Training in progress, step 18500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f56b521d1a393817f17047a20ecf2bb1e83ee9f43692fbe30db28020b9d79b36
+oid sha256:a40b3ec9fac131b936a25a3717ad20559ac04c1beac8d89dd6e2dfe4e69599f5
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af75d0581fbdc90030a2d5f4ec75948b6c9a777f25105f2635a11a66e19a8991
+oid sha256:f0c5233fd48a8ddd485f6a2ec03ff9389775661db4a9e073cc9e6578c35f6acc
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aec74914111c893531d77390ed26a8e62f47c5fd368563e3e2ea395d9971bdd0
+oid sha256:a637703e63dd26bf3fc5d45021980dfb8c6c15b36b34b2b812e241dcfa5b3276
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb36538bca0e8f82a230d205fcda169c895fd4416ff12f18badea8938ea79e34
+oid sha256:ac82d08ac6c84227c6b48fa89b5e8a7f058764ced7fff8850851393f056e0943
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04fb24a5e33627ec28e9d8236874cf729cbb5859a1714c36c632683bea019abf
+oid sha256:d1ac76f538d93ba96883051bed95b0b8b1845abfe936b318341f400f4768f02a
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 16750,
   "best_metric": 1.4708431959152222,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-15500",
-  "epoch": 1.3845088839320052,
+  "epoch": 1.4229674640412275,
   "eval_steps": 250,
-  "global_step": 18000,
+  "global_step": 18500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3104,6 +3104,92 @@
       "eval_samples_per_second": 55.559,
       "eval_steps_per_second": 13.89,
       "step": 18000
+    },
+    {
+      "epoch": 1.3883547419429274,
+      "grad_norm": 1.6790105104446411,
+      "learning_rate": 4.7670306238741216e-05,
+      "loss": 1.4791,
+      "step": 18050
+    },
+    {
+      "epoch": 1.3922005999538496,
+      "grad_norm": 1.1840436458587646,
+      "learning_rate": 4.74129627587221e-05,
+      "loss": 1.4021,
+      "step": 18100
+    },
+    {
+      "epoch": 1.396046457964772,
+      "grad_norm": 1.7883968353271484,
+      "learning_rate": 4.715561927870298e-05,
+      "loss": 1.4637,
+      "step": 18150
+    },
+    {
+      "epoch": 1.3998923159756942,
+      "grad_norm": 1.2177505493164062,
+      "learning_rate": 4.689827579868387e-05,
+      "loss": 1.5123,
+      "step": 18200
+    },
+    {
+      "epoch": 1.4037381739866164,
+      "grad_norm": 1.439232349395752,
+      "learning_rate": 4.6640932318664756e-05,
+      "loss": 1.4579,
+      "step": 18250
+    },
+    {
+      "epoch": 1.4037381739866164,
+      "eval_loss": 1.4953014850616455,
+      "eval_runtime": 17.9127,
+      "eval_samples_per_second": 55.826,
+      "eval_steps_per_second": 13.957,
+      "step": 18250
+    },
+    {
+      "epoch": 1.4075840319975388,
+      "grad_norm": 2.0796408653259277,
+      "learning_rate": 4.638358883864563e-05,
+      "loss": 1.4295,
+      "step": 18300
+    },
+    {
+      "epoch": 1.4114298900084608,
+      "grad_norm": 1.3032926321029663,
+      "learning_rate": 4.6126245358626515e-05,
+      "loss": 1.4733,
+      "step": 18350
+    },
+    {
+      "epoch": 1.4152757480193832,
+      "grad_norm": 0.9058660864830017,
+      "learning_rate": 4.58689018786074e-05,
+      "loss": 1.4446,
+      "step": 18400
+    },
+    {
+      "epoch": 1.4191216060303053,
+      "grad_norm": 2.05460786819458,
+      "learning_rate": 4.561155839858828e-05,
+      "loss": 1.4133,
+      "step": 18450
+    },
+    {
+      "epoch": 1.4229674640412275,
+      "grad_norm": 0.8309249877929688,
+      "learning_rate": 4.535421491856917e-05,
+      "loss": 1.456,
+      "step": 18500
+    },
+    {
+      "epoch": 1.4229674640412275,
+      "eval_loss": 1.480312466621399,
+      "eval_runtime": 18.2137,
+      "eval_samples_per_second": 54.904,
+      "eval_steps_per_second": 13.726,
+      "step": 18500
     }
   ],
   "logging_steps": 50,