initial commit

avg5.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16785664244d8110805afb1ced49b7f8fc5aec327e1ac6cd2024f4bfd3c0f55a
+size 2812902554

config.yaml

@@ -0,0 +1,131 @@
+name: "iwslt14_deenfr_prompt"
+joeynmt_version: "2.3.0"
+model_dir: "iwslt14_prompt"
+use_cuda: True
+fp16: True
+random_seed: 42
+
+data:
+    #train: "iwslt14_prompt/train"    # cf. https://wit3.fbk.eu/2014-01
+    #dev: "iwslt14_prompt/dev"
+    test: "iwslt14_prompt/test.de-en" # ['TED.dev2010', 'TEDX.dev2012', 'TED.tst2010', 'TED.tst2011', 'TED.tst2012']
+    dataset_type: "tsv"
+    sample_dev_subset: 500
+    src:
+        lang: "src"
+        max_length: 512
+        lowercase: False
+        normalize: False
+        level: "bpe"
+        voc_limit: 32000
+        voc_min_freq: 1
+        voc_file: "iwslt14_prompt/src_vocab.txt"
+        tokenizer_type: "sentencepiece"
+        tokenizer_cfg:
+            model_file: "iwslt14_prompt/sp.model"
+            model_type: "unigram"
+            character_coverage: 1.0
+    trg:
+        lang: "trg"
+        max_length: 512
+        lowercase: False
+        normalize: False
+        level: "bpe"
+        voc_limit: 32000
+        voc_min_freq: 1
+        voc_file: "iwslt14_prompt/trg_vocab.txt"
+        tokenizer_type: "sentencepiece"
+        tokenizer_cfg:
+            model_file: "iwslt14_prompt/sp.model"
+            model_type: "unigram"
+            character_coverage: 1.0
+    special_symbols:
+        unk_token: "<unk>"
+        unk_id: 0
+        pad_token: "<pad>"
+        pad_id: 1
+        bos_token: "<s>"
+        bos_id: 2
+        eos_token: "</s>"
+        eos_id: 3
+        sep_token: "<sep>"
+        sep_id: 4
+        lang_tags: ["<de>", "<en>", "<fr>"]
+
+testing:
+    load_model: "iwslt14_prompt/avg5.ckpt"
+    n_best: 1
+    beam_size: 5
+    beam_alpha: 1.0
+    batch_size: 32
+    batch_type: "sentence"
+    max_output_length: 512
+    eval_metrics: ["bleu"]
+    sacrebleu_cfg:
+        tokenize: "13a"
+        lowercase: True
+
+training:
+    #load_model: "iwslt14_prompt/latest.ckpt"
+    #reset_best_ckpt: True
+    #reset_scheduler: True
+    #reset_optimizer: True
+    #reset_iter_state: True
+    optimizer: "adamw"
+    normalization: "tokens"
+    adam_betas: [0.9, 0.98]
+    scheduling: "warmupinversesquareroot"
+    learning_rate_warmup: 10000
+    learning_rate: 0.0002
+    learning_rate_min: 0.0000001
+    weight_decay: 0.001
+    label_smoothing: 0.1
+    loss: "crossentropy"
+    batch_size: 32
+    batch_type: "sentence"
+    batch_multiplier: 4
+    early_stopping_metric: "bleu"
+    epochs: 50
+    validation_freq: 1000
+    logging_freq: 100
+    overwrite: False
+    shuffle: True
+    print_valid_sents: [0, 1, 2, 3]
+    keep_best_ckpts: 5
+
+model:
+    initializer: "xavier_uniform"
+    bias_initializer: "zeros"
+    init_gain: 1.0
+    embed_initializer: "xavier_uniform"
+    embed_init_gain: 1.0
+    tied_embeddings: True
+    tied_softmax: True
+    encoder:
+        type: "transformer"
+        num_layers: 6
+        num_heads: 8
+        embeddings:
+            embedding_dim: 1024
+            scale: True
+            dropout: 0.1
+        # typically ff_size = 4 x hidden_size
+        hidden_size: 1024
+        ff_size: 4096
+        dropout: 0.1
+        layer_norm: "pre"
+        activation: "relu"
+    decoder:
+        type: "transformer"
+        num_layers: 6
+        num_heads: 8
+        embeddings:
+            embedding_dim: 1024
+            scale: True
+            dropout: 0.1
+        # typically ff_size = 4 x hidden_size
+        hidden_size: 1024
+        ff_size: 4096
+        dropout: 0.1
+        layer_norm: "pre"
+        activation: "relu"

sp.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaa7aad830134efe55afcbd6690ec305a7ed1599b10e499d6be3133fb6872251
+size 832871

test.log

@@ -0,0 +1,42 @@
+2024-01-16 17:27:15,168 - INFO - root - Hello! This is Joey-NMT (version 2.3.0).
