Training in progress, step 36500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16887918a2514cde38397627644e79ad7a7cc859123d9755cbcacbf31a8c9f7d
+oid sha256:2f00ee81c87f16a8bdea12f78335f236b7be0e12be02042e846ac3c0d151355c
 size 36730224

last-checkpoint/ar_diffusion_info.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc4a7c0e93c6189640f847962e46079ebcf94653f638d4fdd14079010baf0e65
+oid sha256:efdccb23bf5e306d948f48beb9315429633d26670a250b2f01f01a906be73107
 size 1736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:266a495e1a502f1d39b57b5fcb15d594e7ebb88b9a37c10fcde88037b918f14e
+oid sha256:5d4a503089b873fa58fe7ad923dc676b15a066d799ced08a885cce4c8b7d5b5a
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c600e0bd51e53276481f2f5ca4e889540a7504baebe1c05ac1ae4c81b5b17f3
-size 14180
+oid sha256:b5d0f591d999e8283f8ffbd498c9dcefdfec3c57a9cf9cddf8c2ec79814e55a9
+size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49ec2d3f3b18676d40b30b5547947dd759a32e3455d479b941fbf8c1dd3301d4
+oid sha256:d6a361b5fce627657860521eb50e2574f27b2d4131fa370a849ae347ab3399c1
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:906c43e30b9edc8f130b3f77317e01f206c6e5f1267c22ca4899b9c5968ba8ca
+oid sha256:0cf91a495853427b5f841ab1be3c35766ad0edbc12ff06e2c15160a47811ed22
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 35500,
-  "best_metric": -30.469755172729492,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-35500",
-  "epoch": 2.7690177678640104,
+  "best_global_step": 36500,
+  "best_metric": -30.47022247314453,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-36500",
+  "epoch": 2.8074763479732328,
   "eval_steps": 250,
-  "global_step": 36000,
+  "global_step": 36500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6200,6 +6200,92 @@
       "eval_samples_per_second": 59.708,
       "eval_steps_per_second": 14.927,
       "step": 36000
+    },
+    {
+      "epoch": 2.772863625874933,
+      "grad_norm": 2.303079128265381,
+      "learning_rate": 1.5422174895462695e-05,
+      "loss": -30.4658,
+      "step": 36050
+    },
+    {
+      "epoch": 2.776709483885855,
+      "grad_norm": 1.1409249305725098,
+      "learning_rate": 1.516245487364621e-05,
+      "loss": -30.4659,
+      "step": 36100
+    },
+    {
+      "epoch": 2.780555341896777,
+      "grad_norm": 0.9111425280570984,
+      "learning_rate": 1.4902734851829727e-05,
+      "loss": -30.4658,
+      "step": 36150
+    },
+    {
+      "epoch": 2.784401199907699,
+      "grad_norm": 1.3415731191635132,
+      "learning_rate": 1.4643014830013247e-05,
+      "loss": -30.4659,
+      "step": 36200
+    },
+    {
+      "epoch": 2.7882470579186216,
+      "grad_norm": 0.8532393574714661,
+      "learning_rate": 1.4383294808196765e-05,
+      "loss": -30.4658,
+      "step": 36250
+    },
+    {
+      "epoch": 2.7882470579186216,
+      "eval_loss": -30.469867706298828,
+      "eval_runtime": 17.0192,
+      "eval_samples_per_second": 58.757,
+      "eval_steps_per_second": 14.689,
+      "step": 36250
+    },
+    {
+      "epoch": 2.792092915929544,
+      "grad_norm": 1.6142336130142212,
+      "learning_rate": 1.4123574786380284e-05,
+      "loss": -30.4662,
+      "step": 36300
+    },
+    {
+      "epoch": 2.795938773940466,
+      "grad_norm": 1.9979597330093384,
+      "learning_rate": 1.3863854764563799e-05,
+      "loss": -30.4652,
+      "step": 36350
+    },
+    {
+      "epoch": 2.7997846319513884,
+      "grad_norm": 1.4881914854049683,
+      "learning_rate": 1.3604134742747318e-05,
+      "loss": -30.466,
+      "step": 36400
+    },
+    {
+      "epoch": 2.803630489962311,
+      "grad_norm": 2.0614233016967773,
+      "learning_rate": 1.3344414720930836e-05,
+      "loss": -30.4658,
+      "step": 36450
+    },
+    {
+      "epoch": 2.8074763479732328,
+      "grad_norm": 1.0104310512542725,
+      "learning_rate": 1.3084694699114356e-05,
+      "loss": -30.466,
+      "step": 36500
+    },
+    {
+      "epoch": 2.8074763479732328,
+      "eval_loss": -30.47022247314453,
+      "eval_runtime": 16.8782,
+      "eval_samples_per_second": 59.248,
+      "eval_steps_per_second": 14.812,
+      "step": 36500
     }
   ],
   "logging_steps": 50,