Training in progress, step 12000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:951de22caec4595c4ffeef6e17bf618ff4c5009026d3bf61fbbf6c21e394a753
+oid sha256:04d930c5c4a881dfd26ea978e652c702b6adb1b5b7ed1eed9ca7135e21510049
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94352e8877cdd376b4e0992fbcd1a31c79a5cbb8edc941287bffbb6813ad2fd9
+oid sha256:59ca03346afd36214198fb9410564c8a86b40b37890c4e424de07767c10a30ec
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ce35713c6cfde8b254092a62a162b21058e7d89b73dff276ea2ee9e65249418
+oid sha256:205a7550a4c055924e0126c3501b4b656ca55ae3243c46218f86d29fc2fb9758
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7733da2de8ba0d811f711ea7fdb6cdb69bbfeb6cd9a30bcfdad50f83ead3040c
+oid sha256:699adc1847435a16f1605601a8df2b43b7960dcbb43148ad8a4600f5fe2cb9d4
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d47850787d7113906407c13287aaa8fd754cf26d87c84c8d6940554fabd6e6fa
+oid sha256:638497dfdf5eb5c99bf0b6f11b605f213450ed644d6ebdee360506f0a10a4ae0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 11000,
-  "best_metric": 4.307990074157715,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-11000",
-  "epoch": 0.8845473425121144,
+  "best_global_step": 12000,
+  "best_metric": 1.5159597396850586,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-12000",
+  "epoch": 0.9230059226213368,
   "eval_steps": 250,
-  "global_step": 11500,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1986,6 +1986,92 @@
       "eval_samples_per_second": 53.176,
       "eval_steps_per_second": 13.294,
       "step": 11500
+    },
+    {
+      "epoch": 0.8883932005230367,
+      "grad_norm": 5.072123050689697,
+      "learning_rate": 8.112495864122642e-05,
+      "loss": 4.5564,
+      "step": 11550
+    },
+    {
+      "epoch": 0.8922390585339589,
+      "grad_norm": 3.130788564682007,
+      "learning_rate": 8.08676151612073e-05,
+      "loss": 4.427,
+      "step": 11600
+    },
+    {
+      "epoch": 0.8960849165448812,
+      "grad_norm": 2.615147352218628,
+      "learning_rate": 8.06102716811882e-05,
+      "loss": 4.3831,
+      "step": 11650
+    },
+    {
+      "epoch": 0.8999307745558034,
+      "grad_norm": 8.039403915405273,
+      "learning_rate": 8.035292820116906e-05,
+      "loss": 4.3388,
+      "step": 11700
+    },
+    {
+      "epoch": 0.9037766325667257,
+      "grad_norm": 2.6177854537963867,
+      "learning_rate": 8.009558472114994e-05,
+      "loss": 1.4931,
+      "step": 11750
+    },
+    {
+      "epoch": 0.9037766325667257,
+      "eval_loss": 1.534182071685791,
+      "eval_runtime": 18.0719,
+      "eval_samples_per_second": 55.335,
+      "eval_steps_per_second": 13.834,
+      "step": 11750
+    },
+    {
+      "epoch": 0.9076224905776479,
+      "grad_norm": 1.4090014696121216,
+      "learning_rate": 7.983824124113084e-05,
+      "loss": 1.5524,
+      "step": 11800
+    },
+    {
+      "epoch": 0.9114683485885701,
+      "grad_norm": 1.4773452281951904,
+      "learning_rate": 7.958089776111171e-05,
+      "loss": 1.4703,
+      "step": 11850
+    },
+    {
+      "epoch": 0.9153142065994924,
+      "grad_norm": 1.7350648641586304,
+      "learning_rate": 7.932355428109261e-05,
+      "loss": 1.4752,
+      "step": 11900
+    },
+    {
+      "epoch": 0.9191600646104146,
+      "grad_norm": 1.9704972505569458,
+      "learning_rate": 7.906621080107349e-05,
+      "loss": 1.5257,
+      "step": 11950
+    },
+    {
+      "epoch": 0.9230059226213368,
+      "grad_norm": 1.6183151006698608,
+      "learning_rate": 7.880886732105437e-05,
+      "loss": 1.4704,
+      "step": 12000
+    },
+    {
+      "epoch": 0.9230059226213368,
+      "eval_loss": 1.5159597396850586,
+      "eval_runtime": 17.891,
+      "eval_samples_per_second": 55.894,
+      "eval_steps_per_second": 13.974,
+      "step": 12000
     }
   ],
   "logging_steps": 50,