Training in progress, step 25500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6635748f5efd9f5844c8d4b5d5db81b7d2ecb035e0b0b74854654c135879fa40
+oid sha256:b2e333303611bdcfe53850b8382bc5c6096b913ec43665a75beb67494ee5bcb0
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad541eebf67a51f73b18019a22769780ac860d88ba5ea0fa90f19a9d6cea9ec7
+oid sha256:66d78210b05e1c87c136a3c08a8840809f76d0b17ce40128a18c0fba7403a0f6
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4a89f558d7b243194fee72d6e3b515995ba03b6bdbb2a1ac92b9b326a12ba3e
-size 14308
+oid sha256:dc69f04c57ac233f68440607df3025c3f527f698c64e56350e0ea45b99be0781
+size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a37acbb5f6130f7db2eedbc963d0b24fea22de7a0acc314ee6d2189d860dec7
+oid sha256:92ee59d15723c28ba4726ae8f5244e001c8225a696c80d61ce6d100eb1539722
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32c12577cf6cc4241331592a413ca96d437bc677a535a9ee4eb64f282b42fe2f
+oid sha256:cfd4ecc27bf3b1377a8048f15a651b111fa15d35d5db24035804ad1d2f0064c3
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 24500,
   "best_metric": 1.4431298971176147,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-24500",
-  "epoch": 1.9229290054611183,
+  "epoch": 1.9613875855703409,
   "eval_steps": 250,
-  "global_step": 25000,
+  "global_step": 25500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4308,6 +4308,92 @@
       "eval_samples_per_second": 54.736,
       "eval_steps_per_second": 13.684,
       "step": 25000
+    },
+    {
+      "epoch": 1.9267748634720405,
+      "grad_norm": 1.1179672479629517,
+      "learning_rate": 1.1652512775265614e-05,
+      "loss": 1.5076,
+      "step": 25050
+    },
+    {
+      "epoch": 1.930620721482963,
+      "grad_norm": 0.9407248497009277,
+      "learning_rate": 1.1395169295246496e-05,
+      "loss": 1.468,
+      "step": 25100
+    },
+    {
+      "epoch": 1.9344665794938851,
+      "grad_norm": 1.498488426208496,
+      "learning_rate": 1.113782581522738e-05,
+      "loss": 1.4566,
+      "step": 25150
+    },
+    {
+      "epoch": 1.9383124375048073,
+      "grad_norm": 0.6983101963996887,
+      "learning_rate": 1.0880482335208264e-05,
+      "loss": 1.4621,
+      "step": 25200
+    },
+    {
+      "epoch": 1.9421582955157297,
+      "grad_norm": 1.954953908920288,
+      "learning_rate": 1.0623138855189145e-05,
+      "loss": 1.417,
+      "step": 25250
+    },
+    {
+      "epoch": 1.9421582955157297,
+      "eval_loss": 1.4591727256774902,
+      "eval_runtime": 18.0732,
+      "eval_samples_per_second": 55.331,
+      "eval_steps_per_second": 13.833,
+      "step": 25250
+    },
+    {
+      "epoch": 1.9460041535266517,
+      "grad_norm": 1.6467170715332031,
+      "learning_rate": 1.036579537517003e-05,
+      "loss": 1.4942,
+      "step": 25300
+    },
+    {
+      "epoch": 1.949850011537574,
+      "grad_norm": 1.4509849548339844,
+      "learning_rate": 1.0108451895150913e-05,
+      "loss": 1.4539,
+      "step": 25350
+    },
+    {
+      "epoch": 1.9536958695484963,
+      "grad_norm": 1.6131352186203003,
+      "learning_rate": 9.851108415131796e-06,
+      "loss": 1.3993,
+      "step": 25400
+    },
+    {
+      "epoch": 1.9575417275594185,
+      "grad_norm": 1.880043387413025,
+      "learning_rate": 9.593764935112679e-06,
+      "loss": 1.4449,
+      "step": 25450
+    },
+    {
+      "epoch": 1.9613875855703409,
+      "grad_norm": 1.3041406869888306,
+      "learning_rate": 9.336421455093562e-06,
+      "loss": 1.4918,
+      "step": 25500
+    },
+    {
+      "epoch": 1.9613875855703409,
+      "eval_loss": 1.4548134803771973,
+      "eval_runtime": 18.0544,
+      "eval_samples_per_second": 55.388,
+      "eval_steps_per_second": 13.847,
+      "step": 25500
     }
   ],
   "logging_steps": 50,