Training in progress, step 1325, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94e10e53c76f7ff04829e808c63c93839ebd5429cd67f49bbfeea277b83d07a7
+oid sha256:74682732035656f7a989ee44f1f36f8e416b584aa4564d6a3765d685f4981071
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b3cd44e38766e505ffcc5fc493c2a4306d24f1992cf69d3a5db1a4116a556db
+oid sha256:337ffc24497931d1740d801f5febab092071f825b7858ec9a867066b6a02e90c
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e345de18b4130f225fcea63e9859bfd38ec06f643e0ce309fd7f3ed7f28326
+oid sha256:57cab1721b5ddb43639ccad6e4533ec798a026a004201613eb0b4122b1bbb3f9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dccb9bdfb0022ab0fbffb27c30bb70e7698ed3c92675c6050a89f10b3cdf6042
+oid sha256:13318808563c2924b4edd2b4e6dbfa122edfbebfd027b1583aa4d422089a88ec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010353533342359491,
+  "epoch": 0.010552639752789481,
   "eval_steps": 500,
-  "global_step": 1300,
+  "global_step": 1325,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1567,6 +1567,30 @@
       "reward_std": 0.21537503451108933,
       "rewards/custom_reward_simplified_v7_dblog": 0.709375,
       "step": 1300
+    },
+    {
+      "completion_length": 650.58125,
+      "epoch": 0.010433175906531486,
+      "grad_norm": 0.14920295774936676,
+      "kl": 0.009564152918756008,
+      "learning_rate": 2.5363597441289574e-06,
+      "loss": 0.0004,
+      "reward": 0.828125,
+      "reward_std": 0.2882704295217991,
+      "rewards/custom_reward_simplified_v7_dblog": 0.828125,
+      "step": 1310
+    },
+    {
+      "completion_length": 723.89375,
+      "epoch": 0.010512818470703483,
+      "grad_norm": 0.20945711433887482,
+      "kl": 0.010788540355861187,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0004,
+      "reward": 0.7125,
+      "reward_std": 0.26380954012274743,
+      "rewards/custom_reward_simplified_v7_dblog": 0.7125,
+      "step": 1320
     }
   ],
   "logging_steps": 10,