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:afb1f994dba522602e482c6617e68b2ec24254fe04ad07399654bbd51f70ee28
+oid sha256:79c28d4b4840c8a771d27b1f27c6ac5c00a9f2991d7394f3a6733892a09080ab
 size 36730224

last-checkpoint/ar_diffusion_info.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8076f6cd20d7f4c66417fcba7f62699920c2ac2bc88d4cc342541ab812336f0a
+oid sha256:c30265894652137003ce0d462067739a1e1f87e1fef05727cce7c9bc27d9969d
 size 1544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3531171f249076e214e0e84ae3500c8a6ba16b1c8f7d014a2f1b1fe43cc09834
+oid sha256:35ee565d832de94c600e576ee117f0978437f0823600766c050ee216a94c8988
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5f1da1040925b2052aee2dca0c3fa273b607e957cbf18770059a4080553de3f
+oid sha256:734e3f7dc3063a42733f6397bd808730560212803e7502d677f32c1adc811a33
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac450af05edcacc287976d7cce0a697b2e2b1346a00fb8804e2fa8c2427dff3
+oid sha256:a4379a058e70e2b699ffe8db7ee723ac96ffd7adc9d62248596ac9aebf5e54f3
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01b7c9c1894540a3bb43365814662cd05e754a3caa17602ed4c796362bf454cf
+oid sha256:7f444f08db434c1664e05b94a04b805dac6e17ed393cf9fcf28a82949e586c98
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 29000,
   "best_metric": 0.9999537467956543,
   "best_model_checkpoint": "./ar-diffusion-checkpoints-fixed/checkpoint-29000",
-  "epoch": 2.230597646334897,
+  "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": 57.999,
       "eval_steps_per_second": 14.5,
       "step": 29000
+    },
+    {
+      "epoch": 2.2344435043458195,
+      "grad_norm": 0.5559306740760803,
+      "learning_rate": 5.1772589148897485e-05,
+      "loss": 0.9749,
+      "step": 29050
+    },
+    {
+      "epoch": 2.238289362356742,
+      "grad_norm": 0.6720598936080933,
+      "learning_rate": 5.151286912708101e-05,
+      "loss": 0.9662,
+      "step": 29100
+    },
+    {
+      "epoch": 2.242135220367664,
+      "grad_norm": 1.117200493812561,
+      "learning_rate": 5.125314910526453e-05,
+      "loss": 0.9552,
+      "step": 29150
+    },
+    {
+      "epoch": 2.2459810783785863,
+      "grad_norm": 0.6818645000457764,
+      "learning_rate": 5.0993429083448044e-05,
+      "loss": 0.9032,
+      "step": 29200
+    },
+    {
+      "epoch": 2.2498269363895087,
+      "grad_norm": 0.9796412587165833,
+      "learning_rate": 5.0733709061631564e-05,
+      "loss": 0.9429,
+      "step": 29250
+    },
+    {
+      "epoch": 2.2498269363895087,
+      "eval_loss": 1.0121312141418457,
+      "eval_runtime": 17.3211,
+      "eval_samples_per_second": 57.733,
+      "eval_steps_per_second": 14.433,
+      "step": 29250
+    },
+    {
+      "epoch": 2.2536727944004307,
+      "grad_norm": 1.021713137626648,
+      "learning_rate": 5.047398903981508e-05,
+      "loss": 0.979,
+      "step": 29300
+    },
+    {
+      "epoch": 2.257518652411353,
+      "grad_norm": 1.1321250200271606,
+      "learning_rate": 5.02142690179986e-05,
+      "loss": 1.0327,
+      "step": 29350
+    },
+    {
+      "epoch": 2.261364510422275,
+      "grad_norm": 0.7670277953147888,
+      "learning_rate": 4.9954548996182116e-05,
+      "loss": 0.9668,
+      "step": 29400
+    },
+    {
+      "epoch": 2.2652103684331975,
+      "grad_norm": 1.447698712348938,
+      "learning_rate": 4.9694828974365635e-05,
+      "loss": 0.9288,
+      "step": 29450
+    },
+    {
+      "epoch": 2.26905622644412,
+      "grad_norm": 1.0438776016235352,
+      "learning_rate": 4.9435108952549155e-05,
+      "loss": 1.0154,
+      "step": 29500
+    },
+    {
+      "epoch": 2.26905622644412,
+      "eval_loss": 1.0100510120391846,
+      "eval_runtime": 17.4293,
+      "eval_samples_per_second": 57.375,
+      "eval_steps_per_second": 14.344,
+      "step": 29500
     }
   ],
   "logging_steps": 50,