|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: det-noun-transformer-3 |
|
|
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. --> |
|
|
|
|
|
# det-noun-transformer-3 |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.8604 |
|
|
|
|
|
## 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: 32 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 3 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- training_steps: 3052726 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.229 | 0.03 | 76320 | 4.1966 | |
|
|
| 4.0225 | 1.03 | 152640 | 4.0278 | |
|
|
| 3.9119 | 0.03 | 228960 | 3.9528 | |
|
|
| 3.8437 | 0.03 | 305280 | 3.9120 | |
|
|
| 3.7953 | 1.03 | 381600 | 3.8871 | |
|
|
| 3.7538 | 0.03 | 457920 | 3.8699 | |
|
|
| 3.7193 | 1.03 | 534240 | 3.8599 | |
|
|
| 3.6865 | 0.03 | 610560 | 3.8533 | |
|
|
| 3.6568 | 1.03 | 686880 | 3.8486 | |
|
|
| 3.6323 | 0.03 | 763200 | 3.8451 | |
|
|
| 3.612 | 1.03 | 839520 | 3.8445 | |
|
|
| 3.593 | 0.03 | 915840 | 3.8424 | |
|
|
| 3.5738 | 0.03 | 992160 | 3.8430 | |
|
|
| 3.5506 | 1.03 | 1068480 | 3.8433 | |
|
|
| 3.5384 | 0.03 | 1144800 | 3.8435 | |
|
|
| 3.5287 | 1.03 | 1221120 | 3.8440 | |
|
|
| 3.512 | 0.03 | 1297440 | 3.8463 | |
|
|
| 3.499 | 1.03 | 1373760 | 3.8464 | |
|
|
| 3.4808 | 0.03 | 1450080 | 3.8489 | |
|
|
| 3.4728 | 1.03 | 1526400 | 3.8487 | |
|
|
| 3.4668 | 0.03 | 1602720 | 3.8506 | |
|
|
| 3.4605 | 1.03 | 1679040 | 3.8525 | |
|
|
| 3.4498 | 0.03 | 1755360 | 3.8531 | |
|
|
| 3.4355 | 1.03 | 1831680 | 3.8544 | |
|
|
| 3.4245 | 0.03 | 1908000 | 3.8548 | |
|
|
| 3.4117 | 0.03 | 1984320 | 3.8570 | |
|
|
| 3.401 | 1.03 | 2060640 | 3.8575 | |
|
|
| 3.393 | 0.03 | 2136960 | 3.8583 | |
|
|
| 3.3814 | 1.03 | 2213280 | 3.8602 | |
|
|
| 3.3636 | 0.03 | 2289600 | 3.8605 | |
|
|
| 3.3563 | 1.03 | 2365920 | 3.8619 | |
|
|
| 3.3539 | 0.03 | 2442240 | 3.8625 | |
|
|
| 3.3429 | 1.03 | 2518560 | 3.8624 | |
|
|
| 3.3318 | 0.03 | 2594880 | 3.8638 | |
|
|
| 3.3196 | 1.03 | 2671200 | 3.8634 | |
|
|
| 3.315 | 0.03 | 2747520 | 3.8632 | |
|
|
| 3.3121 | 1.03 | 2823840 | 3.8632 | |
|
|
| 3.3058 | 0.03 | 2900160 | 3.8624 | |
|
|
| 3.3017 | 1.03 | 2976480 | 3.8610 | |
|
|
| 3.2907 | 0.02 | 3052726 | 3.8604 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
