Fine-tuning completed with 130k data rows & 3 epochs

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-en-vi
+tags:
+- translation
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: opus-mt-en-vi
+  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. -->
+
+# opus-mt-en-vi
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-vi](https://huggingface.co/Helsinki-NLP/opus-mt-en-vi) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0545
+- Bleu: 98.1385
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Bleu    |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|
+| 0.1102        | 1.0   | 8333  | 0.0818          | 96.5405 |
+| 0.0625        | 2.0   | 16666 | 0.0584          | 97.9108 |
+| 0.0564        | 3.0   | 24999 | 0.0545          | 98.1385 |
+
+
+### Framework versions
+
+- Transformers 4.37.0
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.1

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      53684
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 53684,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 53684,
+  "renormalize_logits": true,
+  "transformers_version": "4.37.0"
+}