Training in progress, step 13000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd49fdfe9bdd857be5419dddbdbaa6f93701dd16afd12b8202d9abb0f608e217
+oid sha256:211303fda3172e98417fefcf4ae565442875c8e0001f83fa9b613f42eb68e416
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8066ffe6e1fa6681b38c047067ca29a6eed18da1b1acf88431943e295d78e330
+oid sha256:5bf6caeca7f6bd6acaeee1391b627a2e314559d2e523a534ad583a26de79d19e
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a5ae118ec673d57a7f62a6284956ef83acf5113a9420dcd7ba5fd941799b59c
-size 14180
+oid sha256:dbf8948534182fde8a4da31776a53cc78337e1e18ed4b526e2ee8ca99eff5731
+size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63eee2f78c948ec330b424961c4bdfb29608b15bd25064fec9d957a2f7fcbcd2
+oid sha256:501e0348ebe2e7da1549a0a032d61d9c5a8a3fbf8f3846e0f360ce065e6e05b7
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:334ae361472f93791190a5614ebfa0a90c8bcb9632490f070b08594d58ab788b
+oid sha256:da01fa338433614d7203b84552679acf4a96484a8201c92d575f7a8bdc7e698e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 12250,
-  "best_metric": 1.5108226537704468,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-12000",
-  "epoch": 0.9614645027305592,
+  "best_global_step": 13000,
+  "best_metric": 1.5033278465270996,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-13000",
+  "epoch": 0.9999230828397816,
   "eval_steps": 250,
-  "global_step": 12500,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2158,6 +2158,92 @@
       "eval_samples_per_second": 55.797,
       "eval_steps_per_second": 13.949,
       "step": 12500
+    },
+    {
+      "epoch": 0.9653103607414815,
+      "grad_norm": 7.388810634613037,
+      "learning_rate": 7.597808904084407e-05,
+      "loss": 1.5683,
+      "step": 12550
+    },
+    {
+      "epoch": 0.9691562187524037,
+      "grad_norm": 1.5548075437545776,
+      "learning_rate": 7.572074556082496e-05,
+      "loss": 1.4956,
+      "step": 12600
+    },
+    {
+      "epoch": 0.973002076763326,
+      "grad_norm": 1.5935887098312378,
+      "learning_rate": 7.546340208080584e-05,
+      "loss": 1.5363,
+      "step": 12650
+    },
+    {
+      "epoch": 0.9768479347742481,
+      "grad_norm": 1.985238790512085,
+      "learning_rate": 7.520605860078672e-05,
+      "loss": 1.5314,
+      "step": 12700
+    },
+    {
+      "epoch": 0.9806937927851703,
+      "grad_norm": 1.5040565729141235,
+      "learning_rate": 7.494871512076762e-05,
+      "loss": 1.5108,
+      "step": 12750
+    },
+    {
+      "epoch": 0.9806937927851703,
+      "eval_loss": 1.5085468292236328,
+      "eval_runtime": 18.0531,
+      "eval_samples_per_second": 55.392,
+      "eval_steps_per_second": 13.848,
+      "step": 12750
+    },
+    {
+      "epoch": 0.9845396507960926,
+      "grad_norm": 1.2956914901733398,
+      "learning_rate": 7.46913716407485e-05,
+      "loss": 1.4287,
+      "step": 12800
+    },
+    {
+      "epoch": 0.9883855088070148,
+      "grad_norm": 1.1903409957885742,
+      "learning_rate": 7.443402816072938e-05,
+      "loss": 1.5583,
+      "step": 12850
+    },
+    {
+      "epoch": 0.9922313668179371,
+      "grad_norm": 1.9069184064865112,
+      "learning_rate": 7.417668468071026e-05,
+      "loss": 1.5214,
+      "step": 12900
+    },
+    {
+      "epoch": 0.9960772248288593,
+      "grad_norm": 1.7362926006317139,
+      "learning_rate": 7.391934120069114e-05,
+      "loss": 1.55,
+      "step": 12950
+    },
+    {
+      "epoch": 0.9999230828397816,
+      "grad_norm": 1.2136348485946655,
+      "learning_rate": 7.366199772067203e-05,
+      "loss": 1.5035,
+      "step": 13000
+    },
+    {
+      "epoch": 0.9999230828397816,
+      "eval_loss": 1.5033278465270996,
+      "eval_runtime": 18.189,
+      "eval_samples_per_second": 54.978,
+      "eval_steps_per_second": 13.745,
+      "step": 13000
     }
   ],
   "logging_steps": 50,