Training in progress, step 26500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7380e911b47a593b6e6e294e7827a8de2e4e3f7b1b83607bf62e1583c2d7f7a3
+oid sha256:f2e93e89fb68bb8962ff13343b1f03461f74663e88695cc877535d81fccd21cd
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7af7e30906067165a3669470320cb653b4ffd33b1d8a610f3716b94a2f716fce
+oid sha256:06161b85e01debd263697b27f956188143b84ef8f31f2d7a79af45d05330fb3b
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35c260873e53de579d314af7f23d76fd9a02c023129e1ca7c8f1d3d5f4fae1d0
+oid sha256:5b56501523df118c1a33e60d970ee258e92691efddadd68cb368e352ca4fb0c1
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60e9205691ce5148ac9b5c101f7716ac13075c3c3735582239bfb45d9a860e75
+oid sha256:76592baa9e3b0e3d15e021e247d3cfa4915cd052c2c669b30b628ff835c5a245
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e14edeb9123c5eec7e26cdb8d77f3aaa83054aadc39c2057a183c66b1f00314
+oid sha256:3d9b1af634bbca91339a4e0183f53f86b46f1f5a7d978b27638787d68fcb88bd
 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": 1.9998461656795632,
+  "epoch": 2.0383047457887855,
   "eval_steps": 250,
-  "global_step": 26000,
+  "global_step": 26500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4480,6 +4480,92 @@
       "eval_samples_per_second": 55.537,
       "eval_steps_per_second": 13.884,
       "step": 26000
+    },
+    {
+      "epoch": 2.003692023690485,
+      "grad_norm": 1.7356750965118408,
+      "learning_rate": 6.505643174883276e-06,
+      "loss": 1.3839,
+      "step": 26050
+    },
+    {
+      "epoch": 2.0075378817014076,
+      "grad_norm": 2.3067352771759033,
+      "learning_rate": 6.248299694864159e-06,
+      "loss": 1.4348,
+      "step": 26100
+    },
+    {
+      "epoch": 2.01138373971233,
+      "grad_norm": 1.343248724937439,
+      "learning_rate": 5.990956214845041e-06,
+      "loss": 1.3703,
+      "step": 26150
+    },
+    {
+      "epoch": 2.015229597723252,
+      "grad_norm": 1.9424471855163574,
+      "learning_rate": 5.733612734825925e-06,
+      "loss": 1.4304,
+      "step": 26200
+    },
+    {
+      "epoch": 2.0190754557341744,
+      "grad_norm": 1.5383673906326294,
+      "learning_rate": 5.476269254806808e-06,
+      "loss": 1.4118,
+      "step": 26250
+    },
+    {
+      "epoch": 2.0190754557341744,
+      "eval_loss": 1.474881649017334,
+      "eval_runtime": 18.1751,
+      "eval_samples_per_second": 55.02,
+      "eval_steps_per_second": 13.755,
+      "step": 26250
+    },
+    {
+      "epoch": 2.0229213137450963,
+      "grad_norm": 1.803488850593567,
+      "learning_rate": 5.2189257747876905e-06,
+      "loss": 1.4537,
+      "step": 26300
+    },
+    {
+      "epoch": 2.0267671717560187,
+      "grad_norm": 1.8623336553573608,
+      "learning_rate": 4.961582294768574e-06,
+      "loss": 1.3659,
+      "step": 26350
+    },
+    {
+      "epoch": 2.030613029766941,
+      "grad_norm": 1.1901572942733765,
+      "learning_rate": 4.7042388147494575e-06,
+      "loss": 1.4175,
+      "step": 26400
+    },
+    {
+      "epoch": 2.034458887777863,
+      "grad_norm": 1.2967520952224731,
+      "learning_rate": 4.4468953347303406e-06,
+      "loss": 1.458,
+      "step": 26450
+    },
+    {
+      "epoch": 2.0383047457887855,
+      "grad_norm": 1.2987436056137085,
+      "learning_rate": 4.189551854711224e-06,
+      "loss": 1.3965,
+      "step": 26500
+    },
+    {
+      "epoch": 2.0383047457887855,
+      "eval_loss": 1.4528058767318726,
+      "eval_runtime": 18.2495,
+      "eval_samples_per_second": 54.796,
+      "eval_steps_per_second": 13.699,
+      "step": 26500
     }
   ],
   "logging_steps": 50,