Training in progress, step 1350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74682732035656f7a989ee44f1f36f8e416b584aa4564d6a3765d685f4981071
+oid sha256:3b901f880fa9ed0f060f71cce70c866baf6b12ff9b46744f1cd5db7d6a751126
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:337ffc24497931d1740d801f5febab092071f825b7858ec9a867066b6a02e90c
+oid sha256:0632dbbf29d2931fe7ce743e19d0f3cf69ee7a7d9e92be339d9792d785000ee2
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57cab1721b5ddb43639ccad6e4533ec798a026a004201613eb0b4122b1bbb3f9
+oid sha256:fa7f2184140c298d88f1de4da49013475309ad1f88b477c6a086754fa7764dc5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13318808563c2924b4edd2b4e6dbfa122edfbebfd027b1583aa4d422089a88ec
+oid sha256:023537b1d42d463489031d31c03e4c8fead35d65882bdcee8e6825976c4bcbf6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010552639752789481,
+  "epoch": 0.01075174616321947,
   "eval_steps": 500,
-  "global_step": 1325,
+  "global_step": 1350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1591,6 +1591,42 @@
       "reward_std": 0.26380954012274743,
       "rewards/custom_reward_simplified_v7_dblog": 0.7125,
       "step": 1320
+    },
+    {
+      "completion_length": 715.7,
+      "epoch": 0.010592461034875478,
+      "grad_norm": 0.16817767918109894,
+      "kl": 0.013910629483871163,
+      "learning_rate": 2.4636402558710434e-06,
+      "loss": 0.0006,
+      "reward": 0.759375,
+      "reward_std": 0.2193169414997101,
+      "rewards/custom_reward_simplified_v7_dblog": 0.759375,
+      "step": 1330
+    },
+    {
+      "completion_length": 655.90625,
+      "epoch": 0.010672103599047475,
+      "grad_norm": 0.2265154868364334,
+      "kl": 0.00848452327772975,
+      "learning_rate": 2.4272882031422216e-06,
+      "loss": 0.0003,
+      "reward": 0.78125,
+      "reward_std": 0.3443989932537079,
+      "rewards/custom_reward_simplified_v7_dblog": 0.78125,
+      "step": 1340
+    },
+    {
+      "completion_length": 660.075,
+      "epoch": 0.01075174616321947,
+      "grad_norm": 0.24644052982330322,
+      "kl": 0.009867909434251487,
+      "learning_rate": 2.3909515315866606e-06,
+      "loss": 0.0004,
+      "reward": 0.79375,
+      "reward_std": 0.29604131579399107,
+      "rewards/custom_reward_simplified_v7_dblog": 0.79375,
+      "step": 1350
     }
   ],
   "logging_steps": 10,