Training in progress, step 24500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:148bc4d0eefbac736a5e1e51db006feee3c80fa2809dcf1a324a26c2b6a1af91
+oid sha256:9bc54f61ae85f9bb8331e1cdd5923e3fd960989060b059e73b0d0e134dae9e8f
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0caaf0c696e06292fb4788c6d1ed782a2bc166c8931e277457c2a363c59a15e0
+oid sha256:35291a9f57ededb6486e5a5291f2f75b65ad3ee7378c172fe3cff039858844f4
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a529729fbc0762ea5dabee8322aee007fe27ff660b1781623be0f3c2d691e1e
+oid sha256:e6abd220bb5c699b08784d9e5bd7e4f3c387ae6cf3a2fc509bcb49366bfaee15
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:980b9d83aee7d7fc8827a64b1f01d4844412c0e4e95829fb51b9810cfbf95067
+oid sha256:3ead8696fbf0049adb3c84fc53d3c6dc113682fab1d3e945183397e530adbbee
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72fdb6c83da9fe3dd22311fac14925ef29750a1b38bff4165a1e9ae861a1b5d9
+oid sha256:d220408f294f0cc03e84f4b2538adfda082b3a1de023a6d0f995deed07fa75a2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 23750,
-  "best_metric": 1.4543312788009644,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-22000",
-  "epoch": 1.8460118452426735,
+  "best_global_step": 24500,
+  "best_metric": 1.4431298971176147,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-24500",
+  "epoch": 1.884470425351896,
   "eval_steps": 250,
-  "global_step": 24000,
+  "global_step": 24500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4136,6 +4136,92 @@
       "eval_samples_per_second": 55.354,
       "eval_steps_per_second": 13.839,
       "step": 24000
+    },
+    {
+      "epoch": 1.8498577032535959,
+      "grad_norm": 1.3933135271072388,
+      "learning_rate": 1.679423550604757e-05,
+      "loss": 1.45,
+      "step": 24050
+    },
+    {
+      "epoch": 1.853703561264518,
+      "grad_norm": 1.1157580614089966,
+      "learning_rate": 1.6536892026028454e-05,
+      "loss": 1.4916,
+      "step": 24100
+    },
+    {
+      "epoch": 1.8575494192754403,
+      "grad_norm": 1.7401970624923706,
+      "learning_rate": 1.6279548546009337e-05,
+      "loss": 1.4563,
+      "step": 24150
+    },
+    {
+      "epoch": 1.8613952772863627,
+      "grad_norm": 1.4699925184249878,
+      "learning_rate": 1.602220506599022e-05,
+      "loss": 1.4211,
+      "step": 24200
+    },
+    {
+      "epoch": 1.8652411352972849,
+      "grad_norm": 1.1760289669036865,
+      "learning_rate": 1.5764861585971103e-05,
+      "loss": 1.4212,
+      "step": 24250
+    },
+    {
+      "epoch": 1.8652411352972849,
+      "eval_loss": 1.460072636604309,
+      "eval_runtime": 17.8176,
+      "eval_samples_per_second": 56.124,
+      "eval_steps_per_second": 14.031,
+      "step": 24250
+    },
+    {
+      "epoch": 1.869086993308207,
+      "grad_norm": 1.8243287801742554,
+      "learning_rate": 1.5507518105951986e-05,
+      "loss": 1.4594,
+      "step": 24300
+    },
+    {
+      "epoch": 1.8729328513191295,
+      "grad_norm": 0.8821312785148621,
+      "learning_rate": 1.5250174625932868e-05,
+      "loss": 1.3837,
+      "step": 24350
+    },
+    {
+      "epoch": 1.8767787093300514,
+      "grad_norm": 1.673240065574646,
+      "learning_rate": 1.4992831145913753e-05,
+      "loss": 1.395,
+      "step": 24400
+    },
+    {
+      "epoch": 1.8806245673409738,
+      "grad_norm": 1.4853135347366333,
+      "learning_rate": 1.4735487665894636e-05,
+      "loss": 1.5031,
+      "step": 24450
+    },
+    {
+      "epoch": 1.884470425351896,
+      "grad_norm": 2.507054567337036,
+      "learning_rate": 1.4478144185875517e-05,
+      "loss": 1.3909,
+      "step": 24500
+    },
+    {
+      "epoch": 1.884470425351896,
+      "eval_loss": 1.4431298971176147,
+      "eval_runtime": 17.9815,
+      "eval_samples_per_second": 55.613,
+      "eval_steps_per_second": 13.903,
+      "step": 24500
     }
   ],
   "logging_steps": 50,