|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: pp-mod-subj2-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. --> |
|
|
|
# pp-mod-subj2-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: 4.0236 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.7988 | 0.03 | 76320 | 4.8119 | |
|
| 4.5128 | 1.03 | 152640 | 4.5289 | |
|
| 4.3661 | 0.03 | 228960 | 4.3930 | |
|
| 4.2793 | 1.03 | 305280 | 4.3106 | |
|
| 4.2199 | 2.03 | 381600 | 4.2538 | |
|
| 4.1656 | 0.03 | 457920 | 4.2123 | |
|
| 4.1242 | 1.03 | 534240 | 4.1813 | |
|
| 4.0913 | 0.03 | 610560 | 4.1555 | |
|
| 4.0629 | 1.03 | 686880 | 4.1362 | |
|
| 4.0421 | 2.03 | 763200 | 4.1204 | |
|
| 4.0202 | 0.03 | 839520 | 4.1084 | |
|
| 4.0025 | 1.03 | 915840 | 4.0972 | |
|
| 3.989 | 0.03 | 992160 | 4.0882 | |
|
| 3.9751 | 1.03 | 1068480 | 4.0794 | |
|
| 3.9595 | 2.03 | 1144800 | 4.0728 | |
|
| 3.9436 | 0.03 | 1221120 | 4.0676 | |
|
| 3.9344 | 1.03 | 1297440 | 4.0620 | |
|
| 3.9263 | 2.03 | 1373760 | 4.0570 | |
|
| 3.9151 | 0.03 | 1450080 | 4.0538 | |
|
| 3.9114 | 1.03 | 1526400 | 4.0491 | |
|
| 3.9089 | 2.03 | 1602720 | 4.0466 | |
|
| 3.8981 | 0.03 | 1679040 | 4.0438 | |
|
| 3.8904 | 1.03 | 1755360 | 4.0413 | |
|
| 3.8841 | 0.03 | 1831680 | 4.0396 | |
|
| 3.8756 | 1.03 | 1908000 | 4.0376 | |
|
| 3.8743 | 2.03 | 1984320 | 4.0353 | |
|
| 3.8676 | 0.03 | 2060640 | 4.0340 | |
|
| 3.8629 | 1.03 | 2136960 | 4.0330 | |
|
| 3.8599 | 0.03 | 2213280 | 4.0308 | |
|
| 3.856 | 1.03 | 2289600 | 4.0297 | |
|
| 3.8492 | 2.03 | 2365920 | 4.0286 | |
|
| 3.8436 | 0.03 | 2442240 | 4.0276 | |
|
| 3.8417 | 0.03 | 2518560 | 4.0271 | |
|
| 3.8421 | 1.03 | 2594880 | 4.0268 | |
|
| 3.8355 | 0.03 | 2671200 | 4.0259 | |
|
| 3.8387 | 1.03 | 2747520 | 4.0254 | |
|
| 3.8418 | 0.03 | 2823840 | 4.0249 | |
|
| 3.8357 | 1.03 | 2900160 | 4.0245 | |
|
| 3.8343 | 2.03 | 2976480 | 4.0239 | |
|
| 3.8291 | 0.02 | 3052726 | 4.0236 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
