Training in progress, step 22500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7eaab29466400eb2a657f3436b2818198ebc3b9fd87cb963c622b5d81bbf4d9
+oid sha256:48890795503039966e7c3f8690ea5e69f170d6d775e60a7c19814730a3ff98f0
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55f3c6089dbca62c8b2bebd6faf4edc5b1bb8a8a960c2f857f9b4984ed1a89d0
+oid sha256:323d035573abc68ea1fb28a0dbd169b42c919244458b9d48c24a8196ef4f1fbd
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:625da12a62ce1ec712e7ea0b4fc06eed36ff20b9634198d1bc6029989e807f8d
+oid sha256:0edeec917b285b0e88139f206de61b3e301e9b677aa51d87d86f36aba6dd8e7e
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c97cfd73b672df8a5afb8d418c975440124b784cf73259cde1c1d1e99e483d
+oid sha256:b66cb5271b1546b480a6c7621e1addbb2863a83f6bfe9ced4a812a79ec729e68
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:137a43b60deca6dd3da445bd48fbb2a7c159344a7a642ca673dc22a6f6abb915
+oid sha256:ee960841273de5fa43863b36a2f8d901df0b6ff85b61e6b4992f108a85a45d9c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 22000,
-  "best_metric": 1.4664525985717773,
+  "best_global_step": 22250,
+  "best_metric": 1.457463264465332,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-22000",
-  "epoch": 1.6921775248057842,
+  "epoch": 1.7306361049150065,
   "eval_steps": 250,
-  "global_step": 22000,
+  "global_step": 22500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3792,6 +3792,92 @@
       "eval_samples_per_second": 55.454,
       "eval_steps_per_second": 13.863,
       "step": 22000
+    },
+    {
+      "epoch": 1.6960233828167064,
+      "grad_norm": 0.8262001276016235,
+      "learning_rate": 2.7087974706812248e-05,
+      "loss": 1.4304,
+      "step": 22050
+    },
+    {
+      "epoch": 1.6998692408276286,
+      "grad_norm": 1.6224443912506104,
+      "learning_rate": 2.6830631226793128e-05,
+      "loss": 1.4127,
+      "step": 22100
+    },
+    {
+      "epoch": 1.703715098838551,
+      "grad_norm": 1.3338160514831543,
+      "learning_rate": 2.6573287746774014e-05,
+      "loss": 1.4842,
+      "step": 22150
+    },
+    {
+      "epoch": 1.707560956849473,
+      "grad_norm": 1.940238356590271,
+      "learning_rate": 2.6315944266754897e-05,
+      "loss": 1.4279,
+      "step": 22200
+    },
+    {
+      "epoch": 1.7114068148603954,
+      "grad_norm": 2.091132164001465,
+      "learning_rate": 2.6058600786735777e-05,
+      "loss": 1.3779,
+      "step": 22250
+    },
+    {
+      "epoch": 1.7114068148603954,
+      "eval_loss": 1.457463264465332,
+      "eval_runtime": 18.1835,
+      "eval_samples_per_second": 54.995,
+      "eval_steps_per_second": 13.749,
+      "step": 22250
+    },
+    {
+      "epoch": 1.7152526728713176,
+      "grad_norm": 1.4367913007736206,
+      "learning_rate": 2.5801257306716663e-05,
+      "loss": 1.4821,
+      "step": 22300
+    },
+    {
+      "epoch": 1.7190985308822397,
+      "grad_norm": 1.9735435247421265,
+      "learning_rate": 2.5543913826697546e-05,
+      "loss": 1.3754,
+      "step": 22350
+    },
+    {
+      "epoch": 1.7229443888931621,
+      "grad_norm": 1.4968055486679077,
+      "learning_rate": 2.5286570346678426e-05,
+      "loss": 1.4045,
+      "step": 22400
+    },
+    {
+      "epoch": 1.7267902469040843,
+      "grad_norm": 1.0449949502944946,
+      "learning_rate": 2.5029226866659312e-05,
+      "loss": 1.4458,
+      "step": 22450
+    },
+    {
+      "epoch": 1.7306361049150065,
+      "grad_norm": 1.164890170097351,
+      "learning_rate": 2.4771883386640196e-05,
+      "loss": 1.4407,
+      "step": 22500
+    },
+    {
+      "epoch": 1.7306361049150065,
+      "eval_loss": 1.4607012271881104,
+      "eval_runtime": 18.2079,
+      "eval_samples_per_second": 54.921,
+      "eval_steps_per_second": 13.73,
+      "step": 22500
     }
   ],
   "logging_steps": 50,