KanWasTaken/EN-VI-Machine-Translation-RNN

README.md

@@ -0,0 +1,75 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: EN-VI-Machine-Translation-RNN
+  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-RNN
+
+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: 0.7149
+
+## 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: 1024
+- eval_batch_size: 1024
+- 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: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 7.829         | 1.0   | 131  | 5.6878          |
+| 4.0951        | 2.0   | 262  | 2.7482          |
+| 2.1201        | 3.0   | 393  | 1.5308          |
+| 1.3062        | 4.0   | 524  | 1.0420          |
+| 1.0218        | 5.0   | 655  | 0.8985          |
+| 0.927         | 6.0   | 786  | 0.8373          |
+| 0.8817        | 7.0   | 917  | 0.8036          |
+| 0.8538        | 8.0   | 1048 | 0.7808          |
+| 0.8348        | 9.0   | 1179 | 0.7639          |
+| 0.8204        | 10.0  | 1310 | 0.7518          |
+| 0.8099        | 11.0  | 1441 | 0.7427          |
+| 0.802         | 12.0  | 1572 | 0.7357          |
+| 0.7964        | 13.0  | 1703 | 0.7302          |
+| 0.7916        | 14.0  | 1834 | 0.7258          |
+| 0.7871        | 15.0  | 1965 | 0.7223          |
+| 0.7839        | 16.0  | 2096 | 0.7196          |
+| 0.7814        | 17.0  | 2227 | 0.7175          |
+| 0.7801        | 18.0  | 2358 | 0.7161          |
+| 0.7788        | 19.0  | 2489 | 0.7152          |
+| 0.7778        | 20.0  | 2620 | 0.7149          |
+
+
+### Framework versions
+
+- Transformers 4.47.0
+- Pytorch 2.5.1+cu121
+- Datasets 3.3.1
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,12 @@
+{
+  "architectures": [
+    "Seq2SeqRNNModel"
+  ],
+  "dropout": 0.1,
+  "embed_dim": 128,
+  "hidden_dim": 128,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "vocab_size_ipt": 15000,
+  "vocab_size_label": 15000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea7520dd444bfd19df0a9f12fb27fcc2196b3a1adf61406c110ba8e51c48a50
+size 23893728

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f14e643cc297fdb3db7205c5a946d27a4acbaaf4306e2607a8e8d71d972e6c
+size 5240