Training in progress, step 175, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:554efc4b31a2b5b45666110a342ac5c45b243dfe12be5334b44fda80de8f5aa4
+oid sha256:6dcfcc5c43310ecd0c961788b01c80e5440d47ed9c8f7714cccd89f2fa17bedf
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc8a2d96c7bf68d9800f4176d313fab93b3142d7c82237e72e2ae4d9f3e4cb61
+oid sha256:5f460d2e5601bb9d9dcec379b1d6ceebe856b05e27a9a009dc3184ce61288dc0
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edea5f37f705ad565383833c9ad60f92237a837032a0c28939c687cad7d33003
+oid sha256:66fb9abea73c246645ead0d444f9a4b672caf441e06583ad60e47f127001ac47
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30a96a106a18e32bbd701b0dcdc53e964437fa7e7a4942bad969ac65b7f0ae1f
+oid sha256:5452c112a4badabde57c9618a73febc995d1a66be51910ea7f6e7405e540f5cc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011946384625799412,
+  "epoch": 0.0013937448730099314,
   "eval_steps": 500,
-  "global_step": 150,
+  "global_step": 175,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,30 @@
       "reward_std": 0.2411833107471466,
       "rewards/custom_reward_simplified_v7_dblog": 0.675,
       "step": 150
+    },
+    {
+      "completion_length": 735.4375,
+      "epoch": 0.0012742810267519374,
+      "grad_norm": 0.12408847361803055,
+      "kl": 0.0008089728711638599,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.0,
+      "reward": 0.5875,
+      "reward_std": 0.2907834567129612,
+      "rewards/custom_reward_simplified_v7_dblog": 0.5875,
+      "step": 160
+    },
+    {
+      "completion_length": 630.76875,
+      "epoch": 0.0013539235909239334,
+      "grad_norm": 0.14481835067272186,
+      "kl": 0.0008351787488209084,
+      "learning_rate": 3.5416666666666673e-06,
+      "loss": 0.0,
+      "reward": 0.828125,
+      "reward_std": 0.3232325129210949,
+      "rewards/custom_reward_simplified_v7_dblog": 0.828125,
+      "step": 170
     }
   ],
   "logging_steps": 10,