Training in progress, step 1975, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3982e7c096a70a0347821728b97811479223f1df6099204e37383837d91f6f5
+oid sha256:80db105b009fb93114803e32f31508f0e1c0ec28079143f026961c4f4cf3e469
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cc874fd946b4a641da998c3cb0bfa07fd14122b6f28011d2891746400a37ff9
+oid sha256:3477641575947a2ff6bc25fe793ce5f3806bb14bd921d11e487d3914218af487
 size 958299770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81ead0fc04d8776eae671d9a86963a7d3e1d3d1b066678dcfa501494dc5b51a
+oid sha256:e41038421362cc3793a0cf8f1bb2ecf0a45df92fe445e455ba3ea3ee170030cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91dcb5b2d000f105f4d6d1ae7170d8fafaf43f44a4f442aeb38a35f6c7a13bc9
+oid sha256:ae04182ae51e8bdccafb7cc0327b07cc7bf010fe19276cd2a27aeb0d48ae0ab7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015530300013539236,
+  "epoch": 0.015729406423969226,
   "eval_steps": 500,
-  "global_step": 1950,
+  "global_step": 1975,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2347,6 +2347,30 @@
       "reward_std": 0.2747412838041782,
       "rewards/custom_reward_simplified_v7_dblog": 0.725,
       "step": 1950
+    },
+    {
+      "completion_length": 651.70625,
+      "epoch": 0.015609942577711231,
+      "grad_norm": 0.2434624284505844,
+      "kl": 0.01636054664850235,
+      "learning_rate": 4.946920181123904e-07,
+      "loss": 0.0007,
+      "reward": 0.7625,
+      "reward_std": 0.2852359592914581,
+      "rewards/custom_reward_simplified_v7_dblog": 0.7625,
+      "step": 1960
+    },
+    {
+      "completion_length": 654.6625,
+      "epoch": 0.015689585141883226,
+      "grad_norm": 0.20749981701374054,
+      "kl": 0.018196922447532415,
+      "learning_rate": 4.7319158207446953e-07,
+      "loss": 0.0007,
+      "reward": 0.715625,
+      "reward_std": 0.2198973834514618,
+      "rewards/custom_reward_simplified_v7_dblog": 0.715625,
+      "step": 1970
     }
   ],
   "logging_steps": 10,