End of training
Browse files- README.md +76 -0
- generation_config.json +6 -0
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: VietAI/vit5-base
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- sacrebleu
|
| 9 |
+
model-index:
|
| 10 |
+
- name: BaViT_Base_Finetune_v0
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# BaViT_Base_Finetune_v0
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [VietAI/vit5-base](https://huggingface.co/VietAI/vit5-base) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4516
|
| 22 |
+
- Sacrebleu: 7.9929
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 2e-05
|
| 42 |
+
- train_batch_size: 100
|
| 43 |
+
- eval_batch_size: 100
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 15
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|
|
| 54 |
+
| 0.6988 | 1.0 | 468 | 0.6266 | 2.2994 |
|
| 55 |
+
| 0.6014 | 2.0 | 936 | 0.5592 | 4.0780 |
|
| 56 |
+
| 0.5548 | 3.0 | 1404 | 0.5231 | 4.9356 |
|
| 57 |
+
| 0.5239 | 4.0 | 1872 | 0.5022 | 5.6738 |
|
| 58 |
+
| 0.5063 | 5.0 | 2340 | 0.4875 | 6.2733 |
|
| 59 |
+
| 0.4849 | 6.0 | 2808 | 0.4769 | 6.7126 |
|
| 60 |
+
| 0.4701 | 7.0 | 3276 | 0.4705 | 6.9856 |
|
| 61 |
+
| 0.4555 | 8.0 | 3744 | 0.4651 | 7.2721 |
|
| 62 |
+
| 0.4524 | 9.0 | 4212 | 0.4601 | 7.5539 |
|
| 63 |
+
| 0.4388 | 10.0 | 4680 | 0.4571 | 7.6076 |
|
| 64 |
+
| 0.4341 | 11.0 | 5148 | 0.4549 | 7.7267 |
|
| 65 |
+
| 0.4231 | 12.0 | 5616 | 0.4536 | 7.9165 |
|
| 66 |
+
| 0.4174 | 13.0 | 6084 | 0.4519 | 7.9585 |
|
| 67 |
+
| 0.4209 | 14.0 | 6552 | 0.4515 | 7.9864 |
|
| 68 |
+
| 0.4167 | 15.0 | 7020 | 0.4516 | 7.9929 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.48.1
|
| 74 |
+
- Pytorch 2.5.1+cu124
|
| 75 |
+
- Datasets 3.2.0
|
| 76 |
+
- Tokenizers 0.21.0
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.48.1"
|
| 6 |
+
}
|