Training in progress, step 29500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd0781acb6c7fc9ded8317d52242fc4359ee883c01cebb7ec0c3a58b0c6bbbba
+oid sha256:07e30b1489833c4785165cc07964a7967e7f19514998619730c9034b8360f53c
 size 36730224

last-checkpoint/ar_diffusion_info.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a455424fbaf1d98ae947b1c6b0b80b54217206b6f18f1f938075a6676b3f5869
+oid sha256:46a0295e727a34db181fb27c30aad277d445122fca4864b255064b7ceb0d77ad
 size 1736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77d7dc3a28d4fe3231c40525cd0f8f6aa88dc1465a1a1cfd289fcfd760fdc98c
+oid sha256:66bcf02fb2647726be3a605dd48a196698adb22cf814cf2a1eb3624247d8cb63
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:585b1b78ad161d83e10b979be5e13c56f505cb7e3c7f6ffb9bf602329961f81d
-size 14244
+oid sha256:e8bb6451763671a1f8ecb224e2e6bbe40912a0dfb77f3c38d04ffa7b817a7484
+size 14180

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8adfe0c3a658b29afc7477e5e111d27a14f61608e8c22c6eae3e26a58581ec8f
+oid sha256:cf6a40561a300d2a4016646332c8a3a6bbfc4bae22d69367caebfd688033281d
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f58c64de929250270d98ac0602d9b7331b024fd8aa50ab140ef1957df25081
+oid sha256:e0ca12f1afb31cdc8c30b1188ad677485603bdc5a7c9d468bf5797580871892e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 29000,
-  "best_metric": -30.4643497467041,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-29000",
-  "epoch": 2.230597646334897,
+  "best_global_step": 29500,
+  "best_metric": -30.46525001525879,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-29500",
+  "epoch": 2.26905622644412,
   "eval_steps": 250,
-  "global_step": 29000,
+  "global_step": 29500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4996,6 +4996,92 @@
       "eval_samples_per_second": 59.306,
       "eval_steps_per_second": 14.827,
       "step": 29000
+    },
+    {
+      "epoch": 2.2344435043458195,
+      "grad_norm": 2.0510427951812744,
+      "learning_rate": 5.178297794977015e-05,
+      "loss": -30.4589,
+      "step": 29050
+    },
+    {
+      "epoch": 2.238289362356742,
+      "grad_norm": 1.5907058715820312,
+      "learning_rate": 5.1523257927953675e-05,
+      "loss": -30.4597,
+      "step": 29100
+    },
+    {
+      "epoch": 2.242135220367664,
+      "grad_norm": 2.039212226867676,
+      "learning_rate": 5.126353790613718e-05,
+      "loss": -30.4604,
+      "step": 29150
+    },
+    {
+      "epoch": 2.2459810783785863,
+      "grad_norm": 1.4781228303909302,
+      "learning_rate": 5.10038178843207e-05,
+      "loss": -30.4605,
+      "step": 29200
+    },
+    {
+      "epoch": 2.2498269363895087,
+      "grad_norm": 1.5673744678497314,
+      "learning_rate": 5.074409786250423e-05,
+      "loss": -30.4595,
+      "step": 29250
+    },
+    {
+      "epoch": 2.2498269363895087,
+      "eval_loss": -30.46396827697754,
+      "eval_runtime": 16.8497,
+      "eval_samples_per_second": 59.348,
+      "eval_steps_per_second": 14.837,
+      "step": 29250
+    },
+    {
+      "epoch": 2.2536727944004307,
+      "grad_norm": 1.5207022428512573,
+      "learning_rate": 5.048437784068775e-05,
+      "loss": -30.4592,
+      "step": 29300
+    },
+    {
+      "epoch": 2.257518652411353,
+      "grad_norm": 1.9671216011047363,
+      "learning_rate": 5.022465781887126e-05,
+      "loss": -30.46,
+      "step": 29350
+    },
+    {
+      "epoch": 2.261364510422275,
+      "grad_norm": 1.6448663473129272,
+      "learning_rate": 4.996493779705478e-05,
+      "loss": -30.4604,
+      "step": 29400
+    },
+    {
+      "epoch": 2.2652103684331975,
+      "grad_norm": 2.366356372833252,
+      "learning_rate": 4.970521777523829e-05,
+      "loss": -30.4599,
+      "step": 29450
+    },
+    {
+      "epoch": 2.26905622644412,
+      "grad_norm": 2.137887716293335,
+      "learning_rate": 4.944549775342182e-05,
+      "loss": -30.4605,
+      "step": 29500
+    },
+    {
+      "epoch": 2.26905622644412,
+      "eval_loss": -30.46525001525879,
+      "eval_runtime": 16.856,
+      "eval_samples_per_second": 59.326,
+      "eval_steps_per_second": 14.832,
+      "step": 29500
     }
   ],
   "logging_steps": 50,