Training in progress, step 125, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48406050723c4632b096d9bb5f922fc4638bde018d7273a6c359d2017a3916b8
+oid sha256:61d5f3b3956507a0db89b2b255c80a675f44ff5e99a7e6ae7ea27a9dbae5245c
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6f81017639429f085cf1beb42eb4e21b11abf84c9e1924adaa18ff234eacd34
+oid sha256:640381d5936ef49033582656f8fe75d216ab5ee94c287238fec5029f5c57db33
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:012809816f8c97fb24144c32b6f5a3f835af1ad5ede967dfa219831a392cc24c
+oid sha256:841fc0dbc0dff2d8abfca3a999fe5c384dfee0019e02325f871bf3d7abbde657
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f27b85f7221203fd913f6c70f81149a3b5542007e2a85414a014e6774bb0b432
+oid sha256:51e44ce6c7f1c4d261c4ea0ef93ba7bc8b23a59d005cedfd24704873d0d6bb0b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007964256417199608,
+  "epoch": 0.000995532052149951,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 125,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -127,6 +127,30 @@
       "reward_std": 0.21242836564779283,
       "rewards/custom_reward_simplified_v7_dblog": 0.528125,
       "step": 100
+    },
+    {
+      "completion_length": 784.64375,
+      "epoch": 0.0008760682058919569,
+      "grad_norm": 0.17609436810016632,
+      "kl": 0.0007660316972760483,
+      "learning_rate": 2.2916666666666666e-06,
+      "loss": 0.0,
+      "reward": 0.565625,
+      "reward_std": 0.3309394560754299,
+      "rewards/custom_reward_simplified_v7_dblog": 0.565625,
+      "step": 110
+    },
+    {
+      "completion_length": 717.24375,
+      "epoch": 0.000955710770063953,
+      "grad_norm": 0.14550578594207764,
+      "kl": 0.0007782038446748629,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0,
+      "reward": 0.728125,
+      "reward_std": 0.2573545627295971,
+      "rewards/custom_reward_simplified_v7_dblog": 0.728125,
+      "step": 120
     }
   ],
   "logging_steps": 10,