|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: model_xl |
|
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. --> |
|
|
|
# model_xl |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0306 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 12 |
|
- eval_batch_size: 12 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 24 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine_with_restarts |
|
- lr_scheduler_warmup_steps: 500 |
|
- training_steps: 0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 2.6465 | 0.11 | 2000 | 2.3854 | |
|
| 1.5576 | 0.22 | 4000 | 1.4934 | |
|
| 1.3344 | 0.33 | 6000 | 1.2809 | |
|
| 1.2192 | 0.43 | 8000 | 1.1750 | |
|
| 1.1604 | 0.54 | 10000 | 1.1104 | |
|
| 1.108 | 0.65 | 12000 | 1.0707 | |
|
| 1.0949 | 0.76 | 14000 | 1.0461 | |
|
| 1.0759 | 0.87 | 16000 | 1.0332 | |
|
| 1.0622 | 0.98 | 18000 | 1.0306 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.2.0+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.1 |
|
|
