Training in progress, step 10500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbda29e3fc4574d26f4c2d88945024a17cf0a9095cfd76acea4713a70561f4b9
+oid sha256:7bbfabbed60d5906524d5c89409a9d91e99af768406b59d0122cc4c00803b88b
 size 36730224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f807c16f8bec038522bfe252b213fc1087e8a39fb1f495399cdf7ee1d92e00a6
+oid sha256:c1f937a69fd1d3f87ca4cb29a7d82a362b45d23ba437525393801a63c53b09d6
 size 73588346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b4e6f78506ab09c8a3ff311a2dfeb7a6190585c49701c5bd2fcc763c2b50448
+oid sha256:371a8ee92df296caadab094d1243e6f6a8e33531055d940b9b2beb58c3296d37
 size 14180

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5057516ff1b0b207608fc5bf21c504e3b16c8f39cb674a438cf642593270922
+oid sha256:5bd55c94e5f9a6b24aa6ffb24230950971ac714f0b527005b89121745edab7aa
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf5349680f22d749c8735deb8f593d381f787d0e5d89e99661139aee18144bbf
+oid sha256:e3263d434a0173d1bf88ad28980a5eff0fc4c115a390bc663e18dd956338ac6e
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 9500,
   "best_metric": 4.328299045562744,
   "best_model_checkpoint": "./ar-diffusion-checkpoints/checkpoint-9500",
-  "epoch": 0.7691716021844474,
+  "epoch": 0.8076301822936697,
   "eval_steps": 250,
-  "global_step": 10000,
+  "global_step": 10500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1728,6 +1728,92 @@
       "eval_samples_per_second": 53.413,
       "eval_steps_per_second": 13.353,
       "step": 10000
+    },
+    {
+      "epoch": 0.7730174601953695,
+      "grad_norm": 3.490699529647827,
+      "learning_rate": 8.884011617219954e-05,
+      "loss": 4.5294,
+      "step": 10050
+    },
+    {
+      "epoch": 0.7768633182062918,
+      "grad_norm": 4.614148139953613,
+      "learning_rate": 8.858277269218042e-05,
+      "loss": 4.2371,
+      "step": 10100
+    },
+    {
+      "epoch": 0.780709176217214,
+      "grad_norm": 5.6906962394714355,
+      "learning_rate": 8.832542921216132e-05,
+      "loss": 4.5472,
+      "step": 10150
+    },
+    {
+      "epoch": 0.7845550342281363,
+      "grad_norm": 4.382456302642822,
+      "learning_rate": 8.80680857321422e-05,
+      "loss": 4.4282,
+      "step": 10200
+    },
+    {
+      "epoch": 0.7884008922390585,
+      "grad_norm": 4.546772003173828,
+      "learning_rate": 8.781074225212309e-05,
+      "loss": 4.4004,
+      "step": 10250
+    },
+    {
+      "epoch": 0.7884008922390585,
+      "eval_loss": 4.373971462249756,
+      "eval_runtime": 18.9303,
+      "eval_samples_per_second": 52.825,
+      "eval_steps_per_second": 13.206,
+      "step": 10250
+    },
+    {
+      "epoch": 0.7922467502499808,
+      "grad_norm": 3.784317970275879,
+      "learning_rate": 8.755339877210395e-05,
+      "loss": 4.4422,
+      "step": 10300
+    },
+    {
+      "epoch": 0.796092608260903,
+      "grad_norm": 3.11979341506958,
+      "learning_rate": 8.729605529208483e-05,
+      "loss": 4.4909,
+      "step": 10350
+    },
+    {
+      "epoch": 0.7999384662718253,
+      "grad_norm": 4.9711012840271,
+      "learning_rate": 8.703871181206573e-05,
+      "loss": 4.2955,
+      "step": 10400
+    },
+    {
+      "epoch": 0.8037843242827475,
+      "grad_norm": 3.7663426399230957,
+      "learning_rate": 8.678136833204661e-05,
+      "loss": 4.5105,
+      "step": 10450
+    },
+    {
+      "epoch": 0.8076301822936697,
+      "grad_norm": 4.679628372192383,
+      "learning_rate": 8.65240248520275e-05,
+      "loss": 4.5038,
+      "step": 10500
+    },
+    {
+      "epoch": 0.8076301822936697,
+      "eval_loss": 4.3565592765808105,
+      "eval_runtime": 18.9119,
+      "eval_samples_per_second": 52.877,
+      "eval_steps_per_second": 13.219,
+      "step": 10500
     }
   ],
   "logging_steps": 50,