KanWasTaken/EN-VI-Machine-Translation-Transformer

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: EN-VI-Machine-Translation-Transformer
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# EN-VI-Machine-Translation-Transformer
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5433
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 256
+- eval_batch_size: 256
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0705        | 1.0   | 521  | 0.5980          |
+| 0.6527        | 2.0   | 1042 | 0.5660          |
+| 0.6288        | 3.0   | 1563 | 0.5530          |
+| 0.6174        | 4.0   | 2084 | 0.5460          |
+| 0.6117        | 5.0   | 2605 | 0.5433          |
+
+
+### Framework versions
+
+- Transformers 4.47.0
+- Pytorch 2.5.1+cu121
+- Datasets 3.3.1
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,14 @@
+{
+  "architectures": [
+    "Seq2SeqTransformerModel"
+  ],
+  "d_model": 256,
+  "dropout": 0.1,
+  "max_seq_length": 75,
+  "num_heads": 8,
+  "num_layers": 6,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "vocab_size_src": 15000,
+  "vocab_size_tgt": 15000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede7d189aa060eed811233c1b1d91e8dc780ff4848131ea5b1badc48c1091780
+size 115771368

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3b385df19182dca29e0de224a5186a043a610e33657c349b6cd5ccda9af0258
+size 5240