|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: passive-transformer-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. --> |
|
|
|
|
|
# passive-transformer-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: 3.8653 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2239 | 0.03 | 76320 | 4.2000 | |
|
|
| 4.0185 | 1.03 | 152640 | 4.0311 | |
|
|
| 3.9082 | 0.03 | 228960 | 3.9570 | |
|
|
| 3.8408 | 1.03 | 305280 | 3.9162 | |
|
|
| 3.7875 | 0.03 | 381600 | 3.8915 | |
|
|
| 3.7504 | 0.03 | 457920 | 3.8749 | |
|
|
| 3.714 | 0.03 | 534240 | 3.8651 | |
|
|
| 3.6838 | 1.03 | 610560 | 3.8578 | |
|
|
| 3.653 | 0.03 | 686880 | 3.8533 | |
|
|
| 3.6271 | 0.03 | 763200 | 3.8507 | |
|
|
| 3.6035 | 1.03 | 839520 | 3.8488 | |
|
|
| 3.5835 | 0.03 | 915840 | 3.8493 | |
|
|
| 3.5632 | 1.03 | 992160 | 3.8480 | |
|
|
| 3.5411 | 0.03 | 1068480 | 3.8489 | |
|
|
| 3.526 | 1.03 | 1144800 | 3.8480 | |
|
|
| 3.5207 | 0.03 | 1221120 | 3.8501 | |
|
|
| 3.5065 | 1.03 | 1297440 | 3.8504 | |
|
|
| 3.4937 | 0.03 | 1373760 | 3.8521 | |
|
|
| 3.4765 | 0.03 | 1450080 | 3.8519 | |
|
|
| 3.4732 | 1.03 | 1526400 | 3.8536 | |
|
|
| 3.4609 | 0.03 | 1602720 | 3.8539 | |
|
|
| 3.4555 | 1.03 | 1679040 | 3.8561 | |
|
|
| 3.4434 | 0.03 | 1755360 | 3.8587 | |
|
|
| 3.4322 | 1.03 | 1831680 | 3.8572 | |
|
|
| 3.4171 | 0.03 | 1908000 | 3.8598 | |
|
|
| 3.4075 | 1.03 | 1984320 | 3.8603 | |
|
|
| 3.3926 | 0.03 | 2060640 | 3.8622 | |
|
|
| 3.3797 | 1.03 | 2136960 | 3.8634 | |
|
|
| 3.3691 | 0.03 | 2213280 | 3.8639 | |
|
|
| 3.3537 | 1.03 | 2289600 | 3.8646 | |
|
|
| 3.3441 | 0.03 | 2365920 | 3.8662 | |
|
|
| 3.3449 | 0.03 | 2442240 | 3.8671 | |
|
|
| 3.3353 | 1.03 | 2518560 | 3.8675 | |
|
|
| 3.3273 | 0.03 | 2594880 | 3.8683 | |
|
|
| 3.3138 | 1.03 | 2671200 | 3.8681 | |
|
|
| 3.313 | 0.03 | 2747520 | 3.8675 | |
|
|
| 3.3061 | 1.03 | 2823840 | 3.8680 | |
|
|
| 3.3015 | 0.03 | 2900160 | 3.8674 | |
|
|
| 3.2964 | 0.03 | 2976480 | 3.8666 | |
|
|
| 3.2867 | 1.02 | 3052726 | 3.8653 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
