Training in progress, step 27500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05b2f61187a90a08831b51555301b195d55056396e6a01f761a6a8e73fc0fb0c
+oid sha256:50babce35e19ba1c52c051d5771bd2ef5b1fb8837c7eb686a5f692232dc3476b
 size 36730224

last-checkpoint/ar_diffusion_info.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d42710c0be0d1f6e449827dca6d2dbf6f093dff7f08d2e50fa7e4b598258fc4
+oid sha256:a09ffdd971dbd61d394723ea366d9cae6c80cffca01f518b073b9aee24418ca7
 size 1736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8609a692d0f449fd4fe48a33e113f9675a054761fb5543e8bcc2726224373735
+oid sha256:5beb8c7d993dfee78065768c05d693af80563384c89dc9e510ad6471657c1e2b
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70b9bd2f44db4add1360bdb0e6880e4580d8b55e00e8cb6c1ed7b19aa00dc709
-size 14244
+oid sha256:fbdead63124c1fc84f329ca037df0e53909d6ff2384119198ddaf577d7e61369
+size 14308

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f428dc4c0936653e8741f49c8b481e2cc2f0d2a1ce2182ef1df7e775a7d4db5
+oid sha256:6914f08d038d2fd5583fe9d1dfb74316a740319f66641c1d86781bc3fc4b8381
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd4c12276513861c1c95823628d0ead41af33d6fd90ed8d32b3a8011c6219997
+oid sha256:a5dbc7bedb58edd6ffc364b01517a26604f569a354c2be3f565e10596a8fd705
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 27000,
-  "best_metric": -30.46200942993164,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-27000",
-  "epoch": 2.076763325898008,
+  "best_global_step": 27500,
+  "best_metric": -30.462617874145508,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-27500",
+  "epoch": 2.11522190600723,
   "eval_steps": 250,
-  "global_step": 27000,
+  "global_step": 27500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4652,6 +4652,92 @@
       "eval_samples_per_second": 59.762,
       "eval_steps_per_second": 14.941,
       "step": 27000
+    },
+    {
+      "epoch": 2.0806091839089302,
+      "grad_norm": 2.005777359008789,
+      "learning_rate": 6.217177882242942e-05,
+      "loss": -30.457,
+      "step": 27050
+    },
+    {
+      "epoch": 2.084455041919852,
+      "grad_norm": 3.0324509143829346,
+      "learning_rate": 6.191205880061294e-05,
+      "loss": -30.4566,
+      "step": 27100
+    },
+    {
+      "epoch": 2.0883008999307746,
+      "grad_norm": 2.6647162437438965,
+      "learning_rate": 6.165233877879646e-05,
+      "loss": -30.4574,
+      "step": 27150
+    },
+    {
+      "epoch": 2.0921467579416966,
+      "grad_norm": 2.078568458557129,
+      "learning_rate": 6.139261875697998e-05,
+      "loss": -30.4579,
+      "step": 27200
+    },
+    {
+      "epoch": 2.095992615952619,
+      "grad_norm": 1.8361953496932983,
+      "learning_rate": 6.11328987351635e-05,
+      "loss": -30.4566,
+      "step": 27250
+    },
+    {
+      "epoch": 2.095992615952619,
+      "eval_loss": -30.461936950683594,
+      "eval_runtime": 16.9333,
+      "eval_samples_per_second": 59.055,
+      "eval_steps_per_second": 14.764,
+      "step": 27250
+    },
+    {
+      "epoch": 2.0998384739635414,
+      "grad_norm": 2.176724433898926,
+      "learning_rate": 6.087317871334701e-05,
+      "loss": -30.4579,
+      "step": 27300
+    },
+    {
+      "epoch": 2.1036843319744634,
+      "grad_norm": 2.137570858001709,
+      "learning_rate": 6.0613458691530536e-05,
+      "loss": -30.4578,
+      "step": 27350
+    },
+    {
+      "epoch": 2.1075301899853858,
+      "grad_norm": 2.3757429122924805,
+      "learning_rate": 6.0353738669714055e-05,
+      "loss": -30.4576,
+      "step": 27400
+    },
+    {
+      "epoch": 2.111376047996308,
+      "grad_norm": 2.0854310989379883,
+      "learning_rate": 6.009401864789757e-05,
+      "loss": -30.4571,
+      "step": 27450
+    },
+    {
+      "epoch": 2.11522190600723,
+      "grad_norm": 2.1995458602905273,
+      "learning_rate": 5.983429862608109e-05,
+      "loss": -30.4575,
+      "step": 27500
+    },
+    {
+      "epoch": 2.11522190600723,
+      "eval_loss": -30.462617874145508,
+      "eval_runtime": 16.8806,
+      "eval_samples_per_second": 59.24,
+      "eval_steps_per_second": 14.81,
+      "step": 27500
     }
   ],
   "logging_steps": 50,