+2024-01-16 17:27:15,255 - INFO - joeynmt.data - Building tokenizer...
+2024-01-16 17:27:15,340 - INFO - joeynmt.tokenizers - src tokenizer: SentencePieceTokenizer(level=bpe, lowercase=False, normalize=False, filter_by_length=(-1, 512), pretokenizer=none, tokenizer=SentencePieceProcessor, nbest_size=5, alpha=0.0)
+2024-01-16 17:27:15,341 - INFO - joeynmt.tokenizers - trg tokenizer: SentencePieceTokenizer(level=bpe, lowercase=False, normalize=False, filter_by_length=(-1, 512), pretokenizer=none, tokenizer=SentencePieceProcessor, nbest_size=5, alpha=0.0)
+2024-01-16 17:27:15,341 - INFO - joeynmt.data - Building vocabulary...
+2024-01-16 17:28:01,074 - INFO - root - Hello! This is Joey-NMT (version 2.3.0).
+2024-01-16 17:28:01,157 - INFO - joeynmt.data - Building tokenizer...
+2024-01-16 17:28:01,241 - INFO - joeynmt.tokenizers - src tokenizer: SentencePieceTokenizer(level=bpe, lowercase=False, normalize=False, filter_by_length=(-1, 512), pretokenizer=none, tokenizer=SentencePieceProcessor, nbest_size=5, alpha=0.0)
+2024-01-16 17:28:01,242 - INFO - joeynmt.tokenizers - trg tokenizer: SentencePieceTokenizer(level=bpe, lowercase=False, normalize=False, filter_by_length=(-1, 512), pretokenizer=none, tokenizer=SentencePieceProcessor, nbest_size=5, alpha=0.0)
+2024-01-16 17:28:01,242 - INFO - joeynmt.data - Building vocabulary...
+2024-01-16 17:28:11,213 - INFO - joeynmt.data - Loading test set...
+2024-01-16 17:28:11,970 - INFO - numexpr.utils - Note: detected 96 virtual cores but NumExpr set to maximum of 64, check "NUMEXPR_MAX_THREADS" environment variable.
+2024-01-16 17:28:11,970 - INFO - numexpr.utils - Note: NumExpr detected 96 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8.
+2024-01-16 17:28:13,195 - INFO - joeynmt.data - Data loaded.
+2024-01-16 17:28:13,196 - INFO - joeynmt.data - Train dataset: None
+2024-01-16 17:28:13,196 - INFO - joeynmt.data - Valid dataset: None
+2024-01-16 17:28:13,196 - INFO - joeynmt.data -  Test dataset: TsvDataset(split=test, len=6743, src_lang=src, trg_lang=trg, has_trg=True, random_subset=-1, has_src_prompt=True, has_trg_prompt=True)
+2024-01-16 17:28:13,196 - INFO - joeynmt.data - First 10 Src tokens: (0) <unk> (1) <pad> (2) <s> (3) </s> (4) <sep> (5) <de> (6) <en> (7) <fr> (8) , (9) .
