giovo17
/

tfs-mt

+seed: 42
+log_every_iters: 1000
+save_every_iters: 10000
+eval_every_iters: 10000
+update_pbar_every_iters: 100
+time_limit_sec: -1
+checkpoints_retain_n: 5
+model_base_name: tfs_mt
+model_parameters:
+  dropout: 0.1
+model_configs:
+  pretrained_word_embeddings: GloVe
+  positional_embeddings: sinusoidal
+  nano:
+    num_encoder_layers: 4
+    num_decoder_layers: 4
+    d_model: 50
+    num_heads: 4
+    d_ff: 200
+    norm_type: postnorm
+    glove_version: glove.2024.wikigiga.50d
+    glove_filename: wiki_giga_2024_50_MFT20_vectors_seed_123_alpha_0.75_eta_0.075_combined
+  small:
+    num_encoder_layers: 6
+    num_decoder_layers: 6
+    d_model: 100
+    num_heads: 6
+    d_ff: 400
+    norm_type: postnorm
+    glove_version: glove.2024.wikigiga.100d
+    glove_filename: wiki_giga_2024_100_MFT20_vectors_seed_2024_alpha_0.75_eta_0.05.050_combined
+  base:
+    num_encoder_layers: 8
+    num_decoder_layers: 8
+    d_model: 300
+    num_heads: 8
+    d_ff: 800
+    norm_type: postnorm
+    glove_version: glove.2024.wikigiga.300d
+    glove_filename: wiki_giga_2024_300_MFT20_vectors_seed_2024_alpha_0.75_eta_0.05_combined
+  original:
+    num_encoder_layers: 6
+    num_decoder_layers: 6
+    d_model: 512
+    num_heads: 8
+    d_ff: 2048
+    norm_type: postnorm
+training_hp:
+  num_epochs: 2
+  use_amp: true
+  amp_dtype: bfloat16
+  torch_compile_mode: max-autotune
+  loss:
+    type: crossentropy
+    label_smoothing: 0.1
+  optimizer:
+    type: AdamW
+    weight_decay: 0.0001
+    beta1: 0.9
+    beta2: 0.999
+    eps: 1.0e-08
+  lr_scheduler:
+    type: original
+    min_lr: 0.0003
+    max_lr: 0.001
+    warmup_iters: 25000
+    stable_iters_prop: 0.7
+  max_gradient_norm: 5.0
+  early_stopping:
+    enabled: false
+    patience: 40000
+    min_delta: 1.0e-05
+tokenizer:
+  type: word
+  sos_token: <s>
+  eos_token: </s>
+  pad_token: <PAD>
+  unk_token: <UNK>
+  max_seq_len: 131
+  max_vocab_size: 70000
+  vocab_min_freq: 2
+  src_sos_token_idx: 60932
+  src_eos_token_idx: 60854
+  src_pad_token_idx: 18895
+  src_unk_token_idx: 3358
+  tgt_sos_token_idx: 60933
+  tgt_eos_token_idx: 60860
+  tgt_pad_token_idx: 18800
+  tgt_unk_token_idx: 3289
+dataset:
+  dataset_task: machine-translation
+  dataset_id: Helsinki-NLP/europarl
+  dataset_name: en-it
+  train_split: 0.95
+  src_lang: en
+  tgt_lang: it
+  max_len: -1
+train_dataloader:
+  batch_size: 64
+  num_workers: 4
+  shuffle: true
+  drop_last: true
+  prefetch_factor: 2
+  pad_all_to_max_len: true
+test_dataloader:
+  batch_size: 128
+  num_workers: 4
+  shuffle: false
+  drop_last: false
+  prefetch_factor: 2
+  pad_all_to_max_len: true
+chosen_model_size: small
+model_name: tfs_mt_small_260207-0915
+exec_mode: dev
+src_tokenizer_vocab_size: 70000
+tgt_tokenizer_vocab_size: 70000
+num_train_iters_per_epoch: 28889
+num_test_iters_per_epoch: 761