Upload 14 files

.model_score.txt

@@ -0,0 +1 @@
+[0.41641438007354736, 0.3831499218940735, 0.3736233115196228, 0.3348974287509918, 0.3122231960296631]

best_model_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e11e8d61f86d4dd1d661487616331c0c3cdc0dcec407ef0613c5a05b5ca6ce3e
+size 326009981

best_model_1.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f9deaed5862d9bbd3aba40717b0f57eefaabc3abd78afba5a065a965a14d6f2
+size 326009981

best_model_2.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f9deaed5862d9bbd3aba40717b0f57eefaabc3abd78afba5a065a965a14d6f2
+size 326009981

best_model_3.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f9deaed5862d9bbd3aba40717b0f57eefaabc3abd78afba5a065a965a14d6f2
+size 326009981

best_model_4.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f9deaed5862d9bbd3aba40717b0f57eefaabc3abd78afba5a065a965a14d6f2
+size 326009981

bilingual_prototype.yml

@@ -0,0 +1,46 @@
+# data location and config section
+data:
+  train_data_location: laos-vn/Train/train2023
+  eval_data_location:  laos-vn/Dev/dev2023
+  src_lang: .lo
+  trg_lang: .vi
+log_file_models: 'model.log'
+lowercase: false
+build_vocab_kwargs: # additional arguments for build_vocab. See torchtext.vocab.Vocab for mode details
+#  max_size: 50000
+  min_freq: 5
+# model parameters section
+device: cuda
+d_model: 512
+n_layers: 6
+heads: 8
+# inference section
+eval_batch_size: 8
+decode_strategy: BeamSearch
+decode_strategy_kwargs:
+  beam_size: 4 # beam search size
+  length_normalize: 0.6 # recalculate beam position by length. Currently only work in default BeamSearch
+  replace_unk: # tuple of layer/head attention to replace unknown words
+    - 0 # layer
+    - 0 # head
+input_max_length: 200 # input longer than this value will be trimmed in inference. Note that this values are to be used during cached PE, hence, validation set with more than this much tokens will call a warning for the trimming.
+max_length: 160 # only perform up to this much timestep during inference
+train_max_length: 50 # training samples with this much length in src/trg will be discarded
+# optimizer and learning arguments section
+lr: 0.4
+optimizer: Adam
+optimizer_params:
+  betas:
+    - 0.9 # beta1
+    - 0.98 # beta2
+  eps: !!float 1e-9
+n_warmup_steps: 8000
+label_smoothing: 0.1
+dropout: 0.1
+# training config, evaluation, save & load section
+batch_size: 64
+epochs: 20
+printevery: 200
+save_checkpoint_epochs: 1
+maximum_saved_model_eval: 5
+maximum_saved_model_train: 5

model_16.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d01208fa9253a13f84f2d2b2e5327c94055a411a9032db5a19dc07e0cea02cb6
+size 326008477

model_17.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:826fadb03f8167f62f6bcc04c331f87f9de8a1838482d19106cde4c049b0d4f6
+size 326008477

model_18.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f7a5b773b1c2fcedcfae9fea0b088631472ed239f138c36e89470b6c942bd8
+size 326008477

model_19.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ad274c91bba1f3e15782b0da7fe08d85991fd97f7bb7a761f5577eabe1e578
+size 326008477

model_20.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a192ef31e27ab3654a27da59e6af52a0041caa6efecd620b05aea985cf6da4a
+size 326008477

vocab.lo.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c06b7c68f8b3d008e65a71b19dd0f7303da667a9ff24dcb7fd1313f00976a79
+size 1317394

vocab.vi.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dbd3a98cf885e510dbfed80bcdfcb3d4f25c11116d2d26b2a01fa9f14651400
+size 1456341