+2024-01-16 17:28:13,196 - INFO - joeynmt.data - First 10 Trg tokens: (0) <unk> (1) <pad> (2) <s> (3) </s> (4) <sep> (5) <de> (6) <en> (7) <fr> (8) , (9) .
+2024-01-16 17:28:13,196 - INFO - joeynmt.data - Number of unique Src tokens (vocab_size): 32000
+2024-01-16 17:28:13,196 - INFO - joeynmt.data - Number of unique Trg tokens (vocab_size): 32000
+2024-01-16 17:28:13,196 - INFO - joeynmt.model - Building an encoder-decoder model...
+2024-01-16 17:28:16,416 - INFO - joeynmt.model - Enc-dec model built.
+2024-01-16 17:28:16,419 - INFO - joeynmt.model - Total params: 209129472
+2024-01-16 17:28:16,420 - DEBUG - joeynmt.model - Trainable parameters: ['decoder.layer_norm.bias', 'decoder.layer_norm.weight', 'decoder.layers.0.dec_layer_norm.bias', 'decoder.layers.0.dec_layer_norm.weight', 'decoder.layers.0.feed_forward.layer_norm.bias', 'decoder.layers.0.feed_forward.layer_norm.weight', 'decoder.layers.0.feed_forward.pwff_layer.0.bias', 'decoder.layers.0.feed_forward.pwff_layer.0.weight', 'decoder.layers.0.feed_forward.pwff_layer.3.bias', 'decoder.layers.0.feed_forward.pwff_layer.3.weight', 'decoder.layers.0.src_trg_att.k_layer.bias', 'decoder.layers.0.src_trg_att.k_layer.weight', 'decoder.layers.0.src_trg_att.output_layer.bias', 'decoder.layers.0.src_trg_att.output_layer.weight', 'decoder.layers.0.src_trg_att.q_layer.bias', 'decoder.layers.0.src_trg_att.q_layer.weight', 'decoder.layers.0.src_trg_att.v_layer.bias', 'decoder.layers.0.src_trg_att.v_layer.weight', 'decoder.layers.0.trg_trg_att.k_layer.bias', 'decoder.layers.0.trg_trg_att.k_layer.weight', 'decoder.layers.0.trg_trg_att.output_layer.bias', 'decoder.layers.0.trg_trg_att.output_layer.weight', 'decoder.layers.0.trg_trg_att.q_layer.bias', 'decoder.layers.0.trg_trg_att.q_layer.weight', 'decoder.layers.0.trg_trg_att.v_layer.bias', 'decoder.layers.0.trg_trg_att.v_layer.weight', 'decoder.layers.0.x_layer_norm.bias', 'decoder.layers.0.x_layer_norm.weight', 'decoder.layers.1.dec_layer_norm.bias', 'decoder.layers.1.dec_layer_norm.weight', 'decoder.layers.1.feed_forward.layer_norm.bias', 'decoder.layers.1.feed_forward.layer_norm.weight', 'decoder.layers.1.feed_forward.pwff_layer.0.bias', 'decoder.layers.1.feed_forward.pwff_layer.0.weight', 'decoder.layers.1.feed_forward.pwff_layer.3.bias', 'decoder.layers.1.feed_forward.pwff_layer.3.weight', 'decoder.layers.1.src_trg_att.k_layer.bias', 'decoder.layers.1.src_trg_att.k_layer.weight', 'decoder.layers.1.src_trg_att.output_layer.bias', 'decoder.layers.1.src_trg_att.output_layer.weight', 'decoder.layers.1.src_trg_att.q_layer.bias', 'decoder.layers.1.src_trg_att.q_layer.weight', 'decoder.layers.1.src_trg_att.v_layer.bias', 'decoder.layers.1.src_trg_att.v_layer.weight', 'decoder.layers.1.trg_trg_att.k_layer.bias', 'decoder.layers.1.trg_trg_att.k_layer.weight', 'decoder.layers.1.trg_trg_att.output_layer.bias', 