|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: passive-transformer-2 |
|
|
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-2 |
|
|
|
|
|
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: 3.8666 |
|
|
|
|
|
## 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: 2 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:-------:|:---------------:| |
|
|
| 4.2246 | 0.03 | 76320 | 4.1998 | |
|
|
| 4.0196 | 1.03 | 152640 | 4.0316 | |
|
|
| 3.9115 | 0.03 | 228960 | 3.9575 | |
|
|
| 3.8466 | 1.03 | 305280 | 3.9175 | |
|
|
| 3.7925 | 0.03 | 381600 | 3.8923 | |
|
|
| 3.7547 | 1.03 | 457920 | 3.8758 | |
|
|
| 3.7202 | 0.03 | 534240 | 3.8653 | |
|
|
| 3.6871 | 1.03 | 610560 | 3.8579 | |
|
|
| 3.6566 | 0.03 | 686880 | 3.8538 | |
|
|
| 3.632 | 1.03 | 763200 | 3.8516 | |
|
|
| 3.6078 | 0.03 | 839520 | 3.8494 | |
|
|
| 3.5885 | 0.03 | 915840 | 3.8490 | |
|
|
| 3.5684 | 0.03 | 992160 | 3.8483 | |
|
|
| 3.5442 | 1.03 | 1068480 | 3.8490 | |
|
|
| 3.5301 | 0.03 | 1144800 | 3.8506 | |
|
|
| 3.5246 | 1.03 | 1221120 | 3.8516 | |
|
|
| 3.5082 | 0.03 | 1297440 | 3.8520 | |
|
|
| 3.4965 | 1.03 | 1373760 | 3.8527 | |
|
|
| 3.4799 | 0.03 | 1450080 | 3.8542 | |
|
|
| 3.4728 | 1.03 | 1526400 | 3.8547 | |
|
|
| 3.4651 | 0.03 | 1602720 | 3.8565 | |
|
|
| 3.4555 | 1.03 | 1679040 | 3.8588 | |
|
|
| 3.4457 | 0.03 | 1755360 | 3.8600 | |
|
|
| 3.4346 | 1.03 | 1831680 | 3.8608 | |
|
|
| 3.4183 | 0.03 | 1908000 | 3.8626 | |
|
|
| 3.4085 | 1.03 | 1984320 | 3.8633 | |
|
|
| 3.3948 | 0.03 | 2060640 | 3.8646 | |
|
|
| 3.3859 | 1.03 | 2136960 | 3.8653 | |
|
|
| 3.3726 | 0.03 | 2213280 | 3.8674 | |
|
|
| 3.3573 | 1.03 | 2289600 | 3.8681 | |
|
|
| 3.348 | 0.03 | 2365920 | 3.8678 | |
|
|
| 3.3457 | 1.03 | 2442240 | 3.8681 | |
|
|
| 3.3354 | 0.03 | 2518560 | 3.8695 | |
|
|
| 3.3261 | 0.03 | 2594880 | 3.8703 | |
|
|
| 3.3151 | 1.03 | 2671200 | 3.8703 | |
|
|
| 3.3134 | 0.03 | 2747520 | 3.8707 | |
|
|
| 3.3048 | 1.03 | 2823840 | 3.8698 | |
|
|
| 3.3032 | 0.03 | 2900160 | 3.8695 | |
|
|
| 3.2967 | 1.03 | 2976480 | 3.8684 | |
|
|
| 3.2882 | 0.02 | 3052726 | 3.8666 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.33.3 |
|
|
- Pytorch 2.0.1 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
