|
--- |
|
license: mit |
|
base_model: microsoft/deberta-v3-large |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: checkpoints_3_14 |
|
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. --> |
|
|
|
# checkpoints_3_14 |
|
|
|
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9950 |
|
- Map@3: 0.7360 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 0 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Map@3 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 1.6075 | 0.04 | 200 | 1.6074 | 0.6027 | |
|
| 1.5444 | 0.08 | 400 | 1.3248 | 0.6428 | |
|
| 1.4506 | 0.13 | 600 | 1.2670 | 0.6707 | |
|
| 1.3635 | 0.17 | 800 | 1.1671 | 0.6850 | |
|
| 1.3478 | 0.21 | 1000 | 1.0909 | 0.7003 | |
|
| 1.3021 | 0.25 | 1200 | 1.0701 | 0.6923 | |
|
| 1.3284 | 0.29 | 1400 | 1.0627 | 0.7085 | |
|
| 1.2869 | 0.34 | 1600 | 1.0645 | 0.7003 | |
|
| 1.2735 | 0.38 | 1800 | 1.1617 | 0.7043 | |
|
| 1.3019 | 0.42 | 2000 | 1.0272 | 0.7120 | |
|
| 1.2824 | 0.46 | 2200 | 1.0781 | 0.7123 | |
|
| 1.2882 | 0.51 | 2400 | 1.0454 | 0.7178 | |
|
| 1.2699 | 0.55 | 2600 | 1.0439 | 0.7225 | |
|
| 1.2165 | 0.59 | 2800 | 1.0208 | 0.7260 | |
|
| 1.2419 | 0.63 | 3000 | 1.0166 | 0.7292 | |
|
| 1.2395 | 0.67 | 3200 | 1.0065 | 0.7310 | |
|
| 1.2368 | 0.72 | 3400 | 1.0429 | 0.7275 | |
|
| 1.2232 | 0.76 | 3600 | 1.0105 | 0.7353 | |
|
| 1.1969 | 0.8 | 3800 | 1.0017 | 0.7370 | |
|
| 1.2451 | 0.84 | 4000 | 0.9982 | 0.7383 | |
|
| 1.2088 | 0.88 | 4200 | 0.9977 | 0.7372 | |
|
| 1.2229 | 0.93 | 4400 | 0.9953 | 0.7367 | |
|
| 1.2612 | 0.97 | 4600 | 0.9950 | 0.7360 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
