Training in progress, step 26500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:354784630980b3e128043f599d1fa81d4eaeefccc49f9c73ac417f4b9affdc81
+oid sha256:f619cbe8165ed1e2332f6436e4fdf6c896db5237d638a5179f03f772e54deae1
 size 36730224

last-checkpoint/ar_diffusion_info.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a382cd1d7b1cfe5578921e4a35263f149f5e86ef7359d296d8b1f906cce62a74
+oid sha256:0e41f1a18d6f9531a4bd645cd462d9090e6f54162f6fddf017afc585f3099347
 size 1544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbdd51e862aa846114442fbe4fc73ff82d5222c26562144ee40037d5d63ab0b6
+oid sha256:f75a42181e10c429bdf4cde150fa8bd273b194edd1af255a2c46af2a16e4d777
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35c260873e53de579d314af7f23d76fd9a02c023129e1ca7c8f1d3d5f4fae1d0
+oid sha256:5b56501523df118c1a33e60d970ee258e92691efddadd68cb368e352ca4fb0c1
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfd4827b4f5f4123b9a08cd207611b32b5022ac9c327a327659c2a44bd51e209
+oid sha256:3bfa502239c4234c76e8429085577f9d92a7a11c10a2a19927df506f4396be9a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f5beeb269815e15f5dc6759e189a2780818b22a064798960c77eef6918e2b17
+oid sha256:cde03cf528fa40100e793e6bc03d3e643c03bab96500bb8c5705c4e1018be13d
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 24500,
   "best_metric": 1.445096731185913,
   "best_model_checkpoint": "./ar-diffusion-checkpoints-fixed/checkpoint-24500",
-  "epoch": 1.9998461656795632,
+  "epoch": 2.0383047457887855,
   "eval_steps": 250,
-  "global_step": 26000,
+  "global_step": 26500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4480,6 +4480,92 @@
       "eval_samples_per_second": 55.373,
       "eval_steps_per_second": 13.843,
       "step": 26000
+    },
+    {
+      "epoch": 2.003692023690485,
+      "grad_norm": 1.621793508529663,
+      "learning_rate": 6.73557904578864e-05,
+      "loss": 1.369,
+      "step": 26050
+    },
+    {
+      "epoch": 2.0075378817014076,
+      "grad_norm": 2.223520278930664,
+      "learning_rate": 6.709607043606992e-05,
+      "loss": 1.4269,
+      "step": 26100
+    },
+    {
+      "epoch": 2.01138373971233,
+      "grad_norm": 1.4860827922821045,
+      "learning_rate": 6.683635041425344e-05,
+      "loss": 1.3634,
+      "step": 26150
+    },
+    {
+      "epoch": 2.015229597723252,
+      "grad_norm": 2.0796148777008057,
+      "learning_rate": 6.657663039243696e-05,
+      "loss": 1.4233,
+      "step": 26200
+    },
+    {
+      "epoch": 2.0190754557341744,
+      "grad_norm": 1.6398444175720215,
+      "learning_rate": 6.631691037062047e-05,
+      "loss": 1.4058,
+      "step": 26250
+    },
+    {
+      "epoch": 2.0190754557341744,
+      "eval_loss": 1.4733901023864746,
+      "eval_runtime": 18.0349,
+      "eval_samples_per_second": 55.448,
+      "eval_steps_per_second": 13.862,
+      "step": 26250
+    },
+    {
+      "epoch": 2.0229213137450963,
+      "grad_norm": 1.7550077438354492,
+      "learning_rate": 6.605719034880399e-05,
+      "loss": 1.4436,
+      "step": 26300
+    },
+    {
+      "epoch": 2.0267671717560187,
+      "grad_norm": 2.3273561000823975,
+      "learning_rate": 6.579747032698751e-05,
+      "loss": 1.356,
+      "step": 26350
+    },
+    {
+      "epoch": 2.030613029766941,
+      "grad_norm": 1.1432509422302246,
+      "learning_rate": 6.553775030517103e-05,
+      "loss": 1.4116,
+      "step": 26400
+    },
+    {
+      "epoch": 2.034458887777863,
+      "grad_norm": 1.2345376014709473,
+      "learning_rate": 6.527803028335455e-05,
+      "loss": 1.4465,
+      "step": 26450
+    },
+    {
+      "epoch": 2.0383047457887855,
+      "grad_norm": 1.485564112663269,
+      "learning_rate": 6.501831026153807e-05,
+      "loss": 1.3896,
+      "step": 26500
+    },
+    {
+      "epoch": 2.0383047457887855,
+      "eval_loss": 1.4492217302322388,
+      "eval_runtime": 17.9114,
+      "eval_samples_per_second": 55.83,
+      "eval_steps_per_second": 13.958,
+      "step": 26500
     }
   ],
   "logging_steps": 50,