Training in progress, step 23000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48890795503039966e7c3f8690ea5e69f170d6d775e60a7c19814730a3ff98f0
+oid sha256:43ec5a5e069d7a9559066b015901f6cd9d1e5e11a494d63a1a5a07d7cc56ce83
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:323d035573abc68ea1fb28a0dbd169b42c919244458b9d48c24a8196ef4f1fbd
+oid sha256:5655b365a65633fda63eb12cb6b41fa6fff3c01576ce3df81bb8d871bd860169
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0edeec917b285b0e88139f206de61b3e301e9b677aa51d87d86f36aba6dd8e7e
+oid sha256:f21304ce44e93f8f86da1b431eb1e188b0a7d5ce22c8a8c84f5d679245daaffa
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b66cb5271b1546b480a6c7621e1addbb2863a83f6bfe9ced4a812a79ec729e68
+oid sha256:21cd7c7ff5865cbb23888889c7201c6bfb6882d80652a0ade03d69cb9ad78253
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee960841273de5fa43863b36a2f8d901df0b6ff85b61e6b4992f108a85a45d9c
+oid sha256:1fdd8c08bac54a46207946491aba470a601d04858deabd8ec1d66f5286fc9a46
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 22250,
   "best_metric": 1.457463264465332,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-22000",
-  "epoch": 1.7306361049150065,
+  "epoch": 1.7690946850242288,
   "eval_steps": 250,
-  "global_step": 22500,
+  "global_step": 23000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3878,6 +3878,92 @@
       "eval_samples_per_second": 54.921,
       "eval_steps_per_second": 13.73,
       "step": 22500
+    },
+    {
+      "epoch": 1.734481962925929,
+      "grad_norm": 0.9285104870796204,
+      "learning_rate": 2.4514539906621075e-05,
+      "loss": 1.4243,
+      "step": 22550
+    },
+    {
+      "epoch": 1.738327820936851,
+      "grad_norm": 1.2848355770111084,
+      "learning_rate": 2.4257196426601962e-05,
+      "loss": 1.4596,
+      "step": 22600
+    },
+    {
+      "epoch": 1.7421736789477733,
+      "grad_norm": 1.4614371061325073,
+      "learning_rate": 2.3999852946582845e-05,
+      "loss": 1.3918,
+      "step": 22650
+    },
+    {
+      "epoch": 1.7460195369586955,
+      "grad_norm": 0.9543781876564026,
+      "learning_rate": 2.3742509466563724e-05,
+      "loss": 1.4044,
+      "step": 22700
+    },
+    {
+      "epoch": 1.7498653949696177,
+      "grad_norm": 1.602250099182129,
+      "learning_rate": 2.348516598654461e-05,
+      "loss": 1.4607,
+      "step": 22750
+    },
+    {
+      "epoch": 1.7498653949696177,
+      "eval_loss": 1.4677520990371704,
+      "eval_runtime": 18.158,
+      "eval_samples_per_second": 55.072,
+      "eval_steps_per_second": 13.768,
+      "step": 22750
+    },
+    {
+      "epoch": 1.75371125298054,
+      "grad_norm": 1.1664291620254517,
+      "learning_rate": 2.3227822506525494e-05,
+      "loss": 1.5153,
+      "step": 22800
+    },
+    {
+      "epoch": 1.757557110991462,
+      "grad_norm": 1.472679853439331,
+      "learning_rate": 2.2970479026506374e-05,
+      "loss": 1.4774,
+      "step": 22850
+    },
+    {
+      "epoch": 1.7614029690023845,
+      "grad_norm": 1.7927029132843018,
+      "learning_rate": 2.271313554648726e-05,
+      "loss": 1.4551,
+      "step": 22900
+    },
+    {
+      "epoch": 1.7652488270133067,
+      "grad_norm": 2.9085824489593506,
+      "learning_rate": 2.2455792066468143e-05,
+      "loss": 1.4474,
+      "step": 22950
+    },
+    {
+      "epoch": 1.7690946850242288,
+      "grad_norm": 1.8322957754135132,
+      "learning_rate": 2.2198448586449026e-05,
+      "loss": 1.4642,
+      "step": 23000
+    },
+    {
+      "epoch": 1.7690946850242288,
+      "eval_loss": 1.4676103591918945,
+      "eval_runtime": 17.9158,
+      "eval_samples_per_second": 55.817,
+      "eval_steps_per_second": 13.954,
+      "step": 23000
     }
   ],
   "logging_steps": 50,