Training in progress, step 13500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:211303fda3172e98417fefcf4ae565442875c8e0001f83fa9b613f42eb68e416
+oid sha256:a0fec3c5b1e7e374b9bebda92218a1bdc7fadf77f9f2fd358d7738c92849ab15
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bf6caeca7f6bd6acaeee1391b627a2e314559d2e523a534ad583a26de79d19e
+oid sha256:961d4f3f88c2859e92add0976bc93ab8db0649cc3da6695526e297d735998366
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbf8948534182fde8a4da31776a53cc78337e1e18ed4b526e2ee8ca99eff5731
+oid sha256:81ec269cbd23a3955804ddaef963a9e0d68f2087a109e239da5baed50032493e
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:501e0348ebe2e7da1549a0a032d61d9c5a8a3fbf8f3846e0f360ce065e6e05b7
+oid sha256:861918ef9bae87f3c0647e76fd5a519763415c2dba1ede7121af8dc80bfb456a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da01fa338433614d7203b84552679acf4a96484a8201c92d575f7a8bdc7e698e
+oid sha256:483cd8caa2794b8eb45fe09567d024ef71ee8ff6f6ba358a1febd749509b4c7e
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 13000,
   "best_metric": 1.5033278465270996,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-13000",
-  "epoch": 0.9999230828397816,
+  "epoch": 1.038381662949004,
   "eval_steps": 250,
-  "global_step": 13000,
+  "global_step": 13500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2244,6 +2244,92 @@
       "eval_samples_per_second": 54.978,
       "eval_steps_per_second": 13.745,
       "step": 13000
+    },
+    {
+      "epoch": 1.0037689408507038,
+      "grad_norm": 1.291033387184143,
+      "learning_rate": 7.340465424065291e-05,
+      "loss": 1.4455,
+      "step": 13050
+    },
+    {
+      "epoch": 1.007614798861626,
+      "grad_norm": 1.247129201889038,
+      "learning_rate": 7.31473107606338e-05,
+      "loss": 1.4629,
+      "step": 13100
+    },
+    {
+      "epoch": 1.0114606568725482,
+      "grad_norm": 1.2177772521972656,
+      "learning_rate": 7.288996728061467e-05,
+      "loss": 1.5715,
+      "step": 13150
+    },
+    {
+      "epoch": 1.0153065148834706,
+      "grad_norm": 1.2471716403961182,
+      "learning_rate": 7.263262380059556e-05,
+      "loss": 1.4244,
+      "step": 13200
+    },
+    {
+      "epoch": 1.0191523728943928,
+      "grad_norm": 0.8932450413703918,
+      "learning_rate": 7.237528032057644e-05,
+      "loss": 1.4278,
+      "step": 13250
+    },
+    {
+      "epoch": 1.0191523728943928,
+      "eval_loss": 1.5201970338821411,
+      "eval_runtime": 17.9356,
+      "eval_samples_per_second": 55.755,
+      "eval_steps_per_second": 13.939,
+      "step": 13250
+    },
+    {
+      "epoch": 1.022998230905315,
+      "grad_norm": 1.9957834482192993,
+      "learning_rate": 7.211793684055732e-05,
+      "loss": 1.5017,
+      "step": 13300
+    },
+    {
+      "epoch": 1.0268440889162371,
+      "grad_norm": 1.432619571685791,
+      "learning_rate": 7.186059336053821e-05,
+      "loss": 1.4271,
+      "step": 13350
+    },
+    {
+      "epoch": 1.0306899469271595,
+      "grad_norm": 1.3298619985580444,
+      "learning_rate": 7.16032498805191e-05,
+      "loss": 1.5726,
+      "step": 13400
+    },
+    {
+      "epoch": 1.0345358049380817,
+      "grad_norm": 10.102746963500977,
+      "learning_rate": 7.134590640049997e-05,
+      "loss": 1.3938,
+      "step": 13450
+    },
+    {
+      "epoch": 1.038381662949004,
+      "grad_norm": 1.9288721084594727,
+      "learning_rate": 7.108856292048085e-05,
+      "loss": 1.4264,
+      "step": 13500
+    },
+    {
+      "epoch": 1.038381662949004,
+      "eval_loss": 1.5168194770812988,
+      "eval_runtime": 18.139,
+      "eval_samples_per_second": 55.13,
+      "eval_steps_per_second": 13.782,
+      "step": 13500
     }
   ],
   "logging_steps": 50,