'decoder.layers.1.trg_trg_att.output_layer.weight', 'decoder.layers.1.trg_trg_att.q_layer.bias', 'decoder.layers.1.trg_trg_att.q_layer.weight', 'decoder.layers.1.trg_trg_att.v_layer.bias', 'decoder.layers.1.trg_trg_att.v_layer.weight', 'decoder.layers.1.x_layer_norm.bias', 'decoder.layers.1.x_layer_norm.weight', 'decoder.layers.2.dec_layer_norm.bias', 'decoder.layers.2.dec_layer_norm.weight', 'decoder.layers.2.feed_forward.layer_norm.bias', 'decoder.layers.2.feed_forward.layer_norm.weight', 'decoder.layers.2.feed_forward.pwff_layer.0.bias', 'decoder.layers.2.feed_forward.pwff_layer.0.weight', 'decoder.layers.2.feed_forward.pwff_layer.3.bias', 'decoder.layers.2.feed_forward.pwff_layer.3.weight', 'decoder.layers.2.src_trg_att.k_layer.bias', 'decoder.layers.2.src_trg_att.k_layer.weight', 'decoder.layers.2.src_trg_att.output_layer.bias', 'decoder.layers.2.src_trg_att.output_layer.weight', 'decoder.layers.2.src_trg_att.q_layer.bias', 'decoder.layers.2.src_trg_att.q_layer.weight', 'decoder.layers.2.src_trg_att.v_layer.bias', 'decoder.layers.2.src_trg_att.v_layer.weight', 'decoder.layers.2.trg_trg_att.k_layer.bias', 'decoder.layers.2.trg_trg_att.k_layer.weight', 'decoder.layers.2.trg_trg_att.output_layer.bias', 'decoder.layers.2.trg_trg_att.output_layer.weight', 'decoder.layers.2.trg_trg_att.q_layer.bias', 'decoder.layers.2.trg_trg_att.q_layer.weight', 'decoder.layers.2.trg_trg_att.v_layer.bias', 'decoder.layers.2.trg_trg_att.v_layer.weight', 'decoder.layers.2.x_layer_norm.bias', 'decoder.layers.2.x_layer_norm.weight', 'decoder.layers.3.dec_layer_norm.bias', 'decoder.layers.3.dec_layer_norm.weight', 'decoder.layers.3.feed_forward.layer_norm.bias', 'decoder.layers.3.feed_forward.layer_norm.weight', 'decoder.layers.3.feed_forward.pwff_layer.0.bias', 'decoder.layers.3.feed_forward.pwff_layer.0.weight', 'decoder.layers.3.feed_forward.pwff_layer.3.bias', 'decoder.layers.3.feed_forward.pwff_layer.3.weight', 'decoder.layers.3.src_trg_att.k_layer.bias', 'decoder.layers.3.src_trg_att.k_layer.weight', 'decoder.layers.3.src_trg_att.output_layer.bias', 'decoder.layers.3.src_trg_att.output_layer.weight', 'decoder.layers.3.src_trg_att.q_layer.bias', 'decoder.layers.3.src_trg_att.q_layer.weight', 'decoder.layers.3.src_trg_att.v_layer.bias', 'decoder.layers.3.src_trg_att.v_layer.weight', 'decoder.layers.3.trg_trg_att.k_layer.bias', 'decoder.layers.3.trg_trg_att.k_layer.weight', 'decoder.layers.3.trg_trg_att.output_layer.bias', 'decoder.layers.3.trg_trg_att.output_layer.weight', 'decoder.layers.3.trg_trg_att.q_layer.bias', 'decoder.layers.3.trg_trg_att.q_layer.weight', 'decoder.layers.3.trg_trg_att.v_layer.bias', 'decoder.layers.3.trg_trg_att.v_layer.weight', 'decoder.layers.3.x_layer_norm.bias', 'decoder.layers.3.x_layer_norm.weight', 'decoder.layers.4.dec_layer_norm.bias', 