|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: npi-sim-ques-transformer-4 |
|
|
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. --> |
|
|
|
|
|
# npi-sim-ques-transformer-4 |
|
|
|
|
|
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: 3.8610 |
|
|
|
|
|
## 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: 4 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2392 | 0.03 | 76320 | 4.1993 | |
|
|
| 4.0323 | 1.03 | 152640 | 4.0296 | |
|
|
| 3.9279 | 0.03 | 228960 | 3.9548 | |
|
|
| 3.8561 | 1.03 | 305280 | 3.9138 | |
|
|
| 3.8036 | 0.03 | 381600 | 3.8881 | |
|
|
| 3.7625 | 0.03 | 457920 | 3.8710 | |
|
|
| 3.7285 | 1.03 | 534240 | 3.8606 | |
|
|
| 3.6956 | 0.03 | 610560 | 3.8533 | |
|
|
| 3.6668 | 1.03 | 686880 | 3.8490 | |
|
|
| 3.6419 | 0.03 | 763200 | 3.8457 | |
|
|
| 3.6185 | 1.03 | 839520 | 3.8446 | |
|
|
| 3.6021 | 0.03 | 915840 | 3.8438 | |
|
|
| 3.5781 | 1.03 | 992160 | 3.8423 | |
|
|
| 3.5567 | 0.03 | 1068480 | 3.8441 | |
|
|
| 3.5429 | 1.03 | 1144800 | 3.8441 | |
|
|
| 3.5382 | 0.03 | 1221120 | 3.8446 | |
|
|
| 3.5224 | 1.03 | 1297440 | 3.8456 | |
|
|
| 3.5064 | 0.03 | 1373760 | 3.8477 | |
|
|
| 3.4963 | 1.03 | 1450080 | 3.8499 | |
|
|
| 3.4863 | 0.03 | 1526400 | 3.8503 | |
|
|
| 3.4768 | 0.03 | 1602720 | 3.8510 | |
|
|
| 3.4658 | 1.03 | 1679040 | 3.8527 | |
|
|
| 3.4577 | 0.03 | 1755360 | 3.8541 | |
|
|
| 3.4436 | 1.03 | 1831680 | 3.8556 | |
|
|
| 3.4314 | 0.03 | 1908000 | 3.8570 | |
|
|
| 3.4192 | 1.03 | 1984320 | 3.8581 | |
|
|
| 3.4091 | 0.03 | 2060640 | 3.8579 | |
|
|
| 3.4012 | 1.03 | 2136960 | 3.8601 | |
|
|
| 3.3857 | 0.03 | 2213280 | 3.8605 | |
|
|
| 3.3695 | 1.03 | 2289600 | 3.8603 | |
|
|
| 3.3632 | 0.03 | 2365920 | 3.8624 | |
|
|
| 3.3599 | 1.03 | 2442240 | 3.8624 | |
|
|
| 3.3498 | 0.03 | 2518560 | 3.8641 | |
|
|
| 3.3379 | 1.03 | 2594880 | 3.8631 | |
|
|
| 3.3315 | 0.03 | 2671200 | 3.8640 | |
|
|
| 3.3251 | 0.03 | 2747520 | 3.8637 | |
|
|
| 3.3163 | 1.03 | 2823840 | 3.8639 | |
|
|
| 3.3132 | 0.03 | 2900160 | 3.8628 | |
|
|
| 3.3082 | 1.03 | 2976480 | 3.8619 | |
|
|
| 3.2988 | 0.02 | 3052726 | 3.8610 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
