|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: checkpoints_2_18 |
|
|
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_2_18 |
|
|
|
|
|
This model was trained from scratch on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.0162 |
|
|
- Map@3: 0.7248 |
|
|
|
|
|
## 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-06 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
|
| 1.1455 | 0.04 | 200 | 1.0242 | 0.7222 | |
|
|
| 1.1247 | 0.08 | 400 | 1.0420 | 0.7233 | |
|
|
| 1.0755 | 0.13 | 600 | 1.0358 | 0.7222 | |
|
|
| 1.003 | 0.17 | 800 | 1.1454 | 0.7258 | |
|
|
| 1.0276 | 0.21 | 1000 | 1.0685 | 0.7205 | |
|
|
| 0.9733 | 0.25 | 1200 | 1.1443 | 0.7050 | |
|
|
| 1.0409 | 0.29 | 1400 | 1.1388 | 0.7012 | |
|
|
| 0.9511 | 0.34 | 1600 | 1.1830 | 0.7197 | |
|
|
| 1.0153 | 0.38 | 1800 | 1.1344 | 0.7172 | |
|
|
| 1.0024 | 0.42 | 2000 | 1.1659 | 0.7212 | |
|
|
| 0.9657 | 0.46 | 2200 | 1.1938 | 0.7100 | |
|
|
| 0.9993 | 0.51 | 2400 | 1.1777 | 0.7042 | |
|
|
| 1.0174 | 0.55 | 2600 | 1.0811 | 0.7145 | |
|
|
| 0.9792 | 0.59 | 2800 | 1.1281 | 0.7162 | |
|
|
| 1.0442 | 0.63 | 3000 | 1.0792 | 0.7133 | |
|
|
| 1.075 | 0.67 | 3200 | 1.0900 | 0.7165 | |
|
|
| 1.1424 | 0.72 | 3400 | 1.0698 | 0.7188 | |
|
|
| 1.1411 | 0.76 | 3600 | 1.0476 | 0.7193 | |
|
|
| 1.172 | 0.8 | 3800 | 1.0318 | 0.7225 | |
|
|
| 1.208 | 0.84 | 4000 | 1.0224 | 0.7225 | |
|
|
| 1.1975 | 0.88 | 4200 | 1.0195 | 0.7245 | |
|
|
| 1.2282 | 0.93 | 4400 | 1.0168 | 0.7238 | |
|
|
| 1.2635 | 0.97 | 4600 | 1.0162 | 0.7248 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.2 |
|
|
- Pytorch 2.0.1+cu118 |
|
|
- Datasets 2.14.5 |
|
|
- Tokenizers 0.13.3 |
|
|
|
