Training in progress, step 33000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:865f4c0d25d6d9ced43edebb6692446dff7a3f64cbf389d00159f035d1a3d483
+oid sha256:dce2cfe7ef78c1b081a422071300fead0d75106053b5f049a42ada26761ae754
 size 36730224

last-checkpoint/ar_diffusion_info.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de2bea9ba1f10dc4ab6cd0955501f132a43d9bb40b579d36a5635beae8049ddb
+oid sha256:a31437fd444dcaf0935d9c64d6e3d1702f2bb5519ddb595a0202c4f2bd2a612f
 size 1736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f4caac1c7167e850a8b88a11106808943f263aa3a0910bacee3640474942357
+oid sha256:763237292b314fde98770ac7b874a48945d2f1abca3b2c84598219bbffc7efd9
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b10c1c70cd0cab015622c2d710d6b5b113ab6f13d1dc44c1dfd2b187db17dd
+oid sha256:e8bfd573f2544c60f45f4769693f9ca807bef468213a4a6127137e9e334ee28a
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76592baa9e3b0e3d15e021e247d3cfa4915cd052c2c669b30b628ff835c5a245
+oid sha256:38e8022c7f3002679e6fa3f97f4fe89fb5c796e6e8d168c42ccf78f18e8bd32d
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d3294e846471781ea3f86dc01786f346883b49315c332c36d82663ab957ba6
+oid sha256:a609d4c8b7c9c250baf5aaeedbae25a95f3a4513a558852d1de4e86b5f18ff63
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 32500,
   "best_metric": -30.467578887939453,
   "best_model_checkpoint": "./ar-diffusion-checkpoints-progressive-attention/checkpoint-32500",
-  "epoch": 2.4998077070994538,
+  "epoch": 2.5382662872086765,
   "eval_steps": 250,
-  "global_step": 32500,
+  "global_step": 33000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5598,6 +5598,92 @@
       "eval_samples_per_second": 59.252,
       "eval_steps_per_second": 14.813,
       "step": 32500
+    },
+    {
+      "epoch": 2.503653565110376,
+      "grad_norm": 0.964199423789978,
+      "learning_rate": 3.360257642261642e-05,
+      "loss": -30.463,
+      "step": 32550
+    },
+    {
+      "epoch": 2.507499423121298,
+      "grad_norm": 2.097522497177124,
+      "learning_rate": 3.334285640079994e-05,
+      "loss": -30.4637,
+      "step": 32600
+    },
+    {
+      "epoch": 2.5113452811322206,
+      "grad_norm": 1.688252568244934,
+      "learning_rate": 3.308313637898346e-05,
+      "loss": -30.4634,
+      "step": 32650
+    },
+    {
+      "epoch": 2.515191139143143,
+      "grad_norm": 1.733709454536438,
+      "learning_rate": 3.282341635716697e-05,
+      "loss": -30.4629,
+      "step": 32700
+    },
+    {
+      "epoch": 2.519036997154065,
+      "grad_norm": 1.897979974746704,
+      "learning_rate": 3.25636963353505e-05,
+      "loss": -30.4629,
+      "step": 32750
+    },
+    {
+      "epoch": 2.519036997154065,
+      "eval_loss": -30.46739387512207,
+      "eval_runtime": 16.8323,
+      "eval_samples_per_second": 59.41,
+      "eval_steps_per_second": 14.852,
+      "step": 32750
+    },
+    {
+      "epoch": 2.5228828551649873,
+      "grad_norm": 0.9445510506629944,
+      "learning_rate": 3.230397631353401e-05,
+      "loss": -30.4633,
+      "step": 32800
+    },
+    {
+      "epoch": 2.5267287131759097,
+      "grad_norm": 1.7918905019760132,
+      "learning_rate": 3.204425629171753e-05,
+      "loss": -30.4636,
+      "step": 32850
+    },
+    {
+      "epoch": 2.5305745711868317,
+      "grad_norm": 2.108637571334839,
+      "learning_rate": 3.178453626990105e-05,
+      "loss": -30.4635,
+      "step": 32900
+    },
+    {
+      "epoch": 2.534420429197754,
+      "grad_norm": 1.0502158403396606,
+      "learning_rate": 3.152481624808456e-05,
+      "loss": -30.4638,
+      "step": 32950
+    },
+    {
+      "epoch": 2.5382662872086765,
+      "grad_norm": 1.5265525579452515,
+      "learning_rate": 3.126509622626809e-05,
+      "loss": -30.4632,
+      "step": 33000
+    },
+    {
+      "epoch": 2.5382662872086765,
+      "eval_loss": -30.46713638305664,
+      "eval_runtime": 16.8812,
+      "eval_samples_per_second": 59.237,
+      "eval_steps_per_second": 14.809,
+      "step": 33000
     }
   ],
   "logging_steps": 50,