Model card updated after epoch 1

End of Epoch 1: EMA weights upload

End of Epoch 1: Val Loss 4.8248, Val LM 4.8149, PPL 123.34 (raw)

Checkpoint at step 8000 (Epoch 1)

Checkpoint at step 7500 (Epoch 1)

Checkpoint at step 7000 (Epoch 1)

Checkpoint at step 6500 (Epoch 1)

Checkpoint at step 6000 (Epoch 1)

Checkpoint at step 5500 (Epoch 1)

Checkpoint at step 5000 (Epoch 1)

Checkpoint at step 4500 (Epoch 1)

Model card updated after epoch 0

End of Epoch 0: EMA weights upload

End of Epoch 0: Val Loss 4.8829, Val LM 4.8728, PPL 130.69 (raw)

Checkpoint at step 4000 (Epoch 0)

Checkpoint at step 3500 (Epoch 0)

Checkpoint at step 3000 (Epoch 0)

Checkpoint at step 2500 (Epoch 0)

Checkpoint at step 2000 (Epoch 0)

Checkpoint at step 1500 (Epoch 0)

Checkpoint at step 1000 (Epoch 0)

Checkpoint at step 500 (Epoch 0)

initial commit