Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74ea70ab5c294f3be223b52902ee924adb6f2a217f316a909c64447e3b17f8f8
+oid sha256:12b232b0278243d25903d8789b4dba3a6c48116f80cf44f29b224b3a9213825f
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa476b430a4a63248ac2bc81d08a889c28813dea25aaa9356f70340bb7c10542
+oid sha256:f87fd12b6e3592e8e2a065da27b2e13a73a88e79824ecd70f4ced521e1d64d89
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bd88c5d89e3266252b8212d40d27f742ba6d2099c1dc476b1334d403bca3f20
-size 14244
+oid sha256:42de46b2e4c5179833d46fe28b80f469c3d40255a80ec3a104ef7ad1fd3d8210
+size 14180

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23b493d7ad156dc53747ae8d013133956196b2f038f30fe21dd5039c094ada9d
+oid sha256:34bac16fbc99181cf3c30f05bcb7e648ad2c92eef3f334c8cbe294300c1d92e7
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d109e68a9027ba37776e3e3b4c867f8592e84e6e4f33bcbb6b2e5ff20129448
+oid sha256:c205be8a1beb83fa60ead2e2dc0acbbf0de06ae533775758f9d9f2396e1a4003
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 1000,
-  "best_metric": 4.709664344787598,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-1000",
-  "epoch": 0.07691716021844473,
+  "best_global_step": 1500,
+  "best_metric": 4.696172714233398,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-1500",
+  "epoch": 0.1153757403276671,
   "eval_steps": 250,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -180,6 +180,92 @@
       "eval_samples_per_second": 53.177,
       "eval_steps_per_second": 13.294,
       "step": 1000
+    },
+    {
+      "epoch": 0.08076301822936698,
+      "grad_norm": 5.442048072814941,
+      "learning_rate": 0.00013514135509723907,
+      "loss": 4.6134,
+      "step": 1050
+    },
+    {
+      "epoch": 0.0846088762402892,
+      "grad_norm": 4.779583930969238,
+      "learning_rate": 0.00013488401161721995,
+      "loss": 4.7226,
+      "step": 1100
+    },
+    {
+      "epoch": 0.08845473425121145,
+      "grad_norm": 3.221238851547241,
+      "learning_rate": 0.0001346266681372008,
+      "loss": 4.6837,
+      "step": 1150
+    },
+    {
+      "epoch": 0.09230059226213368,
+      "grad_norm": 5.55983304977417,
+      "learning_rate": 0.0001343693246571817,
+      "loss": 4.672,
+      "step": 1200
+    },
+    {
+      "epoch": 0.09614645027305592,
+      "grad_norm": 6.964417934417725,
+      "learning_rate": 0.0001341119811771626,
+      "loss": 4.9043,
+      "step": 1250
+    },
+    {
+      "epoch": 0.09614645027305592,
+      "eval_loss": 4.7052001953125,
+      "eval_runtime": 18.9307,
+      "eval_samples_per_second": 52.824,
+      "eval_steps_per_second": 13.206,
+      "step": 1250
+    },
+    {
+      "epoch": 0.09999230828397816,
+      "grad_norm": 7.476005554199219,
+      "learning_rate": 0.00013385463769714347,
+      "loss": 4.7776,
+      "step": 1300
+    },
+    {
+      "epoch": 0.10383816629490039,
+      "grad_norm": 3.4916040897369385,
+      "learning_rate": 0.00013359729421712435,
+      "loss": 4.7738,
+      "step": 1350
+    },
+    {
+      "epoch": 0.10768402430582263,
+      "grad_norm": 4.028671741485596,
+      "learning_rate": 0.00013333995073710526,
+      "loss": 4.6459,
+      "step": 1400
+    },
+    {
+      "epoch": 0.11152988231674486,
+      "grad_norm": 4.597095489501953,
+      "learning_rate": 0.0001330826072570861,
+      "loss": 4.6778,
+      "step": 1450
+    },
+    {
+      "epoch": 0.1153757403276671,
+      "grad_norm": 5.779391288757324,
+      "learning_rate": 0.000132825263777067,
+      "loss": 4.7938,
+      "step": 1500
+    },
+    {
+      "epoch": 0.1153757403276671,
+      "eval_loss": 4.696172714233398,
+      "eval_runtime": 18.8705,
+      "eval_samples_per_second": 52.993,
+      "eval_steps_per_second": 13.248,
+      "step": 1500
     }
   ],
   "logging_steps": 50,