Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5269dfda02df672ff5f512785d6acc41c5eeb64030130097364401ec39d12432
+oid sha256:e3f7212aa3c90ea7765b266c91a1c37f7ee786da363e1b2a93ee6806ed670ba7
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3385879201f140296e1c3c85763cd7c107c1e3dc677bb3e181707226e4bf6707
+oid sha256:c3a2e36062ee9a9b1c0cbf56796f1692510713b40f9b4e03b6abb5a07dd0001f
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa7f4be2476602644a5192031065606d6ed82d136e38b23d7f2744731a6f29f
+oid sha256:5120bfa84229b68a7f7f0683b8775173af411a1296a86c5d4ff0563ac31f3baf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee275ce469a64df6da50be32d0ddc1123d7db1dcb4c288c48f6b48568c6b719a
+oid sha256:e2085f58dcd21b346b3f76c21f730c3fd85efe25685c7b50b88b346f628559d6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007765150006769618,
+  "epoch": 0.007964256417199608,
   "eval_steps": 500,
-  "global_step": 975,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1171,6 +1171,42 @@
       "reward_std": 0.32862835973501203,
       "rewards/custom_reward_simplified_v7_dblog": 0.978125,
       "step": 970
+    },
+    {
+      "completion_length": 623.40625,
+      "epoch": 0.007804971288855616,
+      "grad_norm": 0.24265889823436737,
+      "kl": 0.006443582929205149,
+      "learning_rate": 3.6865009243691015e-06,
+      "loss": 0.0003,
+      "reward": 0.790625,
+      "reward_std": 0.35499989837408064,
+      "rewards/custom_reward_simplified_v7_dblog": 0.790625,
+      "step": 980
+    },
+    {
+      "completion_length": 677.65625,
+      "epoch": 0.007884613853027612,
+      "grad_norm": 0.23094038665294647,
+      "kl": 0.006802499154582619,
+      "learning_rate": 3.654371533087586e-06,
+      "loss": 0.0003,
+      "reward": 0.80625,
+      "reward_std": 0.3126889310777187,
+      "rewards/custom_reward_simplified_v7_dblog": 0.80625,
+      "step": 990
+    },
+    {
+      "completion_length": 703.0125,
+      "epoch": 0.007964256417199608,
+      "grad_norm": 0.2269383817911148,
+      "kl": 0.006587388808839023,
+      "learning_rate": 3.621997950501156e-06,
+      "loss": 0.0003,
+      "reward": 0.83125,
+      "reward_std": 0.3684743233025074,
+      "rewards/custom_reward_simplified_v7_dblog": 0.83125,
+      "step": 1000
     }
   ],
   "logging_steps": 10,