d752009c136daa63d2e5192d0436e9f517a05256a29a1d9
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5cd380542ca6ebdc2c9615a2d202de165264f9d2ae58f7b2bfacb9d8de839ee
+oid sha256:7af19617d12f68973b352b4834e4eae0cfac54a05ebec7fdf2cf9672e9fc60e7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24517d315a7980594afa12b7baa514099581cb54a0233e1a52a9ab1668536e77
+oid sha256:e7650a78b3490703284735e08ba7951c4a36bd15b43b4406fe9c06b41821adef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0015928512834399217,
+  "epoch": 0.0017919576938699119,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 225,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,30 @@
       "reward_std": 1.1132041677832603,
       "rewards/custom_reward_logic_v4_batch_streak": -2.1110031098127364,
       "step": 200
+    },
+    {
+      "completion_length": 706.54375,
+      "epoch": 0.0016724938476119177,
+      "grad_norm": 0.26098617911338806,
+      "kl": 0.003358338767429814,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 0.0001,
+      "reward": -2.3224770683795213,
+      "reward_std": 1.2092776507139207,
+      "rewards/custom_reward_logic_v4_batch_streak": -2.3224770683795213,
+      "step": 210
+    },
+    {
+      "completion_length": 811.08125,
+      "epoch": 0.0017521364117839139,
+      "grad_norm": 1.0346773862838745,
+      "kl": 0.005868167115841061,
+      "learning_rate": 4.583333333333333e-06,
+      "loss": 0.0002,
+      "reward": -2.6366010539233686,
+      "reward_std": 1.3989030092954635,
+      "rewards/custom_reward_logic_v4_batch_streak": -2.6366010539233686,
+      "step": 220
     }
   ],
   "logging_steps": 10,