|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: results_model8_new |
|
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. --> |
|
|
|
# results_model8_new |
|
|
|
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: 5.8002 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 30 |
|
- num_epochs: 20 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-------:|:------:|:---------------:| |
|
| 6.3402 | 1.1141 | 10000 | 6.2499 | |
|
| 6.0161 | 2.2282 | 20000 | 5.9371 | |
|
| 5.7976 | 3.3422 | 30000 | 5.8868 | |
|
| 5.5778 | 4.4563 | 40000 | 5.8308 | |
|
| 5.4306 | 5.5704 | 50000 | 5.8110 | |
|
| 5.3332 | 6.6845 | 60000 | 5.8593 | |
|
| 5.2095 | 7.7986 | 70000 | 5.8150 | |
|
| 5.1312 | 8.9127 | 80000 | 5.7984 | |
|
| 5.0266 | 10.0267 | 90000 | 5.8415 | |
|
| 4.9492 | 11.1408 | 100000 | 5.8116 | |
|
| 4.9416 | 12.2549 | 110000 | 5.8231 | |
|
| 4.8767 | 13.3690 | 120000 | 5.7562 | |
|
| 4.8295 | 14.4831 | 130000 | 5.7837 | |
|
| 4.7927 | 15.5971 | 140000 | 5.7813 | |
|
| 4.7876 | 16.7112 | 150000 | 5.7653 | |
|
| 4.7466 | 17.8253 | 160000 | 5.7583 | |
|
| 4.7208 | 18.9394 | 170000 | 5.8002 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.0 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
