Training in progress, step 35500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcbe886ef81e28ac4bf6ddf4529a6f997971fc7b47d5cc6b8463fde09b58e295
+oid sha256:cad19b1bbdb7570168a857d04b0badb427b439bfb6d74e023668d1ee7a49d209
 size 36730224

last-checkpoint/ar_diffusion_info.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e405c76f4c76f6b143004e04e6f5ef178d5eb79df9ddf579a7e536122d01ff4
+oid sha256:147d1b9d26e62d2fd8dd2d02dbf00a76a94d4e43d7bf6241907ca36cdc920537
 size 1736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16b9dfda36c1191f9290f5c582e1fc3c2ff79c08ab7ee90848abb8367068ccb4
+oid sha256:cfbea59d5107cfdfc45afcc08cb49f7d291f1d605976088bffde49c00df10f70
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa38e1254b2184d0a59e46181afc6b800a0f129dcd35d1277176baed5ca3bc70
+oid sha256:794b2d7734896f09d529efb9a92a21c928e4cfc02d074667ee89fb5190300335
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b02b69899240ec8f846e73a10979f64f0f7812ffecfcd635d5625acc349acd03
+oid sha256:b4df8567ad6b42579407169e339ee1469d124e6f0bdf185b7ba1cb62f796a196
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c76a5b616a8159a5073e044f9b5bf193ac0fcff7d79d7b67f44d5065ac4e6fa
+oid sha256:f72dabb66926d5f103787feb6d06e607565f49ca5105e75822f116bfd973c31b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 35000,
-  "best_metric": -30.46967315673828,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-35000",
-  "epoch": 2.692100607645566,
+  "best_global_step": 35500,
+  "best_metric": -30.469755172729492,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-35500",
+  "epoch": 2.730559187754788,
   "eval_steps": 250,
-  "global_step": 35000,
+  "global_step": 35500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6028,6 +6028,92 @@
       "eval_samples_per_second": 59.022,
       "eval_steps_per_second": 14.756,
       "step": 35000
+    },
+    {
+      "epoch": 2.6959464656564878,
+      "grad_norm": 1.8203473091125488,
+      "learning_rate": 2.061657533179233e-05,
+      "loss": -30.4653,
+      "step": 35050
+    },
+    {
+      "epoch": 2.69979232366741,
+      "grad_norm": 1.8032426834106445,
+      "learning_rate": 2.0356855309975846e-05,
+      "loss": -30.4652,
+      "step": 35100
+    },
+    {
+      "epoch": 2.7036381816783326,
+      "grad_norm": 1.6480307579040527,
+      "learning_rate": 2.0097135288159365e-05,
+      "loss": -30.465,
+      "step": 35150
+    },
+    {
+      "epoch": 2.7074840396892546,
+      "grad_norm": 1.4139653444290161,
+      "learning_rate": 1.983741526634288e-05,
+      "loss": -30.4647,
+      "step": 35200
+    },
+    {
+      "epoch": 2.711329897700177,
+      "grad_norm": 1.9126203060150146,
+      "learning_rate": 1.95776952445264e-05,
+      "loss": -30.4651,
+      "step": 35250
+    },
+    {
+      "epoch": 2.711329897700177,
+      "eval_loss": -30.4685115814209,
+      "eval_runtime": 17.0035,
+      "eval_samples_per_second": 58.812,
+      "eval_steps_per_second": 14.703,
+      "step": 35250
+    },
+    {
+      "epoch": 2.7151757557110994,
+      "grad_norm": 1.5345407724380493,
+      "learning_rate": 1.931797522270992e-05,
+      "loss": -30.465,
+      "step": 35300
+    },
+    {
+      "epoch": 2.7190216137220213,
+      "grad_norm": 0.8343766331672668,
+      "learning_rate": 1.9058255200893437e-05,
+      "loss": -30.4653,
+      "step": 35350
+    },
+    {
+      "epoch": 2.7228674717329437,
+      "grad_norm": 0.7670063972473145,
+      "learning_rate": 1.8798535179076957e-05,
+      "loss": -30.4652,
+      "step": 35400
+    },
+    {
+      "epoch": 2.7267133297438657,
+      "grad_norm": 0.913152813911438,
+      "learning_rate": 1.8538815157260476e-05,
+      "loss": -30.4652,
+      "step": 35450
+    },
+    {
+      "epoch": 2.730559187754788,
+      "grad_norm": 1.1838785409927368,
+      "learning_rate": 1.8279095135443993e-05,
+      "loss": -30.4654,
+      "step": 35500
+    },
+    {
+      "epoch": 2.730559187754788,
+      "eval_loss": -30.469755172729492,
+      "eval_runtime": 16.8431,
+      "eval_samples_per_second": 59.371,
+      "eval_steps_per_second": 14.843,
+      "step": 35500
     }
   ],
   "logging_steps": 50,