'decoder.layers.4.dec_layer_norm.weight', 'decoder.layers.4.feed_forward.layer_norm.bias', 'decoder.layers.4.feed_forward.layer_norm.weight', 'decoder.layers.4.feed_forward.pwff_layer.0.bias', 'decoder.layers.4.feed_forward.pwff_layer.0.weight', 'decoder.layers.4.feed_forward.pwff_layer.3.bias', 'decoder.layers.4.feed_forward.pwff_layer.3.weight', 'decoder.layers.4.src_trg_att.k_layer.bias', 'decoder.layers.4.src_trg_att.k_layer.weight', 'decoder.layers.4.src_trg_att.output_layer.bias', 'decoder.layers.4.src_trg_att.output_layer.weight', 'decoder.layers.4.src_trg_att.q_layer.bias', 'decoder.layers.4.src_trg_att.q_layer.weight', 'decoder.layers.4.src_trg_att.v_layer.bias', 'decoder.layers.4.src_trg_att.v_layer.weight', 'decoder.layers.4.trg_trg_att.k_layer.bias', 'decoder.layers.4.trg_trg_att.k_layer.weight', 'decoder.layers.4.trg_trg_att.output_layer.bias', 'decoder.layers.4.trg_trg_att.output_layer.weight', 'decoder.layers.4.trg_trg_att.q_layer.bias', 'decoder.layers.4.trg_trg_att.q_layer.weight', 'decoder.layers.4.trg_trg_att.v_layer.bias', 'decoder.layers.4.trg_trg_att.v_layer.weight', 'decoder.layers.4.x_layer_norm.bias', 'decoder.layers.4.x_layer_norm.weight', 'decoder.layers.5.dec_layer_norm.bias', 'decoder.layers.5.dec_layer_norm.weight', 'decoder.layers.5.feed_forward.layer_norm.bias', 'decoder.layers.5.feed_forward.layer_norm.weight', 'decoder.layers.5.feed_forward.pwff_layer.0.bias', 'decoder.layers.5.feed_forward.pwff_layer.0.weight', 'decoder.layers.5.feed_forward.pwff_layer.3.bias', 'decoder.layers.5.feed_forward.pwff_layer.3.weight', 'decoder.layers.5.src_trg_att.k_layer.bias', 'decoder.layers.5.src_trg_att.k_layer.weight', 'decoder.layers.5.src_trg_att.output_layer.bias', 'decoder.layers.5.src_trg_att.output_layer.weight', 'decoder.layers.5.src_trg_att.q_layer.bias', 'decoder.layers.5.src_trg_att.q_layer.weight', 'decoder.layers.5.src_trg_att.v_layer.bias', 'decoder.layers.5.src_trg_att.v_layer.weight', 'decoder.layers.5.trg_trg_att.k_layer.bias', 'decoder.layers.5.trg_trg_att.k_layer.weight', 'decoder.layers.5.trg_trg_att.output_layer.bias', 'decoder.layers.5.trg_trg_att.output_layer.weight', 'decoder.layers.5.trg_trg_att.q_layer.bias', 'decoder.layers.5.trg_trg_att.q_layer.weight', 'decoder.layers.5.trg_trg_att.v_layer.bias', 'decoder.layers.5.trg_trg_att.v_layer.weight', 'decoder.layers.5.x_layer_norm.bias', 'decoder.layers.5.x_layer_norm.weight', 'encoder.layer_norm.bias', 'encoder.layer_norm.weight', 'encoder.layers.0.feed_forward.layer_norm.bias', 'encoder.layers.0.feed_forward.layer_norm.weight', 'encoder.layers.0.feed_forward.pwff_layer.0.bias', 'encoder.layers.0.feed_forward.pwff_layer.0.weight', 'encoder.layers.0.feed_forward.pwff_layer.3.bias', 'encoder.layers.0.feed_forward.pwff_layer.3.weight', 'encoder.layers.0.layer_norm.bias', 'encoder.layers.0.layer_norm.weight', 