|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: debug_fict-full-lstm-42 |
|
|
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. --> |
|
|
|
|
|
# debug_fict-full-lstm-42 |
|
|
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 7.8466 |
|
|
|
|
|
## 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: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 10.8142 | 0.08 | 10 | 10.8052 | |
|
|
| 10.7959 | 0.16 | 20 | 10.7830 | |
|
|
| 10.7637 | 0.24 | 30 | 10.7251 | |
|
|
| 10.62 | 0.32 | 40 | 10.3063 | |
|
|
| 9.8971 | 0.4 | 50 | 9.2732 | |
|
|
| 9.0782 | 0.48 | 60 | 8.6678 | |
|
|
| 8.5836 | 0.56 | 70 | 8.3319 | |
|
|
| 8.4033 | 0.64 | 80 | 8.1296 | |
|
|
| 8.2454 | 0.72 | 90 | 8.0021 | |
|
|
| 8.1265 | 0.8 | 100 | 7.9212 | |
|
|
| 8.0655 | 0.88 | 110 | 7.8713 | |
|
|
| 8.1315 | 0.96 | 120 | 7.8466 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
