|
--- |
|
base_model: toobiza/MT-smart-feather-100 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: MT-bumbling-jazz-110 |
|
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. --> |
|
|
|
# MT-bumbling-jazz-110 |
|
|
|
This model is a fine-tuned version of [toobiza/MT-smart-feather-100](https://huggingface.co/toobiza/MT-smart-feather-100) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3325 |
|
- Loss Ce: 0.0008 |
|
- Loss Bbox: 0.0411 |
|
- Cardinality Error: 1.0 |
|
- Giou: 93.8060 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- 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 | Loss Ce | Loss Bbox | Cardinality Error | Giou | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:-----------------:|:-------:| |
|
| 3.0324 | 0.21 | 100 | 0.2384 | 0.0006 | 0.0280 | 1.0 | 95.1515 | |
|
| 3.0821 | 0.43 | 200 | 0.2353 | 0.0005 | 0.0270 | 1.0 | 95.0779 | |
|
| 3.1303 | 0.64 | 300 | 0.2509 | 0.0005 | 0.0297 | 1.0 | 94.9938 | |
|
| 3.1438 | 0.85 | 400 | 0.2649 | 0.0004 | 0.0316 | 1.0 | 94.7667 | |
|
| 3.0505 | 1.07 | 500 | 0.3075 | 0.0007 | 0.0368 | 1.0 | 93.9513 | |
|
| 3.3453 | 1.28 | 600 | 0.3260 | 0.0007 | 0.0401 | 1.0 | 93.8608 | |
|
| 2.9246 | 1.49 | 700 | 0.2985 | 0.0009 | 0.0357 | 1.0 | 94.1213 | |
|
| 2.8508 | 1.71 | 800 | 0.2933 | 0.0008 | 0.0349 | 1.0 | 94.1778 | |
|
| 2.9657 | 1.92 | 900 | 0.3315 | 0.0009 | 0.0410 | 1.0 | 93.8321 | |
|
| 3.1487 | 2.13 | 1000 | 0.3340 | 0.0008 | 0.0411 | 1.0 | 93.7168 | |
|
| 3.1254 | 2.35 | 1100 | 0.3098 | 0.0008 | 0.0379 | 1.0 | 94.1191 | |
|
| 2.4966 | 2.56 | 1200 | 0.3171 | 0.0008 | 0.0384 | 1.0 | 93.8997 | |
|
| 2.8596 | 2.77 | 1300 | 0.3294 | 0.0008 | 0.0404 | 1.0 | 93.7750 | |
|
| 3.2516 | 2.99 | 1400 | 0.3325 | 0.0008 | 0.0411 | 1.0 | 93.8060 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.13.3 |
|
|