'encoder.layers.0.src_src_att.k_layer.bias', 'encoder.layers.0.src_src_att.k_layer.weight', 'encoder.layers.0.src_src_att.output_layer.bias', 'encoder.layers.0.src_src_att.output_layer.weight', 'encoder.layers.0.src_src_att.q_layer.bias', 'encoder.layers.0.src_src_att.q_layer.weight', 'encoder.layers.0.src_src_att.v_layer.bias', 'encoder.layers.0.src_src_att.v_layer.weight', 'encoder.layers.1.feed_forward.layer_norm.bias', 'encoder.layers.1.feed_forward.layer_norm.weight', 'encoder.layers.1.feed_forward.pwff_layer.0.bias', 'encoder.layers.1.feed_forward.pwff_layer.0.weight', 'encoder.layers.1.feed_forward.pwff_layer.3.bias', 'encoder.layers.1.feed_forward.pwff_layer.3.weight', 'encoder.layers.1.layer_norm.bias', 'encoder.layers.1.layer_norm.weight', 'encoder.layers.1.src_src_att.k_layer.bias', 'encoder.layers.1.src_src_att.k_layer.weight', 'encoder.layers.1.src_src_att.output_layer.bias', 'encoder.layers.1.src_src_att.output_layer.weight', 'encoder.layers.1.src_src_att.q_layer.bias', 'encoder.layers.1.src_src_att.q_layer.weight', 'encoder.layers.1.src_src_att.v_layer.bias', 'encoder.layers.1.src_src_att.v_layer.weight', 'encoder.layers.2.feed_forward.layer_norm.bias', 'encoder.layers.2.feed_forward.layer_norm.weight', 'encoder.layers.2.feed_forward.pwff_layer.0.bias', 'encoder.layers.2.feed_forward.pwff_layer.0.weight', 'encoder.layers.2.feed_forward.pwff_layer.3.bias', 'encoder.layers.2.feed_forward.pwff_layer.3.weight', 'encoder.layers.2.layer_norm.bias', 'encoder.layers.2.layer_norm.weight', 'encoder.layers.2.src_src_att.k_layer.bias', 'encoder.layers.2.src_src_att.k_layer.weight', 'encoder.layers.2.src_src_att.output_layer.bias', 'encoder.layers.2.src_src_att.output_layer.weight', 'encoder.layers.2.src_src_att.q_layer.bias', 'encoder.layers.2.src_src_att.q_layer.weight', 'encoder.layers.2.src_src_att.v_layer.bias', 'encoder.layers.2.src_src_att.v_layer.weight', 'encoder.layers.3.feed_forward.layer_norm.bias', 'encoder.layers.3.feed_forward.layer_norm.weight', 'encoder.layers.3.feed_forward.pwff_layer.0.bias', 'encoder.layers.3.feed_forward.pwff_layer.0.weight', 'encoder.layers.3.feed_forward.pwff_layer.3.bias', 'encoder.layers.3.feed_forward.pwff_layer.3.weight', 'encoder.layers.3.layer_norm.bias', 'encoder.layers.3.layer_norm.weight', 'encoder.layers.3.src_src_att.k_layer.bias', 'encoder.layers.3.src_src_att.k_layer.weight', 'encoder.layers.3.src_src_att.output_layer.bias', 'encoder.layers.3.src_src_att.output_layer.weight', 'encoder.layers.3.src_src_att.q_layer.bias', 'encoder.layers.3.src_src_att.q_layer.weight', 'encoder.layers.3.src_src_att.v_layer.bias', 'encoder.layers.3.src_src_att.v_layer.weight', 'encoder.layers.4.feed_forward.layer_norm.bias', 'encoder.layers.4.feed_forward.layer_norm.weight', 'encoder.layers.4.feed_forward.pwff_layer.0.bias', 'encoder.layers.4.feed_forward.pwff_layer.0.weight', 