Training in progress, step 12500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04d930c5c4a881dfd26ea978e652c702b6adb1b5b7ed1eed9ca7135e21510049
+oid sha256:cd49fdfe9bdd857be5419dddbdbaa6f93701dd16afd12b8202d9abb0f608e217
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59ca03346afd36214198fb9410564c8a86b40b37890c4e424de07767c10a30ec
+oid sha256:8066ffe6e1fa6681b38c047067ca29a6eed18da1b1acf88431943e295d78e330
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:205a7550a4c055924e0126c3501b4b656ca55ae3243c46218f86d29fc2fb9758
-size 14244
+oid sha256:9a5ae118ec673d57a7f62a6284956ef83acf5113a9420dcd7ba5fd941799b59c
+size 14180

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:699adc1847435a16f1605601a8df2b43b7960dcbb43148ad8a4600f5fe2cb9d4
+oid sha256:63eee2f78c948ec330b424961c4bdfb29608b15bd25064fec9d957a2f7fcbcd2
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:638497dfdf5eb5c99bf0b6f11b605f213450ed644d6ebdee360506f0a10a4ae0
+oid sha256:334ae361472f93791190a5614ebfa0a90c8bcb9632490f070b08594d58ab788b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 12000,
-  "best_metric": 1.5159597396850586,
+  "best_global_step": 12250,
+  "best_metric": 1.5108226537704468,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-12000",
-  "epoch": 0.9230059226213368,
+  "epoch": 0.9614645027305592,
   "eval_steps": 250,
-  "global_step": 12000,
+  "global_step": 12500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2072,6 +2072,92 @@
       "eval_samples_per_second": 55.894,
       "eval_steps_per_second": 13.974,
       "step": 12000
+    },
+    {
+      "epoch": 0.926851780632259,
+      "grad_norm": 1.736138939857483,
+      "learning_rate": 7.855152384103525e-05,
+      "loss": 1.5304,
+      "step": 12050
+    },
+    {
+      "epoch": 0.9306976386431813,
+      "grad_norm": 1.807916283607483,
+      "learning_rate": 7.829418036101613e-05,
+      "loss": 1.4984,
+      "step": 12100
+    },
+    {
+      "epoch": 0.9345434966541035,
+      "grad_norm": 1.1977109909057617,
+      "learning_rate": 7.803683688099702e-05,
+      "loss": 1.4307,
+      "step": 12150
+    },
+    {
+      "epoch": 0.9383893546650258,
+      "grad_norm": 0.8386535048484802,
+      "learning_rate": 7.77794934009779e-05,
+      "loss": 1.444,
+      "step": 12200
+    },
+    {
+      "epoch": 0.942235212675948,
+      "grad_norm": 1.395053744316101,
+      "learning_rate": 7.752214992095878e-05,
+      "loss": 1.4866,
+      "step": 12250
+    },
+    {
+      "epoch": 0.942235212675948,
+      "eval_loss": 1.5108226537704468,
+      "eval_runtime": 18.0888,
+      "eval_samples_per_second": 55.283,
+      "eval_steps_per_second": 13.821,
+      "step": 12250
+    },
+    {
+      "epoch": 0.9460810706868702,
+      "grad_norm": 1.5271111726760864,
+      "learning_rate": 7.726480644093966e-05,
+      "loss": 1.4849,
+      "step": 12300
+    },
+    {
+      "epoch": 0.9499269286977925,
+      "grad_norm": 3.0610506534576416,
+      "learning_rate": 7.700746296092054e-05,
+      "loss": 1.4613,
+      "step": 12350
+    },
+    {
+      "epoch": 0.9537727867087147,
+      "grad_norm": 1.8968026638031006,
+      "learning_rate": 7.675011948090143e-05,
+      "loss": 1.591,
+      "step": 12400
+    },
+    {
+      "epoch": 0.957618644719637,
+      "grad_norm": 1.748979926109314,
+      "learning_rate": 7.649277600088231e-05,
+      "loss": 1.4781,
+      "step": 12450
+    },
+    {
+      "epoch": 0.9614645027305592,
+      "grad_norm": 1.6586661338806152,
+      "learning_rate": 7.62354325208632e-05,
+      "loss": 1.4668,
+      "step": 12500
+    },
+    {
+      "epoch": 0.9614645027305592,
+      "eval_loss": 1.5503162145614624,
+      "eval_runtime": 17.9222,
+      "eval_samples_per_second": 55.797,
+      "eval_steps_per_second": 13.949,
+      "step": 12500
     }
   ],
   "logging_steps": 50,