Training in progress, step 27000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2e93e89fb68bb8962ff13343b1f03461f74663e88695cc877535d81fccd21cd
+oid sha256:1ecb2f2e99a3f55ce283ec3c73dc04b2a38b8d596c5eb8a739f6b0463f816d0e
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06161b85e01debd263697b27f956188143b84ef8f31f2d7a79af45d05330fb3b
+oid sha256:4aa7532d5b46ff1991d1c3ddb490b4cebca7a510adb0c584bc416f8e750a93e4
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b56501523df118c1a33e60d970ee258e92691efddadd68cb368e352ca4fb0c1
+oid sha256:a7cb9cecde71619f5455094db9dbc10b01ced14b7fff166fcfd1f46df6e480f1
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76592baa9e3b0e3d15e021e247d3cfa4915cd052c2c669b30b628ff835c5a245
+oid sha256:38e8022c7f3002679e6fa3f97f4fe89fb5c796e6e8d168c42ccf78f18e8bd32d
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d9b1af634bbca91339a4e0183f53f86b46f1f5a7d978b27638787d68fcb88bd
+oid sha256:84d9c773d9d655234bd445b24c5fab29b1818f6d34a0b08096443007d2a42d37
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 24500,
   "best_metric": 1.4431298971176147,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-24500",
-  "epoch": 2.0383047457887855,
+  "epoch": 2.076763325898008,
   "eval_steps": 250,
-  "global_step": 26500,
+  "global_step": 27000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4566,6 +4566,92 @@
       "eval_samples_per_second": 54.796,
       "eval_steps_per_second": 13.699,
       "step": 26500
+    },
+    {
+      "epoch": 2.042150603799708,
+      "grad_norm": 1.0049172639846802,
+      "learning_rate": 3.932208374692107e-06,
+      "loss": 1.3012,
+      "step": 26550
+    },
+    {
+      "epoch": 2.04599646181063,
+      "grad_norm": 1.193533182144165,
+      "learning_rate": 3.6748648946729894e-06,
+      "loss": 1.4038,
+      "step": 26600
+    },
+    {
+      "epoch": 2.0498423198215523,
+      "grad_norm": 1.6459178924560547,
+      "learning_rate": 3.417521414653873e-06,
+      "loss": 1.4089,
+      "step": 26650
+    },
+    {
+      "epoch": 2.0536881778324743,
+      "grad_norm": 0.546062171459198,
+      "learning_rate": 3.160177934634756e-06,
+      "loss": 1.3675,
+      "step": 26700
+    },
+    {
+      "epoch": 2.0575340358433967,
+      "grad_norm": 1.7894645929336548,
+      "learning_rate": 2.9028344546156386e-06,
+      "loss": 1.4585,
+      "step": 26750
+    },
+    {
+      "epoch": 2.0575340358433967,
+      "eval_loss": 1.460014820098877,
+      "eval_runtime": 18.2356,
+      "eval_samples_per_second": 54.838,
+      "eval_steps_per_second": 13.709,
+      "step": 26750
+    },
+    {
+      "epoch": 2.061379893854319,
+      "grad_norm": 1.1368170976638794,
+      "learning_rate": 2.645490974596522e-06,
+      "loss": 1.4038,
+      "step": 26800
+    },
+    {
+      "epoch": 2.065225751865241,
+      "grad_norm": 1.698556900024414,
+      "learning_rate": 2.388147494577405e-06,
+      "loss": 1.4592,
+      "step": 26850
+    },
+    {
+      "epoch": 2.0690716098761635,
+      "grad_norm": 1.3114346265792847,
+      "learning_rate": 2.130804014558288e-06,
+      "loss": 1.4566,
+      "step": 26900
+    },
+    {
+      "epoch": 2.0729174678870854,
+      "grad_norm": 1.7974728345870972,
+      "learning_rate": 1.8734605345391713e-06,
+      "loss": 1.5074,
+      "step": 26950
+    },
+    {
+      "epoch": 2.076763325898008,
+      "grad_norm": 1.4648147821426392,
+      "learning_rate": 1.6161170545200544e-06,
+      "loss": 1.4478,
+      "step": 27000
+    },
+    {
+      "epoch": 2.076763325898008,
+      "eval_loss": 1.4667593240737915,
+      "eval_runtime": 18.1467,
+      "eval_samples_per_second": 55.107,
+      "eval_steps_per_second": 13.777,
+      "step": 27000
     }
   ],
   "logging_steps": 50,