Update README.md

README.md

@@ -44,26 +44,26 @@ The training is done in one stage with 8192 tokens per sample for the whole run.
 See training details [here](https://github.com/timpal0l/ModernBERT/blob/main/training/trainer_lumi.yaml)
 ## Training Stats
 ```python
-[token=1111697940119/1198510347252]:
-    Train time/batch: 810316
-    Train time/sample: 155580672
-    Train time/batch_in_epoch: 810316
-    Train time/sample_in_epoch: 155580672
-    Train time/token: 1111696598857
-    Train time/token_in_epoch: 1111696598857
-    Train trainer/device_train_microbatch_size: 3
-    Train loss/train/total: 0.9964
-    Train throughput/batches_per_sec: 1.3299
-    Train throughput/samples_per_sec: 255.3482
-    Train throughput/device/batches_per_sec: 0.0208
-    Train throughput/device/samples_per_sec: 3.9898
-    Train throughput/tokens_per_sec: 1820973.2233
-    Train throughput/device/tokens_per_sec: 28452.7066
-    Train time/train: 171.1475
-    Train time/val: 0.0000
-    Train time/total: 171.1475
-    Train lr-StableAdamW/group0: 0.0000
-    Train lr-StableAdamW/group1: 0.0000
+[token=1198511677292/1198510347252]:
+  Train time/batch: 873585
+  Train time/sample: 167728320
+  Train time/batch_in_epoch: 3558
+  Train time/sample_in_epoch: 683136
+  Train time/token: 1198510256276
+  Train time/token_in_epoch: 4882888303
+  Train trainer/device_train_microbatch_size: 3
+  Train loss/train/total: 0.9966
+  Train throughput/batches_per_sec: 1.3117
+  Train throughput/samples_per_sec: 251.8442
+  Train throughput/device/batches_per_sec: 0.0205
+  Train throughput/device/samples_per_sec: 3.9351
+  Train throughput/tokens_per_sec: 1804244.5198
+  Train throughput/device/tokens_per_sec: 28191.3206
+  Train time/train: 184.5555
+  Train time/val: 0.0000
+  Train time/total: 184.5555
+  Train lr-StableAdamW/group0: 0.0000
+  Train lr-StableAdamW/group1: 0.0000
 ```
 ## Intended Use  
 This is a **research artefact** and is only intended for **research purposes**.