diff options
Diffstat (limited to 'training/experiments')
| -rw-r--r-- | training/experiments/image_transformer.yaml | 13 |
1 files changed, 9 insertions, 4 deletions
diff --git a/training/experiments/image_transformer.yaml b/training/experiments/image_transformer.yaml index 9e8f9fc..bedcbb5 100644 --- a/training/experiments/image_transformer.yaml +++ b/training/experiments/image_transformer.yaml @@ -1,9 +1,12 @@ +seed: 4711 + network: + desc: null type: ImageTransformer args: encoder: - type: None - args: None + type: null + args: null num_decoder_layers: 4 hidden_dim: 256 num_heads: 4 @@ -12,6 +15,7 @@ network: transformer_activation: glu model: + desc: null type: LitTransformerModel args: optimizer: @@ -31,11 +35,11 @@ model: weight: None ignore_index: -100 reduction: mean - monitor: val_loss mapping: sentence_piece data: + desc: null type: IAMExtendedParagraphs args: batch_size: 16 @@ -55,6 +59,7 @@ callbacks: patience: 10 trainer: + desc: null args: stochastic_weight_avg: true auto_scale_batch_size: binsearch @@ -62,6 +67,6 @@ trainer: fast_dev_run: false gpus: 1 precision: 16 - max_epocs: 512 + max_epochs: 512 terminate_on_nan: true weights_summary: true |