'encoder.layers.4.feed_forward.pwff_layer.3.bias', 'encoder.layers.4.feed_forward.pwff_layer.3.weight', 'encoder.layers.4.layer_norm.bias', 'encoder.layers.4.layer_norm.weight', 'encoder.layers.4.src_src_att.k_layer.bias', 'encoder.layers.4.src_src_att.k_layer.weight', 'encoder.layers.4.src_src_att.output_layer.bias', 'encoder.layers.4.src_src_att.output_layer.weight', 'encoder.layers.4.src_src_att.q_layer.bias', 'encoder.layers.4.src_src_att.q_layer.weight', 'encoder.layers.4.src_src_att.v_layer.bias', 'encoder.layers.4.src_src_att.v_layer.weight', 'encoder.layers.5.feed_forward.layer_norm.bias', 'encoder.layers.5.feed_forward.layer_norm.weight', 'encoder.layers.5.feed_forward.pwff_layer.0.bias', 'encoder.layers.5.feed_forward.pwff_layer.0.weight', 'encoder.layers.5.feed_forward.pwff_layer.3.bias', 'encoder.layers.5.feed_forward.pwff_layer.3.weight', 'encoder.layers.5.layer_norm.bias', 'encoder.layers.5.layer_norm.weight', 'encoder.layers.5.src_src_att.k_layer.bias', 'encoder.layers.5.src_src_att.k_layer.weight', 'encoder.layers.5.src_src_att.output_layer.bias', 'encoder.layers.5.src_src_att.output_layer.weight', 'encoder.layers.5.src_src_att.q_layer.bias', 'encoder.layers.5.src_src_att.q_layer.weight', 'encoder.layers.5.src_src_att.v_layer.bias', 'encoder.layers.5.src_src_att.v_layer.weight', 'src_embed.lut.weight']
+2024-01-16 17:28:16,421 - INFO - joeynmt.prediction - Loading model from models/iwslt14_prompt/avg5.ckpt
+2024-01-16 17:28:24,668 - INFO - joeynmt.prediction - DataParallelWrapper(
+  (module): DataParallel(
+    (module): Model(
+    	encoder=TransformerEncoder(num_layers=6, num_heads=8, alpha=1.0, layer_norm="pre", activation=ReLU()),
+    	decoder=TransformerDecoder(num_layers=6, num_heads=8, alpha=1.0, layer_norm="pre", activation=ReLU()),
+    	src_embed=Embeddings(embedding_dim=1024, vocab_size=32000),
+    	trg_embed=Embeddings(embedding_dim=1024, vocab_size=32000),
+    	loss_function=XentLoss(criterion=KLDivLoss(), smoothing=0.1))
+  )
+)
+2024-01-16 17:28:24,681 - INFO - joeynmt.prediction - Decoding on test set... (device: cuda, n_gpu: 2, use_ddp: False, fp16: True)
+2024-01-16 17:28:24,681 - INFO - joeynmt.prediction - Predicting 6743 example(s)... (Beam search with beam_size=5, beam_alpha=1.0, n_best=1, min_output_length=1, max_output_length=512, return_prob='none', generate_unk=True, repetition_penalty=-1, no_repeat_ngram_size=-1)
+2024-01-16 18:19:58,646 - INFO - joeynmt.prediction - Generation took 3093.9641[sec].
+2024-01-16 18:20:00,112 - INFO - joeynmt.metrics - nrefs:1|case:lc|eff:no|tok:13a|smooth:exp|version:2.4.0
+2024-01-16 18:20:00,115 - INFO - joeynmt.prediction - Evaluation result (beam search): bleu:  35.28, 1.3136[sec]
+2024-01-16 18:20:00,128 - INFO - joeynmt.prediction - Translations saved to: iwslt14_prompt/hyp.test.

