|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: full2-lstm-1 |
|
|
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-1 |
|
|
|
|
|
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: 3.9693 |
|
|
|
|
|
## 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: 1 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.7908 | 0.03 | 76320 | 4.7591 | |
|
|
| 4.503 | 1.03 | 152640 | 4.4757 | |
|
|
| 4.3573 | 0.03 | 228960 | 4.3392 | |
|
|
| 4.2734 | 1.03 | 305280 | 4.2557 | |
|
|
| 4.2087 | 0.03 | 381600 | 4.1996 | |
|
|
| 4.1623 | 1.03 | 457920 | 4.1579 | |
|
|
| 4.1299 | 0.03 | 534240 | 4.1275 | |
|
|
| 4.0985 | 1.03 | 610560 | 4.1030 | |
|
|
| 4.0681 | 0.03 | 686880 | 4.0831 | |
|
|
| 4.0451 | 1.03 | 763200 | 4.0677 | |
|
|
| 4.0249 | 0.03 | 839520 | 4.0546 | |
|
|
| 4.0052 | 1.03 | 915840 | 4.0434 | |
|
|
| 3.9931 | 0.03 | 992160 | 4.0340 | |
|
|
| 3.978 | 1.03 | 1068480 | 4.0267 | |
|
|
| 3.9631 | 0.03 | 1144800 | 4.0203 | |
|
|
| 3.9499 | 1.03 | 1221120 | 4.0141 | |
|
|
| 3.9341 | 0.03 | 1297440 | 4.0091 | |
|
|
| 3.9257 | 1.03 | 1373760 | 4.0043 | |
|
|
| 3.9144 | 0.03 | 1450080 | 4.0004 | |
|
|
| 3.9117 | 0.03 | 1526400 | 3.9971 | |
|
|
| 3.9051 | 1.03 | 1602720 | 3.9939 | |
|
|
| 3.9014 | 0.03 | 1679040 | 3.9910 | |
|
|
| 3.9001 | 1.03 | 1755360 | 3.9879 | |
|
|
| 3.8949 | 0.03 | 1831680 | 3.9852 | |
|
|
| 3.8882 | 1.03 | 1908000 | 3.9834 | |
|
|
| 3.8832 | 0.03 | 1984320 | 3.9819 | |
|
|
| 3.8759 | 1.03 | 2060640 | 3.9804 | |
|
|
| 3.8706 | 0.03 | 2136960 | 3.9790 | |
|
|
| 3.8694 | 1.03 | 2213280 | 3.9776 | |
|
|
| 3.8642 | 0.03 | 2289600 | 3.9764 | |
|
|
| 3.8565 | 1.03 | 2365920 | 3.9754 | |
|
|
| 3.853 | 0.03 | 2442240 | 3.9741 | |
|
|
| 3.8458 | 1.03 | 2518560 | 3.9735 | |
|
|
| 3.8418 | 0.03 | 2594880 | 3.9724 | |
|
|
| 3.8351 | 0.03 | 2671200 | 3.9713 | |
|
|
| 3.8391 | 0.03 | 2747520 | 3.9706 | |
|
|
| 3.8383 | 0.03 | 2823840 | 3.9701 | |
|
|
| 3.839 | 0.03 | 2900160 | 3.9698 | |
|
|
| 3.8427 | 0.03 | 2976480 | 3.9694 | |
|
|
| 3.8414 | 1.02 | 3052726 | 3.9693 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
