Training in progress, step 8500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8feea685a107f8ccd353fa0c6a7247dc35bf0b9ab63a5ddc15a9bb4d1290d199
+oid sha256:620de4edf53add8da5dbe95866a8bac876c40a3dc9c90cedc8474a386ec15455
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66b6610111b8d0f3342d2760bc32d4c23e23f0a918f9dd58106e340817cbdd89
+oid sha256:b8995b41577d3d005c4fed5c2507e98c14db04d3eb6c0cbf4dcde21e469d9590
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d6bc30a519d7cae432bede0d2778a805102f7cbeae9a244275827f72067499b
-size 14180
+oid sha256:a993eb83d217882b8d4270d606bf3996e74fd8745c32e817e4ed4a0c36ae01a8
+size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe40af48d21f2cca8886bf415fbb1d77078d013ee962c12ffd6bac84ee28801
+oid sha256:929f0b36206c13ecf045b54d1e7d9597c22d5c9d16a63b3190a152cdd52e97ae
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d34cb07567bc31e1dbbaa78fe1d8a500cecd9a370ce5d35295b9afb817d2e6c
+oid sha256:a7dbaa01ecd0154e55c0c938d1611846e23b19dc766ea41b92962589d9d1b91a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 7250,
-  "best_metric": 4.4039154052734375,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-7000",
-  "epoch": 0.6153372817475579,
+  "best_global_step": 8500,
+  "best_metric": 4.392988204956055,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-8500",
+  "epoch": 0.6537958618567803,
   "eval_steps": 250,
-  "global_step": 8000,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1384,6 +1384,92 @@
       "eval_samples_per_second": 52.962,
       "eval_steps_per_second": 13.241,
       "step": 8000
+    },
+    {
+      "epoch": 0.6191831397584802,
+      "grad_norm": 4.333257675170898,
+      "learning_rate": 9.912870850336384e-05,
+      "loss": 4.3148,
+      "step": 8050
+    },
+    {
+      "epoch": 0.6230289977694023,
+      "grad_norm": 5.497674465179443,
+      "learning_rate": 9.887136502334472e-05,
+      "loss": 4.5952,
+      "step": 8100
+    },
+    {
+      "epoch": 0.6268748557803245,
+      "grad_norm": 4.110482215881348,
+      "learning_rate": 9.861402154332561e-05,
+      "loss": 4.5036,
+      "step": 8150
+    },
+    {
+      "epoch": 0.6307207137912468,
+      "grad_norm": 3.9359841346740723,
+      "learning_rate": 9.835667806330649e-05,
+      "loss": 4.409,
+      "step": 8200
+    },
+    {
+      "epoch": 0.634566571802169,
+      "grad_norm": 4.095981597900391,
+      "learning_rate": 9.809933458328738e-05,
+      "loss": 4.3515,
+      "step": 8250
+    },
+    {
+      "epoch": 0.634566571802169,
+      "eval_loss": 4.438499927520752,
+      "eval_runtime": 18.9189,
+      "eval_samples_per_second": 52.857,
+      "eval_steps_per_second": 13.214,
+      "step": 8250
+    },
+    {
+      "epoch": 0.6384124298130913,
+      "grad_norm": 4.357822895050049,
+      "learning_rate": 9.784199110326825e-05,
+      "loss": 4.3767,
+      "step": 8300
+    },
+    {
+      "epoch": 0.6422582878240135,
+      "grad_norm": 3.039700508117676,
+      "learning_rate": 9.758979449284952e-05,
+      "loss": 4.4542,
+      "step": 8350
+    },
+    {
+      "epoch": 0.6461041458349358,
+      "grad_norm": 6.7661919593811035,
+      "learning_rate": 9.73324510128304e-05,
+      "loss": 4.4073,
+      "step": 8400
+    },
+    {
+      "epoch": 0.649950003845858,
+      "grad_norm": 4.223692893981934,
+      "learning_rate": 9.70751075328113e-05,
+      "loss": 4.4904,
+      "step": 8450
+    },
+    {
+      "epoch": 0.6537958618567803,
+      "grad_norm": 4.621217250823975,
+      "learning_rate": 9.681776405279216e-05,
+      "loss": 4.7717,
+      "step": 8500
+    },
+    {
+      "epoch": 0.6537958618567803,
+      "eval_loss": 4.392988204956055,
+      "eval_runtime": 18.8399,
+      "eval_samples_per_second": 53.079,
+      "eval_steps_per_second": 13.27,
+      "step": 8500
     }
   ],
   "logging_steps": 50,