Training in progress, step 19000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a40b3ec9fac131b936a25a3717ad20559ac04c1beac8d89dd6e2dfe4e69599f5
+oid sha256:311747411e2afa5d7eccbe8cecbb8cdb7e90a57933bbd475e13a86444c738348
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0c5233fd48a8ddd485f6a2ec03ff9389775661db4a9e073cc9e6578c35f6acc
+oid sha256:d2f809198f83026b95c49f46554873d5da0e0e71fe0da56c9b70dbf1713b8974
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a637703e63dd26bf3fc5d45021980dfb8c6c15b36b34b2b812e241dcfa5b3276
+oid sha256:3c57dd490464340c9b3aa212b9d3844b50cfd1f6b44323e804e87459d3ff333e
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac82d08ac6c84227c6b48fa89b5e8a7f058764ced7fff8850851393f056e0943
+oid sha256:792eb1c103c6d8002801463d13e95f663702a503555882676ea8b65ffc1a8b9a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1ac76f538d93ba96883051bed95b0b8b1845abfe936b318341f400f4768f02a
+oid sha256:948224c00888abda491e877156775666f24f3b7dcd8d2d0a471fc44df7d812bd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 16750,
-  "best_metric": 1.4708431959152222,
+  "best_global_step": 18750,
+  "best_metric": 1.4680087566375732,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-15500",
-  "epoch": 1.4229674640412275,
+  "epoch": 1.4614260441504499,
   "eval_steps": 250,
-  "global_step": 18500,
+  "global_step": 19000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3190,6 +3190,92 @@
       "eval_samples_per_second": 54.904,
       "eval_steps_per_second": 13.726,
       "step": 18500
+    },
+    {
+      "epoch": 1.42681332205215,
+      "grad_norm": 1.0496591329574585,
+      "learning_rate": 4.5096871438550054e-05,
+      "loss": 1.3723,
+      "step": 18550
+    },
+    {
+      "epoch": 1.4306591800630721,
+      "grad_norm": 1.273758053779602,
+      "learning_rate": 4.483952795853093e-05,
+      "loss": 1.4747,
+      "step": 18600
+    },
+    {
+      "epoch": 1.4345050380739943,
+      "grad_norm": 1.3594483137130737,
+      "learning_rate": 4.458218447851181e-05,
+      "loss": 1.564,
+      "step": 18650
+    },
+    {
+      "epoch": 1.4383508960849165,
+      "grad_norm": 1.773634672164917,
+      "learning_rate": 4.43248409984927e-05,
+      "loss": 1.4344,
+      "step": 18700
+    },
+    {
+      "epoch": 1.4421967540958387,
+      "grad_norm": 0.7939924001693726,
+      "learning_rate": 4.406749751847358e-05,
+      "loss": 1.3798,
+      "step": 18750
+    },
+    {
+      "epoch": 1.4421967540958387,
+      "eval_loss": 1.4680087566375732,
+      "eval_runtime": 18.0287,
+      "eval_samples_per_second": 55.467,
+      "eval_steps_per_second": 13.867,
+      "step": 18750
+    },
+    {
+      "epoch": 1.446042612106761,
+      "grad_norm": 1.4785016775131226,
+      "learning_rate": 4.3810154038454466e-05,
+      "loss": 1.5316,
+      "step": 18800
+    },
+    {
+      "epoch": 1.4498884701176833,
+      "grad_norm": 2.1929142475128174,
+      "learning_rate": 4.355281055843535e-05,
+      "loss": 1.4498,
+      "step": 18850
+    },
+    {
+      "epoch": 1.4537343281286055,
+      "grad_norm": 1.816432237625122,
+      "learning_rate": 4.3295467078416225e-05,
+      "loss": 1.5089,
+      "step": 18900
+    },
+    {
+      "epoch": 1.4575801861395277,
+      "grad_norm": 2.589778423309326,
+      "learning_rate": 4.303812359839711e-05,
+      "loss": 1.4011,
+      "step": 18950
+    },
+    {
+      "epoch": 1.4614260441504499,
+      "grad_norm": 1.6828664541244507,
+      "learning_rate": 4.2780780118378e-05,
+      "loss": 1.3803,
+      "step": 19000
+    },
+    {
+      "epoch": 1.4614260441504499,
+      "eval_loss": 1.4737956523895264,
+      "eval_runtime": 17.9628,
+      "eval_samples_per_second": 55.67,
+      "eval_steps_per_second": 13.918,
+      "step": 19000
     }
   ],
   "logging_steps": 50,