Training in progress, step 23500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43ec5a5e069d7a9559066b015901f6cd9d1e5e11a494d63a1a5a07d7cc56ce83
+oid sha256:50a6df0bbfc398611c32e7b9c5fbb763744e8ae009392a4507e80b8d8789121b
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5655b365a65633fda63eb12cb6b41fa6fff3c01576ce3df81bb8d871bd860169
+oid sha256:0956d4f6e738505bc85b225ecdc67ba6447932a06854f4fbb04754e75f0ec5f7
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f21304ce44e93f8f86da1b431eb1e188b0a7d5ce22c8a8c84f5d679245daaffa
+oid sha256:9cb49390cd54c8aca2233c64b9e33d7396d51837a032de9f6d8f9419982ba2ef
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21cd7c7ff5865cbb23888889c7201c6bfb6882d80652a0ade03d69cb9ad78253
+oid sha256:237814c22cb1dd740221cf140f477bd2c79d67cf7a39877240384dff408cb23a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fdd8c08bac54a46207946491aba470a601d04858deabd8ec1d66f5286fc9a46
+oid sha256:165f78a7ed0419fbaa8390d2bc8415e98ea8d31ac33ee06224d036bb3edf4415
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 22250,
   "best_metric": 1.457463264465332,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-22000",
-  "epoch": 1.7690946850242288,
+  "epoch": 1.8075532651334512,
   "eval_steps": 250,
-  "global_step": 23000,
+  "global_step": 23500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3964,6 +3964,92 @@
       "eval_samples_per_second": 55.817,
       "eval_steps_per_second": 13.954,
       "step": 23000
+    },
+    {
+      "epoch": 1.7729405430351513,
+      "grad_norm": 0.7428656220436096,
+      "learning_rate": 2.194110510642991e-05,
+      "loss": 1.4475,
+      "step": 23050
+    },
+    {
+      "epoch": 1.7767864010460732,
+      "grad_norm": 1.4552706480026245,
+      "learning_rate": 2.1683761626410793e-05,
+      "loss": 1.517,
+      "step": 23100
+    },
+    {
+      "epoch": 1.7806322590569956,
+      "grad_norm": 1.1563323736190796,
+      "learning_rate": 2.1426418146391676e-05,
+      "loss": 1.4806,
+      "step": 23150
+    },
+    {
+      "epoch": 1.7844781170679178,
+      "grad_norm": 1.7244662046432495,
+      "learning_rate": 2.116907466637256e-05,
+      "loss": 1.4492,
+      "step": 23200
+    },
+    {
+      "epoch": 1.78832397507884,
+      "grad_norm": 1.642321228981018,
+      "learning_rate": 2.0911731186353442e-05,
+      "loss": 1.4196,
+      "step": 23250
+    },
+    {
+      "epoch": 1.78832397507884,
+      "eval_loss": 1.4725000858306885,
+      "eval_runtime": 18.1814,
+      "eval_samples_per_second": 55.001,
+      "eval_steps_per_second": 13.75,
+      "step": 23250
+    },
+    {
+      "epoch": 1.7921698330897624,
+      "grad_norm": 1.1381646394729614,
+      "learning_rate": 2.0654387706334325e-05,
+      "loss": 1.4653,
+      "step": 23300
+    },
+    {
+      "epoch": 1.7960156911006846,
+      "grad_norm": 1.2550010681152344,
+      "learning_rate": 2.0397044226315208e-05,
+      "loss": 1.4836,
+      "step": 23350
+    },
+    {
+      "epoch": 1.7998615491116068,
+      "grad_norm": 1.4335628747940063,
+      "learning_rate": 2.013970074629609e-05,
+      "loss": 1.4403,
+      "step": 23400
+    },
+    {
+      "epoch": 1.8037074071225292,
+      "grad_norm": 1.8901276588439941,
+      "learning_rate": 1.9882357266276974e-05,
+      "loss": 1.4562,
+      "step": 23450
+    },
+    {
+      "epoch": 1.8075532651334512,
+      "grad_norm": 1.2078189849853516,
+      "learning_rate": 1.9625013786257857e-05,
+      "loss": 1.4221,
+      "step": 23500
+    },
+    {
+      "epoch": 1.8075532651334512,
+      "eval_loss": 1.4660383462905884,
+      "eval_runtime": 18.0656,
+      "eval_samples_per_second": 55.354,
+      "eval_steps_per_second": 13.838,
+      "step": 23500
     }
   ],
   "logging_steps": 50,