Training in progress, step 27000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6613ebe36b9e1a2df92d9382e8e15ccd7231d770ac79cb6d90e8b9367b797cf7
+oid sha256:05b2f61187a90a08831b51555301b195d55056396e6a01f761a6a8e73fc0fb0c
 size 36730224

last-checkpoint/ar_diffusion_info.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2b095fc07e922d1a9c25ee8346efcd5a2c81d54dca44bdafb5d0e9f2eb3e24a
+oid sha256:0d42710c0be0d1f6e449827dca6d2dbf6f093dff7f08d2e50fa7e4b598258fc4
 size 1736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48420f70a29712473c5bb303eab046f0a5752cf153d61f00e861f4b58f5de680
+oid sha256:8609a692d0f449fd4fe48a33e113f9675a054761fb5543e8bcc2726224373735
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c390a1583910e22230c4196130b3c0f41baef66bad1306d608f5ab988da167b
+oid sha256:70b9bd2f44db4add1360bdb0e6880e4580d8b55e00e8cb6c1ed7b19aa00dc709
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f954f12f0ff9cbb91d568da9d7d6eaeb4be153ad115ee9d2d8bb42b61371b07
+oid sha256:1f428dc4c0936653e8741f49c8b481e2cc2f0d2a1ce2182ef1df7e775a7d4db5
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab838be4b789037996449256e9db759ef182f16c1a4c58aef4a8a8c11a05ec15
+oid sha256:cd4c12276513861c1c95823628d0ead41af33d6fd90ed8d32b3a8011c6219997
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 25750,
-  "best_metric": -30.4610538482666,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-25000",
-  "epoch": 2.0383047457887855,
+  "best_global_step": 27000,
+  "best_metric": -30.46200942993164,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-27000",
+  "epoch": 2.076763325898008,
   "eval_steps": 250,
-  "global_step": 26500,
+  "global_step": 27000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4566,6 +4566,92 @@
       "eval_samples_per_second": 59.478,
       "eval_steps_per_second": 14.869,
       "step": 26500
+    },
+    {
+      "epoch": 2.042150603799708,
+      "grad_norm": 2.257894992828369,
+      "learning_rate": 6.476897904059424e-05,
+      "loss": -30.4568,
+      "step": 26550
+    },
+    {
+      "epoch": 2.04599646181063,
+      "grad_norm": 3.5271377563476562,
+      "learning_rate": 6.450925901877776e-05,
+      "loss": -30.4569,
+      "step": 26600
+    },
+    {
+      "epoch": 2.0498423198215523,
+      "grad_norm": 2.4597764015197754,
+      "learning_rate": 6.424953899696128e-05,
+      "loss": -30.4565,
+      "step": 26650
+    },
+    {
+      "epoch": 2.0536881778324743,
+      "grad_norm": 2.209780693054199,
+      "learning_rate": 6.39898189751448e-05,
+      "loss": -30.4567,
+      "step": 26700
+    },
+    {
+      "epoch": 2.0575340358433967,
+      "grad_norm": 2.887272834777832,
+      "learning_rate": 6.373009895332831e-05,
+      "loss": -30.4562,
+      "step": 26750
+    },
+    {
+      "epoch": 2.0575340358433967,
+      "eval_loss": -30.461790084838867,
+      "eval_runtime": 16.8176,
+      "eval_samples_per_second": 59.462,
+      "eval_steps_per_second": 14.865,
+      "step": 26750
+    },
+    {
+      "epoch": 2.061379893854319,
+      "grad_norm": 1.9459458589553833,
+      "learning_rate": 6.347037893151183e-05,
+      "loss": -30.4557,
+      "step": 26800
+    },
+    {
+      "epoch": 2.065225751865241,
+      "grad_norm": 1.4567102193832397,
+      "learning_rate": 6.321065890969535e-05,
+      "loss": -30.4562,
+      "step": 26850
+    },
+    {
+      "epoch": 2.0690716098761635,
+      "grad_norm": 2.8089401721954346,
+      "learning_rate": 6.295093888787887e-05,
+      "loss": -30.4562,
+      "step": 26900
+    },
+    {
+      "epoch": 2.0729174678870854,
+      "grad_norm": 1.6846117973327637,
+      "learning_rate": 6.269121886606239e-05,
+      "loss": -30.4563,
+      "step": 26950
+    },
+    {
+      "epoch": 2.076763325898008,
+      "grad_norm": 2.10868501663208,
+      "learning_rate": 6.243149884424591e-05,
+      "loss": -30.4575,
+      "step": 27000
+    },
+    {
+      "epoch": 2.076763325898008,
+      "eval_loss": -30.46200942993164,
+      "eval_runtime": 16.733,
+      "eval_samples_per_second": 59.762,
+      "eval_steps_per_second": 14.941,
+      "step": 27000
     }
   ],
   "logging_steps": 50,