Training in progress, step 30000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e30b1489833c4785165cc07964a7967e7f19514998619730c9034b8360f53c
+oid sha256:c9b68b51e8fff66c24bd9ee085ab44d3554951464da7ab022967415b754cf619
 size 36730224

last-checkpoint/ar_diffusion_info.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46a0295e727a34db181fb27c30aad277d445122fca4864b255064b7ceb0d77ad
+oid sha256:229d656242ed8712fdd306a0f42393369161471860d19a45511ec4ebba2eec8b
 size 1736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66bcf02fb2647726be3a605dd48a196698adb22cf814cf2a1eb3624247d8cb63
+oid sha256:fc097ff8976ee4fc15d35ce0745b655d5cf5baab3d164ed0f5744f84b5086d15
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8bb6451763671a1f8ecb224e2e6bbe40912a0dfb77f3c38d04ffa7b817a7484
-size 14180
+oid sha256:106cdbfaa2871ae8858cf090dc4670993314fc222b66209c733e45aaa0593c8b
+size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf6a40561a300d2a4016646332c8a3a6bbfc4bae22d69367caebfd688033281d
+oid sha256:8c5e675752fddbcf16f4c1fa12af2560850af8a650e75d66360b1809b0c4855e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0ca12f1afb31cdc8c30b1188ad677485603bdc5a7c9d468bf5797580871892e
+oid sha256:8c42fd76c7d2355a8c5f5acae442ab359b95f2436abcae0b56f6b159f7226239
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 29500,
-  "best_metric": -30.46525001525879,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-29500",
-  "epoch": 2.26905622644412,
+  "best_global_step": 30000,
+  "best_metric": -30.46541976928711,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-30000",
+  "epoch": 2.307514806553342,
   "eval_steps": 250,
-  "global_step": 29500,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5082,6 +5082,92 @@
       "eval_samples_per_second": 59.326,
       "eval_steps_per_second": 14.832,
       "step": 29500
+    },
+    {
+      "epoch": 2.272902084455042,
+      "grad_norm": 2.2537872791290283,
+      "learning_rate": 4.918577773160533e-05,
+      "loss": -30.4599,
+      "step": 29550
+    },
+    {
+      "epoch": 2.2767479424659642,
+      "grad_norm": 1.9328151941299438,
+      "learning_rate": 4.8926057709788844e-05,
+      "loss": -30.4602,
+      "step": 29600
+    },
+    {
+      "epoch": 2.280593800476886,
+      "grad_norm": 2.076399326324463,
+      "learning_rate": 4.866633768797237e-05,
+      "loss": -30.4607,
+      "step": 29650
+    },
+    {
+      "epoch": 2.2844396584878086,
+      "grad_norm": 1.552717924118042,
+      "learning_rate": 4.840661766615588e-05,
+      "loss": -30.46,
+      "step": 29700
+    },
+    {
+      "epoch": 2.288285516498731,
+      "grad_norm": 1.7150416374206543,
+      "learning_rate": 4.81468976443394e-05,
+      "loss": -30.4601,
+      "step": 29750
+    },
+    {
+      "epoch": 2.288285516498731,
+      "eval_loss": -30.464597702026367,
+      "eval_runtime": 16.899,
+      "eval_samples_per_second": 59.175,
+      "eval_steps_per_second": 14.794,
+      "step": 29750
+    },
+    {
+      "epoch": 2.292131374509653,
+      "grad_norm": 2.387169122695923,
+      "learning_rate": 4.788717762252292e-05,
+      "loss": -30.4604,
+      "step": 29800
+    },
+    {
+      "epoch": 2.2959772325205754,
+      "grad_norm": 2.8682591915130615,
+      "learning_rate": 4.762745760070644e-05,
+      "loss": -30.4607,
+      "step": 29850
+    },
+    {
+      "epoch": 2.299823090531498,
+      "grad_norm": 2.2639787197113037,
+      "learning_rate": 4.736773757888996e-05,
+      "loss": -30.4605,
+      "step": 29900
+    },
+    {
+      "epoch": 2.3036689485424198,
+      "grad_norm": 1.8516710996627808,
+      "learning_rate": 4.7108017557073475e-05,
+      "loss": -30.4601,
+      "step": 29950
+    },
+    {
+      "epoch": 2.307514806553342,
+      "grad_norm": 2.0204548835754395,
+      "learning_rate": 4.6848297535256994e-05,
+      "loss": -30.4602,
+      "step": 30000
+    },
+    {
+      "epoch": 2.307514806553342,
+      "eval_loss": -30.46541976928711,
+      "eval_runtime": 16.9539,
+      "eval_samples_per_second": 58.983,
+      "eval_steps_per_second": 14.746,
+      "step": 30000
     }
   ],
   "logging_steps": 50,