Commit
•
44f17b2
1
Parent(s):
7a439e6
Training complete
Browse files
README.md
CHANGED
|
@@ -3,6 +3,8 @@ base_model: vinai/bartpho-syllable
|
|
| 3 |
tags:
|
| 4 |
- text2text-generation
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: vietnamese-correction-nlp
|
| 8 |
results: []
|
|
@@ -15,13 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [vinai/bartpho-syllable](https://huggingface.co/vinai/bartpho-syllable) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
-
|
| 19 |
-
-
|
| 20 |
-
- eval_runtime: 781.5801
|
| 21 |
-
- eval_samples_per_second: 8.956
|
| 22 |
-
- eval_steps_per_second: 2.239
|
| 23 |
-
- epoch: 1.3333
|
| 24 |
-
- step: 5000
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -48,9 +45,17 @@ The following hyperparameters were used during training:
|
|
| 48 |
- total_train_batch_size: 8
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
-
- num_epochs:
|
| 52 |
- mixed_precision_training: Native AMP
|
| 53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
### Framework versions
|
| 55 |
|
| 56 |
- Transformers 4.40.2
|
|
|
|
| 3 |
tags:
|
| 4 |
- text2text-generation
|
| 5 |
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- sacrebleu
|
| 8 |
model-index:
|
| 9 |
- name: vietnamese-correction-nlp
|
| 10 |
results: []
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [vinai/bartpho-syllable](https://huggingface.co/vinai/bartpho-syllable) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.1795
|
| 21 |
+
- Sacrebleu: 26.6215
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 45 |
- total_train_batch_size: 8
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
+
- num_epochs: 1
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
|
| 54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|
|
| 55 |
+
| 0.4541 | 0.4 | 5000 | 0.2183 | 25.8874 |
|
| 56 |
+
| 0.2794 | 0.8 | 10000 | 0.1835 | 26.5453 |
|
| 57 |
+
|
| 58 |
+
|
| 59 |
### Framework versions
|
| 60 |
|
| 61 |
- Transformers 4.40.2
|
runs/May16_20-24-33_985d97da84b9/events.out.tfevents.1715900475.985d97da84b9.3748.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:593171c0f57cd4eb5caf9cc570983312d07c1fdb6673d1bed41ca1936180c98f
|
| 3 |
+
size 412
|