|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: rel-cl-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. --> |
|
|
|
# rel-cl-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: 3.9792 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
| 4.7938 | 0.03 | 76319 | 4.7559 | |
|
| 4.5099 | 0.03 | 152638 | 4.4756 | |
|
| 4.3688 | 1.03 | 228957 | 4.3427 | |
|
| 4.2817 | 0.03 | 305276 | 4.2613 | |
|
| 4.2191 | 1.03 | 381595 | 4.2047 | |
|
| 4.1676 | 0.03 | 457914 | 4.1641 | |
|
| 4.1315 | 0.03 | 534233 | 4.1336 | |
|
| 4.1017 | 0.03 | 610552 | 4.1102 | |
|
| 4.0701 | 1.03 | 686871 | 4.0906 | |
|
| 4.05 | 0.03 | 763190 | 4.0741 | |
|
| 4.0306 | 1.03 | 839509 | 4.0620 | |
|
| 4.0118 | 0.03 | 915828 | 4.0515 | |
|
| 3.992 | 0.03 | 992147 | 4.0427 | |
|
| 3.9801 | 1.03 | 1068466 | 4.0348 | |
|
| 3.9659 | 0.03 | 1144785 | 4.0278 | |
|
| 3.9568 | 1.03 | 1221104 | 4.0221 | |
|
| 3.9456 | 0.03 | 1297424 | 4.0166 | |
|
| 3.9318 | 1.03 | 1373744 | 4.0121 | |
|
| 3.9242 | 0.03 | 1450064 | 4.0080 | |
|
| 3.9185 | 1.03 | 1526384 | 4.0051 | |
|
| 3.9133 | 0.03 | 1602704 | 4.0016 | |
|
| 3.9104 | 0.03 | 1679024 | 3.9993 | |
|
| 3.9076 | 1.03 | 1755344 | 3.9968 | |
|
| 3.8999 | 0.03 | 1831664 | 3.9944 | |
|
| 3.8906 | 1.03 | 1907984 | 3.9928 | |
|
| 3.8829 | 0.03 | 1984304 | 3.9910 | |
|
| 3.879 | 1.03 | 2060624 | 3.9893 | |
|
| 3.874 | 0.03 | 2136944 | 3.9882 | |
|
| 3.8682 | 1.03 | 2213264 | 3.9871 | |
|
| 3.8628 | 0.03 | 2289584 | 3.9859 | |
|
| 3.8627 | 0.03 | 2365904 | 3.9848 | |
|
| 3.86 | 0.03 | 2442224 | 3.9838 | |
|
| 3.8535 | 1.03 | 2518544 | 3.9829 | |
|
| 3.8496 | 0.03 | 2594864 | 3.9822 | |
|
| 3.8468 | 1.03 | 2671184 | 3.9813 | |
|
| 3.8472 | 0.03 | 2747504 | 3.9811 | |
|
| 3.8477 | 1.03 | 2823824 | 3.9803 | |
|
| 3.8478 | 0.03 | 2900144 | 3.9800 | |
|
| 3.8477 | 0.03 | 2976464 | 3.9796 | |
|
| 3.8446 | 0.02 | 3052726 | 3.9792 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
