Training in progress, step 11000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bbfabbed60d5906524d5c89409a9d91e99af768406b59d0122cc4c00803b88b
+oid sha256:932444defba9a5b8dd44f88b8bcb52ab659664a28676382e15a373cf36bf6034
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f937a69fd1d3f87ca4cb29a7d82a362b45d23ba437525393801a63c53b09d6
+oid sha256:f80012b6836a364fdec2135af886ce664e83e4046832b07a32b6501d8f4ef656
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:371a8ee92df296caadab094d1243e6f6a8e33531055d940b9b2beb58c3296d37
-size 14180
+oid sha256:3d7167878bddb7c0a88c66ad0b0be73885dac80e1980348d5e68d660c4a16ce9
+size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bd55c94e5f9a6b24aa6ffb24230950971ac714f0b527005b89121745edab7aa
+oid sha256:42adf2998e15e06307e725ba7dcb6c52fc0a94a297e1345e89da412c057a53a6
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3263d434a0173d1bf88ad28980a5eff0fc4c115a390bc663e18dd956338ac6e
+oid sha256:f034f97f7b7aead49a2646d657b2abae10ec15daef82d04e9386fb7172dbeddc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 9500,
-  "best_metric": 4.328299045562744,
-  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-9500",
-  "epoch": 0.8076301822936697,
+  "best_global_step": 11000,
+  "best_metric": 4.307990074157715,
+  "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-11000",
+  "epoch": 0.8460887624028921,
   "eval_steps": 250,
-  "global_step": 10500,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1814,6 +1814,92 @@
       "eval_samples_per_second": 52.877,
       "eval_steps_per_second": 13.219,
       "step": 10500
+    },
+    {
+      "epoch": 0.811476040304592,
+      "grad_norm": 4.561670303344727,
+      "learning_rate": 8.626668137200838e-05,
+      "loss": 4.6428,
+      "step": 10550
+    },
+    {
+      "epoch": 0.8153218983155142,
+      "grad_norm": 3.155518054962158,
+      "learning_rate": 8.600933789198925e-05,
+      "loss": 4.4605,
+      "step": 10600
+    },
+    {
+      "epoch": 0.8191677563264365,
+      "grad_norm": 4.021768093109131,
+      "learning_rate": 8.575199441197014e-05,
+      "loss": 4.2982,
+      "step": 10650
+    },
+    {
+      "epoch": 0.8230136143373586,
+      "grad_norm": 4.348796844482422,
+      "learning_rate": 8.549465093195102e-05,
+      "loss": 4.649,
+      "step": 10700
+    },
+    {
+      "epoch": 0.8268594723482809,
+      "grad_norm": 4.647562503814697,
+      "learning_rate": 8.523730745193191e-05,
+      "loss": 4.2873,
+      "step": 10750
+    },
+    {
+      "epoch": 0.8268594723482809,
+      "eval_loss": 4.3483662605285645,
+      "eval_runtime": 18.9227,
+      "eval_samples_per_second": 52.847,
+      "eval_steps_per_second": 13.212,
+      "step": 10750
+    },
+    {
+      "epoch": 0.8307053303592031,
+      "grad_norm": 3.9260427951812744,
+      "learning_rate": 8.497996397191279e-05,
+      "loss": 4.3823,
+      "step": 10800
+    },
+    {
+      "epoch": 0.8345511883701254,
+      "grad_norm": 3.7108564376831055,
+      "learning_rate": 8.472262049189368e-05,
+      "loss": 4.42,
+      "step": 10850
+    },
+    {
+      "epoch": 0.8383970463810476,
+      "grad_norm": 4.9123663902282715,
+      "learning_rate": 8.446527701187455e-05,
+      "loss": 4.5828,
+      "step": 10900
+    },
+    {
+      "epoch": 0.8422429043919698,
+      "grad_norm": 3.7289183139801025,
+      "learning_rate": 8.420793353185543e-05,
+      "loss": 4.3134,
+      "step": 10950
+    },
+    {
+      "epoch": 0.8460887624028921,
+      "grad_norm": 4.0350542068481445,
+      "learning_rate": 8.395059005183632e-05,
+      "loss": 4.3768,
+      "step": 11000
+    },
+    {
+      "epoch": 0.8460887624028921,
+      "eval_loss": 4.307990074157715,
+      "eval_runtime": 18.7713,
+      "eval_samples_per_second": 53.273,
+      "eval_steps_per_second": 13.318,
+      "step": 11000
     }
   ],
   "logging_steps": 50,