validations.txt

@@ -0,0 +1,29 @@
+Steps: 1000	loss: 5.33320	acc: 0.13981	ppl: 207.09943	bleu: 0.01656	LR: 0.00002000	*
+Steps: 2000	loss: 4.71079	acc: 0.19451	ppl: 111.13951	bleu: 0.55809	LR: 0.00004000	*
+Steps: 3000	loss: 4.20917	acc: 0.26398	ppl: 67.30097	bleu: 2.02249	LR: 0.00006000	*
+Steps: 4000	loss: 3.50676	acc: 0.36811	ppl: 33.33998	bleu: 6.85361	LR: 0.00008000	*
+Steps: 5000	loss: 3.10499	acc: 0.42404	ppl: 22.30898	bleu: 12.10052	LR: 0.00010000	*
+Steps: 6000	loss: 2.74785	acc: 0.47426	ppl: 15.60911	bleu: 15.55999	LR: 0.00012000	*
+Steps: 7000	loss: 2.59354	acc: 0.49875	ppl: 13.37698	bleu: 19.94671	LR: 0.00014000	*
+Steps: 8000	loss: 2.49535	acc: 0.51680	ppl: 12.12593	bleu: 20.80670	LR: 0.00016000	*
+Steps: 9000	loss: 2.32676	acc: 0.53745	ppl: 10.24473	bleu: 20.65046	LR: 0.00018000	
+Steps: 10000	loss: 2.32525	acc: 0.53374	ppl: 10.22927	bleu: 23.89984	LR: 0.00020000	*
+Steps: 11000	loss: 2.26839	acc: 0.54531	ppl: 9.66380	bleu: 24.47579	LR: 0.00019069	*
+Steps: 12000	loss: 2.21879	acc: 0.55346	ppl: 9.19621	bleu: 26.33193	LR: 0.00018257	*
+Steps: 13000	loss: 2.11914	acc: 0.56789	ppl: 8.32394	bleu: 25.80609	LR: 0.00017541	
+Steps: 14000	loss: 2.13339	acc: 0.57107	ppl: 8.44348	bleu: 27.53361	LR: 0.00016903	*
+Steps: 15000	loss: 2.10158	acc: 0.57200	ppl: 8.17911	bleu: 25.89823	LR: 0.00016330	
+Steps: 16000	loss: 2.01063	acc: 0.58820	ppl: 7.46800	bleu: 26.88964	LR: 0.00015811	
+Steps: 17000	loss: 2.03856	acc: 0.58597	ppl: 7.67955	bleu: 28.32236	LR: 0.00015339	*
+Steps: 18000	loss: 2.04342	acc: 0.58335	ppl: 7.71696	bleu: 26.54742	LR: 0.00014907	
+Steps: 19000	loss: 2.02208	acc: 0.58512	ppl: 7.55403	bleu: 27.41188	LR: 0.00014510	
+Steps: 20000	loss: 1.96965	acc: 0.59832	ppl: 7.16818	bleu: 27.44443	LR: 0.00014142	
+Steps: 21000	loss: 2.00185	acc: 0.58957	ppl: 7.40273	bleu: 27.51776	LR: 0.00013801	
+Steps: 22000	loss: 1.91933	acc: 0.60069	ppl: 6.81640	bleu: 27.78165	LR: 0.00013484	
+Steps: 23000	loss: 1.93601	acc: 0.60446	ppl: 6.93107	bleu: 29.21029	LR: 0.00013188	*
+Steps: 24000	loss: 1.95600	acc: 0.59864	ppl: 7.07096	bleu: 27.79109	LR: 0.00012910	
+Steps: 25000	loss: 2.00381	acc: 0.59484	ppl: 7.41723	bleu: 26.95928	LR: 0.00012649	
+Steps: 26000	loss: 2.05070	acc: 0.58464	ppl: 7.77331	bleu: 27.30420	LR: 0.00012403	
+Steps: 27000	loss: 1.94814	acc: 0.59961	ppl: 7.01565	bleu: 28.05348	LR: 0.00012172	
+Steps: 28000	loss: 2.04584	acc: 0.58991	ppl: 7.73569	bleu: 26.18726	LR: 0.00011952	
+Steps: 29000	loss: 2.09793	acc: 0.58589	ppl: 8.14927	bleu: 25.79140	LR: 0.00011744