Update README.md
Browse files
README.md
CHANGED
|
@@ -1,93 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
base_model: UBC-NLP/AraT5v2-base-1024
|
| 3 |
-
tags:
|
| 4 |
-
- generated_from_trainer
|
| 5 |
-
datasets:
|
| 6 |
-
- opus100
|
| 7 |
-
metrics:
|
| 8 |
-
- bleu
|
| 9 |
-
model-index:
|
| 10 |
-
- name: finetune-t5-base-on-opus100-Ar2En-without-optimization
|
| 11 |
-
results:
|
| 12 |
-
- task:
|
| 13 |
-
name: Sequence-to-sequence Language Modeling
|
| 14 |
-
type: text2text-generation
|
| 15 |
-
dataset:
|
| 16 |
-
name: opus100
|
| 17 |
-
type: opus100
|
| 18 |
-
config: ar-en
|
| 19 |
-
split: train[:7000]
|
| 20 |
-
args: ar-en
|
| 21 |
-
metrics:
|
| 22 |
-
- name: Bleu
|
| 23 |
-
type: bleu
|
| 24 |
-
value: 10.4288
|
| 25 |
-
---
|
| 26 |
-
|
| 27 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
-
|
| 30 |
-
# finetune-t5-base-on-opus100-Ar2En-without-optimization
|
| 31 |
-
|
| 32 |
-
This model is a fine-tuned version of [UBC-NLP/AraT5v2-base-1024](https://huggingface.co/UBC-NLP/AraT5v2-base-1024) on the opus100 dataset.
|
| 33 |
-
It achieves the following results on the evaluation set:
|
| 34 |
-
- Loss: 3.0042
|
| 35 |
-
- Bleu: 10.4288
|
| 36 |
-
- Gen Len: 10.739
|
| 37 |
-
|
| 38 |
-
## Model description
|
| 39 |
-
|
| 40 |
-
More information needed
|
| 41 |
-
|
| 42 |
-
## Intended uses & limitations
|
| 43 |
-
|
| 44 |
-
More information needed
|
| 45 |
-
|
| 46 |
-
## Training and evaluation data
|
| 47 |
-
|
| 48 |
-
More information needed
|
| 49 |
-
|
| 50 |
-
## Training procedure
|
| 51 |
-
|
| 52 |
-
### Training hyperparameters
|
| 53 |
-
|
| 54 |
-
The following hyperparameters were used during training:
|
| 55 |
-
- learning_rate: 2e-05
|
| 56 |
-
- train_batch_size: 10
|
| 57 |
-
- eval_batch_size: 10
|
| 58 |
-
- seed: 42
|
| 59 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
-
- lr_scheduler_type: linear
|
| 61 |
-
- num_epochs: 18
|
| 62 |
-
- mixed_precision_training: Native AMP
|
| 63 |
-
|
| 64 |
-
### Training results
|
| 65 |
-
|
| 66 |
-
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
| 67 |
-
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
|
| 68 |
-
| 10.1448 | 1.0 | 210 | 3.9256 | 2.8335 | 9.4988 |
|
| 69 |
-
| 4.9822 | 2.0 | 420 | 3.5760 | 4.9001 | 10.3329 |
|
| 70 |
-
| 4.42 | 3.0 | 630 | 3.4037 | 5.6973 | 10.301 |
|
| 71 |
-
| 4.1414 | 4.0 | 840 | 3.3057 | 6.5224 | 10.5559 |
|
| 72 |
-
| 3.9451 | 5.0 | 1050 | 3.2169 | 7.409 | 10.7571 |
|
| 73 |
-
| 3.7972 | 6.0 | 1260 | 3.1759 | 8.1445 | 10.5908 |
|
| 74 |
-
| 3.6687 | 7.0 | 1470 | 3.1340 | 8.246 | 10.7451 |
|
| 75 |
-
| 3.5494 | 8.0 | 1680 | 3.1098 | 8.5656 | 10.7616 |
|
| 76 |
-
| 3.4748 | 9.0 | 1890 | 3.0749 | 9.052 | 10.8798 |
|
| 77 |
-
| 3.3945 | 10.0 | 2100 | 3.0725 | 9.3223 | 10.6794 |
|
| 78 |
-
| 3.314 | 11.0 | 2310 | 3.0511 | 9.67 | 10.6871 |
|
| 79 |
-
| 3.2606 | 12.0 | 2520 | 3.0398 | 9.6105 | 10.6531 |
|
| 80 |
-
| 3.2314 | 13.0 | 2730 | 3.0211 | 10.0661 | 10.752 |
|
| 81 |
-
| 3.1557 | 14.0 | 2940 | 3.0188 | 10.0724 | 10.7188 |
|
| 82 |
-
| 3.1571 | 15.0 | 3150 | 3.0148 | 10.3648 | 10.7596 |
|
| 83 |
-
| 3.1213 | 16.0 | 3360 | 3.0061 | 10.4008 | 10.7784 |
|
| 84 |
-
| 3.1111 | 17.0 | 3570 | 3.0077 | 10.4588 | 10.7155 |
|
| 85 |
-
| 3.0851 | 18.0 | 3780 | 3.0042 | 10.4288 | 10.739 |
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
### Framework versions
|
| 89 |
-
|
| 90 |
-
- Transformers 4.35.2
|
| 91 |
-
- Pytorch 2.0.0
|
| 92 |
-
- Datasets 2.1.0
|
| 93 |
-
- Tokenizers 0.15.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|