|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: full2-lstm-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. --> |
|
|
|
|
|
# full2-lstm-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: 3.9723 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.7959 | 0.03 | 76320 | 4.7638 | |
|
|
| 4.5079 | 1.03 | 152640 | 4.4815 | |
|
|
| 4.3625 | 0.03 | 228960 | 4.3450 | |
|
|
| 4.2769 | 1.03 | 305280 | 4.2616 | |
|
|
| 4.2133 | 0.03 | 381600 | 4.2046 | |
|
|
| 4.167 | 0.03 | 457920 | 4.1638 | |
|
|
| 4.1327 | 0.03 | 534240 | 4.1323 | |
|
|
| 4.1009 | 1.03 | 610560 | 4.1073 | |
|
|
| 4.0712 | 0.03 | 686880 | 4.0878 | |
|
|
| 4.0477 | 1.03 | 763200 | 4.0715 | |
|
|
| 4.0282 | 0.03 | 839520 | 4.0582 | |
|
|
| 4.0086 | 1.03 | 915840 | 4.0472 | |
|
|
| 3.9979 | 0.03 | 992160 | 4.0375 | |
|
|
| 3.9819 | 1.03 | 1068480 | 4.0296 | |
|
|
| 3.9663 | 0.03 | 1144800 | 4.0231 | |
|
|
| 3.9521 | 1.03 | 1221120 | 4.0175 | |
|
|
| 3.9375 | 0.03 | 1297440 | 4.0120 | |
|
|
| 3.929 | 1.03 | 1373760 | 4.0072 | |
|
|
| 3.9164 | 0.03 | 1450080 | 4.0034 | |
|
|
| 3.9149 | 1.03 | 1526400 | 3.9997 | |
|
|
| 3.9088 | 0.03 | 1602720 | 3.9969 | |
|
|
| 3.9042 | 1.03 | 1679040 | 3.9941 | |
|
|
| 3.9046 | 0.03 | 1755360 | 3.9915 | |
|
|
| 3.8983 | 1.03 | 1831680 | 3.9891 | |
|
|
| 3.8929 | 0.03 | 1908000 | 3.9868 | |
|
|
| 3.8857 | 1.03 | 1984320 | 3.9849 | |
|
|
| 3.8807 | 0.03 | 2060640 | 3.9831 | |
|
|
| 3.8737 | 0.03 | 2136960 | 3.9818 | |
|
|
| 3.8729 | 1.03 | 2213280 | 3.9802 | |
|
|
| 3.8669 | 0.03 | 2289600 | 3.9789 | |
|
|
| 3.8603 | 0.03 | 2365920 | 3.9781 | |
|
|
| 3.8562 | 1.03 | 2442240 | 3.9771 | |
|
|
| 3.8473 | 0.03 | 2518560 | 3.9763 | |
|
|
| 3.8437 | 1.03 | 2594880 | 3.9755 | |
|
|
| 3.8393 | 0.03 | 2671200 | 3.9749 | |
|
|
| 3.8432 | 0.03 | 2747520 | 3.9742 | |
|
|
| 3.8431 | 1.03 | 2823840 | 3.9735 | |
|
|
| 3.8439 | 0.03 | 2900160 | 3.9730 | |
|
|
| 3.8476 | 1.03 | 2976480 | 3.9726 | |
|
|
| 3.8466 | 0.02 | 3052726 | 3.9723 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
