Training in progress, step 16000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6067e5da0c9bf8b752e4ae8c8bf60db131ffcb5bdc72c1bef0c50cf034756793
+oid sha256:72bbf1639eb1e5bb9c61f65f54a93961c6ba815ff973db8268065d37b1392548
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70b3ce160c7b776e775a166f1cb68bd1487d55fdb2e7ccd66b23097de2464f87
+oid sha256:ca4486e1d2b5552334fa9da91cfad2dd01fc4b1d85bf70178d94c3a9a06c15d0
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e443e4b8c749db54f7826bd4573803e0f05009235443f881fa9932376e1aba8
-size 14244
+oid sha256:2268c750118e17cd7866635da6e44831e071d618455f938ab68da6b4daa1e485
+size 14180

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c46d93b856d73467b22e6683f2d8e760cc9d35c9e6261e9397f7ae15ef306957
+oid sha256:d55844b7da2e1071a7670fddb811c2bc2d24a926bedcc2bd08e1031b2ef69bf6
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:682c1f39bde20c90a4373af21bd5402ac0e8e55951fcfe8f05caeac3b074ab9a
+oid sha256:b1ee899fe281691d25f12760d42a5b17bb85c5d0104daf152b3a9bdedb20881a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 15500,
-  "best_metric": 1.4925825595855713,
+  "best_global_step": 15750,
+  "best_metric": 1.4893933534622192,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-15500",
-  "epoch": 1.1922159833858934,
+  "epoch": 1.2306745634951157,
   "eval_steps": 250,
-  "global_step": 15500,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2674,6 +2674,92 @@
       "eval_samples_per_second": 54.91,
       "eval_steps_per_second": 13.727,
       "step": 15500
+    },
+    {
+      "epoch": 1.1960618413968156,
+      "grad_norm": 2.7062911987304688,
+      "learning_rate": 6.053748023969707e-05,
+      "loss": 1.4145,
+      "step": 15550
+    },
+    {
+      "epoch": 1.1999076994077378,
+      "grad_norm": 1.5163620710372925,
+      "learning_rate": 6.028013675967794e-05,
+      "loss": 1.4322,
+      "step": 15600
+    },
+    {
+      "epoch": 1.2037535574186602,
+      "grad_norm": 1.342063546180725,
+      "learning_rate": 6.002279327965883e-05,
+      "loss": 1.4696,
+      "step": 15650
+    },
+    {
+      "epoch": 1.2075994154295824,
+      "grad_norm": 1.8180099725723267,
+      "learning_rate": 5.9765449799639715e-05,
+      "loss": 1.4647,
+      "step": 15700
+    },
+    {
+      "epoch": 1.2114452734405046,
+      "grad_norm": 1.951982855796814,
+      "learning_rate": 5.9508106319620595e-05,
+      "loss": 1.5141,
+      "step": 15750
+    },
+    {
+      "epoch": 1.2114452734405046,
+      "eval_loss": 1.4893933534622192,
+      "eval_runtime": 18.1951,
+      "eval_samples_per_second": 54.96,
+      "eval_steps_per_second": 13.74,
+      "step": 15750
+    },
+    {
+      "epoch": 1.2152911314514268,
+      "grad_norm": 1.7536894083023071,
+      "learning_rate": 5.925076283960148e-05,
+      "loss": 1.514,
+      "step": 15800
+    },
+    {
+      "epoch": 1.2191369894623492,
+      "grad_norm": 1.1857939958572388,
+      "learning_rate": 5.899341935958237e-05,
+      "loss": 1.4745,
+      "step": 15850
+    },
+    {
+      "epoch": 1.2229828474732714,
+      "grad_norm": 1.2500842809677124,
+      "learning_rate": 5.873607587956324e-05,
+      "loss": 1.4325,
+      "step": 15900
+    },
+    {
+      "epoch": 1.2268287054841935,
+      "grad_norm": 2.025336742401123,
+      "learning_rate": 5.847873239954413e-05,
+      "loss": 1.4913,
+      "step": 15950
+    },
+    {
+      "epoch": 1.2306745634951157,
+      "grad_norm": 1.1440426111221313,
+      "learning_rate": 5.8221388919525014e-05,
+      "loss": 1.451,
+      "step": 16000
+    },
+    {
+      "epoch": 1.2306745634951157,
+      "eval_loss": 1.492313265800476,
+      "eval_runtime": 18.0024,
+      "eval_samples_per_second": 55.548,
+      "eval_steps_per_second": 13.887,
+      "step": 16000
     }
   ],
   "logging_steps": 50,