|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: npi-sim-ques-lstm-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. --> |
|
|
|
# npi-sim-ques-lstm-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: 3.9715 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.8041 | 0.03 | 76320 | 4.7586 | |
|
| 4.5148 | 1.03 | 152640 | 4.4771 | |
|
| 4.3758 | 0.03 | 228960 | 4.3429 | |
|
| 4.286 | 1.03 | 305280 | 4.2606 | |
|
| 4.2235 | 0.03 | 381600 | 4.2032 | |
|
| 4.1769 | 1.03 | 457920 | 4.1622 | |
|
| 4.1388 | 0.03 | 534240 | 4.1311 | |
|
| 4.1054 | 1.03 | 610560 | 4.1065 | |
|
| 4.0766 | 0.03 | 686880 | 4.0882 | |
|
| 4.0509 | 1.03 | 763200 | 4.0714 | |
|
| 4.0307 | 0.03 | 839520 | 4.0580 | |
|
| 4.0163 | 1.03 | 915840 | 4.0468 | |
|
| 3.9939 | 0.03 | 992160 | 4.0374 | |
|
| 3.9762 | 0.03 | 1068480 | 4.0297 | |
|
| 3.9649 | 1.03 | 1144800 | 4.0224 | |
|
| 3.9597 | 0.03 | 1221120 | 4.0163 | |
|
| 3.9488 | 1.03 | 1297440 | 4.0111 | |
|
| 3.9365 | 0.03 | 1373760 | 4.0063 | |
|
| 3.9318 | 1.03 | 1450080 | 4.0024 | |
|
| 3.9244 | 0.03 | 1526400 | 3.9980 | |
|
| 3.9184 | 1.03 | 1602720 | 3.9953 | |
|
| 3.9142 | 0.03 | 1679040 | 3.9931 | |
|
| 3.9091 | 1.03 | 1755360 | 3.9907 | |
|
| 3.9024 | 0.03 | 1831680 | 3.9885 | |
|
| 3.8957 | 1.03 | 1908000 | 3.9863 | |
|
| 3.8879 | 0.03 | 1984320 | 3.9844 | |
|
| 3.8829 | 1.03 | 2060640 | 3.9828 | |
|
| 3.8797 | 0.03 | 2136960 | 3.9809 | |
|
| 3.8701 | 1.03 | 2213280 | 3.9796 | |
|
| 3.8611 | 0.03 | 2289600 | 3.9784 | |
|
| 3.8603 | 0.03 | 2365920 | 3.9774 | |
|
| 3.8637 | 1.03 | 2442240 | 3.9764 | |
|
| 3.8601 | 0.03 | 2518560 | 3.9757 | |
|
| 3.8531 | 0.03 | 2594880 | 3.9747 | |
|
| 3.855 | 0.03 | 2671200 | 3.9740 | |
|
| 3.8516 | 1.03 | 2747520 | 3.9734 | |
|
| 3.8512 | 0.03 | 2823840 | 3.9728 | |
|
| 3.852 | 0.03 | 2900160 | 3.9722 | |
|
| 3.8529 | 1.03 | 2976480 | 3.9717 | |
|
| 3.8489 | 0.02 | 3052726 | 3.9715 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
