Downloads · 30 days
12
7% of all-time downloads
jako_mbartLarge_sup_run1
yesj1234/jako_mbartLarge_sup_run1
jako_mbartLarge_sup_run1 is a machine learning model from yesj1234. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
180
Public
Parameters
611M
22 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt14.7 GB · 60%
At a glance
- Library
- transformers
- Model type
- mbart
- Access
- Public
- Created
- Jan 15, 2024
- Updated
- Jan 15, 2024
- SHA
- fb52691c
Base models
Model card
From the Hugging Face model README
<!-- 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. -->
finetuned_model
This model is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6568
- Bleu: 58.837
- Gen Len: 15.7689
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: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2500
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.7629 | 1.0 | 43024 | 0.7231 | 54.9608 | 16.1273 |
| 0.6355 | 2.0 | 86048 | 0.6641 | 57.5735 | 15.9938 |
| 0.5464 | 3.0 | 129072 | 0.6568 | 58.837 | 15.7689 |
| 0.4444 | 4.0 | 172096 | 0.6777 | 59.3055 | 15.7545 |
| 0.3458 | 5.0 | 215120 | 0.7215 | 59.1341 | 15.7016 |
| 0.2702 | 6.0 | 258144 | 0.8013 | 59.0721 | 15.6936 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Library
- transformers
- Type
- mbart
- Languages
- ja, ko
- Created
- Jan 15, 2024
- Updated
- Jan 15, 2024