Training in progress, step 975, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0cdab5afe89842ddf5f951fefb2a7cbceecc5e593787e5da35a587fa2f1fc19
+oid sha256:5269dfda02df672ff5f512785d6acc41c5eeb64030130097364401ec39d12432
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aefb33efb95cb0cda912996733876b57741f474e96d089d56f4d5c60b686c3d
+oid sha256:3385879201f140296e1c3c85763cd7c107c1e3dc677bb3e181707226e4bf6707
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3343f12ec5e83ccbe5792e5a25a22293eb382ff3f3b0b26a3d274d79100cbe82
+oid sha256:0aa7f4be2476602644a5192031065606d6ed82d136e38b23d7f2744731a6f29f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:039c08ad2d08bc621e50ca4bc0d72f4e62aa003991d9f191336efa92cd4bd720
+oid sha256:ee275ce469a64df6da50be32d0ddc1123d7db1dcb4c288c48f6b48568c6b719a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007566043596339628,
+  "epoch": 0.007765150006769618,
   "eval_steps": 500,
-  "global_step": 950,
+  "global_step": 975,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1147,6 +1147,30 @@
       "reward_std": 0.2690692335367203,
       "rewards/custom_reward_simplified_v7_dblog": 0.775,
       "step": 950
+    },
+    {
+      "completion_length": 706.7125,
+      "epoch": 0.007645686160511624,
+      "grad_norm": 0.11362796276807785,
+      "kl": 0.0065676989033818245,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0003,
+      "reward": 0.753125,
+      "reward_std": 0.3238763153553009,
+      "rewards/custom_reward_simplified_v7_dblog": 0.753125,
+      "step": 960
+    },
+    {
+      "completion_length": 591.60625,
+      "epoch": 0.00772532872468362,
+      "grad_norm": 0.006601857952773571,
+      "kl": 0.0061999865574762225,
+      "learning_rate": 3.7183793278181063e-06,
+      "loss": 0.0002,
+      "reward": 0.978125,
+      "reward_std": 0.32862835973501203,
+      "rewards/custom_reward_simplified_v7_dblog": 0.978125,
+      "step": 970
     }
   ],
   "logging_steps": 10,