|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: zlm-fil-ceb_b64_le5_s8000 |
|
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. --> |
|
|
|
# zlm-fil-ceb_b64_le5_s8000 |
|
|
|
This model was trained from scratch on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4134 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2000 |
|
- training_steps: 8000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:--------:|:----:|:---------------:| |
|
| 0.4019 | 21.7391 | 500 | 0.4143 | |
|
| 0.4064 | 43.4783 | 1000 | 0.4132 | |
|
| 0.4034 | 65.2174 | 1500 | 0.4122 | |
|
| 0.3985 | 86.9565 | 2000 | 0.4148 | |
|
| 0.396 | 108.6957 | 2500 | 0.4123 | |
|
| 0.3958 | 130.4348 | 3000 | 0.4139 | |
|
| 0.3928 | 152.1739 | 3500 | 0.4132 | |
|
| 0.3914 | 173.9130 | 4000 | 0.4139 | |
|
| 0.3916 | 195.6522 | 4500 | 0.4123 | |
|
| 0.3919 | 217.3913 | 5000 | 0.4122 | |
|
| 0.3844 | 239.1304 | 5500 | 0.4126 | |
|
| 0.3908 | 260.8696 | 6000 | 0.4137 | |
|
| 0.3854 | 282.6087 | 6500 | 0.4133 | |
|
| 0.3885 | 304.3478 | 7000 | 0.4140 | |
|
| 0.3849 | 326.0870 | 7500 | 0.4143 | |
|
| 0.386 | 347.8261 | 8000 | 0.4134 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|
