Training in progress, step 1075, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c517880b0082e2bcb63d8211700cdd79ad1d1f579b6f02724e95147c38123717
+oid sha256:2e63f562503cde4d1609bdfb5b6ab6f77c5fe28e4f0a6050e851ea2af44237d5
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5406ffadfafdfa7cf7f681c6664efb80bcc0b985474ab680a228faccaf8306e8
+oid sha256:d72c9de7fe76e79fa0ee85dee9ef7d5c5eb70eeb4012b9f202e48837659a1230
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb85692bb929f1b45dfc4dfc2779fe5d2efe84959814e3288f8282f3bc4be529
+oid sha256:c0d186837651a0003ac9e9fbed4fdf98fb1ae1d63f07bd77dc2bd854dfe532ca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:142ecd6835d46a3b266c47dbf70129eebe02431f0096c3935ee9314ce11a43fa
+oid sha256:380aefd38169e510ac1b1face660871b8639e3f1495c211aa0b0ddac9bd8c95d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008362469238059589,
+  "epoch": 0.008561575648489578,
   "eval_steps": 500,
-  "global_step": 1050,
+  "global_step": 1075,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1267,6 +1267,30 @@
       "reward_std": 0.33950999528169634,
       "rewards/custom_reward_simplified_v7_dblog": 0.790625,
       "step": 1050
+    },
+    {
+      "completion_length": 621.4875,
+      "epoch": 0.008442111802231585,
+      "grad_norm": 0.25109627842903137,
+      "kl": 0.006540448497980833,
+      "learning_rate": 3.4230153682817112e-06,
+      "loss": 0.0003,
+      "reward": 0.85,
+      "reward_std": 0.30627945214509966,
+      "rewards/custom_reward_simplified_v7_dblog": 0.85,
+      "step": 1060
+    },
+    {
+      "completion_length": 671.04375,
+      "epoch": 0.00852175436640358,
+      "grad_norm": 0.1299162656068802,
+      "kl": 0.006574284215457737,
+      "learning_rate": 3.389126904537192e-06,
+      "loss": 0.0003,
+      "reward": 0.865625,
+      "reward_std": 0.37070034593343737,
+      "rewards/custom_reward_simplified_v7_dblog": 0.865625,
+      "step": 1070
     }
   ],
   "logging_steps": 10,