Training in progress, step 19500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311747411e2afa5d7eccbe8cecbb8cdb7e90a57933bbd475e13a86444c738348
+oid sha256:879ead83bd2c1fe46b7e68211ea0caa2723b2414cf5d08c8c7b5b29823750c25
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2f809198f83026b95c49f46554873d5da0e0e71fe0da56c9b70dbf1713b8974
+oid sha256:8a6fddc34b7b7d3235b23dac04ebf76b113434f948440bce4f7bae9c4f95c22a
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c57dd490464340c9b3aa212b9d3844b50cfd1f6b44323e804e87459d3ff333e
+oid sha256:aa7c19bbb017976e63ac5e9fec3eea0eda0cf5868e0275e6b00fde078e2c850d
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792eb1c103c6d8002801463d13e95f663702a503555882676ea8b65ffc1a8b9a
+oid sha256:abdb0a20afab4dc0c80b1c5f76a237a0247272f8d00055102fe692e4d58c1f05
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:948224c00888abda491e877156775666f24f3b7dcd8d2d0a471fc44df7d812bd
+oid sha256:488aaa88c1afe9c9c3279271cc45e297a0d20ece7902b965486e19f7d9811602
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 18750,
   "best_metric": 1.4680087566375732,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-15500",
-  "epoch": 1.4614260441504499,
+  "epoch": 1.4998846242596724,
   "eval_steps": 250,
-  "global_step": 19000,
+  "global_step": 19500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3276,6 +3276,92 @@
       "eval_samples_per_second": 55.67,
       "eval_steps_per_second": 13.918,
       "step": 19000
+    },
+    {
+      "epoch": 1.4652719021613723,
+      "grad_norm": 1.3094508647918701,
+      "learning_rate": 4.252343663835888e-05,
+      "loss": 1.4726,
+      "step": 19050
+    },
+    {
+      "epoch": 1.4691177601722945,
+      "grad_norm": 2.1354212760925293,
+      "learning_rate": 4.2266093158339764e-05,
+      "loss": 1.4343,
+      "step": 19100
+    },
+    {
+      "epoch": 1.4729636181832166,
+      "grad_norm": 1.395593523979187,
+      "learning_rate": 4.200874967832065e-05,
+      "loss": 1.4834,
+      "step": 19150
+    },
+    {
+      "epoch": 1.476809476194139,
+      "grad_norm": 0.8917800784111023,
+      "learning_rate": 4.1751406198301524e-05,
+      "loss": 1.4625,
+      "step": 19200
+    },
+    {
+      "epoch": 1.480655334205061,
+      "grad_norm": 2.179772138595581,
+      "learning_rate": 4.149406271828241e-05,
+      "loss": 1.4832,
+      "step": 19250
+    },
+    {
+      "epoch": 1.480655334205061,
+      "eval_loss": 1.480191946029663,
+      "eval_runtime": 17.952,
+      "eval_samples_per_second": 55.704,
+      "eval_steps_per_second": 13.926,
+      "step": 19250
+    },
+    {
+      "epoch": 1.4845011922159834,
+      "grad_norm": 1.3308861255645752,
+      "learning_rate": 4.12367192382633e-05,
+      "loss": 1.4555,
+      "step": 19300
+    },
+    {
+      "epoch": 1.4883470502269056,
+      "grad_norm": 1.6867352724075317,
+      "learning_rate": 4.0979375758244176e-05,
+      "loss": 1.4116,
+      "step": 19350
+    },
+    {
+      "epoch": 1.4921929082378278,
+      "grad_norm": 2.161247491836548,
+      "learning_rate": 4.072203227822506e-05,
+      "loss": 1.4262,
+      "step": 19400
+    },
+    {
+      "epoch": 1.4960387662487502,
+      "grad_norm": 1.717690110206604,
+      "learning_rate": 4.046468879820595e-05,
+      "loss": 1.3896,
+      "step": 19450
+    },
+    {
+      "epoch": 1.4998846242596724,
+      "grad_norm": 1.0118234157562256,
+      "learning_rate": 4.020734531818682e-05,
+      "loss": 1.4503,
+      "step": 19500
+    },
+    {
+      "epoch": 1.4998846242596724,
+      "eval_loss": 1.478628396987915,
+      "eval_runtime": 18.0209,
+      "eval_samples_per_second": 55.491,
+      "eval_steps_per_second": 13.873,
+      "step": 19500
     }
   ],
   "logging_steps": 50,