Training in progress, step 9500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d41b0a6b7b93326606bd1adb6fe554c4f3a4896093e8d2cda0d85615659fbea9
+oid sha256:4b9baf2c6ba5ebbe672256c852fecb5f216fb3f2e6bf3f464d3b0a62f927a601
 size 36730224

last-checkpoint/ar_diffusion_info.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61e6388870be8d5091de8ee4171a40d8d34fd90416acec89a4530ab1810d1d11
+oid sha256:d40db6775badf11b35e39be49c6fef0bc883f3580d3d852ee11aee4261d7eedd
 size 1736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8114c7619958e289ae818af20bbbb40ca496ec99d1d2cf5336f332be768bd676
+oid sha256:71923ca4e5165f8d69e24064ca7c57c4feab7a075d2d60f03dd76eb79c8d3ad8
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f82ab7544ab0f2c7299f888437f6d772f90becf0f776876608740887a96023f
+oid sha256:632e9f7e063df82f0a0f7f24d19a972e733d8fb69f46a15890d826ee60504fae
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c86e9949dede8e9039d4479cc9a7b6de2de62acc5bc9bce167cc78f0df5d789
+oid sha256:599596a3cb79dad5f0353c782d77b8e23494fd9a0c28c4b3bdb9f32604aafb58
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67134d509d59e4154961ca89be855a6a8dd7ecee21023e7a214d3f3e40df8ac6
+oid sha256:37b10e7fbb18174f6f934d4c5e8eb4aeea59a6280951bc7b58e46146366fc7ea
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 8750,
-  "best_metric": 1.3920339345932007,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-8500",
-  "epoch": 0.6922544419660026,
+  "best_global_step": 9500,
+  "best_metric": 1.382208228111267,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-9500",
+  "epoch": 0.7307130220752249,
   "eval_steps": 250,
-  "global_step": 9000,
+  "global_step": 9500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1556,6 +1556,92 @@
       "eval_samples_per_second": 59.652,
       "eval_steps_per_second": 14.913,
       "step": 9000
+    },
+    {
+      "epoch": 0.6961002999769248,
+      "grad_norm": 2.0058114528656006,
+      "learning_rate": 0.00015561904267199958,
+      "loss": 1.4288,
+      "step": 9050
+    },
+    {
+      "epoch": 0.6999461579878471,
+      "grad_norm": 0.9105901122093201,
+      "learning_rate": 0.00015535932265018312,
+      "loss": 1.4271,
+      "step": 9100
+    },
+    {
+      "epoch": 0.7037920159987693,
+      "grad_norm": 1.241396188735962,
+      "learning_rate": 0.00015509960262836663,
+      "loss": 1.3543,
+      "step": 9150
+    },
+    {
+      "epoch": 0.7076378740096916,
+      "grad_norm": 1.2965749502182007,
+      "learning_rate": 0.00015483988260655017,
+      "loss": 1.3501,
+      "step": 9200
+    },
+    {
+      "epoch": 0.7114837320206138,
+      "grad_norm": 1.4165613651275635,
+      "learning_rate": 0.00015458016258473365,
+      "loss": 1.4465,
+      "step": 9250
+    },
+    {
+      "epoch": 0.7114837320206138,
+      "eval_loss": 1.3871207237243652,
+      "eval_runtime": 16.7909,
+      "eval_samples_per_second": 59.556,
+      "eval_steps_per_second": 14.889,
+      "step": 9250
+    },
+    {
+      "epoch": 0.7153295900315361,
+      "grad_norm": 1.7752403020858765,
+      "learning_rate": 0.00015432044256291717,
+      "loss": 1.4282,
+      "step": 9300
+    },
+    {
+      "epoch": 0.7191754480424583,
+      "grad_norm": 1.6717677116394043,
+      "learning_rate": 0.0001540607225411007,
+      "loss": 1.3986,
+      "step": 9350
+    },
+    {
+      "epoch": 0.7230213060533806,
+      "grad_norm": 1.290183186531067,
+      "learning_rate": 0.00015380100251928422,
+      "loss": 1.3891,
+      "step": 9400
+    },
+    {
+      "epoch": 0.7268671640643027,
+      "grad_norm": 1.6836214065551758,
+      "learning_rate": 0.00015354128249746773,
+      "loss": 1.4028,
+      "step": 9450
+    },
+    {
+      "epoch": 0.7307130220752249,
+      "grad_norm": 0.5705507397651672,
+      "learning_rate": 0.00015328156247565127,
+      "loss": 1.365,
+      "step": 9500
+    },
+    {
+      "epoch": 0.7307130220752249,
+      "eval_loss": 1.382208228111267,
+      "eval_runtime": 16.8905,
+      "eval_samples_per_second": 59.205,
+      "eval_steps_per_second": 14.801,
+      "step": 9500
     }
   ],
   "logging_steps": 50,