| data: exp/dataset.de-en | |
| save_model: exp/model.de-en | |
| save_checkpoint_steps: 10000 | |
| keep_checkpoint: 10 | |
| seed: 3435 | |
| train_steps: 200000 | |
| valid_steps: 10000 | |
| warmup_steps: 8000 | |
| report_every: 100 | |
| decoder_type: transformer | |
| encoder_type: transformer | |
| word_vec_size: 512 | |
| rnn_size: 512 | |
| layers: 6 | |
| transformer_ff: 2048 | |
| heads: 8 | |
| accum_count: 2 | |
| optim: adam | |
| adam_beta1: 0.9 | |
| adam_beta2: 0.998 | |
| decay_method: noam | |
| learning_rate: 2.0 | |
| max_grad_norm: 0.0 | |
| batch_size: 4096 | |
| batch_type: tokens | |
| normalization: tokens | |
| dropout: 0.1 | |
| label_smoothing: 0.1 | |
| max_generator_batches: 2 | |
| param_init: 0.0 | |
| param_init_glorot: 'true' | |
| position_encoding: 'true' | |
| world_size: 4 | |
| gpu_ranks: | |
| - 0 | |
| - 1 | |
| - 2 | |
| - 3 | |