Training in progress, step 20500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff1d47cdb13e83e8fe6a9d20b6c173dfae48b029aecf5c92bf458772133f5b2
+oid sha256:c3fe29335718233e84f1e65e1e50047d21ed0639ab8d8950d51643ac36288179
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c26f8a7499e23aa16477b380bf134293878cb8936b98f8cad1d8a606fc561e1a
+oid sha256:9c45065f737f44883104a4351c674ace9478a208428702e003f4cf5e07e96452
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b205d8106465470d82a9f668e113b1a4c937f3fe768b385e78f85eb171e49cc2
+oid sha256:5dbffb5b9d940a96eb51dbe7a35860718ecfeca99437ad8b1b71dbafaefdd573
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:344e181f9677a4d18097c7085524ad711f8dfb151d42735faf9658fba6102bed
+oid sha256:007715702cfbd38b6fa4b8b523a7e58a1cfb0651b5c1c69d07c436463e26a8bf
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fc471d6cffa6d4b3db986d1e54c37de8f3b7f607849783a6e6b32bce97519eb
+oid sha256:780bb1353dd0d4e52605608cc24ae3410777df1acea35ed02a82bdb21fa7ba07
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 18750,
-  "best_metric": 1.4680087566375732,
+  "best_global_step": 20250,
+  "best_metric": 1.4672300815582275,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-15500",
-  "epoch": 1.5383432043688947,
+  "epoch": 1.576801784478117,
   "eval_steps": 250,
-  "global_step": 20000,
+  "global_step": 20500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3448,6 +3448,92 @@
       "eval_samples_per_second": 55.233,
       "eval_steps_per_second": 13.808,
       "step": 20000
+    },
+    {
+      "epoch": 1.542189062379817,
+      "grad_norm": 1.4523636102676392,
+      "learning_rate": 3.7376567037976546e-05,
+      "loss": 1.4538,
+      "step": 20050
+    },
+    {
+      "epoch": 1.5460349203907393,
+      "grad_norm": 1.854066252708435,
+      "learning_rate": 3.7119223557957426e-05,
+      "loss": 1.4532,
+      "step": 20100
+    },
+    {
+      "epoch": 1.5498807784016613,
+      "grad_norm": 1.8892920017242432,
+      "learning_rate": 3.6861880077938306e-05,
+      "loss": 1.4301,
+      "step": 20150
+    },
+    {
+      "epoch": 1.5537266364125837,
+      "grad_norm": 1.2957504987716675,
+      "learning_rate": 3.6609683467519574e-05,
+      "loss": 1.4613,
+      "step": 20200
+    },
+    {
+      "epoch": 1.5575724944235059,
+      "grad_norm": 1.9040348529815674,
+      "learning_rate": 3.635233998750046e-05,
+      "loss": 1.3847,
+      "step": 20250
+    },
+    {
+      "epoch": 1.5575724944235059,
+      "eval_loss": 1.4672300815582275,
+      "eval_runtime": 17.9888,
+      "eval_samples_per_second": 55.59,
+      "eval_steps_per_second": 13.898,
+      "step": 20250
+    },
+    {
+      "epoch": 1.561418352434428,
+      "grad_norm": 1.4990596771240234,
+      "learning_rate": 3.609499650748134e-05,
+      "loss": 1.4243,
+      "step": 20300
+    },
+    {
+      "epoch": 1.5652642104453505,
+      "grad_norm": 2.344515562057495,
+      "learning_rate": 3.583765302746222e-05,
+      "loss": 1.4971,
+      "step": 20350
+    },
+    {
+      "epoch": 1.5691100684562724,
+      "grad_norm": 2.2836570739746094,
+      "learning_rate": 3.5580309547443106e-05,
+      "loss": 1.4641,
+      "step": 20400
+    },
+    {
+      "epoch": 1.5729559264671948,
+      "grad_norm": 1.0165778398513794,
+      "learning_rate": 3.5322966067423986e-05,
+      "loss": 1.4268,
+      "step": 20450
+    },
+    {
+      "epoch": 1.576801784478117,
+      "grad_norm": 0.5663600564002991,
+      "learning_rate": 3.506562258740487e-05,
+      "loss": 1.3487,
+      "step": 20500
+    },
+    {
+      "epoch": 1.576801784478117,
+      "eval_loss": 1.4733059406280518,
+      "eval_runtime": 18.0399,
+      "eval_samples_per_second": 55.433,
+      "eval_steps_per_second": 13.858,
+      "step": 20500
     }
   ],
   "logging_steps": 50,