Training in progress, step 6000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce807f113eae8af3f76aad00110eac4aaa67725db83293608e360d0ae6f2138c
+oid sha256:a554f35b6a17be128fce6b6dde18077ae472e710857689bc82a3a107a5064b70
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b62d615ea1686f1839d2072736549e7fb167c1df54c146af3bd0e3c76f28b705
+oid sha256:7489e1764b16dc1b56ae149e381b65054da7550c9735ed9c2fdc8fc794efba0e
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:452f9d1449e365d91136837164af087a289325b1bf94b381d6eeb9d18ffa0513
+oid sha256:12c22be93200b6ea29a5a43fdc896fd16b0e2c374bfcbb275fb907bb85c40cd3
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f428dc4c0936653e8741f49c8b481e2cc2f0d2a1ce2182ef1df7e775a7d4db5
+oid sha256:6914f08d038d2fd5583fe9d1dfb74316a740319f66641c1d86781bc3fc4b8381
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b342bb583b996f802c3b66f99264c907dce5eb33ed829269a76eaa3a6c0e850c
+oid sha256:0f20cc39b1ac70cfd962157cd5b033ae7e76e9f02816bf84f00fd90791d769ab
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 5000,
   "best_metric": 4.414160251617432,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-5000",
-  "epoch": 0.42304438120144605,
+  "epoch": 0.4615029613106684,
   "eval_steps": 250,
-  "global_step": 5500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -954,6 +954,92 @@
       "eval_samples_per_second": 52.851,
       "eval_steps_per_second": 13.213,
       "step": 5500
+    },
+    {
+      "epoch": 0.4268902392123683,
+      "grad_norm": 4.470078945159912,
+      "learning_rate": 0.00011199073563471931,
+      "loss": 4.543,
+      "step": 5550
+    },
+    {
+      "epoch": 0.43073609722329054,
+      "grad_norm": 5.099395751953125,
+      "learning_rate": 0.00011173339215470019,
+      "loss": 4.4515,
+      "step": 5600
+    },
+    {
+      "epoch": 0.4345819552342128,
+      "grad_norm": 3.210951805114746,
+      "learning_rate": 0.00011147604867468107,
+      "loss": 4.4605,
+      "step": 5650
+    },
+    {
+      "epoch": 0.43842781324513497,
+      "grad_norm": 4.092874050140381,
+      "learning_rate": 0.00011121870519466196,
+      "loss": 4.6267,
+      "step": 5700
+    },
+    {
+      "epoch": 0.4422736712560572,
+      "grad_norm": 2.756460666656494,
+      "learning_rate": 0.00011096136171464283,
+      "loss": 4.4338,
+      "step": 5750
+    },
+    {
+      "epoch": 0.4422736712560572,
+      "eval_loss": 4.457804203033447,
+      "eval_runtime": 18.7914,
+      "eval_samples_per_second": 53.216,
+      "eval_steps_per_second": 13.304,
+      "step": 5750
+    },
+    {
+      "epoch": 0.44611952926697945,
+      "grad_norm": 5.140827178955078,
+      "learning_rate": 0.00011070401823462372,
+      "loss": 4.5102,
+      "step": 5800
+    },
+    {
+      "epoch": 0.4499653872779017,
+      "grad_norm": 6.364997863769531,
+      "learning_rate": 0.0001104466747546046,
+      "loss": 4.5594,
+      "step": 5850
+    },
+    {
+      "epoch": 0.45381124528882394,
+      "grad_norm": 5.3479695320129395,
+      "learning_rate": 0.00011018933127458548,
+      "loss": 4.4067,
+      "step": 5900
+    },
+    {
+      "epoch": 0.4576571032997462,
+      "grad_norm": 3.728893518447876,
+      "learning_rate": 0.00010993198779456637,
+      "loss": 4.4689,
+      "step": 5950
+    },
+    {
+      "epoch": 0.4615029613106684,
+      "grad_norm": 6.3881611824035645,
+      "learning_rate": 0.00010967464431454724,
+      "loss": 4.5641,
+      "step": 6000
+    },
+    {
+      "epoch": 0.4615029613106684,
+      "eval_loss": 4.457447052001953,
+      "eval_runtime": 18.8382,
+      "eval_samples_per_second": 53.084,
+      "eval_steps_per_second": 13.271,
+      "step": 6000
     }
   ],
   "logging_steps": 50,